Pubblicazioni di Stefano SQUARTINI

169 pubblicazioni disponibili classificate nel seguente modo:

Nr. doc. Classificazioni
92 4 Contributo in Atti di Convegno (Proceeding)
41 2 Contributo in Volume
34 1 Contributo su Rivista
2 3 Libro

Pagine [   1   | 2 ]

Anno Risorsa
Convolutional Neural Networks with 3-D Kernels for Voice Activity Detection in a Multiroom Environment
WIRN 2016, Proceeding of
Autore/i: Vecchiotti, P.; Vesperini, F.; Principi, E.; Squartini, S.; Piazza, F
Classificazione: 4 Contributo in Atti di Convegno (Proceeding)
Abstract: This paper focuses on employing Convolutional Neural Net- works (CNN) with 3-D kernels for Voice Activity Detectors in multi-room domestic scenarios (mVAD). This technology is compared with the Multi Layer Perceptron (MLP) and interesting advancements are observed with respect to previous works of the authors. In order to approximate real- life scenarios, the DIRHA dataset is exploited. It has been recorded in a home environment by means of several microphones arranged in vari- ous rooms. Our study is composed by a multi-stage analysis focusing on the selection of the network size and the input microphones in relation with their number and position. Results are evaluated in terms of Speech Activity Detection error rate (SAD). The CNN-mVAD outperforms the other method with a significant solidity in terms of performance statis- tics, achieving in the best overall case a SAD equal to 7.0%.
Scheda della pubblicazione: https://iris.univpm.it/handle/11566/241540 Collegamento a IRIS

Fall Detection by Using an Innovative Floor Acoustic Sensor
WIRN 2016, Proceeding of
Autore/i: Droghini, D.; Principi, E.; Squartini, S.; Piazza, F
Classificazione: 4 Contributo in Atti di Convegno (Proceeding)
Abstract: Supporting people in their homes is an important issue both for ethical and practical reasons. Indeed, in the recent years, the scientific community devoted particular attention to detecting human falls, since the first cause of death for elderly people is due to the consequences of a fall. In this paper, we propose a human fall classification system based on an innovative floor acoustic sensor able to capture the acoustic waves transmitted through the floor. The algorithm employed is able to discriminate human falls from non falls and it is based on Mel-Frequency Cepstral Coefficients and a two class Support Vector Machine. The dataset employed for performance evaluation is composed by falls of a human mimicking doll, everyday objects and everyday noises. The obtained results show that the proposed solution is suitable for human fall detection in realistic scenarios, allowing to guarantee a 0% miss probability at very low false positive rates.
Scheda della pubblicazione: https://iris.univpm.it/handle/11566/241539 Collegamento a IRIS

2017 A Combined One-Class SVM and Template-Matching Approach for User-Aided Human Fall Detection by Means of Floor Acoustic Features
COMPUTATIONAL INTELLIGENCE AND NEUROSCIENCE
Autore/i: Droghini, Diego; Ferretti, Daniele; Principi, Emanuele; Squartini, Stefano; Piazza, Francesco
Classificazione: 1 Contributo su Rivista
Abstract: The primary cause of injury-related death for the elders is represented by falls. The scientific community devoted them particular attention, since injuries can be limited by an early detection of the event. The solution proposed in this paper is based on a combined One-Class SVM (OCSVM) and template-matching classifier that discriminate human falls from nonfalls in a semisupervised framework. Acoustic signals are captured by means of a Floor Acoustic Sensor; then Mel-Frequency Cepstral Coefficients and Gaussian Mean Supervectors (GMSs) are extracted for the fall/nonfall discrimination. Here we propose a single-sensor two-stage user-aided approach: in the first stage, the OCSVM detects abnormal acoustic events. In the second, the template-matching classifier produces the final decision exploiting a set of template GMSs related to the events marked as false positives by the user. The performance of the algorithm has been evaluated on a corpus containing human falls and nonfall sounds. Compared to the OCSVM only approach, the proposed algorithm improves the performance by 10.14% in clean conditions and 4.84% in noisy conditions. Compared to Popescu and Mahnot (2009) the performance improvement is 19.96% in clean conditions and 8.08% in noisy conditions.
Scheda della pubblicazione: https://iris.univpm.it/handle/11566/249952 Collegamento a IRIS

2017 Energy management with support of PV partial shading modelling in Micro Grid environments
ENERGIES
Autore/i: Severini, Marco; Principi, Emanuele; Fagiani, Marco; Squartini, Stefano; Piazza, Francesco
Classificazione: 1 Contributo su Rivista
Abstract: Although photovoltaic power plants are suitable local energy sources in Micro Grid environments, when large plants are involved, partial shading and inaccurate modelling of the plant can affect both the design of the Micro Grid as well as the energy management process that allows for lowering the overall Micro Grid demand towards the main grid. To investigate the issue, a Photovoltaic Plant simulation model, based on a real life power plant, and an energy management system, based on a real life Micro Grid environment, have been integrated to evaluate the performance of a Micro Grid under partial shading conditions. Using a baseline energy production model as a reference, the energy demand of the Micro Grid has been computed in sunny and partial shading conditions. The experiments reveal that an estimation based on a simplified PV model can exceed by 65% the actual production. With regards to Micro Grid design, on sunny days, the expected costs, based on a simplified PV model, can be 5.5% lower than the cost based on the double inverter model. In single cloud scenarios, the underrating can reach 28.3%. With regard to the management process, if the energy yield is estimated by means of a simplified PV model, the actual cost can be from 17.1% to 21.5% higher than the theoretical cost expected at design time.
Scheda della pubblicazione: https://iris.univpm.it/handle/11566/249946 Collegamento a IRIS

2017 Exploiting Heterogeneous Data for the Estimation of Particles Size Distribution in Industrial Plant
Mechatronika 2016, Proceedings of
Autore/i: Rossetti, Damiano; Squartini, Stefano; Collura, Stefano; Zhang, Yu
Classificazione: 4 Contributo in Atti di Convegno (Proceeding)
Abstract: In industrial environments, it is often difficult and expensive to collect a good amount of data to adequately train expert systems for regression purposes. Therefore the usage of already available data, related to environments showing similar characteristics, could represent an effective approach to find a good balance between regression performance and the amount of data to gather for training. In this paper, the authors propose two alternative strategies for improving the regression performance by using heterogeneous data, i.e. data coming from diverse environments with respect to the one taken as reference for testing. These strategies are based on a standard machine learning algorithm, i.e. the Artificial Neural Network (ANN). The employed data came from measurements in industrial plants for energy production through the combustion of coal powder. The powder is transported in air within ducts and its size is detected by means of Acoustic Emissions (AE) produced by the impact of powder on the inner surface of the duct. The estimation of powder size distribution from AE signals is the task addressed in this work. Computer simulations show how the proposed strategies achieve a relevant improvement of regression performance with respect to the standard approach, using ANN directly on the dataset related to the reference plant.
Scheda della pubblicazione: https://iris.univpm.it/handle/11566/240733 Collegamento a IRIS

2017 User-aided Footprint Extraction for Appliance Modelling in Non-Intrusive Load Monitoring
SSCI 2016, Proceedings on
Autore/i: Bonfigli, Roberto; Principi, Emanuele; Squartini, Stefano; Fagiani, Marco; Severini, Marco; Piazza, Francesco
Classificazione: 4 Contributo in Atti di Convegno (Proceeding)
Abstract: In the area of Non-Intrusive Load Monitoring (NILM), many approaches need a supervised procedure of appliance modelling, in order to provide the informations about the appliances to the disaggregation algorithm and to obtain the disaggregated consumptions related to each one of them. In many approaches, the appliance modelling relies on the consumption footprint, which is a typical working cycle of the appliance. Since the NILM system has only the aggregated power consumption available, the recorded footprint might be corrupted by other appliances, which can not be turned off during this period, i.e., the fridge and freezer in the household. Furthermore, the user needs a facilitated procedure, in order to obtain a clean footprint from the aggregated power signal in real scenario. Therefore, a user-aided footprint extraction procedure is needed. In this work, this procedure is defined as a NILM problem with two sources, i.e., the desired appliance and the fridge-freezer combination. One of the resulting disaggregated profiles of the algorithm corresponds to the extracted footprint. Then, this is used for the appliance modelling stage to create te corresponding Hidden Markov Model (HMM), suitable for the Additive Factorial Approximate Maximum a Posteriori (AFAMAP) algorithm. The effectiveness of the footprint extraction procedure is evaluated through the confidence of the disaggregation output of a real problem, using a span of 30 days data taken from two different datasets (AMPds, ECO). The experiments are conducted using the HMM from the extracted footprint, compared to the con- fidence of the same problem using the HMM from the true footprint, as appliance level consumption. The results show that the performance are comparable, with the worst relative F1 loss of 3.83%, demonstrating the effectiveness of the footprint extraction procedure.
Scheda della pubblicazione: https://iris.univpm.it/handle/11566/240732 Collegamento a IRIS

2017 Deep Recurrent Neural Network-based Autoencoders for Acoustic Novelty Detection
COMPUTATIONAL INTELLIGENCE AND NEUROSCIENCE
Autore/i: Marchi, Erik; Vesperini, Fabio; Squartini, Stefano; Schuller, Bjoern
Classificazione: 1 Contributo su Rivista
Abstract: In the emerging field of acoustic novelty detection, most research efforts are devoted to probabilistic approaches such as mixture models or state-space models. Only recent studies introduced (pseudo-)generative models for acoustic novelty detection with recurrent neural networks in the form of an autoencoder. In these approaches, auditory spectral features of the next short-term frame are predicted from the previous frames by means of Long-Short Term Memory recurrent denoising autoencoders. The reconstruction error between the input and the output of the autoencoder is used as activation signal to detect novel events. There is no evidence of studies focused on comparing previous efforts to automatically recognise novel events from audio signals and giving a broad and in depth evaluation of recurrent neural network-based autoencoders. The present contribution aims to consistently evaluate our recent novel approaches to fill this white spot in the literature and provide insight by extensive evaluations carried out on three databases: A3Novelty, PASCAL CHiME, and PROMETHEUS. Besides providing an extensive analysis of novel and state-of-the-art methods, the article shows how RNN-based autoencoders outperform statistical approaches up to an absolute improvement of 16.4 % average F -measure over the three databases.
Scheda della pubblicazione: https://iris.univpm.it/handle/11566/240182 Collegamento a IRIS

2017 Classification of Bearing Faults Through Time-Frequency Analysis and Image Processing
Mechatronika 2016, Proceedings of
Autore/i: Rossetti, Damiano; Zhang, Yu; Squartini, Stefano; Collura, Stefano
Classificazione: 4 Contributo in Atti di Convegno (Proceeding)
Abstract: The present work proposes a new technique for bearing fault classification that combines time-frequency analysis with image processing. This technique uses vibration signals from bearing housings to detect bearing conditions and classify the faults. By means of Empirical Mode Decomposition (EMD), each vibration signal is decomposed into Intrinsic Mode Functions (IMFs). Principal Components Analysis (PCA) is then performed on the matrix of the decomposed IMFs and the important principal components are chosen. The spectrogram is obtained for each component by means of the Short Time Fourier Transform (STFT) to obtain an image that represents the time-frequency relationship of the main components of the analyzed signal. Furthermore, Image Moments are extracted from the spectrogram images of principal components in order to obtain an array of features for each signal that can be handled by the classification algorithm. 8 images are selected for each signal and 17 moments for each image, so an array of 136 features is associated with every signal. Finally, the classification is performed using a standard machine learning technique, i.e. Support Vector Machine (SVM), in the proposed technique. The dataset used in this work include data collected for various rotating speeds and loads, in order to obtain a set of different operating conditions, by a Roller Bearing Faults Simulator. The results have shown that the developed technique provides classification effectively, with a single classifier, of bearing faults characterized by different rotating speeds and different loads.
Scheda della pubblicazione: https://iris.univpm.it/handle/11566/240734 Collegamento a IRIS

2016 Combining evolution strategies and neural network procedures for compression driver design
Neural Networks (IJCNN), 2016 International Joint Conference on
Autore/i: Gasparini, Michele; Vesperini, Fabio; Cecchi, Stefania; Squartini, Stefano; Piazza, Francesco; Toppi, Romolo
Classificazione: 4 Contributo in Atti di Convegno (Proceeding)
Abstract: Compression driver design involves the study of complex mathematical models characterized by a great number of variables, implying high computational cost and long design time. Therefore, an optimization procedure is required to enhance the design procedure, especially from the parameters point of view. In this paper, a combined approach based both on evolution strategy procedure and neural network model is presented. Taking into consideration several tests on a real compression driver, the proposed method is capable to enhance the design procedure from the point of view of obtained frequency response and of the computational performance.
Scheda della pubblicazione: https://iris.univpm.it/handle/11566/239797 Collegamento a IRIS

2016 An experimental study on new features for activity of daily living recognition
Neural Networks (IJCNN), 2016 International Joint Conference on
Autore/i: Ferretti, Daniele; Principi, Emanuele; Squartini, Stefano; Mandolini, Luigi
Classificazione: 4 Contributo in Atti di Convegno (Proceeding)
Abstract: In the last few years, the researchers have spent many efforts in developing advanced systems for activity daily living (ADL) recognition in diverse applicative contexts, as home automation and ambient assisted living. Some of these need to know in real time the actions performed by a user, and this involves a number of additional issues to be taken into account during the recognition. In this paper, we present some improvements of a sliding window based approach to perform ADL recognition in a online fashion, i.e., recognizing activities as and when new sensor events are recorded. We describe seven methods used to extract features from the sequence of sensor events. The first four relate to previous works regarding the system of ADL recognition described, while, the last three represent the original contribution of this work. Support Vector Machine (SVM) has been used as classifier. Several experiments have been carried out by using a public smart home dataset and obtained results show that two of the three novel approaches allow to improve the recognition performance of the conventional methods, up to an increment of 5% with respect to the baseline feature extraction approach.
Scheda della pubblicazione: https://iris.univpm.it/handle/11566/239796 Collegamento a IRIS

2016 Deep neural networks for Multi-Room Voice Activity Detection: Advancements and comparative evaluation
Neural Networks (IJCNN), 2016 International Joint Conference on
Autore/i: Vesperini, Fabio; Vecchiotti, Paolo; Principi, Emanuele; Squartini, Stefano; Piazza, Francesco
Editore: IEEE
Classificazione: 4 Contributo in Atti di Convegno (Proceeding)
Abstract: This paper focuses on Voice Activity Detectors (VAD) for multi-room domestic scenarios based on deep neural network architectures. Interesting advancements are observed with respect to a previous work. A comparative and extensive analysis is lead among four different neural networks (NN). In particular, we exploit Deep Belief Network (DBN), Multi-Layer Perceptron (MLP), Bidirectional Long Short-Term Memory recurrent neural network (BLSTM) and Convolutional Neural Network (CNN). The latter has recently encountered a large success in the computational audio processing field and it has been successfully employed in our task. Two home recorded datasets are used in order to approximate real-life scenarios. They contain audio files from several microphones arranged in various rooms, from whom six features are extracted and used as input for the deep neural classifiers. The output stage has been redesigned compared to the previous author's contribution, in order to take advantage of the networks discriminative ability. Our study is composed by a multi-stage analysis focusing on the selection of the features, the network size and the input microphones. Results are evaluated in terms of Speech Activity Detection error rate (SAD). As result, a best SAD equal to 5.8% and 2.6% is reached respectively in the two considered datasets. In addiction, a significant solidity in terms of microphone positioning is observed in the case of CNN.
Scheda della pubblicazione: https://iris.univpm.it/handle/11566/239799 Collegamento a IRIS

