[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-126176-en":3,"doc-seo-126176-105":31,"detail-sidebar-cat-0-en-105":93},{"code":4,"msg":5,"data":6},0,"success",{"doc_id":7,"user_id":8,"nickname":9,"user_avatar":10,"doc_module":4,"category_id":11,"category_name":12,"doc_title":13,"doc_description":14,"doc_content":15,"file_id":16,"file_url":17,"file_type":18,"file_size":19,"view_count":20,"is_deleted":4,"is_public":21,"is_downloadable":21,"audit_status":21,"page_count":22,"language":23,"language_code":24,"site_id":25,"html_lang":24,"table_of_contents":26,"faqs":27,"seo_title":28,"seo_description":14,"update_tm":29,"read_time":30},126176,3985741905716,"Rowan","https://ap-avatar.wpscdn.com/davatar_994ba38a5ba835b3df7d355c54d3ed8d",8,"Research & Report","ENERGY-EFFICIENT TIME SERIES ANALYSIS WITH MACHINE LEARNING AND DEEP LEARNING ON EMBEDDED COMPUTING PLATFORMS","This Ph.D. thesis develops techniques and solutions for energy-efficient time-series analysis using automated learning on resource-constrained, low-power computing platforms, leveraging both deep learning and traditional machine learning. The research frames time-series modeling as a task executed under the constraints of low-power edge devices, with an emphasis on single- and multi-core embedded microcontrollers. It addresses binary classification, multi-class classification, and regression across domains including biosignal processing, industrial sensing, epilepsy detection, and sEMG-based hand modeling for wearable human-machine interfaces, demonstrating accuracy–efficiency effectiveness for industrial, clinical, and consumer applications.","DOTTORATO DI RICERCA IN DATA SCIENCE AND COMPUTATION Ciclo 35  \nSettore Concorsuale: 09/E3-ELETTRONICA  \nSettore Scientifico Disciplinare: ING-INF/01-ELETTRONICA  \nENERGY-EFFICIENT TIME SERIES ANALYSIS WITH MACHINE LEARNING AND DEEP LEARNING ON EMBEDDED COMPUTING PLATFORMS  \nPresentata da: Marcello Zanghieri  \nCoordinatore Dottorato Supervisore  \nDaniele Bonacorsi Luca Benini  \nCo-supervisori  \nSimone Benatti  \nFrancesco Conti  \nEsame finale anno 2024  \nALMA MATER STUDIORUM-UNIVERSITY OF BOLOGNA  \nEnergy-Efficient Time Series Analysis with Machine Learning and Deep Learning on Embedded Computing Platforms  \nby Marcello Zanghieri  \nA thesis submitted for the degree of  \nDoctor of Philosophy  \nin the  \nSchool of Engineering and Architecture Department of Electrical, Electronic, and Information Engineering (DEI)  \nMay 2024  \nI dedicate this thesis to my family.  \nAcknowledgments  \nI wish to thank my supervisor, Prof. Luca Benini, for the opportunity to pursue my PhD in his research group and for his constant guidance. I also thank my co-supervisors, Prof. Simone Benatti and Prof. Francesco Conti, for their persevering supervision, their teachings, and the motivation they gave me. I thank all three of them for the support and independence they gave me. I also want to thank Dr. Francesco Beneventi for the technical help at the beginning of my PhD and for his vast patience.  \nI thank Prof. Giacomo Indiveri for welcoming me to his NCS group at INI for a visiting research period. I thank him and Dr. Elisa Donati for following my work.  \nI thank Dr. Elisabetta Farella and Prof. Melika Payvand for their willingness to review this thesis.  \nI address special thanks to Panagiota (Iota) Dimopoulou for guiding us DSC PhD students through the bureaucratic and formal stages of the programme in the first years. I also thank our PhD coordinator, Prof. Daniele Bonacorsi, for the accurate and timely directions at the end of the PhD.  \nFinally, I want to thank all my colleagues at the EEES Lab for creating this enjoyable and inspiring environment.  \nAbstract  \nThe present Ph.D. thesis presents techniques and solutions for energy-efficient timeseries analysis based on automated learning executed on resource-constrained, low-power computing platforms, with an interest in both Deep Learning and traditional, non-deep Machine Learning. This dissertation spans diverse domains, from algorithmic research on the accuracy-efficiency tradeoff in processing different biosignals to applied research inspired by industrial scenarios.  \nThe unifying methodology that brings all the research questions addressed in this thesis under the same perspective is the interest in time-series analysis as a task to be performed in the presence of the resource constraints characteristic of low-power edge computing devices. In particular, a special focus is devoted to single- and multi-core embedded microcontrollers (MCUs) .  \nThis dissertation covers the three major types of automated learning tasks: binary classification, multi-class (single-label) classification, and regression. Starting from binary classification, this work presents a proximity sensor for active safety in industrial machinery, accurate and robust against acoustic noise, and a setup for epilepsy detection from intracranial electroencephalography. Both solutions are based on a Temporal Convolutional Network (TCN) executed on an embedded MCU, showcasing the power and versatility of the approach. Moving to multi-class (single-label) classification and regression, the research effort was entirely devoted to the topic of hand modeling from the surface electromyographic (sEMG) signal. Starting with off-device TCNs for the recognition of discrete hand gestures, the classification setup is advanced by carrying out the deployment on a multi-core MCU and by studying heuristics for unsupervised adaptation to compensate for changes in arm posture. Then, regression was addressed for amore fluid and versatile control of H","cbCaiuTdhm2w9KWc","https://ap.wps.com/l/cbCaiuTdhm2w9KWc","pdf",14307986,5,1,162,"English","en",105,"# Introduction\n## Contributions & Thesis Structure\n# Background\n## Temporal Convolutional Networks\n## Microcontrollers of Interest\n## Embedding Deep Networks: Compression & Deployment\n## sEMG-based Human-Machine Interfaces\n# Binary Classification\n## An Extreme-Edge TCN-based Low-Latency Collision-Avoidance Safety System for Industrial Machinery","[{\"question\":\"What is the central focus of the thesis?