Martina Capuzzo, A. Zanella, Maddalena Zuccotto, Federico Cunico, M. Cristani, A. Castellini, A. Farinelli, L. Gamberini
{"title":"IoT Systems for Healthy and Safe Life Environments","authors":"Martina Capuzzo, A. Zanella, Maddalena Zuccotto, Federico Cunico, M. Cristani, A. Castellini, A. Farinelli, L. Gamberini","doi":"10.1109/RTSI55261.2022.9905193","DOIUrl":"https://doi.org/10.1109/RTSI55261.2022.9905193","url":null,"abstract":"The past two years have been sadly marked by the worldwide spread of the SARS-Cov-19 pandemic. The first line of defense against this and other pandemic threats is to respect interpersonal distances, use masks, and sanitize hands, air, and objects. Some of these countermeasures are becoming part of our daily lives, as they are now considered good practices to reduce the risk of infection and contagion. In this context, we present Safe Place, a modular system enabled by Internet of Things (IoT) that is designed to improve the safety and healthiness of living environments. This system combines several sensors and actuators produced by different vendors with self-regulating procedures and Artificial Intelligence (AI) algorithms to limit the spread of viruses and other pathogens, and increase the quality and comfort offered to people while minimizing the energy consumption.We discuss the main objectives of the system and its implementation, showing preliminary results that assess its potentials in enhancing the conditions of living and working spaces.","PeriodicalId":261718,"journal":{"name":"2022 IEEE 7th Forum on Research and Technologies for Society and Industry Innovation (RTSI)","volume":"92 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-08-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122938952","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Nick Rigogiannis, Aikaterini Kotsidimou, Ioannis Arzanas, C. Kyritsi, N. Papanikolaou
{"title":"Comparative Performance Study of Hybrid Si/SiC Insulated-Gate Bipolar Transistors","authors":"Nick Rigogiannis, Aikaterini Kotsidimou, Ioannis Arzanas, C. Kyritsi, N. Papanikolaou","doi":"10.1109/RTSI55261.2022.9905217","DOIUrl":"https://doi.org/10.1109/RTSI55261.2022.9905217","url":null,"abstract":"This paper studies the performance of hybrid Si/SiC IGBTs, in comparison with conventional Si devices, in the prospect of future commercialization of all-SiC IGBTs. Both commercially available and custom-developed device models are evaluated, via LTspice® simulations, in a simple step-down DC-DC conversion application. For the simulation models of commercial, discrete, hybrid IGBTs, devices by Infineon Technologies® are considered, with voltage and current ratings of up to 650 V and 75 A, respectively. High-performance SiC Schottky diodes are also employed, as IGBT antiparallel diodes, in various scenarios. Simulations are carried out for various IGBT cases and operating conditions (i.e., temperature, switching frequency), whereas the device power losses (conduction and switching) are estimated for each case. Finally, simulation results highlight the minimized power losses and the superior performance of hybrid Si/SiC IGBTs, compared to standard Si devices.","PeriodicalId":261718,"journal":{"name":"2022 IEEE 7th Forum on Research and Technologies for Society and Industry Innovation (RTSI)","volume":"46 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-08-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124118399","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
G. Chicco, A. Ciocia, A. Mazza, R. Porumb, F. Spertino
{"title":"Knowledge Discovery from the Statistical Analysis of On-Site Photovoltaic System Data","authors":"G. Chicco, A. Ciocia, A. Mazza, R. Porumb, F. Spertino","doi":"10.1109/RTSI55261.2022.9905207","DOIUrl":"https://doi.org/10.1109/RTSI55261.2022.9905207","url":null,"abstract":"This paper presents some novel ideas and findings to assist data analysts and operators in discovering specific situations from the analysis of photovoltaic data collected in the field. The daily time series of solar irradiance and active power production are transformed into probability distribution functions (PDFs), then the skewness of the PDF is assessed as a potential indicator of orientation of the PV system in directions different from South. The relevant PDFs corresponding to bright days are identified by applying a clustering procedure. The combined calculation of skewness and correlation between solar irradiance and active power data is also used to discover specific cases in which high shadowing occurs in particular days of the year and at particular times. The analyses are carried out by using data collected on-site in PV systems installed at different locations.","PeriodicalId":261718,"journal":{"name":"2022 IEEE 7th Forum on Research and Technologies for Society and Industry Innovation (RTSI)","volume":"25 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-08-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126978989","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Mikolaj Pudo, Natalia Szczepanek, Bozena Lukasiak, A. Janicki