2016 SW framework for simulation and evaluation of partial shading effects in configurable PV systems
2016 IEEE 16th International Conference on Environment and Electrical Engineering (EEEIC)
Autore/i: Marco, Severini; Andrea, Scorrano; Stefano, Squartini; Marco, Fagiani; Francesco, Piazza
Editore: IEEE
Classificazione: 4 Contributo in Atti di Convegno (Proceeding)
Abstract: This SW framework is proposed as a design tool, which simulates the energy production of the system, while considering the characteristics of a photovoltaic (PV) power plant. The framework is made available upon request to the scientific community. The model takes into account not only the specification of the panels, the topology of the array and the conditions of the weather, but also the irradiation and the shading patterns, as well as the maximum power point tracking (MPPT) algorithm. The proposed tool allows to evaluate the performance of PV power plants being designed, while taking into account not only the design parameters but also the environmental characteristics, including the weather or terrain. However, differently from other tools, it also allows to compare the performance of MPPT algorithms, thus supporting the design of the PV power plant. Our experiments reveal that, in a plant of 4160 panels and about 6691 square meters, with a peak power of 998.5 kWp, dividing the PV modules among 13 inverter (320 modules each) and supporting the MPPT procedure, the yield loss can be lowered by about 13% with respect to a centralized PV plant with standard MPPT approaches. Over a year, the estimated increase of the income is over 3200 C.
Scheda della pubblicazione: https://iris.univpm.it/handle/11566/238340 Collegamento a IRIS

2016 Wireless Networked Music Performance
SPRINGERBRIEFS IN ELECTRICAL AND COMPUTER ENGINEERING
Autore/i: Gabrielli, Leonardo; Squartini, Stefano
Editore: Springer Singapore
Classificazione: 3 Libro
Scheda della pubblicazione: https://iris.univpm.it/handle/11566/230579 Collegamento a IRIS

2016 Exploiting temporal features and pressure data for automatic leakage detection in smart water grids
Evolutionary Computation (CEC), 2016 IEEE Congress on
Autore/i: Fagiani, M.; Squartini, S.; Bonfigli, R.; Severini, M.; Piazza, F.
Classificazione: 4 Contributo in Atti di Convegno (Proceeding)
Abstract: In this paper, the unsupervised approach recently proposed by the authors for automatic leakage detection in smart water grids is extended. First of all, the EPANET tool is adopted in order to simulate more realistic leakages. Also, with respect to the original work, an additional time resolution, of 30 minutes, is included, based on the water dataset of the Almanac of Minutely Power Dataset (AMPds). New experiments are performed, as well, to evaluate the results of the application of both temporal features and pressure data. The pressure data is obtained by means of the EPANEt tool, whereas the leakages are induced at run-time for a more realistic behaviour. Two alternative sets of temporal features are evaluated by combining them with the features extracted from both flow and pressure data. Gaussian Mixture Models (GMMs), Hidden Markov Models (HMMs), and One-Class Support Vector Machine (OC-SVM) are used to characterize the normal data behaviour, under a comparative perspective. A feature selection strategy is adopted in computer simulations and the resulting performance indices are evaluated in terms of Area Under Curve (AUC). The obtained results show that the introduction of the temporal information produces a slight performance improvement for both flow and pressure data, but, most importantly, the combination of flow and pressure features allows a significant improvement of leakage detection for both GMM and HMM at every resolution, up to 88% of AUC.
Scheda della pubblicazione: https://iris.univpm.it/handle/11566/240730 Collegamento a IRIS

2016 DCASE 2016 Acoustic Scene Classification Using Convolutional Neural Networks
Proceedings of the Detection and Classification of Acoustic Scenes and Events 2016 Workshop (DCASE2016)
Autore/i: Valenti, Michele; Diment, Aleksandr; Parascandolo, Giambattista; Squartini, Stefano; Virtanen, Tuomas
Editore: Tampere University of Technology. Department of Signal Processing
Classificazione: 2 Contributo in Volume
Abstract: This workshop paper presents our contribution for the task of acoustic scene classification proposed for the “detection and classification of acoustic scenes and events” (D-CASE) 2016 challenge. We propose the use of a convolutional neural network trained to classify short sequences of audio, represented by their log-mel spectrogram. In addition we use a training method that can be used when the validation performance of the system saturates as the training proceeds. The performance is evaluated on the public acoustic scene classification development dataset provided for the D-CASE challenge. The best accuracy score obtained by our configuration on a four-folded cross-validation setup is 79.0%. It constitutes a 8.8% relative improvement with respect to the baseline system, based on a Gaussian mixture model classifier.
Scheda della pubblicazione: https://iris.univpm.it/handle/11566/239808 Collegamento a IRIS

2016 A Statistical Framework for Automatic Leakage Detection in Smart Water and Gas Grids
ENERGIES
Autore/i: Fagiani, Marco; Squartini, Stefano; Gabrielli, Leonardo; Severini, Marco; Piazza, Francesco
Classificazione: 1 Contributo su Rivista
Abstract: In the last few years, due to the technological improvement of advanced metering infrastructures, water and natural gas grids can be regarded as smart-grids, similarly to power ones. However, considering the number of studies related to the application of computational intelligence to distribution grids, the gap between power grids and water/gas grids is notably wide. For this purpose, in this paper, a framework for leakage identification is presented. The framework is composed of three sections aimed at the extraction and the selection of features and at the detection of leakages. A variation of the Sequential Feature Selection (SFS) algorithm is used to select the best performing features within a set, including, also, innovative temporal ones. The leakage identification is based on novelty detection and exploits the characterization of a normality model. Three statistical approaches, The Gaussian Mixture Model (GMM), Hidden Markov Model (HMM) and One-Class Support Vector Machine (OC-SVM), are adopted, under a comparative perspective. Both residential and office building environments are investigated by means of two datasets. One is the Almanac of Minutely Power dataset (AMPds), and it provides water and gas data consumption at 1, 10 and 30 min of time resolution; the other is the Department of International Development (DFID) dataset, and it provides water and gas data consumption at 30 min of time resolution. The achieved performance, computed by means of the Area Under the Curve (AUC), reaches 90% in the office building case study, thus confirming the suitability of the proposed approach for applications in smart water and gas grids.
Scheda della pubblicazione: https://iris.univpm.it/handle/11566/238339 Collegamento a IRIS

2016 Smart AMI based demand-response management in a micro-grid environment
Clemson University Power Systems Conference, PSC 2016
Autore/i: Fusco, Vito; Venayagamoorthy, Ganesh K.; Squartini, Stefano; Piazza, Francesco
Editore: Institute of Electrical and Electronics Engineers Inc.
Classificazione: 4 Contributo in Atti di Convegno (Proceeding)
Abstract: Reliable operation of the electrical grid requires balancing between generation and energy demand at any time instant. Increasing penetration of intermittent sources of alternative generation compromises reliability and introduces significant price volatility. As a solution, demand response strategies have been studied to provide the necessary demand-side flexibility for utility to absorb some volatility. In this paper, a demand-response management (DRM) system is proposed, where a service provider finds a mutual optimal solution for the utility and the customers in a microgrid setting. This could be used by a service provider interacting with the respective customers and utility under the existence of some DRM agreements. In this study, a micro-grid consisting of a smart neighbourhood of twelve customers is taken as experimental case study and an advanced metering infrastructure (AMI) is implemented. Based on the formulation of an optimization problem which exploits price-responsive demand flexibility and the AMI infrastructure, a win-win-win strategy is presented. By shaping load patterns according to market pricing, the proposed method led to higher cost savings for the flexible customers and the utility, with consistent profit margins achieved by the service provider. Results for a range of typical scenarios are presented to demonstrate the effectiveness of the proposed demand-response management framework.
Scheda della pubblicazione: https://iris.univpm.it/handle/11566/238341 Collegamento a IRIS

2016 Pairwise Decomposition with Deep Neural Networks and Multiscale Kernel Subspace Learning for Acoustic Scene Classification
Proceedings of the Detection and Classification of Acoustic Scenes and Events 2016 Workshop (DCASE2016)
Autore/i: Marchi, Erik; Tonelli, Dario; Xu, Xinzhou; Ringeval, Fabien; Deng, Jun; Squartini, Stefano; Schuller, Bjoern
Editore: Tampere University of Technology. Department of Signal Processing
Classificazione: 2 Contributo in Volume
Abstract: We propose a system for acoustic scene classification using pairwise decomposition with deep neural networks and dimensionality reduction by multiscale kernel subspace learning. It is our contribution to the Acoustic Scene Classification task of the IEEE AASP Challenge on Detection and Classification of Acoustic Scenes and Events (DCASE2016). The system classifies 15 different acoustic scenes. First, auditory spectral features are extracted and fed into 15 binary deep multilayer perceptron neural networks (MLP). MLP are trained with the `one-against-all' paradigm to perform a pairwise decomposition. In a second stage, a large number of spectral, cepstral, energy and voicing-related audio features are extracted. Multiscale Gaussian kernels are then used in constructing optimal linear combination of Gram matrices for multiple kernel subspace learning. The reduced feature set is fed into a nearest-neighbour classifier. Predictions from the two systems are then combined by a threshold-based decision function. On the official development set of the challenge, an accuracy of 81.4% is achieved.
Scheda della pubblicazione: https://iris.univpm.it/handle/11566/239807 Collegamento a IRIS

2016 Machine learning techniques for the estimation of particle size distribution in industrial plants
Advances in Neural Networks
Autore/i: Rossetti, Damiano; Squartini, Stefano; Collura, Stefano
Editore: Springer Science and Business Media Deutschland GmbH
Classificazione: 2 Contributo in Volume
Abstract: This paper aims to evaluate the effectiveness of different Machine Learning algorithms for the estimation of Particle Size Distribution (PSD) of powder by means of Acoustic Emissions (AE). In industrial plants it is very useful to use non-invasive and adaptable systems for monitoring the particle size, for this reason the AE represents an important mean for detecting the particle size. To create a model that relates the AE with the powder size, Machine Learning is a viable approach to model a complex system without knowing all the variables in details. The test results show a good estimation accuracy for the various Machine Learning algorithms employed in this study.
Scheda della pubblicazione: https://iris.univpm.it/handle/11566/240192 Collegamento a IRIS

2016 ELM Based Algorithms for Acoustic Template Matching in Home Automation Scenarios: Advancements and Performance Analysis
Recent Advances in Nonlinear Speech Processing
Autore/i: Della Porta, G.; Principi, E.; Ferroni, G.; Squartini, S.; Hussain, A.; Piazza, F.
Classificazione: 2 Contributo in Volume
Abstract: Speech and sound recognition in home automation scenarios has been gaining an increasing interest in the last decade. One interesting approach addressed in the literature is based on the template matching paradigm, which is characterized by ease of implementation and independence on large datasets for system training. Moving from a recent contribution of some of the authors, where an Extreme Learn-ing Machine algorithm was proposed and evaluated, a wider performance analysis in diverse operating conditions is provided here, together with some relevant improvements. These are allowed by the employment of supervector features as input, for the first time used with ELMs, up to the authors’ knowledge. As already verified in other application contexts and with different learning systems, this ensures a more robust characterization of the speech segment to be classified, also in presence of mismatch between training and testing data. The accomplished computer simulations confirm the effectiveness of the approach, with F1-Measure performance up to 99% in the multicondition case, and a computational time reduction factor close to 4, with respect to the SVM counterpart.
Scheda della pubblicazione: https://iris.univpm.it/handle/11566/230583 Collegamento a IRIS

2016 Improving the performance of the AFAMAP algorithm for Non-Intrusive Load Monitoring
Evolutionary Computation (CEC), 2016 IEEE Congress on
Autore/i: Bonfigli, R.; Severini, M.; Squartini, S.; Fagiani, M.; Piazza, F.
Classificazione: 4 Contributo in Atti di Convegno (Proceeding)
Abstract: Among the many electrical load disaggregation methods, often referred to as Non-Intrusive Load Monitoring techniques, the Additive Factorial Approximate MAP (AFAMAP) algorithm has shown outstanding capabilities and, therefore, it is nowadays regarded as a reference model. In order to achieve more accurate disaggregation results, and to satisfy real life environment requirements, further improvements in the algorithm are needed. In this work, the AFAMAP algorithm has been extended, by means of a differential forward model, thus complementing the existing differential backward model. Furthermore, an aggregated data examination method has been employed, aimed to the detection of inadmissible working state combinations of appliances, as well as the constraints setting based on the reactive power disaggregation feedback. The new approach has been evaluated by means of a subset, spanning over 6 months, of the Almanac of Minutely Power dataset (AMPds). On purpose, a real life environment, accounting 6 appliances, has been modelled and the carried out experiments revealed a improvement up to 18% with respect to the baseline AFAMAP.
Scheda della pubblicazione: https://iris.univpm.it/handle/11566/240731 Collegamento a IRIS

2016 A neural network based algorithm for speaker localization in a multi-room environment
Machine Learning for Signal Processing (MLSP), 2016 IEEE 26th International Workshop on
Autore/i: Vesperini, Fabio; Vecchiotti, Paolo; Principi, Emanuele; Squartini, Stefano; Piazza, Francesco
Editore: IEEE
Classificazione: 4 Contributo in Atti di Convegno (Proceeding)
Abstract: A Speaker Localization algorithm based on Neural Networks for multi-room domestic scenarios is proposed in this paper. The approach is fully data-driven and employs a Neural Network fed by GCC-PHAT (Generalized Cross Correlation Phase Transform) Patterns, calculated by means of the microphone signals, to determine the speaker position in the room under analysis. In particular, we deal with a multi-room case study, in which the acoustic scene of each room is influenced by sounds emitted in the other rooms. The algorithm is tested against the home recorded DIRHA dataset, characterized by multiple wall and ceiling microphone signals for each room. In particular, we focused on the speaker localization problem in two distinct neighbouring rooms. We assumed the presence of an Oracle multi-room Voice Activity Detector (VAD) in our experiments. A three-stage optimization procedure has been adopted to find the best network configuration and GCC-PHAT Patterns combination. Moreover, an algorithm based on Time Difference of Arrival (TDOA), recently proposed in literature for the addressed applicative context, has been considered as term of comparison. As result, the proposed algorithm outperforms the reference one, providing an average localization error, expressed in terms of RMSE, equal to 525 mm against 1465 mm. Concluding, we also assessed the algorithm performance when a real VAD, recently proposed by some of the authors, is used. Even though a degradation of localization capability is registered (an average RMSE equal to 770 mm), still a remarkable improvement with respect to the state of the art performance is obtained.
Scheda della pubblicazione: https://iris.univpm.it/handle/11566/239800 Collegamento a IRIS

