[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-125781-en":3,"doc-seo-125781-105":30,"detail-sidebar-cat-0-en-105":91},{"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":4,"is_deleted":4,"is_public":20,"is_downloadable":20,"audit_status":20,"page_count":21,"language":22,"language_code":23,"site_id":24,"html_lang":23,"table_of_contents":25,"faqs":26,"seo_title":27,"seo_description":14,"update_tm":28,"read_time":29},125781,4810365810221,"Aurora","https://ap-avatar.wpscdn.com/davatar_155a257f0dc6eb9ab79c44ca47cae57d",7,"Healthcare","Machine Learning Techniques for Low-Power Mobile Health Systems","Machine learning techniques are developed for low-power mobile health systems with a focus on wearable sensing and energy-efficient inference. The thesis presents a feature-augmented hybrid CNN method for stress recognition using wrist-based photoplethysmography, including pre-processing, segmentation, feature extraction, and experimental evaluation with defined datasets and metrics. It also proposes neural contextual bandits for dynamic sensor selection in body-area networks, combining adaptive CNN classification with neural Thompson sampling and evaluating memory and energy consumption.","UC Irvine  \nUC Irvine Electronic Theses and Dissertations  \nTitle  \nMachine Learning Techniques for Low-Power Mobile Health Systems  \nPermalink  \n[https://escholarship.org/uc/item/9wx191sv](https://escholarship.org/uc/item/9wx191sv)  \nAuthor  \nChen, Luke  \nPublication Date  \n2023  \nCopyright Information  \nThis work is made available under the terms of a Creative Commons Attribution  \nNonCommercial License, availalbe at [https://creativecommons.org/licenses/by-nc/4.0/](https://creativecommons.org/licenses/by-nc/4.0/)[ ](https://creativecommons.org/licenses/by-nc/4.0/)[Peer reviewed|Thesis/dissertation](Peer reviewed|Thesis/dissertation)  \n[eScholarship.org](eScholarship.org) Powered by the California Digital Library  \nUniversity of California  \nUNIVERSITY OF CALIFORNIA,  \nIRVINE  \nMachine Learning Techniques for Low-Power Mobile Health Systems  \nTHESIS  \nsubmitted in partial satisfaction of the requirements  \nfor the degree of  \nMASTER OF SCIENCE  \nin Electrical and Computer Engineering  \nby  \nLuke Chen  \nThesis Committee:  \nProfessor Mohammad Al Faruque, Chair Assistant Professor Peter Tseng Assistant Professor Salma Elmalaki  \n© 2021 IEEE  \n© 2022 Berken, Demirel, Luke Chen, et al. All other materials © 2023 Luke Chen  \nDEDICATION  \nTo my family for their unconditional love and support.  \nTABLE OF CONTENTS  \nPage  \nLIST OF FIGURES v  \nLIST OF TABLES vi  \nACKNOWLEDGMENTS vii  \nABSTRACT OF THE THESIS viii  \n1 Introduction 1  \n1.1 Background .................................... 1  \n1.1.1 Stress Recognition ............................ 1  \n1.1.2 Cardiovascular Disease Detection .................... 2  \n1.1.3 Advancements in Wearable Technologies ................ 2  \n1.1.4 Advancements in Machine Learning Techniques ............ 3  \n2 Feature Augmented Hybrid CNN for Stress Recognition Using Wristbased Photoplethysmography Sensor 4  \n2.1 Photoplethysmography .............................. 4  \n2.2 Methodology ................................... 6  \n2.2.1 Pre-processing ............................... 6  \n2.2.2 Segmentation ............................... 6  \n2.2.3 Feature extraction ............................ 7  \n2.2.4 Hybrid CNN (H-CNN) Architecture ................... 7  \n2.3 Experimental Evaluation ............................. 8  \n2.3.1 Dataset .................................. 8  \n2.3.2 Performance Metric ............................ 9  \n2.3.3 Model Training and Evaluation ..................... 10  \n2.4 Chapter Conclusion ................................ 12  \n3 Neural Contextual Bandits Based Dynamic Sensor Selection for Low-Power Body-Area Networks 13  \n3.1 Body-Area-Networks ............................... 13  \n3.2 Motivation ..................................... 16  \n3.3 Methodology ................................... 17  \n3.3.1 Adaptive CNN Classifier ......................... 17  \n3.3.2 Neural Thompson Sampling ....................... 19  \n3.3.3 Context Extraction ............................ 20  \n3.4 Experimental Setup ................................ 20  \n3.4.1 Training Classifier ............................ 20  \n3.4.2 Training Bandits ............................. 21  \n3.5 Experiments and Results ............................. 22  \n3.6 Memory and Energy Consumption Evaluation ................. 24  \n3.7 Chapter Conclusion ................................ 27  \n4 Conclusion 28  \nBibliography 29  \nLIST OF FIGURES  \nPage  \n2.1 Overview of Our Proposed Methodology .................... 6  \n2.2 Performance Comparison on 3-Class (Baseline vs Stress vs Amusement) Classification ...................................... 11  \n2.3 Performance Comparison on 2-Class (Stress vs Non-stress) Classification .. 12  \n3.1 The classification performance of each class with different sensor combinations 16  \n3.2 Proposed Classifier and Neural Bandit Architecture .............. 