{"title":"Semi-Supervised Learning with Limited Data for Automatic Speech Recognition","authors":"Mikolaj Pudo, Natalia Szczepanek, Bozena Lukasiak, A. Janicki","doi":"10.1109/RTSI55261.2022.9905112","DOIUrl":"https://doi.org/10.1109/RTSI55261.2022.9905112","url":null,"abstract":"In this paper, we analyze the performance of semi-supervised learning (SSL) methods for the automatic speech recognition (ASR) task. We focus on the case of model adaptation using small unlabeled datasets. The basic SSL method that we apply uses pseudo-labels generated by the adapted model itself, however, we also propose and analyze a number of improvements to SSL. Furthermore, we investigate the possibility of using these methods on the datasets with the token distributions significantly different from the one represented by the training data. We show that in certain conditions, even very small amounts of data can improve the ASR model performance. Using the proposed SSL variant, we were able to reduce WER by 12-22%, depending on the dataset.","PeriodicalId":261718,"journal":{"name":"2022 IEEE 7th Forum on Research and Technologies for Society and Industry Innovation (RTSI)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-08-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130015577","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Quentin Demouron, A. Morel, D. Gibus, A. Benhemou, A. Badel
{"title":"Resistive Load Influence on the Power and Bandwidth of Bistable Energy Harvesters","authors":"Quentin Demouron, A. Morel, D. Gibus, A. Benhemou, A. Badel","doi":"10.1109/RTSI55261.2022.9905162","DOIUrl":"https://doi.org/10.1109/RTSI55261.2022.9905162","url":null,"abstract":"Bistable piezoelectric energy harvesters are prominent solutions in the field of vibration energy harvesting due to their broadband behavior. However, the impact of the electrical interface and especially the load impedance needs to be addressed. In this study, the impact of the electrical load resistance on the dynamic of the bistable piezoelectric energy harvester has been studied. Through a parametric study, the present paper shows that the load resistance impacts both the harvested power and the bandwidth of the harvester. The analytical expression of the mass displacement, critical angular frequency and harvested power have been obtained, based on a truncated harmonic balance method. A comparison between the analytical model and experimental measurement on a custom bistable energy harvester is then presented. The experimental results are in good agreement with the analytical model, which proves the validity of the proposed model and analysis. The results presented in this study should be considered in the development of maximum power point tracking algorithms and orbit jump strategies.","PeriodicalId":261718,"journal":{"name":"2022 IEEE 7th Forum on Research and Technologies for Society and Industry Innovation (RTSI)","volume":"22 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-08-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132081025","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Artur Piana, Siqi Wang, João F. Sulzbach, Paolo Zaniboni, Raphael El-Haddad, A. Benlarbi-Delai, G. Klisnick, Pietro M. Ferreira
{"title":"Smart IoT - Implementation of Neuromorphic Circuits","authors":"Artur Piana, Siqi Wang, João F. Sulzbach, Paolo Zaniboni, Raphael El-Haddad, A. Benlarbi-Delai, G. Klisnick, Pietro M. Ferreira","doi":"10.1109/RTSI55261.2022.9905153","DOIUrl":"https://doi.org/10.1109/RTSI55261.2022.9905153","url":null,"abstract":"This paper presents a simple analog neuromorphic system in microelectronics suitable for an audio source localization problem. The receptor can find the relative position of an audio source by the information of angles and distances according to acquire acoustic signals. In this paper, we focus on the angle detection, but some information of the distance is also presented. This paper also presents the development of some alternatives to the most important circuit blocks in neuromorphic systems: the neurons and the synapses. The results are validated in two different levels: the system level and the transistor level.","PeriodicalId":261718,"journal":{"name":"2022 IEEE 7th Forum on Research and Technologies for Society and Industry Innovation (RTSI)","volume":"85 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-08-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131932972","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Convergent Approximate Message Passing by Alternating Constrained Minimization of Bethe Free Energy","authors":"D. Slock","doi":"10.1109/RTSI55261.2022.9905221","DOIUrl":"https://doi.org/10.1109/RTSI55261.2022.9905221","url":null,"abstract":"Approximate Message Passing (AMP) allows for Bayesian inference in linear models with non identically independently distributed (n.i.i.d.) Gaussian priors and measurements of the linear mixture outputs with n.i.i.d. Gaussian noise. It represents an efficient technique for approximate inference which becomes accurate when both rows and columns of the measurement matrix can be treated as sets of independent vectors and both dimensions become large. It has been shown that the fixed points of AMP correspond to extrema of a large system limit of the Bethe Free Energy (LSL-BFE), which represents a meaningful approximation optimization criterion regardless of whether the measurement matrix exhibits the independence properties. However, the convergence of AMP can be notoriously problematic for certain measurement matrices and the only sure fix so far is damping (by a difficult to determine amount). In this paper we revisit the AMP algorithm by rigorously applying an alternating constrained minimization strategy to an appropriately reparameterized LSL-BFE with matched variable and constraint partitioning. This guarantees convergence, and due to convexity in the Gaussian case, to the global optimum. We show that the AMP estimates converge to the Linear Minimum Mean Squared Error (LMMSE) estimates, regardless of the behavior of the variances. In the LSL, the variances also converge to the LMMSE values, and hence to the correct values.","PeriodicalId":261718,"journal":{"name":"2022 IEEE 7th Forum on