2016 Acoustic cues from the floor: A new approach for fall classification
EXPERT SYSTEMS WITH APPLICATIONS
Autore/i: Principi, Emanuele; Droghini, Diego; Squartini, Stefano; Olivetti, Paolo; Piazza, Francesco
Classificazione: 1 Contributo su Rivista
Abstract: The interest in assistive technologies for supporting people at home is constantly increasing, both in academia and industry. In this context, the authors propose a fall classification system based on an innovative acoustic sensor that operates similarly to stethoscopes and captures the acoustic waves transmitted through the floor. The sensor is designed to minimize the impact of aerial sounds in recordings, thus allowing a more focused acoustic description of fall events. The audio signals acquired by means of the sensor are processed by a fall recognition algorithm based on Mel-Frequency Cepstral Coefficients, Supervectors and Support Vector Machines to discriminate among different types of fall events. The performance of the algorithm has been evaluated against a specific audio corpus comprising falls of a human mimicking doll and of everyday objects. The results showed that the floor sensor significantly improves the performance respect to an aerial microphone: in particular, the F1-Measure is 6.50% higher in clean conditions and 8.76% higher in mismatched noisy conditions. The proposed approach, thus, has a considerable advantage over aerial solutions since it is able to achieve higher fall classification performance using a simpler algorithmic pipeline and hardware setup.
Scheda della pubblicazione: https://iris.univpm.it/handle/11566/236004 Collegamento a IRIS

2015 Acoustic Template-Matching for Automatic Emergency State Detection: an ELM based algorithm
NEUROCOMPUTING
Autore/i: E. Principi; S. Squartini; E. Cambria; F. Piazza
Classificazione: 1 Contributo su Rivista
Abstract: Extreme Learning Machine (ELM) represents a popular paradigm for training feedforward neural networks due to its fast learning time. This paper applies the technique for the automatic classification of speech utterances. Power Normalized Cepstral Coefficients (PNCC) are employed as feature vectors and ELM performs the final classification. Both the baseline ELM algorithm and ELM with kernel have been employed and tested. Due to the fixed number of input neurons in the ELM, a length normalization algorithm is employed to transform the PNCC sequence into a vector of fixed length. Length normalization has been performed using two techniques: the first is based on Dynamic Time Warping (DTW) distances, the second on the vectorized outerproduct of trajectory matrix. Experiments have been conducted on the TIDIGITS corpus, to assess the performance on an isolated speech recognition task, and on ITAAL, to validate the system in an emergency detection task in realistic acoustic conditions. The ELM approach has been compared to template matching based on Dynamic Time Warping and to a Support Vector Machine based speech recognizer. The obtained results demonstrated the effectiveness of the approach both in terms of recognition performance and execution times. In particular, classification based on PNCCs, DTW distances and ELM kernel resulted in the best performing algorithm both in terms of recognition accuracy and execution times.
Scheda della pubblicazione: https://iris.univpm.it/handle/11566/153902 Collegamento a IRIS

2015 Short-term Load Forecasting for Smart Water and Gas Grids: a comparative evaluation
2015 IEEE 15th International Conference on Environment and Electrical Engineering, EEEIC 2015 - Conference Proceedings
Autore/i: Fagiani, M.; Squartini, S.; Bonfigli, R.; Piazza, F.
Editore: IEEE
Classificazione: 4 Contributo in Atti di Convegno (Proceeding)
Abstract: Moving from a recent publication of Fagiani et al. [1], short-term predictions of water and natural gas consumption are performed exploiting state-of-the-art techniques. Specifically, for two datasets, the performance of Support Vector Regression (SVR), Extreme Learning Machine (ELM), Genetic Programming (GP), Artificial Neural Networks (ANNs), Echo State Networks (ESNs), and Deep Belief Networks (DBNs) are compared adopting common evaluation criteria. Concerning the datasets, the Almanac of Minutely Power Dataset (AMPds) is used to compute predictions with domestic consumption, 2 year of recordings, and to perform further evaluations with the available heterogeneous data, such as energy and temperature. Whereas, predictions of building consumption are performed with the datasets recorded at the Department for International Development (DFID). In addition, the results achieved for the previous release of the AMPds, 1 year of recordings, are also reported, in order to evaluate the impact of seasonality in forecasting performance. Finally, the achieved results validate the suitability of ANN, SVR and ELM approaches for prediction applications in small-grid scenario. Specifically, for the domestic consumption the best performance are achieved by SVR and ANN, for natural gas and water, respectively. Whereas, the ANN shows the best results for both water and natural gas forecasting in building scenario.
Scheda della pubblicazione: https://iris.univpm.it/handle/11566/230592 Collegamento a IRIS

2015 Computational Energy Management in Smart Grids
NEUROCOMPUTING
Autore/i: Squartini, S.; Liu, D.; Piazza, F.; Zhao, D.; He, H.
Classificazione: 1 Contributo su Rivista
Scheda della pubblicazione: https://iris.univpm.it/handle/11566/230588 Collegamento a IRIS

2015 A review of datasets and load forecasting techniques for smart natural gas and water grids: Analysis and experiments
NEUROCOMPUTING
Autore/i: Fagiani, M.; Squartini, S; Gabrielli, L; Spinsante,S; Piazza, F
Classificazione: 1 Contributo su Rivista
Abstract: In this paper, experiments concerning the prediction of water and natural gas consumption are presented, focusing on how to exploit data heterogeneity to get a reliable outcome. Prior to this, an up-to-date state-of-the-art review on the available datasets and forecasting techniques of water and natural gas consumption, is conducted. A collection of techniques (Artificial Neural Networks, Deep Belief Networks, Echo State Networks, Support Vector Regression, Genetic Programming and Extended Kalman Filter-Genetic Programming), partially selected from the state-of-the-art ones, are evaluated using the few publicly available datasets. The tests are performed according to two key aspects: homogeneous evaluation criteria and application of heterogeneous data. Experiments with heterogeneous data obtained combining multiple types of resources (water, gas, energy and temperature), aimed to short-term prediction, have been possible using the Almanac of Minutely Power dataset (AMPds). On the contrary, the Energy Information Administration (E.I.A.) data are used for long-term prediction combining gas and temperature information. At the end, the selected approaches have been evaluated using the sole Tehran water consumption for long-term forecasts (thanks to the full availability of the dataset). The AMPds and E.I.A. natural gas results show a correlation with temperature, that produce a performance improvement. The ANN and SVR approaches achieved good performance for both long/short-term predictions, while the EKF-GP showed good outcomes with the E.I.A. datasets. Finally, it is the authors' purpose to create a valid starting point for future works that aim to develop innovative forecasting approaches, providing a fair comparison among different computational intelligence and machine learning techniques.
Scheda della pubblicazione: https://iris.univpm.it/handle/11566/230155 Collegamento a IRIS

2015 A Deep Neural Network approach for Voice Activity Detection in multi-room domestic scenarios
Proceedings of the International Joint Conference on Neural Networks
Autore/i: Ferroni, G.; Bonfigli, R.; Principi, E.; Squartini, S.; Piazza, F.
Classificazione: 4 Contributo in Atti di Convegno (Proceeding)
Abstract: This paper presents a Voice Activity Detector (VAD) for multi-room domestic scenarios. A multi-room VAD (mVAD) simultaneously detects the time boundaries of a speech segment and determines the room where it was generated. The proposed approach is fully data-driven and is based on a Deep Neural Network (DNN) pre-trained as a Deep Belief Network (DBN) and fine-tuned by a standard error back-propagation method. Six different types of feature sets are extracted and combined from multiple microphone signals in order to perform the classification. The proposed DBN-DNN multi-room VAD (simply referred to as DBN-mVAD) is compared to other two NN based mVADs: a Multi-Layer Perceptron (MLP-mVAD) and a Bidirectional Long Short-Term Memory recurrent neural network (BLSTM-mVAD). A large multi-microphone dataset, recorded in a home, is used to assess the performance through a multi-stage analysis strategy comprising multiple feature selection stages alternated by network size and input microphones selections. The proposed approach notably outperforms the alternative algorithms in the first feature selection stage and in the network selection one. In terms of area under precision-recall curve (AUC), the absolute increment respect to the BLST-mVAD is 5.55%, while respect to the MLP-mVAD is 2.65%. Hence, solely the proposed approach undergoes the remaining selection stages. In particular, the DBN-mVAD achieves significant improvements: in terms of AUC and F-measure the absolute increments are equal to 10.41% and 8.56% with respect to the first stage of DBN-mVAD.
Scheda della pubblicazione: https://iris.univpm.it/handle/11566/230585 Collegamento a IRIS

2015 Multi-apartment residential microgrid with electrical and thermal storage devices: experimental analysis and simulation of energy management strategies
APPLIED ENERGY
Autore/i: G. Comodi; A. Giantomassi; M. Severini; S. Squartini; F. Ferracuti; A. Fonti; D. Nardi Cesarini; M. Morodo; F. Polonara
Classificazione: 1 Contributo su Rivista
Abstract: The paper presents the operational results of a real life residential microgrid which includes six apartments, a 20 kWp photovoltaic plant, a solar based thermal energy plant, a geothermal heat pump, a thermal energy storage, in the form of a 1300 litres water tank and two 5.8 kWh batteries supplying, each, a couple of apartments. Thanks to the thermal energy storage, the solar based thermal energy plant is able to satisfy the 100% of the hot water summer demand. Therefore the thermal energy storage represents a fundamental element in the management of the residential demand of thermal energy. It collects renewable thermal energy during day-time to release it during night-time, effectively shaving the peak of the thermal energy demand. The two electric storages, on the other hand, provide the hosted electrical subsystems with the ability to effectively increase the self-consumption of the local energy production, thus lowering the amount of energy surplus to be sold back to the grid, and increasing the self- sufficiency of the microgrid. For instance, the storage has supported self-consumption up to the 58.1% of local energy production with regard to the first battery, and up to the 63.5% with regard to the second one. Also, 3165 and 3365 yearly hours of fully autonomous activity have been recorded thanks to the first, and the second battery respectively. On the other hand, the yearly average efficiency amounts to 63.7%, and 65.3% respectively, for the first and second battery. In the second part of the paper we propose a computational framework to evaluate the overall performance of the microgrid system, while accounting different operating conditions and energy management policies. From this perspective, the framework acts as a useful modelling and design tool, to assess the opportunity of employing alternative energy management system topologies and strategies. Eight different configurations, with growing complexity, have been derived from the original system on purpose. The simulations, carried out based on real data related to one-year time period, have provided results showing that, the higher the integration level of electrical and thermal storage is, the higher degree of self-sufficiency can be achieved by the microgrid, and, in turn, the more consistent the yearly energy saving become.Nevertheless, despite the energy cost reduction achievable with the availability of storage systems in the Leaf House, their high investment cost made them not really profitable at the current price conditions for devices and energy purchase.
Scheda della pubblicazione: https://iris.univpm.it/handle/11566/179304 Collegamento a IRIS

2015 A Novel Approach for Automatic Acoustic Novelty Detection Using a Denoising Autoencoder with Bidirectional LSTM Neural Networks
Proceedings of ICASSP 2015
Autore/i: Marchi, E.; Vesperini, F.; Eyben, F.; Squartini, S.; Schuller, B.
Classificazione: 4 Contributo in Atti di Convegno (Proceeding)
Abstract: Acoustic novelty detection aims at identifying abnormal/novel acoustic signals which differ from the reference/normal data that the system was trained with. In this paper we present a novel unsupervised approach based on a denoising autoencoder. In our approach auditory spectral features are processed by a denoising autoencoder with bidirectional Long Short-Term Memory recurrent neural networks. We use the reconstruction error between the input and the output of the autoencoder as activation signal to detect novel events. The autoencoder is trained on a public database which contains recordings of typical in-home situations such as talking, watching television, playing and eating. The evaluation was performed on more than 260 different abnormal events. We compare results with state-of-theart methods and we conclude that our novel approach significantly outperforms existing methods by achieving up to 93.4% F-Measure.
Scheda della pubblicazione: https://iris.univpm.it/handle/11566/230580 Collegamento a IRIS

2015 Energy management with the support of dynamic pricing strategies in real micro-grid scenarios
Proceedings of the International Joint Conference on Neural Networks
Autore/i: Severini, M.; Squartini, S.; Fagiani, M.; Piazza, F.
Classificazione: 4 Contributo in Atti di Convegno (Proceeding)
Abstract: Although smart grids are regarded as the technology to overcome the limits of nowadays power distribution grids, the transition will require much time. Dynamic pricing, a straightforward implementation of demand response, may provide the means to manipulate the grid load thus extending the life expectancy of current technology. However, to integrate a dynamic pricing scheme in the crowded pool of technologies, available at demand side, a proper energy manager with the support of a pricing profile forecaster is mandatory. Although energy management and price forecasting are recurrent topics, in literature they have been addressed separately. On the other hand, in this work, the aim is to investigate how well an energy manager is able to perform in presence of data uncertainty originating from the forecasting process. On purpose, an energy and resource manager has been revised and extended in the current manuscript. Finally, it has been complemented with a price forecasting technique, based on the Extreme Learning Machine paradigm. The proposed forecaster has proven to be better performing and more robust, with respect to the most common forecasting approaches. The energy manager, as well, has proven that the energy efficiency of the residential environment can be improved significantly. Nonetheless, to achieve the theoretical optimum, forecasting techniques tailored for that purpose may be required.
Scheda della pubblicazione: https://iris.univpm.it/handle/11566/230586 Collegamento a IRIS

2015 A floor acoustic sensor for fall classification
138th Audio Engineering Society Convention 2015
Autore/i: Principi, E.; Olivetti, P.; Squartini, S.; Bonfigli, R.; Piazza, F.
Classificazione: 4 Contributo in Atti di Convegno (Proceeding)
Abstract: The interest in assistive technologies for supporting people at home is constantly increasing, both in academia and industry. In this context, the authors propose a fall classification system based on an innovative acoustic sensor that operates similarly to stethoscopes and captures the acoustic waves transmitted through the floor. The sensor is designed to minimize the impact of aerial sounds in recordings, thus allowing a more focused acoustic description of fall events. In this preliminary work, the audio signals acquired by means of the sensor are processed by a fall recognition algorithm based on Mel-Frequency Cepstral Coefficients, Supervectors and Support Vector Machines, to discriminate among different types of fall events. The performance of the algorithm has been evaluated against a specific audio corpus comprising falls of persons and of common objects. The results show the effectiveness of the approach.
Scheda della pubblicazione: https://iris.univpm.it/handle/11566/230581 Collegamento a IRIS

2015 An integrated system for voice command recognition and emergency detection based on audio signals
EXPERT SYSTEMS WITH APPLICATIONS
Autore/i: Principi, E.; Squartini, S.; Ferroni, G.; Bonfigli, R.; Piazza, F.
Classificazione: 1 Contributo su Rivista
Abstract: The recent reports on population ageing in the most advanced countries are driving governments and the scientific community to focus on technologies for providing assistance to people in their own homes. Particular attention has been devoted to solutions based on acoustic signals since they provide a convenient way to monitor people activities and they enable hands-free human–machine interfaces. In this context, this paper presents a complete solution for voice command recognition and emergency detection based on audio signals entirely integrated in a low-consuming embedded platform. The system combines an active operation mode were distress calls are captured and a vocal interface is enabled for controlling the home automation subsystem, and a pro-active mode, were a novelty detection algorithm detects abnormal acoustic events to alert the user of a possible emergency. In the first operation mode, a Voice Activity Detector captures voice segments of the audio signal, and a speech recogniser detects commands and distress calls. In the pro-active mode, an acoustic novelty detector is employed in order to be able to deal with unknown sounds, thus not requiring an explicit modelling of emergency sounds. In addition, the system integrates a VoIP infrastructure so that emergencies can be communicated to relatives or care centres. The monitoring unit is equipped with multiple microphones and it is connected to the home local area network to communicate with the home automation subsystem. The algorithms have been implemented in a low-consuming embedded platform based on a ARM Cortex-A8 CPU. The effectiveness of the adopted algorithms has been tested on two different databases: ITAAL and A3Novelty. The obtained results show that the adopted solutions are suitable for speech and audio event monitoring in a realistic scenario.
Scheda della pubblicazione: https://iris.univpm.it/handle/11566/224934 Collegamento a IRIS