\",\"answer\":\"The thesis focuses on energy-efficient time-series analysis using automated learning on resource-constrained low-power edge platforms, with special attention to embedded microcontrollers.\"},{\"question\":\"Which automated learning task types are covered?\",\"answer\":\"It covers three major automated learning tasks: binary classification, multi-class (single-label) classification, and regression.\"},{\"question\":\"How does the research address both deep learning and traditional machine learning?\",\"answer\":\"It develops solutions that use deep learning approaches such as Temporal Convolutional Networks while also considering non-deep machine learning techniques within the broader energy-efficiency and accuracy-efficiency research agenda.\"}]","ENERGY-EFFICIENT TIME SERIES ANALYSIS WITH MACHINE LEARNING AND DEEP LEARNING ON EMBEDDED COMPUTING PLATFORMS | PDF",1785903611,408,{"code":4,"msg":32,"data":33},"ok",{"site_id":25,"language":24,"slug":34,"title":13,"keywords":35,"description":14,"schema_data":36,"social_meta":88,"head_meta":90,"extra_data":92,"updated_unix":29},"energy-efficient-time-series-analysis-with-machine-learning-and-deep-learning-on-embedded-computing-platforms","",{"@graph":37,"@context":87},[38,55,70],{"@type":39,"itemListElement":40},"BreadcrumbList",[41,45,49,52],{"item":42,"name":43,"@type":44,"position":21},"https://docshare.wps.com","Home","ListItem",{"item":46,"name":47,"@type":44,"position":48},"https://docshare.wps.com/document/","Document",2,{"item":50,"name":12,"@type":44,"position":51},"https://docshare.wps.com/document/research-report/",3,{"item":53,"name":13,"@type":44,"position":54},"https://docshare.wps.com/document/energy-efficient-time-series-analysis-with-machine-learning-and-deep-learning-on-embedded-computing-platforms/126176/",4,{"url":53,"name":13,"@type":56,"author":57,"headline":13,"publisher":59,"fileFormat":62,"inLanguage":24,"description":14,"dateModified":63,"datePublished":64,"encodingFormat":62,"isAccessibleForFree":65,"interactionStatistic":66},"DigitalDocument",{"name":9,"@type":58},"Person",{"url":42,"name":60,"@type":61},"DocShare","Organization","application/pdf","2026-08-23","2026-08-05",true,{"@type":67,"interactionType":68,"userInteractionCount":20},"InteractionCounter",{"@type":69},"ViewAction",{"@type":71,"mainEntity":72},"FAQPage",[73,79,83],{"name":74,"@type":75,"acceptedAnswer":76},"What is the central focus of the thesis?","Question",{"text":77,"@type":78},"The thesis focuses on energy-efficient time-series analysis using automated learning on resource-constrained low-power edge platforms, with special attention to embedded microcontrollers.","Answer",{"name":80,"@type":75,"acceptedAnswer":81},"Which automated learning task types are covered?",{"text":82,"@type":78},"It covers three major automated learning tasks: binary classification, multi-class (single-label) classification, and regression.",{"name":84,"@type":75,"acceptedAnswer":85},"How does the research address both deep learning and traditional machine learning?",{"text":86,"@type":78},"It develops solutions that use deep learning approaches such as Temporal Convolutional Networks while also considering non-deep machine learning techniques within the broader energy-efficiency and accuracy-efficiency research agenda.","https://schema.org",{"og:url":53,"og:type":89,"og:title":13,"og:site_name":60,"og:description":14},"article",{"robots":91,"canonical":53},"index,follow",{"doc_id":7,"site_id":25},{"code":4,"msg":5,"data":94},[95,99,103,107,111,116,121,124,129,132,136],{"id":21,"doc_module":4,"doc_module_name":47,"category_name":96,"show_sort_weight":97,"slug":98},"Story & Novel",90,"story-novel",{"id":48,"doc_module":4,"doc_module_name":47,"category_name":100,"show_sort_weight":101,"slug":102},"Literature",80,"literature",{"id":54,"doc_module":4,"doc_module_name":47,"category_name":104,"show_sort_weight":105,"slug":106},"Exam",70,"exam",{"id":20,"doc_module":4,"doc_module_name":47,"category_name":108,"show_sort_weight":109,"slug":110},"Comic",60,"comic",{"id":112,"doc_module":4,"doc_module_name":47,"category_name":113,"show_sort_weight":114,"slug":115},6,"Technology",50,"technology",{"id":117,"doc_module":4,"doc_module_name":47,"category_name":118,"show_sort_weight":119,"slug":120},7,"Healthcare",40,"healthcare",{"id":11,"doc_module":4,"doc_module_name":47,"category_name":12,"show_sort_weight":122,"slug":123},30,"research-report",{"id":125,"doc_module":4,"doc_module_name":47,"category_name":126,"show_sort_weight":127,"slug":128},9,"Religion & Spirituality",20,"religion-spirituality",{"id":127,"doc_module":4,"doc_module_name":47,"category_name":130,"show_sort_weight":127,"slug":131},"World Cup","world-cup",{"id":133,"doc_module":4,"doc_module_name":47,"category_name":134,"show_sort_weight":133,"slug":135},10,"Lifestyle","lifestyle",{"id":137,"doc_module":4,"doc_module_name":47,"category_name":138,"show_sort_weight":20,"slug":139},19,"General","general"]