Research and Technologies for Society and Industry Innovation (RTSI)","volume":"158 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-08-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133184926","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Bifurcation and stability analysis of a Dual-Active-Bridge dc-dc converter working under non-linear control","authors":"Franzese Pasquale, S. Meo, L. Toscano","doi":"10.1109/RTSI55261.2022.9905089","DOIUrl":"https://doi.org/10.1109/RTSI55261.2022.9905089","url":null,"abstract":"The Dual-Active-Bridge dc-dc converter is increasingly used in different fields of power electronics. This converter has different advantages compared to other topologies but can run into its operating range in areas of instability that limit its application. For this reason, the paper develops an accurate discrete large-signal sampled-data model of the controlled converter, then it carries out a stability and bifurcation analysis of the system to determine guidelines to increase the stability region of the controlled system. The control strategy is a discrete non-linear method based on the linearization of Jacobian matrixes. Then the tuning of regulator is a dynamic pole placement implemented using root locus analysis; the assigned poles have been chosen minimizing the 2norm of eigenvalues. This tuning process results in a combination of the pole placement strategy and of the gain scheduling approach, that means both robust and adaptative. Such analysis has been verified by MATLAB simulations. The numerical results show the strong dependence of the stability of the controlled system on the resistance of the output filter capacitor and on the parameters of controller.","PeriodicalId":261718,"journal":{"name":"2022 IEEE 7th Forum on Research and Technologies for Society and Industry Innovation (RTSI)","volume":"15 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-08-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121899214","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
L. Angrisani, P. Arpaia, M. D’Arco, E. D. Benedetto, Antonio Esposito, Monica Imbò
{"title":"The Environmental Sustainability of Measurements: A Practical Case-study With The Wheatstone bridge","authors":"L. Angrisani, P. Arpaia, M. D’Arco, E. D. Benedetto, Antonio Esposito, Monica Imbò","doi":"10.1109/RTSI55261.2022.9905201","DOIUrl":"https://doi.org/10.1109/RTSI55261.2022.9905201","url":null,"abstract":"Sustainability is becoming one of the most important topics in almost all contexts. Because of climate change, it is imperative to be aware of the environmental impact of our actions, and so to re-evaluate the way processes are performed, including in the measurement domain. This paper discusses for the first time the environmental impact of a measurement. The analysis was carried on in the framework of recommendations by the International Telecommunication Union, which particularize ISO standards on life cycle assessment and carbon footprint to the Information and Communication Technology field. The carbon footprint was estimated for each element of a measurement by considering hardware, software, working environment, and operator-related footprint. Data were retrieved from previous literature or from public sustainability reports. As a case study, a classical resistance measurement with Wheatstone bridge was considered. Three scenarios were analysed: in-presence operation with manual control of instruments; in-presence operation with an automatic measuring station; and, finally, remote operation with an automatic measuring station. Results show that a common amount for every scenario spans from about 3000 kg to 18 000kg of equivalent carbon emission (CO2,eq) per year, wherein most of the variation derives from usage of air conditioning. Also, remote operation should be preferred to in-presence one (900kg to 1600kg of CO2,eq versus 1800kg to 4300kg of CO2,eq, with possible addition of 170kg to 310kg for the automatic measuring station).","PeriodicalId":261718,"journal":{"name":"2022 IEEE 7th Forum on Research and Technologies for Society and Industry Innovation (RTSI)","volume":"97 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-08-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125451544","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Belkacem Khaldi, F. Harrou, Dairi Abdelkader, Ying Sun
{"title":"Gated Recurrent Unit Based Short-Term Network for Robot Swarm Motion Forecasting","authors":"Belkacem Khaldi, F. Harrou, Dairi Abdelkader, Ying Sun","doi":"10.1109/RTSI55261.2022.9905085","DOIUrl":"https://doi.org/10.1109/RTSI55261.2022.9905085","url":null,"abstract":"This work introduces a short term forecasting gated recurrent unites framework for swarm motion speed forecasting. This is motivated by the growing need of addressing such forecasting challenges in order to keep swarm robotic systems executing daily collective operations and accomplishing tasks more successfully in groups. The framework is based on the BiGRU model and its performances is compared to its base GRU model. The framework is built upon sensor measurements collected using a simulated swarm of e-puck robots performing a simple pattern formation task in a free/no-free obstacles scenarios. Findings show how accurate BiGRU is in forecasting swarm motion speed while compared to GRU.","PeriodicalId":261718,"journal":{"name":"2022 IEEE 7th Forum on Research and Technologies for Society and Industry Innovation (RTSI)","volume":"87 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-08-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115220570","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}