2015 Clock skew compensation by adaptive resampling for audio networking
138th Audio Engineering Society Convention 2015
Autore/i: Gabrielli, L.; Bussolotto, M.; Squartini, S.; Adriaensen, F.
Classificazione: 4 Contributo in Atti di Convegno (Proceeding)
Abstract: Wired Audio Networking is an established practice since years, based on both proprietary solutions or open hardware and protocols. One of the most cost-effective solutions is the use of a general purpose IEEE 802.3 infrastructure and personal computers running IP based protocols. One obvious shortcoming of such setup is the lack of synchronization at the audio level and the presence of a network delay affected by jitter. Two approaches to sustain a continuous audio flow are described, implemented by the authors in open source projects based on a relative and absolute time adaptive resampling. A description of the mechanisms is provided along with simulated and measured results, which show the validity of both approaches.
Scheda della pubblicazione: https://iris.univpm.it/handle/11566/230582 Collegamento a IRIS

2015 Non-Linear Prediction with LSTM Recurrent Neural Networks for Acoustic Novelty Detection
Proceedings of the International Joint Conference on Neural Networks
Autore/i: Marchi, E.; Vesperini, F.; Weninger, F.; Eyben, F.; Squartini, S.; Schuller, B.
Classificazione: 4 Contributo in Atti di Convegno (Proceeding)
Abstract: Acoustic novelty detection aims at identifying abnormal/novel acoustic signals which differ from the reference/normal data that the system was trained with. In this paper we present a novel approach based on non-linear predictive denoising autoencoders. In our approach, auditory spectral features of the next short-term frame are predicted from the previous frames by means of Long-Short Term Memory (LSTM) recurrent denoising autoencoders. We show that this yields an effective generative model for audio. The reconstruction error between the input and the output of the autoencoder is used as activation signal to detect novel events. The autoencoder is trained on a public database which contains recordings of typical in-home situations such as talking, watching television, playing and eating. The evaluation was performed on more than 260 different abnormal events. We compare results with state-of-the-art methods and we conclude that our novel approach significantly outperforms existing methods by achieving up to 94.4% F-Measure.
Scheda della pubblicazione: https://iris.univpm.it/handle/11566/230587 Collegamento a IRIS

2015 Unsupervised algorithms for non-intrusive load monitoring: An up-to-date overview
2015 IEEE 15th International Conference on Environment and Electrical Engineering, EEEIC 2015 - Conference Proceedings
Autore/i: Bonfigli, R.; Squartini, S.; Fagiani, M.; Piazza, F.
Editore: IEEE
Classificazione: 4 Contributo in Atti di Convegno (Proceeding)
Abstract: Research on Smart Grids has recently focused on the energy monitoring issue, with the objective to maximize the user consumption awareness in building contexts on one hand, and to provide a detailed description of customer habits to the utilities on the other. One of the hottest topic in this field is represented by Non-Intrusive Load Monitoring (NILM): it refers to those techniques aimed at decomposing the consumption aggregated data acquired at a single point of measurement into the diverse consumption profiles of appliances operating in the electrical system under study. The focus here is on unsupervised algorithms, which are the most interesting and of practical use in real case scenarios. Indeed, these methods rely on a sustainable amount of a-priori knowledge related to the applicative context of interest, thus minimizing the user intervention to operate, and are targeted to extract all information to operate directly from the measured aggregate data. This paper reports and describes the most promising unsupervised NILM methods recently proposed in the literature, by dividing them into two main categories: load classification and source separation approaches. An overview of the public available dataset used on purpose and a comparative analysis of the algorithms performance is provided, together with a discussion of challenges and future research directions.
Scheda della pubblicazione: https://iris.univpm.it/handle/11566/230591 Collegamento a IRIS

2015 A Novelty Detection approach to identify the occurrence of leakage in Smart Gas and Water Grids
Proceedings of the International Joint Conference on Neural Networks
Autore/i: Fagiani, M.; Squartini, S.; Severini, M.; Piazza, F.
Classificazione: 4 Contributo in Atti di Convegno (Proceeding)
Abstract: In this paper, a novelty detection algorithm for the identification of leakages in smart water/gas grid contexts is proposed. It is based on two separate stages: the first deals with the creation of the statistical leakage-free model, whereas the second evaluates the eventual occurrence of leakage on the basis of the model likelihood. Up to the authors' knowledge, this approach has never been used in the application scenario of interest. A set of several features are extracted from the Almanac of Minutely Power Dataset, and a suboptimal selection is executed to determinate the best combination. The abnormal event (leakage) is induced by manipulating the consumption in the test set. A total of 10 background models are created, by employing both Gaussian Mixture Models (GMMs) and Hidden Markov Models (HMMs) under a comparative perspective, and each of them is adopted to detect 10 leakages, with random duration, length and starting time. Finally, the performance are evaluated in terms of Area Under Curve (AUC) of the Receiver Operating Characteristic (ROC). Obtained results are more than encouraging: the best average AUCs of 85.60% and 87.97% are achieved with HMM, at 1 minute resolution, for natural gas and water, respectively. Specifically, considering true detection rates (TDRs) of 100%, the natural gas exhibits an overall false detection rate (FDR) of 17.11%, and the water achieves an overall FDR of 13.79%.
Scheda della pubblicazione: https://iris.univpm.it/handle/11566/230584 Collegamento a IRIS

2015 Signer Independent Isolated Italian Sign Recognition Based on Hidden Markov Models
PATTERN ANALYSIS AND APPLICATIONS
Autore/i: M. Fagiani; E. Principi; S. Squartini; F. Piazza
Classificazione: 1 Contributo su Rivista
Abstract: Sign languages represent the most natural way to communicate for deaf and hard of hearing. However, there are often barriers between people using this kind of languages and hearing people, typically oriented to express themselves by means of oral languages. In order to facilitate the social inclu- siveness in everyday life for deaf minorities, technology can play an impor- tant role. Indeed many attempts have been recently made by the scientific community to develop automatic translation tools. Unfortunately, not many solutions are actually available for the Italian Sign Language (Lingua Italiana dei Segni - LIS) case study, specially for what concerns the recognition task. In this paper the authors want to face such a lack, in particular addressing the signer-independent case study, i.e., when the signers in the testing set are to included in the training set. From this perspective, the proposed algorithm represents the first real attempt in the LIS case. The automatic recognizer is based on Hidden Markov Models (HMMs) and video features have been extracted by using the OpenCV open source library. The effectiveness of the HMM system is validated by a comparative evaluation with Support Vector Machine approach. The video material used to train the recognizer and testing its performance consists in a database that the authors have deliberately cre- ated by involving ten signers and 147 isolated-sign videos for each signer. The database is publicly available. Computer simulations have shown the effective- ness of the adopted methodology, with recognition accuracies comparable to those obtained by the automatic tools developed for other sign languages.
Scheda della pubblicazione: https://iris.univpm.it/handle/11566/179303 Collegamento a IRIS

2015 Domestic Water and Natural Gas Demand Forecasting by using Heterogeneous Data: A Preliminary Study
Advances in Neural Networks: Computational and Theoretical Issues
Autore/i: Fagiani, M.; Squartini, S.; Gabrielli, L.; Spinsante, S.; Piazza, F.
Editore: Springer Science and Business Media Deutschland GmbH
Classificazione: 2 Contributo in Volume
Abstract: In this paper a preliminary study concerning prediction of domestic consumptions of water and natural gas based on genetic pro- gramming (GP) and its combination with extended Kalman Filter (EKF) is presented. The used database (AMPds) are composed of power, water, natural gas consumptions and temperatures. The study aims to investi- gate novel solutions and adopts state-of-the-art approaches to forecast resource demands using heterogeneous data of an household scenario. In order to have a better insight of the prediction performance and properly evaluate possible correlation between the various data types, the GP ap- proach has been applied varying the combination of input data, the time resolution, the number of previous data used for the prediction (lags) and the maximum depth of the tree. The best performance for both water and natural gas prediction have been achieved using the results obtained by the GP model created for a time resolution of 24 h, and using a set of input data composed of both water and natural gas consumptions. The results confirm the presence of a strong correlation between natural gas and water consumptions. Additional experiments have been executed in order to evaluate the effect of the prediction performance using long period heterogeneous data, obtained from the U.S. Energy Information Administration (E.I.A.).
Scheda della pubblicazione: https://iris.univpm.it/handle/11566/225146 Collegamento a IRIS

2015 Energy-Aware Task Scheduler for Self-Powered Sensor Nodes: from Model to Firmware
AD HOC NETWORKS
Autore/i: M. Severini; S. Squartini; F. Piazza; M. Conti
Classificazione: 1 Contributo su Rivista
Abstract: The self-powering paradigm surely represents a challenging issue in the Wireless Sensor Network (WSN) field. The chance of supplying the sen- sor node with environmental energy is attractive not only to make it au- tonomous and reduce the human intervention for battery substitution but also to improve the overall WSN flexibility and applicability. From this same perspective, a relevant role is played by the node task scheduling, which is required to face strong constraints due to energy availability limitations. On purpose, some of the authors have recently proposed an Energy-Aware ap- proach (namely Energy-Aware Lazy Scheduling Algorithm, EA-LSA), which shows a certain versatility in efficiently exploiting the harvested energy, re- ducing the starving occurrences in non-ideal conditions, with respect to the no-EA counterpart. In this work a task scheduler based on the EA-LSA technique has been implemented on a low-cost and commercially available platform, from Texas Instruments, with the aim to propose an open and easy-to-use HW/SW ref- erence for the community working in the field. The firmware, including the hardware abstraction and the scheduling routine layers, has been developed from scratch. Moreover, a few tasks have been developed so that the device activity could be simulated in a realistic scenario. To monitor the harvesting process an emulated energy harvester has been devised and included in the overall framework. The different task energy consumptions have been measured by means of an energy audit tool, specifically set up in order to properly gauge the very low current consumptions of the device. Experiments performed under different power income levels, allowed to positively conclude about the effectiveness of the implemented Energy-Aware scheduler, its flexibility in terms of environmental energy exploitation, and therefore its suitability for involvement in real-world WSNs.
Scheda della pubblicazione: https://iris.univpm.it/handle/11566/174308 Collegamento a IRIS

2014 Reducing the Latency in Live Music Transmission with the BeagleBoard xM Through Resampling
Proceedings od EDERC 2014
Autore/i: L. Gabrielli; M. Bussolotto; S. Squartini
Classificazione: 4 Contributo in Atti di Convegno (Proceeding)
Abstract: In previous works, a widespread embedded platform, the BeagleBoard xM, was shown to provide sufficient through-put and acceptable latency for live music control and audio signals transmission on standard LAN and WLAN protocols. Although the preliminary work opened the way for further investigations, the software stack did not prove efficient enough to deliver stable audio performance below the perceptual latency threshold for good ensemble playing. This work reports on a custom Debian Linux image, called WeMUST-OS for the BeagleBoard xM, configured for the task at hand by careful low-level ALSA driver configuration with the DM3730 SoC and the TPS65950 audio codec to improve local audio input/output latency. Furthermore Jacktrip, an application for music audio transmission, has been modified with added support to resampling enabling seamless connection with other devices running audio at different sample rate and period size. Leveraging these two achievements, latency is shown to keep under perceptual threshold for ensemble music performance including transmission of the monitoring signal.
Scheda della pubblicazione: https://iris.univpm.it/handle/11566/179905 Collegamento a IRIS

2014 A Nonlinear Second-Order Digital Oscillator For Virtual Acoustic Feedback
Proceedings of ICASSP2014
Autore/i: L. Gabrielli; M. Giobbi; S. Squartini; V. Valimaki
Classificazione: 4 Contributo in Atti di Convegno (Proceeding)
Abstract: The guitar feedback effect, or howling, is well known to the general public and identified with many rock music genres and it is the only case of acoustic feedback employed for musical purposes. Virtual Acoustic Feedback (VAF), is regarded as the extension of this phenomenon to any instrument or sound source by means of virtual acoustics and is meant to enrich the sound palette of a musician. The study of the acoustic feedback as a musical tool and computational techniques for its emulation have been scarcely addressed in literature. In this paper a nonlinear feedback oscillator is proposed and its properties derived. The oscillator does not necessarily need to be connected to a virtual instrument, thus enables to process any kind of pitched real-time input.
Scheda della pubblicazione: https://iris.univpm.it/handle/11566/153903 Collegamento a IRIS

2014 Smart Water Grids for Smart Cities: a Sustainable Prototype Demonstrator
Proceedings of EuCNC 2014
Autore/i: L. Gabrielli; M. Pizzichini; S. Spinsante; S. Squartini; R. Gavazzi
Classificazione: 4 Contributo in Atti di Convegno (Proceeding)
Abstract: n the framework of a smart city, information and communications technologies are applied to tackle urban living challenges, with the aim of improving the citizens' quality of life, through a more efficient use of limited resources. Urban sensing by wireless sensor networks allows the collection, processing, analysis, and dissemination of valuable information, that is used to design adequate policies matching the users' needs, and avoiding non-ecological wasting of resources. To face an increasing water demand, and ensure a safe access to clean water resources, a network of sensor nodes could be located along water pipes. The automatic monitoring of the water grid, and the smart metering of water consumptions could be enabled, to increase the users' awareness, and improve the efficiency of the infrastructure management. To this aim, the paper presents a prototype demonstrator of a smart water metering infrastructure, developed in cooperation with Telecom Italia Lab, and built upon self-powered nodes in a Wireless Metering Bus capillary network at 169 MHz. The main elements of the system are presented, and the attainable performance discussed, through a number of experimental results.
Scheda della pubblicazione: https://iris.univpm.it/handle/11566/171904 Collegamento a IRIS

2014 A Real-Time Implementation of an Acoustic Novelty Detector on the BeagleBoard-xM
Proceedings of EDERC2014
Autore/i: R. Bonfigli; G. Ferroni; E. Principi; S. Squartini; F. Piazza
Classificazione: 4 Contributo in Atti di Convegno (Proceeding)
Abstract: Novelty detection consists in recognising events that deviate from normality. This paper presents the implementation of a real-time statistical novelty detector on the BeagleBoard-xM. The application processes an incoming audio signal, extracts Power Normalized Cepstral Coefficients and determines whether a novelty sound is present or not based on a statistical model of normality. The novelty detector has been implemented as a standalone graphical application capable of running in real-time on the BeagleBoard-xM platform. Experiments have been conducted to assess the performance of the solution in terms of both detection performance and of real-time capabilities. The results demonstrate that the system is able to operate in real-time on the BeagleBoard-xM with a real-time factor equal to 8.10%, and an F-Measure equal to 77.41%.
Scheda della pubblicazione: https://iris.univpm.it/handle/11566/179903 Collegamento a IRIS

2014 Neural Networks Based Methods for Voice Activity Detection in a Multi-room Domestic Environment
Proceedings of the First Italian Conference on Computational Linguistics CLiC-it 2014 & the Fourth International Workshop EVALITA 2014
Autore/i: G. Ferroni; R. Bonfigli; E. Principi; S. Squartini; F. Piazza
Classificazione: 4 Contributo in Atti di Convegno (Proceeding)
Abstract: A plethora of Voice or Speaker Activity Detection systems exist in literature. They are indeed a fundamental part of complex systems that deals with speech processing. In this work the authors exploit neural network based VAD to address the speaker activity detection in a multi-room domestic scenario. The goal is to detect the voice activity in each of the two target rooms in presence of other sounds and speeches occurring in other rooms and outside. A large dataset recorded in a smart-home is provided and result obtained are acceptable.
Scheda della pubblicazione: https://iris.univpm.it/handle/11566/205118 Collegamento a IRIS

2014 BAR LIS: a web application for Italian Sign Language based interaction
AMBIENT ASSISTED LIVING
Autore/i: Luca Nardi; Matteo Rubini; Stefano Squartini; Emanuele Principi; Francesco Piazza
Editore: Springer Verlag Germany:Tiergartenstrasse 17, D 69121 Heidelberg Germany:011 49 6221 3450, EMAIL: g.braun@springer.de, INTERNET: http://www.springer.de, Fax: 011 49 6221 345229
Classificazione: 2 Contributo in Volume
Abstract: This work presents the development and testing of BAR LIS (BAR in Italian Sign Language), a web application created in collaboration with the Ancona division of Ente Nazionale Sordi (ENS) and presented during X Masters Awards 2012 event in Senigallia, Italy. BAR LIS was structured as a small dictionary of words and related signs in LIS, Italian Sign Language (presented as 3D rendered animations) in order to ease communication between people attending the X Masters event and hearing impaired personnel of the ENS stall, which included a small coffee shop. A more extensive set of words was later created and tested with ENS members in order to study the impact of resolution of 3D models on comprehensibility and quality of the signs.
Scheda della pubblicazione: https://iris.univpm.it/handle/11566/127262 Collegamento a IRIS

2014 Riconoscimento Automatico di Richieste di Aiuto e Comandi di Domotica per Ambient Assisted Living
X Convegno Nazionale dell'Associazione Italiana di Scienze della Voce
Autore/i: E. Principi; S. Squartini; F. Piazza
Classificazione: 4 Contributo in Atti di Convegno (Proceeding)
Scheda della pubblicazione: https://iris.univpm.it/handle/11566/205117 Collegamento a IRIS

2014 Wireless M-Bus Sensor Networks for Smart Water Grids: Analysis and Results
INTERNATIONAL JOURNAL OF DISTRIBUTED SENSOR NETWORKS
Autore/i: S. Spinsante; S. Squartini; L. Gabrielli; M. Pizzichini; E. Gambi; F. Piazza
Classificazione: 1 Contributo su Rivista
Abstract: Wireless sensor network technologies are experiencing an impressive development, as they represent one of the building blocks upon which new paradigms, such as Internet of Things and Smart Cities, may be implemented. Among the different applications enabled by such technologies, automatic monitoring of the water grid, and smart metering of water consumptions, may have a great impact on the preservation of one of the most valued, and increasingly scarce, natural resources. Sensor nodes located along water pipes cannot rely on the availability of power grid facilities to get the necessary energy imposed by their working conditions. In this sense, an energy-efficient design of the network architecture, and the evaluation of Energy Harvesting techniques to sustain its nodes, becomes of paramount importance. This paper investigates the suitability of a Wireless Metering Bus-based solution for the implementation of smart water grids, by evaluating network and node related performance, through simulations, prototype design, and experimental tests, which confirm the feasibility and efficiency of the proposal.
Scheda della pubblicazione: https://iris.univpm.it/handle/11566/171903 Collegamento a IRIS

2014 Computational Framework based on Task and Resource Scheduling for Micro Grid Design
Proceedings of IJCNN2014
Autore/i: M. Severini; S. Squartini; F. Piazza
Classificazione: 4 Contributo in Atti di Convegno (Proceeding)
Abstract: Within micro grid scenarios, optimal energy management represents an important paradigm to improve the grid efficiency while lowering its burden. While usually real time energy management is considered, an offline approach can be also adopted to maximize the grid efficiency in certain contexts. Indeed, by evaluating the energy management performance according to the user needs, it is possible to asses which technologies allow the overall system to operate at its best, given the expected load level. From this perspective, a computational framework based on the "Mixed-Integer Linear Programming" paradigm has been proposed in this paper as a tool to simulate the micro grid behaviour in terms of energy consumption and in dependence on the technology of choice. By modelling the energy production and storage means, the pool of electricity tasks, and the thermal behaviour of the building, suitable energy management policies for the micro grid scenario under study can be developed and tested in different operating conditions and time horizons. Moreover, the forecasting paradigm has been integrated into the framework to deal with data uncertainty, and a Neural Network approach has been employed on purpose. Performed computer simulations, related to a six-apartments building scenario, have proven that the suggested framework can fruitfully be adopted to assess the effectiveness of different technical solutions in terms of overall energy cost, thus supporting the decisional process occurring during the micro grid design.
Scheda della pubblicazione: https://iris.univpm.it/handle/11566/153907 Collegamento a IRIS

2014 Audio Onset Detection: A Wavelet Packet Based Approach with Recurrent Neural Networks
Proceedings of IJCNN2014
Autore/i: E. Marchi; G. Ferroni; F. Eyben; S. Squartini; B. Schuller
Classificazione: 4 Contributo in Atti di Convegno (Proceeding)
Abstract: This paper concerns the exploitation of multi-resolution time-frequency features via Wavelet Packet Transform to improve audio onset detection. In our approach, Wavelet Packet Energy Coefficients (WPEC) and Auditory Spectral Features (ASF) are processed by Bidirectional Long Short-Term Memory (BLSTM) recurrent neural network that yields the onsets location. The combination of the two feature sets, together with the BLSTM based detector, form an advanced energy-based approach that takes advantage from the multi-resolution analysis given by the wavelet decomposition of the audio input signal. The neural network is trained with a large database of onset data covering various genres and onset types. Due to its data-driven nature, our approach does not require the onset detection method and its parameters to be tuned to a particular type of music. We show a comparison with other types and sizes of recurrent neural networks and we compare results with state-of-the-art methods on the whole onset dataset. We conclude that our approach significantly increase performance in terms of F-measure without any music genres or onset type constraints.
Scheda della pubblicazione: https://iris.univpm.it/handle/11566/153905 Collegamento a IRIS

2014 Improving the performance of a in-home acoustic monitoring system by integrating a vocal effort classification algorithm
Proceedings of AES 136th Convention
Autore/i: E. Principi; S. Squartini; F. Piazza
Classificazione: 4 Contributo in Atti di Convegno (Proceeding)
Scheda della pubblicazione: https://iris.univpm.it/handle/11566/153910 Collegamento a IRIS

2014 Learning capabilities of ELM-trained Time-Varying Neural Networks
Recent Advances of Neural Network Models and Applications
Autore/i: S. Squartini; Y. Ye; F. Piazza
Editore: Springer Verlag Germany:Tiergartenstrasse 17, D 69121 Heidelberg Germany:011 49 6221 3450, EMAIL: g.braun@springer.de, INTERNET: http://www.springer.de, Fax: 011 49 6221 345229
Classificazione: 2 Contributo in Volume
Scheda della pubblicazione: https://iris.univpm.it/handle/11566/127266 Collegamento a IRIS

2014 Smart Home Task and Energy Resource Scheduling based on Nonlinear Programming
Recent Advances of Neural Network Models and Applications
Autore/i: M. Severini; S. Squartini; G. Surace; F. Piazza
Editore: Springer Verlag Germany:Tiergartenstrasse 17, D 69121 Heidelberg Germany:011 49 6221 3450, EMAIL: g.braun@springer.de, INTERNET: http://www.springer.de, Fax: 011 49 6221 345229
Classificazione: 2 Contributo in Volume
Scheda della pubblicazione: https://iris.univpm.it/handle/11566/127267 Collegamento a IRIS

2014 Computational Intelligence in Smart Water and Gas Grids: an Up-to-Date Overview
Proceedings of IJCNN2014
Autore/i: M. Fagiani; S. Squartini; L. Gabrielli; M. Pizzichini; S. Spinsante
Classificazione: 4 Contributo in Atti di Convegno (Proceeding)
Abstract: Computational Intelligence plays a relevant role in several Smart Grid applications, and there is a florid literature in this regard. However, most of the efforts have been oriented to the electrical energy field, for which many contributions have appeared so far, also facilitated by the availability of suitable databases to use for system training and testing. Different is the case for the water and gas scenarios: this work is thus oriented to present the state-of-the-art techniques for these grids, from 2009 to date. In particular, the focus is on load forecasting and leakage detection applications, that are the most addressed in the literature and present the biggest interest from a commercial point of view as well: the main characteristics and registered performance for all the reviewed approaches are reported. Along this direction, an extensive search of used databases has been performed and thus made available to the research community.
Scheda della pubblicazione: https://iris.univpm.it/handle/11566/153908 Collegamento a IRIS

2014 Advanced Integration of Multimedia Assistive Technologies: a prospective outlook
Proceedings of MESA 2014
Autore/i: D. Liciotti; G. Ferroni; E. Frontoni; S. Squartini; E. Principi; R. Bonfigli; P. Zingaretti; F. Piazza
Classificazione: 4 Contributo in Atti di Convegno (Proceeding)
Abstract: In the recent years several studies on population ageing in the most advanced countries argued that the share of people older than 65 years is steadily increasing. In order to tackle this phenomena, a significant effort has been devoted to the development of advanced technologies for supervising the domestic environments and their inhabitants to provide them assistance in their own home. In this context, the present paper aims to delineate a novel, highly-integrated system for advanced analysis of human behaviours. It is based on the fusion of the audio and vision frameworks, developed at the Multimedia Assistive Technology Laboratory (MATeLab) of the Università Politecnica delle Marche, in order to operate in the ambient assisted living context exploiting audio-visual domain features. The existing video framework exploits vertical RGB-D sensors for people tracking, interaction analysis and users activities detection in domestic scenarios. The depth information has been used to remove the affect of the appearance variation and to evaluate users activities inside the home and in front of the fixtures. In addition, group interactions are monitored and analysed. On the other side, the audio framework recognises voice commands by continuously monitoring the acoustic home environment. In addition, a hands-free communication to a relative or to a healthcare centre is automatically triggered when a distress call is detected. Echo and interference cancellation algorithms guarantee the high-quality communication and reliable speech recognition, respectively. The system we intend to delineate, thus, exploits multi-domain information, gathered from audio and video frameworks each, and stores them in a remote cloud for instant processing and analysis of the scene. Related actions are consequently performed.
Scheda della pubblicazione: https://iris.univpm.it/handle/11566/179906 Collegamento a IRIS

2014 Multi-resolution Linear Prediction Based Features for Audio Onset Detection with Bidirectional LSTM Neural Networks
Proceedings of ICASSP2014
Autore/i: E. Marchi; G. Ferroni; F. Eyben; L. Gabrielli; S. Squartini; B. Schuller
Classificazione: 4 Contributo in Atti di Convegno (Proceeding)
Abstract: A plethora of different onset detection methods have been proposed in the recent years. However, few attempts have been made with respect to widely-applicable approaches in order to achieve superior performances over different types of music and with considerable temporal precision. In this paper, we present a multi-resolution approach based on discrete wavelet transform and linear prediction filtering that improves time resolution and performance of onset detection in different musical scenarios. In our approach, wavelet coefficients and forward prediction errors are combined with auditory spectral features and then processed by a bidirectional Long Short-Term Memory recurrent neural network, which acts as reduction function. The network is trained with a large database of onset data covering various genres and onset types. We compare results with state-of-the-art methods on a dataset that includes Bello, Glover and ISMIR 2004 Ballroom sets, and we conclude that our approach significantly outperforms existing methods in terms of F-Measure. For pitched non percussive music an absolute improvement of 7.5% is reported.
Scheda della pubblicazione: https://iris.univpm.it/handle/11566/153904 Collegamento a IRIS

2014 Power Normalized Cepstral Coefficients based supervectors and i-vectors for small vocabulary speech recognition
Proceedings of IJCNN2014
Autore/i: E. Principi; S. Squartini; F. Piazza
Classificazione: 4 Contributo in Atti di Convegno (Proceeding)
Abstract: Template-matching and discriminative techniques, like support vector machines (SVMs), have been widely used for automatic speech recognition. Both methods require that varying length sequences are mapped to vectors of fixed lengths: in template-matching, the problem is solved by means of dynamic time warping (DTW), while in SVM with dynamic kernels. The supervector and i-vector paradigms seem to represent a valid solution to such a problem when SVM are employed for classification. In this work, Gaussian mean supervectors (GMS), Gaussian posterior probability supervectors (GPPS) and i-vectors are evaluated as features both for template-matching and for SVM-based speech recognition in a comparative fashion. All these features are based on Power Normalized Cepstral Coefficients (PNCCs) directly extracted from speech utterances. The different methods are assessed in small vocabulary speech recognition tasks using two distinct corpora, and they have been compared to DTW, dynamic time alignment kernel (DTAK), outerproduct of trajectory matrix, and PocketSphinx as further recognition techniques to be evaluated. Experimental results showed the appropriateness of the supervector and i-vector based solutions with respect to the other state-of-the art techniques here addressed.
Scheda della pubblicazione: https://iris.univpm.it/handle/11566/153906 Collegamento a IRIS

2014 Energy Demand Management Through Uncertain Data Forecasting: An Hybrid Approach
Frontiers of Intelligent Control and Information Processing
Autore/i: M. Severini; S. Squartini; F. Piazza
Editore: World Scientific Publishing Company
Classificazione: 2 Contributo in Volume
Abstract: Although Smart Grids may represent the solution to the limits of nowa- days Power Grid, the turnover may not occur in the next future yet due the complex nature of energy distribution. Thus, as a more short term effort, to improve the responsiveness of the energy demand to the power grid load, more and more energy providers apply dynamic pricing schemes for grid users. Believing that dynamic pricing policies may be an effective asset even at a micro-grid level, an hybrid en- ergy management scheme is proposed in this contribution. While the nonlinear nature of a micro grid, involving the task allocation and the thermal constraint satisfaction, can be modeled as a mixed integer nonlinear programming problem, neural-network forecasting abilities can provide a sustainable support under real- istic operating conditions. Based on the forecast of solar energy production and grid energy prices and outdoor temperature, the optimization of tasks allocation is aimed to lower both the user costs and the grid burden while accounting the ther- mal comfort of the user. Through computer simulations, whose degree of realism is enhanced by the adoption of forecast data, the shift of the grid load towards low energy price hours is confirmed.
Scheda della pubblicazione: https://iris.univpm.it/handle/11566/136663 Collegamento a IRIS

2014 Adaptive Digital Oscillator for Virtual Acoustic Feedback
Proceedings of AES 136th Convention
Autore/i: L. Gabrielli; M. Giobbi; S. Squartini; V. Valimaki
Classificazione: 4 Contributo in Atti di Convegno (Proceeding)
Abstract: In the domain of Virtual Acoustics research, the emulation of acoustic feedback, such as the so-called guitar howling, has been scarcely addressed. This paper takes pace from this peculiar effect to introduce a computational technique aimed at its emulation and extension to possible new scenarios of Virtual Acoustics. A nonlinear digital oscillator for real-time operation with good stability properties and low computational cost is employed to emulate guitar feedback (or guitar howling). The oscillator frequency is tuned according to a pitch detection system that adaptively tracks pitch changes in real-time. A real-time implementation of the algorithm in the Puredata environment has been developed to provide guitar howling emulation.
Scheda della pubblicazione: https://iris.univpm.it/handle/11566/153909 Collegamento a IRIS

2013 A New System for Automatic Recognition of Italian Sign Language
Neural Nets and Surroundings
Autore/i: M. Fagiani; E. Principi; S. Squartini; F. Piazza
Editore: Springer Verlag Germany:Tiergartenstrasse 17, D 69121 Heidelberg Germany:011 49 6221 3450, EMAIL: g.braun@springer.de, INTERNET: http://www.springer.de, Fax: 011 49 6221 345229
Classificazione: 2 Contributo in Volume
Abstract: This work proposes a preliminary study of an automatic recognition system for the Italian Sign Language (Lingua Italiana dei Segni - LIS). Several other attempts have been made in the literature, but they are typically oriented to international languages. The system is composed of a feature extraction stage, and a sign recognition stage. Each sign is represeted by a single Hidden Markov Model, with parameters estimated through the resubstitution method. Then, starting from a set of features related to the position and the shape of head and hands, the Sequential Forward Selection technique has been applied to obtain feature vectors with the minimum dimension and the best recognition performance. Experiments have been performed using the cross-validation method on the Italian Sign Language Database A3LIS-147, maintaining the orthogonality between training and test sets. The obtained recognition accuracy averaged across all signers is 47.24%, which represents an encouraging result and demonstrates the effectiveness of the idea.
Scheda della pubblicazione: https://iris.univpm.it/handle/11566/83970 Collegamento a IRIS

2013 A Comparison Between Different Optimization Techniques for Energy Scheduling in Smart Home Environment
Neural Nets and Surroundings
Autore/i: F. De Angelis; M. Boaro; D. Fuselli; S. Squartini; F. Piazza
Editore: Springer Verlag Germany:Tiergartenstrasse 17, D 69121 Heidelberg Germany:011 49 6221 3450, EMAIL: g.braun@springer.de, INTERNET: http://www.springer.de, Fax: 011 49 6221 345229
Classificazione: 2 Contributo in Volume
Abstract: Nowadays a correct use of energy is a crucial aspect, in fact cost and energy waste reduction are the main goals that must be achieved. To reach this objective an optimal energy management must be obtained through some techniques and optimization algorithms, in order to provide the best solution in terms of cost. In this work a comparison between different methods for energy scheduling is proposed and some analytical results are reported, in order to offer a clear overview for each technique, in terms of advantages and disadvantages. A residential scenario is considered for computer simulations, in which a system storage and renewable resources are available and exploitable to match the user load demand. © Springer-Verlag Berlin Heidelberg 2013.
Scheda della pubblicazione: https://iris.univpm.it/handle/11566/83969 Collegamento a IRIS

2013 Home Energy Resource Scheduling Algorithms and their dependency on the Battery Model
Proceedings of IEEE Symposium Series on Computational Intelligence 2013
Autore/i: Stefano Squartini; Danilo Fuselli; Matteo Boaro; Francesco De Angelis; Francesco Piazza
Classificazione: 4 Contributo in Atti di Convegno (Proceeding)
Abstract: Smart Home Energy Management is a very hot topic within the scientific community and some interesting solutions are also available on the market. One key issue is represented by the capability of planning the usage of energy resources in order to reduce the overall energy costs. This means that, considering the dynamic electricity price and the availability of adequately sized storage system, the expert system is supposed to automatically decide the more convenient policy to administer the electrical energy flux from and towards the grid. In this work a comparison between different methods for home energy resource scheduling is proposed and analyzed from the perspective of the dependency of their performance on the employed battery model, with special focus on its capacity and charge/discharge rates. A typical grid-connected residential energy system is considered for performed computer simulations, in which a system storage and renewable resources are available and exploitable to match the user load demand. Obtained results allows the authors to provide interesting guidelines for the selection of the battery features.
Scheda della pubblicazione: https://iris.univpm.it/handle/11566/86657 Collegamento a IRIS

2013 Energy Aware Lazy Scheduling Algorithm for Energy-Harvesting Sensor Nodes
NEURAL COMPUTING & APPLICATIONS
Autore/i: M. Severini; S. Squartini; F. Piazza
Classificazione: 1 Contributo su Rivista
Abstract: The main problem in dealing with energy-harvesting (EH) sensor nodes is represented by the scarcity and non-stationarity of powering, due to the nature of the renewable energy sources. In this work, the authors address the problem of task scheduling in processors located in sensor nodes powered by EH sources. Some interesting solutions have appeared in the literature in the recent past, as the lazy scheduling algorithm (LSA), which represents a performing mix of scheduling effectiveness and ease of implementation. With the aim of achieving a more efficient and conservative management of energy resources, a new improved LSA solution is here proposed. Indeed, the automatic ability of foreseeing at run-time the task energy starving (i.e. the impossibility of finalizing a task due to the lack of power) is integrated within the original LSA approach. Moreover, some modifications have been applied in order to reduce the LSA computational complexity and thus maximizing the amount of energy available for task execution. The resulting technique, namely energy-aware LSA, has then been tested in comparison with the original one, and a relevant performance improvement has been registered both in terms of number of executable tasks and in terms of required computational burden.
Scheda della pubblicazione: https://iris.univpm.it/handle/11566/74221 Collegamento a IRIS

2013 On-line Sequential Extreme Learning Machine in Nonstationary Environments
NEUROCOMPUTING
Autore/i: Y. Ye; S. Squartini; F. Piazza
Classificazione: 1 Contributo su Rivista
Abstract: System identification in nonstationary environments represents a challenging problem to solve and lots of efforts have been put by the scientific community in the last decades to provide adequate solutions on purpose. Most of them are targeted to work under the system linearity assumption, but also some have been proposed to deal with the nonlinear case study. In particular the authors have recently advanced a neural architecture, namely time-varying neural networks (TV-NN), which has shown remarkable identification properties in the presence of nonlinear and nonstationary conditions. TV-NN training is an issue due to the high number of free parameters and the extreme learning machine (ELM) approach has been successfully used on purpose. ELM is a fast learning algorithm that has recently caught much attention within the neural networks (NNs) research community. Many variants of ELM have been appeared in recent literature, specially for the stationary case study. The reference one for TV-NN training is named ELM-TV and is of batch-learning type. In this contribution an online sequential version of ELM-TV is developed, in response to the need of dealing with applications where sequential arrival or large number of training data occurs. This algorithm generalizes the corresponding counterpart working under stationary conditions. Its performances have been evaluated in some nonstationary and nonlinear system identification tasks and related results show that the advanced technique produces comparable generalization performances to ELM-TV, ensuring at the same time all benefits of an online sequential approach.
Scheda della pubblicazione: https://iris.univpm.it/handle/11566/74218 Collegamento a IRIS

2013 A distributed system for recognizing home automation commands and distress calls in the Italian language
Proceedings of Interspeech 2013
Autore/i: E. Principi; S. Squartini; F. Piazza; D. Fuselli; M. Bonifazi
Classificazione: 4 Contributo in Atti di Convegno (Proceeding)
Abstract: This paper describes a system for recognizing distress calls and home automation voice commands in a smart-home. Distress calls are recognized with the purpose of assisting people in their own homes: when they are detected, a phone call is automatically established with a contact in a address book and the person can request for assistance. The voice call is established through a voice over ip stack, with hands-free communication guaranteed by an acoustic echo canceller. The acoustic environment is constantly monitored by several low-consuming devices distributed throughout the home. In each device, a voice activity detector detects speech segments, and a speech recognition engine recognizes commands and distress calls. Robustness to environmental disturbances has been increased by employing Power Normalized Cepstral Coefficients and by using an adaptive algorithm for interference cancellation. An Italian speech corpus of home automation commands and distress calls has been developed for evaluation purposes. The corpus has been recorded in a real room using multiple microphones, and each sentence has been uttered both in normal and shouted speaking styles. The system performance has been assessed in terms of commands/distress recognition accuracy in order to prove the effectiveness of the approach.
Scheda della pubblicazione: https://iris.univpm.it/handle/11566/112686 Collegamento a IRIS

2013 A digital waveguide based approach for Clavinet modeling and synthesis
EURASIP JOURNAL ON ADVANCES IN SIGNAL PROCESSING
Autore/i: Leonardo Gabrielli; Vesa Välimäki; Henri Penttinen; Stefano Squartini; Stefan Bilbao
Classificazione: 1 Contributo su Rivista
Abstract: The Clavinet is an electromechanical musical instrument produced in the mid-twentieth century. As is the case for other vintage instruments, it is subject to aging and requires great effort to be maintained or restored. This paper reports analyses conducted on a Hohner Clavinet D6 and proposes a computational model to faithfully reproduce the Clavinet sound in real time, from tone generation to the emulation of the electronic components. The string excitation signal model is physically inspired and represents a cheap solution in terms of both computational resources and especially memory requirements (compared, e.g., to sample playback systems). Pickups and amplifier models have been implemented which enhance the natural character of the sound with respect to previous work. A model has been implemented on a real-time software platform, Pure Data, capable of a 10-voice polyphony with low latency on an embedded device. Finally, subjective listening tests conducted using the current model are compared to previous tests showing slightly improved results.
Scheda della pubblicazione: https://iris.univpm.it/handle/11566/92861 Collegamento a IRIS

2013 An Embedded-processor driven Test Bench for Acoustic Feedback Cancellation in real environments
AES 134th Convention
Autore/i: F. Faccenda; S. Squartini; E. Principi; L. Gabrielli; F. Piazza
Classificazione: 4 Contributo in Atti di Convegno (Proceeding)
Abstract: In order to facilitate the communication among speakers, speech reinforcement systems equipped with microphones and loudspeakers are employed. Due to the acoustic couplings between them, the speech intelligibility may result ruined and, moreover, high channel gains could drive the system to instability. Acoustic Feedback Cancellation (AFC) methods need to be applied to keep the system stable. In this work, a new Test Bench for testing AFC algorithms in real environments is proposed. It is based on the TMS320C6748 processor, running the Suppressor-PEM algorithm, a recent technique based on the PEM-AFROW paradigm. The partitioned block frequency domain adaptive filter (PB-FDAF) paradigm has been adopted to keep the computational complexity low. A professional sound card and a PC, where an automatic gain controller has been implemented to prevent signal clipping, complete the framework. Several experimental tests confirmed the framework suitability to operate under diverse acoustic conditions.
Scheda della pubblicazione: https://iris.univpm.it/handle/11566/91064 Collegamento a IRIS

2013 A Speech-Based System for In-Home Emergency Detection and Remote Assistance
AES 134th Convention
Autore/i: E. Principi; D. Fuselli; S. Squartini; M. Bonifazi; F. Piazza
Classificazione: 4 Contributo in Atti di Convegno (Proceeding)
Abstract: This paper describes a system for the detection of emergency states and for the remote assistance of people in their own homes. Emergencies are detected recognizing distress calls by means of a speech recognition engine. When an emergency is detected, a phone call is automatically established with a relative or friend by means of a VoIP stack and an Acoustic Echo Canceller. Several low-consuming embedded units are distributed throughout the house to monitor the acoustic environment, and one central unit coordinates the system operation. This unit also integrates multimedia content delivery services, and home automation functionalities. Being an ongoing project, this paper describes the entire system and then focuses on the algorithms implemented for the acoustic monitoring and the hands-free communication services. Preliminary experiments have been conducted to assess the performance of the recognition module in noisy and reverberated environments, and the out of grammar rejection capabilities. Results showed that the implemented Power Normalized Cepstral Coefficients extraction pipeline improves the word recognition accuracy in noisy and reverberated conditions, and that introducing a "garbage phone" in the acoustic model allows to effectively reject out of grammar words and sentences.
Scheda della pubblicazione: https://iris.univpm.it/handle/11566/91067 Collegamento a IRIS

2013 Hybrid Soft Computing algorithmic framework for Smart Home Energy Management
SOFT COMPUTING
Autore/i: M. Severini; S. Squartini; F. Piazza
Classificazione: 1 Contributo su Rivista
Abstract: Energy management in Smart Home environments is undoubtedly one of the pressing issues in the Smart Grid research field. The aim typically consists in developing a suitable engineering solution able to maximally exploit the availability of renewable resources. Due to the presence of diverse cooperating devices, a complex model, involving the characterization of nonlinear phenomena, is indeed required on purpose. In this paper an Hybrid Soft Computing algorithmic framework, where genetic, neural networks and deterministic optimization algorithms jointly operate, is proposed to perform an efficient scheduling of the electrical tasks and of the activity of energy resources, by adequately handling the inherent nonlinear aspects of the energy management model. In particular, in order to address the end-user comfort constraints, the home thermal characterization is needed: this is accomplished by a nonlinear model relating the energy demand with the required temperature profile. A genetic algorithm, based on such model, is then used to optimally allocate the energy request to match the user thermal constraints, and therefore to allow the mixed-integer deterministic optimization algorithm to determine the remaining energy management actions. From this perspective, the ability to schedule the tasks and allocate the overall energy resources over a finite time horizon is assessed by means of diverse computer simulations in realistic conditions, allowing the authors to positively conclude about the effectiveness of the proposed approach. The degree of realism of the simulated scenario is confirmed by the usage of solar energy production forecasted data, obtained by means of a neural-network based algorithm which completes the framework.
Scheda della pubblicazione: https://iris.univpm.it/handle/11566/112685 Collegamento a IRIS

2013 A Finite Difference Method for the Excitation of a Digital Waveguide String Model
AES 134th Convention
Autore/i: L. Gabrielli; L. Remaggi; S. Squartini; V. Valimaki
Classificazione: 4 Contributo in Atti di Convegno (Proceeding)
Abstract: With Digital Waveguide modeling (DWG) a number of excitation methods have been proposed to feed the delay line properly. Generally speaking these may be based on signal models fitting recorded samples, excitation signals extracted from recorded samples or digital filter networks. While allowing for a stable, computationally efficient sound emulation, they may be unable to emulate secondary effects generated by the physical interaction of, e.g., distributed interaction of string and hammer. On the other hand, FDTD (Finite Difference Time Domain) models are more accurate in the emulation of the physical excitation mechanism at the expense of a higher computational cost and a complex coefficient design to ensure numerical stability. In this work a mixed model is proposed composed of a second-order FDTD model, a commuted DWG and an adaptor block to join the two sections. Properties of the model are provided and computer results are given for the case of the Clavinet tangent-string mechanism as an example application.
Scheda della pubblicazione: https://iris.univpm.it/handle/11566/91065 Collegamento a IRIS

2013 Advancements and Performance analysis on the Wireless Music Studio (WeMUST) framework
AES 134th Convention
Autore/i: L. Gabrielli; S. Squartini; F. Piazza
Classificazione: 4 Contributo in Atti di Convegno (Proceeding)
Abstract: Music production devices and musical instruments can take advantage of IEEE 802.11 wireless networks for interconnection and audio data sharing. In previous works such networks have been proved able to support high-quality audio streaming between devices at acceptable latencies, in several application scenarios. In this work, a prototype device discovery mechanism is described to improve ease of use and flexibility. A diagnostic tool is also described and provided to the community which allows to characterize average network latency and packet loss. Lower latencies are reported after software optimization and sustainability of multiple audio channels is also proved by means of experimental tests.
Scheda della pubblicazione: https://iris.univpm.it/handle/11566/91066 Collegamento a IRIS

2013 Real-Life Voice Activity Detection with LSTM Recurrent Neural Networks and application to Holliwood Movies
Acoustics, Speech and Signal Processing (ICASSP), 2013 IEEE International Conference on
Autore/i: Florian Eyben; Felix Weninger; Stefano Squartini; Björn Schuller
Classificazione: 4 Contributo in Atti di Convegno (Proceeding)
Abstract: A novel, data-driven approach to voice activity detection is presented. The approach is based on Long Short-Term Memory Recurrent Neural Networks trained on standard RASTA-PLP frontend features. To approximate real-life scenarios, large amounts of noisy speech instances are mixed by using both read and spontaneous speech from the TIMIT and Buckeye corpora, and adding real long term recordings of diverse noise types. The approach is evaluated on unseen synthetically mixed test data as well as a real-life test set consisting of four full-length Hollywood movies. A frame-wise Equal Error Rate (EER) of 33.2% is obtained for the four movies and an EER of 9.6% is obtained for the synthetic test data at a peak SNR of 0 dB, clearly outperforming three state-of-the-art reference algorithms under the same conditions.
Scheda della pubblicazione: https://iris.univpm.it/handle/11566/91063 Collegamento a IRIS

2013 A Real-Time Speech Enhancement Framework in Noisy and Reverberated Acoustic Scenarios
COGNITIVE COMPUTATION
Autore/i: Rudy Rotili; Emanuele Principi; Stefano Squartini; Bjoern Schuller
Classificazione: 1 Contributo su Rivista
Abstract: This paper deals with speech enhancement in noisy reverberated environments where multiple speakers are active. The authors propose an advanced real-time speech processing front-end aimed at automatically reducing the distortions introduced by room reverberation in distant speech signals, also considering the presence of background noise, and thus to achieve a significant improvement in speech quality for each speaker. The overall framework is composed of three cooperating blocks, each one fulfilling a specific task: speaker diarization, room impulse responses identification and speech dereverberation. In particular, the speaker diarization algorithm pilots the operations performed in the other two algorithmic stages, which have been suitably designed and parametrized to operate with noisy speech observations. Extensive computer simulations have been performed by using a subset of the AMI database under different realistic noisy and reverberated conditions. Obtained results show the effectiveness of the approach
Scheda della pubblicazione: https://iris.univpm.it/handle/11566/81571 Collegamento a IRIS

2013 A Real-time Dual-Channel Speech Reinforcement System for Intra-Cabin Communication
AES
Autore/i: F. Faccenda; S. Squartini; E. Principi; L. Gabrielli; F. Piazza
Classificazione: 1 Contributo su Rivista
Abstract: To facilitate communications among passengers in a large vehicle, an appropriate system with microphones, loudspeakers, and amplifiers is needed. However, a signal processing algorithm is required to avoid feedback and instability. Borrowing from speech-reinforcement research, the authors use a room-modeling adaptive feedback-cancellation approach that combines the Prediction Error Method and adaptive filtering. And, by including a suppressor filter, the system can be extended to a dual-channel scenario that supports bidirectional communications, where additional feedback paths must be considered with respect to the single-channel case study. In order to achieve low latencies and real-time processing, the partitioned block frequency domain adaptive filter algorithm has been adopted. Voice-activity and double-talk detectors have been included as well. Computer simulations in various acoustic conditions have shown the effectiveness of this approach.
Scheda della pubblicazione: https://iris.univpm.it/handle/11566/136662 Collegamento a IRIS

2013 The Neural Paradigm for Complex Systems: new Algorithms and Applications
NEURAL COMPUTING & APPLICATIONS
Autore/i: Squartini S.; Jinhu Lu; Qinglai Wei
Classificazione: 1 Contributo su Rivista
Scheda della pubblicazione: https://iris.univpm.it/handle/11566/62534 Collegamento a IRIS

2013 Action dependent heuristic dynamic programming for home energy resource scheduling
INTERNATIONAL JOURNAL OF ELECTRICAL POWER & ENERGY SYSTEMS
Autore/i: Danilo Fuselli; Francesco De Angelis; Matteo Boaro; Stefano Squartini; Qinglai Wei; Derong Liu; Francesco Piazza
Classificazione: 1 Contributo su Rivista
Abstract: Energy management in smart home environment is nowadays a crucial aspect on which technologies have been focusing on in order to save costs and minimize energy waste. This goal can be reached by means of an energy resource scheduling strategy provided by a suitable optimization technique. The proposed solution involves a class of Adaptive Critic Designs (ACDs) called Action Dependent Heuristic Dynamic Programming (ADHDP) that uses two neural networks, namely the Action and the Critic Network. This scheme is able to minimize a given Utility Function over a certain time horizon. In order to increase the performances of the ADHDP algorithm, suitable Particle Swarm Optimization (PSO) based procedures are used to pretrain the weights of the Action and the Critic networks. The results provided by PSO techniques and by a non-optimal baseline approach are also used as elements of comparison. Computer simulations have been carried out in different residential scenarios. An historical data set for solar irradiation has been used to simulate the behavior of a photovoltaic array to obtain renewable energy and the main grid is used to supply the load and charge the battery when necessary. The results confirm that the ADHDP is able to reduce the overall energy cost with respect to the baseline solution and the PSO techniques. Moreover, the validity of this method has also been shown in a more realistic context where only forecasted values of solar irradiation and electricity price can be used.
Scheda della pubblicazione: https://iris.univpm.it/handle/11566/86146 Collegamento a IRIS

2013 Advances on Brain Inspired Computing
COGNITIVE COMPUTATION
Autore/i: Stefano Squartini; Sanqing Hu; Qingshan Liu
Classificazione: 1 Contributo su Rivista
Scheda della pubblicazione: https://iris.univpm.it/handle/11566/86658 Collegamento a IRIS

2013 Evaluation of the Wireless M-Bus Standard for Future Smart Water Grids
Proceedings of IEEE IWCMC 2013
Autore/i: S. Spinsante; M. Pizzichini; M. Mencarelli; S. Squartini; E. Gambi
Classificazione: 4 Contributo in Atti di Convegno (Proceeding)
Abstract: The most recent Wireless Sensor Networks technologies can provide viable solutions to perform automatic monitoring of the water grid, and smart metering of water consumptions. However, sensor nodes located along water pipes cannot access power grid facilities, to get the necessary energy imposed by their working conditions. In this sense, it is of basic importance to design the network architecture in such a way as to require the minimum possible power. This paper investigates the suitability of the Wireless Metering Bus protocol for possible adoption in future smart water grids, by evaluating its transmission performance, through simulations and experimental tests executed by means of prototype sensor nodes.
Scheda della pubblicazione: https://iris.univpm.it/handle/11566/100863 Collegamento a IRIS

2013 Optimization Algorithms for Home Energy Resource Scheduling in presence of data uncertainty
Proceedings of ICICIP 2013
Autore/i: Stefano Squartini; Matteo Boaro; Francesco De Angelis; Danilo Fuselli; Francesco Piazza
Classificazione: 4 Contributo in Atti di Convegno (Proceeding)
Abstract: Smart Home Energy Management is a very hot topic for the scientific community and some interesting solutions have also recently appeared on the market. One key issue is represented by the capability of planning the usage of energy resources in order to reduce the overall energy costs. This means that, considering the dynamic electricity price and the availability of adequately sized storage system, the expert system is supposed to automatically decide the more convenient policy for energy management from and towards the grid. In this work a comparison among different linear and nonlinear methods for home energy resource scheduling is proposed, considering the presence of data uncertainty into account. Indeed, whereas the employment of advanced optimization frameworks can take advantage by their inherent offline approach, the need to forecast the energy price and the amount of self-generated power. A residential scenario, in which a system storage and renewable resources are available and exploitable to match the user load demand, has been considered for performed computer simulations: obtained results show how the offline approaches provide good performance also in presence of uncertain data.
Scheda della pubblicazione: https://iris.univpm.it/handle/11566/91061 Collegamento a IRIS

2013 Wireless M-Bus Sensor Nodes in Smart Water Grids: the Energy Issue
Proceedings of ICICIP 2013
Autore/i: Stefano Squartini; Leonardo Gabrielli; Matteo Mencarelli; Mirco Pizzichini; Susanna Spinsante; Francesco Piazza
Classificazione: 4 Contributo in Atti di Convegno (Proceeding)
Abstract: Smart Metering is one of the key issues in modern energy efficiency technologies. Several efforts have been recently made in developing suitable communication protocols for metering data management and transmission, and the Metering-Bus (M-Bus) is a relevant standard example, with a wide diffusion in the European market. This paper deals with its wireless evolution, namely Wireless M-Bus (WM-Bus), and in particular looks at it from the energy consumption perspective. Indeed, specially in those applicative scenarios where the grid powering is not available, like in water and gas metering settings, it is fundamental to guarantee the sustainability of the meter itself, by means of long-life batteries or suitable energy harvesting technologies. The present work analyzes all these aspects directly referring to a specific HW/SW implementation of the WM-Bus variants, providing some useful guidelines for its application in the smart water grid context.
Scheda della pubblicazione: https://iris.univpm.it/handle/11566/91062 Collegamento a IRIS

2013 Optimal Home Energy Management under Dynamic Electrical and Thermal Constraints
IEEE TRANSACTIONS ON INDUSTRIAL INFORMATICS
Autore/i: F. De Angelis; M. Boaro; D. Fuselli; S. Squartini; F. Piazza; Q. Wei
Classificazione: 1 Contributo su Rivista
Abstract: The optimization of energy consumption, with consequent costs reduction, is one of the main challenges in present and future smart grids. Of course, this has to occur keeping the living comfort for the end-user unchanged. In this work, an approach based on the mixed-integer linear programming paradigm, which is able to provide an optimal solution in terms of tasks power consumption and management of renewable resources, is developed. The proposed algorithm yields an optimal task scheduling under dynamic electrical constraints, while simultaneously ensuring the thermal comfort according to the user needs. On purpose, a suitable thermal model based on heat-pump usage has been considered in the framework. Some computer simulations using real data have been performed, and obtained results confirm the efficiency and robustness of the algorithm, also in terms of achievable cost savings.
Scheda della pubblicazione: https://iris.univpm.it/handle/11566/83995 Collegamento a IRIS

2012 Environmental Robust Speech and Speaker Recognition through Multi-channel Histogram Equalization
NEUROCOMPUTING
Autore/i: Squartini S.; Principi E.; Rotili R.; Piazza F.
Classificazione: 1 Contributo su Rivista
Abstract: Feature statistics normalization in the cepstral domain is one of the most performing approaches for robust automaticspeech and speaker recognition in noisy acoustic scenarios: feature coefficients are normalized by using suitable linear or nonlinear transformations in order to match the noisy speech statistics to the clean speech one. Histogram equalization (HEQ) belongs to such a category of algorithms and has proved to be effective on purpose and therefore taken here as reference. In this paper the presence of multi-channel acoustic channels is used to enhance the statistics modeling capabilities of the HEQ algorithm, by exploiting the availability of multiple noisy speech occurrences, with the aim of maximizing the effectiveness of the cepstra normalization process. Computer simulations based on the Aurora 2 database in speech and speaker recognition scenarios have shown that a significant recognition improvement with respect to the single-channel counterpart and other multi-channel techniques can be achieved confirming the effectiveness of the idea. The proposed algorithmic configuration has also been combined with the kernel estimation technique in order to further improve the speech recognition performances.
Scheda della pubblicazione: https://iris.univpm.it/handle/11566/62532 Collegamento a IRIS

2012 ELM in nonstationary environment: Extreme Learning Machine and its variants for Time-Varying Neural Networks case study
Autore/i: Yibin Ye; Stefano Squartini; Francesco Piazza
Editore: LAP LAMBERT Academic Publishing
Classificazione: 3 Libro
Abstract: System identification in nonstationary environment represents a challenging problem and an advaned neural architecture namely Time-Varying Neural Net- works (TV-NN) has shown remarkable identification properties in nonlinear and nonstationary conditions. Time-varying weights, each being a linear com- bination of a certain set of basis functions, are used in such kind of networks instead of stable ones, which inevitalbly increases the number of free parame- ters. Therefore, an Extreme Learning Machine (ELM) approach is developed to accelerate the training procedure for TV-NN. What is more, in order to ob- tain a more compact structure, or determine several important parameters, or update the network more efficiently in online case, several variants of ELM-TV are proposed and discussed in the book. Related computer simulations have been carried out and show the effectiveness of the algorithms.
Scheda della pubblicazione: https://iris.univpm.it/handle/11566/171905 Collegamento a IRIS

2012 Dominance Detection in A Reverberated Acoustic Scenario
Advances in Neural Networks - ISNN2012
Autore/i: E. Principi; R. Rotili; M. Woellmer; S. Squartini; B. Schuller
Editore: Springer Verlag Germany:Tiergartenstrasse 17, D 69121 Heidelberg Germany:011 49 6221 3450, EMAIL: g.braun@springer.de, INTERNET: http://www.springer.de, Fax: 011 49 6221 345229
Classificazione: 2 Contributo in Volume
Abstract: This work proposes a dominance detection framework operating in reverberated environments. The framework is composed of a speech enhancement front-end, which automatically reduces the distortions introduced by room reverberation in the speech signals, and a dominance detector, which processes the enhanced signals and estimates the most and least dominant person in a segment. The front-end is composed by three cooperating blocks: speaker diarization, room impulse responses identification and speech dereverberation. The dominance estimation algorithm is based on bidirectional Long Short-Term Memory networks which allow for context-sensitive activity classification from audio feature functionals extracted via the real-time speech feature extraction toolkit openSMILE. Experiments have been performed suitably reverberating the DOME dataset: the absolute accuracy improvement averaged over the addressed reverberated conditions is 32.68% in the most dominant person estimation task and 36.56% in the least dominant person estimation one, both with full agreement among annotators.
Scheda della pubblicazione: https://iris.univpm.it/handle/11566/74300 Collegamento a IRIS

2012 Networked BeagleBoards for Wireless Music Applications
EDERC2012 Proceedings
Autore/i: L. Gabrielli; S. Squartini; E. Principi; F. Piazza
Classificazione: 4 Contributo in Atti di Convegno (Proceeding)
Abstract: One of the most demanding challenges in the field of audio engineering is the transmission of low-latency high quality audio streams over networks. While several protocols nowadays allow wired local network streaming, much effort is still required to achieve similar goals over existing wireless LAN technologies. While the challenge is still far from being solved, several design issues can be highlighted and future scenarios can be outlined. This paper proposes the setup of a wireless music production system based on open hardware and open software which requires relatively low setup effort while allowing for a high flexibility of use. The hardware platform is the Beagleboard, based on Texas Instruments DM3730, running a GNU/Linux OS and the computer music language Pure Data. Such a device can capture electric instrument audio, generate sound, send MIDI or OSC control data, and stream to PCs and other embedded devices operating as mixers, effect racks and so on, enabling an ecosystem of flexible and open devices. Tests conducted on a home wireless network show acceptable latency for many applications.
Scheda della pubblicazione: https://iris.univpm.it/handle/11566/80043 Collegamento a IRIS

2012 A pickup model for the Clavinet
Proc. of the 15th Int. Conference on Digital Audio Effects (DAFx-12)
Autore/i: Luca Remaggi; Leonardo Gabrielli; Rafael Cauduro Dias de Paiva; Vesa Välimäki; Stefano Squartini
Classificazione: 4 Contributo in Atti di Convegno (Proceeding)
Abstract: In this paper recent findings on magnetic transducers are applied to the analysis and modeling of Clavinet pickups. The Clavinet is a stringed instrument having similarities to the electric guitar, it has magnetic single coil pickups used to transduce the string vibration to an electrical quantity. Data gathered during physical inspection and electrical measurements are used to build a complete model which accounts for nonlinearities in the magnetic flux. The model is inserted in a Digital Waveguide (DWG) model for the Clavinet string for its evaluation.
Scheda della pubblicazione: https://iris.univpm.it/handle/11566/81569 Collegamento a IRIS

2012 Optimal Battery Management with ADHDP in Smart Home Environments
Advances in Neural Networks - ISNN2012
Autore/i: D. Fuselli; F. de Angelis; M. Boaro; D. Liu; Q. Wei; S. Squartini; F. Piazza
Editore: Springer Verlag Germany:Tiergartenstrasse 17, D 69121 Heidelberg Germany:011 49 6221 3450, EMAIL: g.braun@springer.de, INTERNET: http://www.springer.de, Fax: 011 49 6221 345229
Classificazione: 2 Contributo in Volume
Abstract: In this paper an optimal controller for battery management in smart home environments is presented in order to save costs and minimize energy waste. The considered scenario includes a load profile that must always be satisfied, a battery-system that is able to storage electrical energy, a photovoltaic (PV) panel, and the main grid that is used when it is necessary to satisfy the load requirements or charge the battery. The optimal controller design is based on a class of adaptive critic designs (ACDs) called action dependent heuristic dynamic programming (ADHDP). Results obtained with this scheme outperform the ones obtained by using the particle swarm optimization (PSO) method.
Scheda della pubblicazione: https://iris.univpm.it/handle/11566/74301 Collegamento a IRIS

2012 CO-WORKER: Towards real-time and context-aware systems for human collaborative knowledge building
COGNITIVE COMPUTATION
Autore/i: Stefano Squartini; Anna Esposito
Classificazione: 1 Contributo su Rivista
Abstract: The information exchange occurring during human interactions, conveyed through verbal and nonverbal communication modes, builds up a new-shared knowledge among the interacting people. A current automatic meeting assistance system is just able to store such an exchange (for successive offline processing), while it would be valuable developing automatic tools that provide appropriate support as it takes place. Currently, the international scientific community is strongly committed toward the implementation of intelligent instruments able to recognize and process in real-time relevant interactional signals in order to provide timely support to the happening interaction. This work will argue on an even more comprehensive paradigm for collaborative computer support to human interaction, not adequately addressed in the literature so far, concerning the implementation of human–computer interaction (HCI) systems able to process in real-time multimodal signals, to infer contextual information, and support in a collaborative way human interaction in-group activities, such as learning, discussion, work cooperation, decision-making, and problem solving. Such systems should act as co-workers, actively cooperating and contributing to the group’s knowledge building and pretending to share with the group, significances and individual potentialities rather than act as passive data storing devices. In carrying out their functions, these HCI systems will be placed on a group cognitive level, where individual purposes, actions, and emotions are mediated by the group interaction, and meanings are mainly built through the group shared knowledge and experience.
Scheda della pubblicazione: https://iris.univpm.it/handle/11566/66990 Collegamento a IRIS

2012 Ibrida: a new DWT-domain sound hybridization tool
AES 45th International Conference Proceedings
Autore/i: Gabrielli L.; Squartini S.
Classificazione: 4 Contributo in Atti di Convegno (Proceeding)
Abstract: This paper presents a new deterministic algorithm for the creative morphing or hybridization of two sounds, for use in movies and videogames sonification, experimental music composition or creative sound synthesis. The algorithm is based on DiscreteWavelet Transform (DWT) filter banks, for sound decomposition, and one IDWT filter bank where a mix of the DWT coefficients streams is transformed back in the time domain for output. The use of the DWT for this purpose proves more computationally efficient than stochastic methods while more perceptually oriented than DFT because of its nonuniform time-frequency decomposition and introduces less control parameters. The addition of an onset detection algorithm in the wavelet domain helps creating dynamic morphing. A Pure Data implementation of the algorithm has been performed to investigate the problem of controlling the morphing parameters with physical interfaces such as touch sensitive screens.
Scheda della pubblicazione: https://iris.univpm.it/handle/11566/66726 Collegamento a IRIS

2012 Robust sensorless speed control of permanent magnet synchronous motors: A C2000 based implementation
EDERC 2012 - Proceedings of the 5th European DSP in Education and Research Conference
Autore/i: Coacci, D.; Ippoliti, G.; Longhi, S.; Orlando, G.; Pirro, M.; Squartini, S.
Classificazione: 4 Contributo in Atti di Convegno (Proceeding)
Scheda della pubblicazione: https://iris.univpm.it/handle/11566/80041 Collegamento a IRIS

2012 Conversational Speech Recognition In Non-Stationary Reverberated Environment
Behavioural Cognitive Systems
Autore/i: Rotili R.; Principi E.; Woellmer M.; Squartini S.; Schuller B.
Editore: Springer Verlag Germany:Tiergartenstrasse 17, D 69121 Heidelberg Germany:011 49 6221 3450, EMAIL: g.braun@springer.de, INTERNET: http://www.springer.de, Fax: 011 49 6221 345229
Classificazione: 2 Contributo in Volume
Abstract: This paper presents a conversational speech recognition system able to operate in non-stationary reverberated environments. The system is composed of a dereverberation front-end exploiting multiple distant microphones, and a speech recognition engine. The dereverberation front-end identifies a room impulse response by means of a blind channel identification stage based on the Unconstrained Normalized Multi-Channel Frequency Domain Least Mean Square algorithm. The dereverberation stage is based on the adaptive inverse filter theory and uses the identified responses to obtain a set of inverse filters which are then exploited to estimate the clean speech. The speech recognizer is based on tied-state cross-word triphone models and decodes features computed from the dereverberated speech signal. Experiments conducted on the Buckeye corpus of conversational speech report a relative word accuracy improvement of 17.48% in the stationary case and of 11.16% in the non-stationary one.
Scheda della pubblicazione: https://iris.univpm.it/handle/11566/66725 Collegamento a IRIS

2012 Real-Time Activity Detection in a Multi-Talker Reverberated Environment
COGNITIVE COMPUTATION
Autore/i: Emanuele Principi; Rudy Rotili; Martin Woellmer; Florian Eyben; Stefano Squartini; Bjoern Schuller
Classificazione: 1 Contributo su Rivista
Abstract: This paper proposes a real-time person activity detection framework operating in presence of multiple sources in reverberated environments. Such a framework is composed by two main parts: The speech enhancement front-end and the activity detector. The aim of the former is to automatically reduce the distortions introduced by room reverberation in the available distant speech signals and thus to achieve a significant improvement of speech quality for each speaker. The overall front-end is composed by three cooperating blocks, each one fulfilling a specific task: Speaker diarization, room impulse responses identification, and speech dereverberation. In particular, the speaker diarization algorithm is essential to pilot the operations performed in the other two stages in accordance with speakers' activity in the room. The activity estimation algorithm is based on bidirectional Long Short-Term Memory networks which allow for context-sensitive activity classification from audio feature functionals extracted via the real-time speech feature extraction toolkit openSMILE. Extensive computer simulations have been performed by using a subset of the AMI database for activity evaluation in meetings: Obtained results confirm the effectiveness of the approach.
Scheda della pubblicazione: https://iris.univpm.it/handle/11566/66823 Collegamento a IRIS

2012 A Real-Time Speech Enhancement Front-End for Multi-Talker Reverberated Scenarios
Speech Enhancement, Modeling and Recognition- Algorithms and Applications
Autore/i: Rotili R.; Principi E.; Squartini S.; Piazza F.
Editore: Intech Open
Classificazione: 2 Contributo in Volume
Scheda della pubblicazione: https://iris.univpm.it/handle/11566/66153 Collegamento a IRIS

2012 On-line Extreme Learning Machine for Training Time-Varying Neural Networks
Bio-Inspired Computing and Applications, Lecture Notes in Computer Science Volume 6840
Autore/i: Ye Y.; Squartini S.; Piazza F.
Editore: Springer - LNCS
Classificazione: 2 Contributo in Volume
Abstract: Time-Varying Neural Networks(TV-NN) represent a powerful tool for nonstationary systems identification tasks, as shown in some recent works of the authors. Extreme Learning Machine approach can train TV-NNs efficiently: the reference algorithm is named ELM-TV and is of batch-learning type. In this paper, we generalize an online sequential version of ELM to TV-NN and evaluate its performances in two nonstationary systems identification tasks. The results show that our proposed algorithm produces comparable generalization performances to ELM-TV with certain benefits to those applications with sequential arrival or large number of training data.
Scheda della pubblicazione: https://iris.univpm.it/handle/11566/63382 Collegamento a IRIS

2012 Real-Time Speech Recognition in a Multi-Talker Reverberated Acoustic Scenario
Advanced Intelligent Computing
Autore/i: Rotili R.; Principi E.; Squartini S.; Schuller B.
Editore: Springer - LNCS
Classificazione: 2 Contributo in Volume
Abstract: This paper proposes a real-time algorithmic framework for Automatic Speech Recognition (ASR) in presence of multiple sources in reverberated environment. The addressed real-life acoustic scenario definitely asks for a robust signal processing solution to reduce the impact of source mixing and reverberation on ASR performances. Here the authors show how the implemented approach allows to improve recognition accuracies under real-time processing constraints and overlapping distant-talking speakers. A suitable database has been generated on purpose, by adapting an existing large vocabulary continuous speech recognition (LVCSR) corpus to deal with the acoustic conditions under study.
Scheda della pubblicazione: https://iris.univpm.it/handle/11566/63381 Collegamento a IRIS

2012 Towards a portable wireless platform for networked performance
Proceedings of CIM2012
Autore/i: L. Gabrielli; S. Squartini; F. Piazza; M. Mencarelli
Classificazione: 4 Contributo in Atti di Convegno (Proceeding)
Abstract: Networked musical performances have gained increasing interest in recent years due to the high availability of com- putational power on common laptops, their networking ca- pabilities and their increasing versatility. Their size and weight however can limit the freedom of the performer. This poster describes the ongoing activities concerning the setup and enhancement of a small computing platform for sound synthesis and musical composition based on the Bea- gleBoard xM and capable of streaming audio in a wireless network.
Scheda della pubblicazione: https://iris.univpm.it/handle/11566/86656 Collegamento a IRIS

2012 Stereophonic Hands-Free Communication System based on Microphone Array Fixed Beamforming: Real-Time Implementation and Evaluation
EURASIP JOURNAL ON AUDIO, SPEECH, AND MUSIC PROCESSING
Autore/i: Matteo Pirro; Stefano Squartini; Laura Romoli; Francesco Piazza
Classificazione: 1 Contributo su Rivista
Abstract: In this article, the authors propose an optimally designed fixed beamformer (BF) for stereophonic acoustic echo cancelation (SAEC) in real hands-free communication applications. Several contributions related to the combination of beamforming and echo cancelation have appeared in the literature so far, but, up to the authors' knowledge, the idea of using optimal fixed BFs in a real-time SAEC system both for echo reduction and stereophonic audio rendering is first addressed in this contribution. The employment of such designed BFs allows positively addressing both issues, as the several simulated and real tests seem to confirm. In particular, the stereo-recording quality attainable through the proposed approach has been preliminarily evaluated by means of subjective listening tests. Moreover, the overall system robustness against microphone array imperfections and noise presence has been experimentally evaluated. This allowed the authors to implement a real hands-free communication system in which the usage of the proposed beamforming technique has proven its superiority with respect to the usual two-microphone one in terms of echo reduction, and guaranteeing a comparable spatial image. Moreover, the proposed framework requires a low computational cost increment with regard to the baseline approach, since only few extra filtering operations with short filters need to be executed. Nevertheless, according to the performed simulations, the BF-based SAEC configuration seems to not require the signal decorrelation module, resulting in an overall computational saving.
Scheda della pubblicazione: https://iris.univpm.it/handle/11566/81570 Collegamento a IRIS

2012 Low Power High-Performance Computing on the BeagleBoard Platform
EDERC2012 Proceedings
Autore/i: E. Principi; V. Colagiacomo; S. Squartini; F. Piazza
Classificazione: 4 Contributo in Atti di Convegno (Proceeding)
Abstract: The ever increasing energy requirements of supercomputers and server farms is driving the scientific and industrial communities to take in deeper consideration the energy efficiency of computing equipments. This contribution addresses the issue proposing a cluster of ARM processors for high performance computing. The cluster is composed of five BeagleBoard-xM, with one board managing the cluster, and the other boards executing the actual processing. The software platform is based on the Angstrom GNU/Linux distribution and is equipped with a distributed file system to ease sharing data and code among the nodes of the cluster, and with tools for managing tasks and monitoring the status of each node. The computational capabilities of the cluster have been assessed through High-Performance Linpack and a cluster-wide speaker diarization algorithm, while power consumption has been measured using a clamp meter. Experimental results obtained in the speaker diarization task showed that the energy efficiency of the BeagleBoard-xM cluster is comparable to the one of a laptop computer equipped with a Intel Core2 Duo T8300 running at 2.4 GHz. Furthermore, removing the bottleneck due to the Ethernet interface, the BeagleBoard-xM cluster is able to achieve a superior energy efficiency.
Scheda della pubblicazione: https://iris.univpm.it/handle/11566/80042 Collegamento a IRIS

2012 Optimal Task and Energy Scheduling in Dynamic Residential Scenarios
Advances in Neural Networks - ISNN2012
Autore/i: F. De Angelis; D. Fuselli; M. Boaro; S. Squartini; F. Piazza; Q. Wei; D. Wang
Editore: Springer Verlag Germany:Tiergartenstrasse 17, D 69121 Heidelberg Germany:011 49 6221 3450, EMAIL: g.braun@springer.de, INTERNET: http://www.springer.de, Fax: 011 49 6221 345229
Classificazione: 2 Contributo in Volume
Abstract: Smart homes of the future will include automation systems that will provide lower energy consumption costs and comfortable environments to end users. In this work we propose an algorithm, based on the "Mixed-Integer Linear Programming" paradigm, able to find the optimal task and energy scheduling in realistic residential scenarios, in order to reduce costs and satisfy the user requirements at the same time. Both the static and the dynamic case studies have been addressed on purpose and results obtained from computer simulations seem to confirm the effectiveness of the idea.
Scheda della pubblicazione: https://iris.univpm.it/handle/11566/74303 Collegamento a IRIS

2012 A New Italian Sign Language Database
Advances in Brain Inspired Cognitive Systems
Autore/i: M. Fagiani; E. Principi; S. Squartini; F. Piazza
Editore: Springer Verlag Germany:Tiergartenstrasse 17, D 69121 Heidelberg Germany:011 49 6221 3450, EMAIL: g.braun@springer.de, INTERNET: http://www.springer.de, Fax: 011 49 6221 345229
Classificazione: 2 Contributo in Volume
Abstract: In this work a new video database of Italian Sign Language (Lingua Italiana dei Segni - LIS) is proposed. Several other attempts have been made in the literature, but they are typically oriented to international languages (like the American Sign Language - ASL). As in speech, also this kind of language presents different peculiarities strictly depending on the geographical location where it is used. The authors have firstly observed that a specific database for LIS is missing and this shoved them to develop the one here presented. It has been conceived to be used in Automatic Sign Recognition and Synthesis (often referred as Automatic Translation into Sign Languages) applications, which represent an important technological opportunity to augment the social inclusion of people with severe hearing impairments. The Database, namely A3LIS-147, is free and available for download.
Scheda della pubblicazione: https://iris.univpm.it/handle/11566/74228 Collegamento a IRIS





Università Politecnica delle Marche P.zza Roma 22, 60121 Ancona Tel (+39) 071.220.1, Fax (+39) 071.220.2324 P.I. 00382520427