18  \n3.3 The energy consumption of transfer operation for different lead combinationsand proposed adaptive solution ......................... 25  \n3.4 Comparison of comp","cbCaic7kNSjI5Iny","https://ap.wps.com/l/cbCaic7kNSjI5Iny","pdf",857061,1,42,"English","en",105,"# 1 Introduction\n## 1.1 Background\n# 2 Feature Augmented Hybrid CNN for Stress Recognition Using Wristbased Photoplethysmography Sensor\n## 2.2 Methodology\n# 3 Neural Contextual Bandits Based Dynamic Sensor Selection for Low-Power Body-Area Networks\n## 3.3 Methodology\n# 4 Conclusion\n# Bibliography","[{\"question\":\"What problem does the thesis address in low-power mobile health systems?\",\"answer\":\"It targets accurate sensing and inference under low-power constraints, focusing on stress recognition and energy-aware operation in wearable and body-area network settings.\"},{\"question\":\"How is stress recognition performed in the proposed approach?\",\"answer\":\"The thesis builds a feature-augmented hybrid CNN using wrist-based photoplethysmography, with steps including pre-processing, segmentation, feature extraction, and hybrid CNN architecture design, followed by experimental evaluation.\"},{\"question\":\"What is dynamic sensor selection and how is it modeled here?\",\"answer\":\"Dynamic sensor selection is framed using neural contextual bandits, where adaptive CNN classification is combined with neural Thompson sampling and context extraction to decide sensor use.\"}]","Machine Learning Techniques for Low-Power Mobile Health Systems | PDF",1785901171,106,{"code":4,"msg":31,"data":32},"ok",{"site_id":24,"language":23,"slug":33,"title":13,"keywords":34,"description":14,"schema_data":35,"social_meta":86,"head_meta":88,"extra_data":90,"updated_unix":28},"machine-learning-techniques-for-low-power-mobile-health-systems","",{"@graph":36,"@context":85},[37,54,68],{"@type":38,"itemListElement":39},"BreadcrumbList",[40,44,48,51],{"item":41,"name":42,"@type":43,"position":20},"https://docshare.wps.com","Home","ListItem",{"item":45,"name":46,"@type":43,"position":47},"https://docshare.wps.com/document/","Document",2,{"item":49,"name":12,"@type":43,"position":50},"https://docshare.wps.com/document/healthcare/",3,{"item":52,"name":13,"@type":43,"position":53},"https://docshare.wps.com/document/machine-learning-techniques-for-low-power-mobile-health-systems/125781/",4,{"url":52,"name":13,"@type":55,"author":56,"headline":13,"publisher":58,"fileFormat":61,"inLanguage":23,"description":14,"dateModified":62,"datePublished":62,"encodingFormat":61,"isAccessibleForFree":63,"interactionStatistic":64},"DigitalDocument",{"name":9,"@type":57},"Person",{"url":41,"name":59,"@type":60},"DocShare","Organization","application/pdf","2026-08-05",true,{"@type":65,"interactionType":66,"userInteractionCount":4},"InteractionCounter",{"@type":67},"ViewAction",{"@type":69,"mainEntity":70},"FAQPage",[71,77,81],{"name":72,"@type":73,"acceptedAnswer":74},"What problem does the thesis address in low-power mobile health systems?","Question",{"text":75,"@type":76},"It targets accurate sensing and inference under low-power constraints, focusing on stress recognition and energy-aware operation in wearable and body-area network settings.","Answer",{"name":78,"@type":73,"acceptedAnswer":79},"How is stress recognition performed in the proposed approach?",{"text":80,"@type":76},"The thesis builds a feature-augmented hybrid CNN using wrist-based photoplethysmography, with steps including pre-processing, segmentation, feature extraction, and hybrid CNN architecture design, followed by experimental evaluation.",{"name":82,"@type":73,"acceptedAnswer":83},"What is dynamic sensor selection and how is it modeled here?",{"text":84,"@type":76},"Dynamic sensor selection is framed using neural contextual bandits, where adaptive CNN classification is combined with neural Thompson sampling and context extraction to decide sensor use.","https://schema.org",{"og:url":52,"og:type":87,"og:title":13,"og:site_name":59,"og:description":14},"article",{"robots":89,"canonical":52},"index,follow",{"doc_id":7,"site_id":24},{"code":4,"msg":5,"data":92},[93,97,101,105,110,115,118,123,128,131,135],{"id":20,"doc_module":4,"doc_module_name":46,"category_name":94,"show_sort_weight":95,"slug":96},"Story & Novel",90,"story-novel",{"id":47,"doc_module":4,"doc_module_name":46,"category_name":98,"show_sort_weight":99,"slug":100},"Literature",80,"literature",{"id":53,"doc_module":4,"doc_module_name":46,"category_name":102,"show_sort_weight":103,"slug":104},"Exam",70,"exam",{"id":106,"doc_module":4,"doc_module_name":46,"category_name":107,"show_sort_weight":108,"slug":109},5,"Comic",60,"comic",{"id":111,"doc_module":4,"doc_module_name":46,"category_name":112,"show_sort_weight":113,"slug":114},6,"Technology",50,"technology",{"id":11,"doc_module":4,"doc_module_name":46,"category_name":12,"show_sort_weight":116,"slug":117},40,"healthcare",{"id":119,"doc_module":4,"doc_module_name":46,"category_name":120,"show_sort_weight":121,"slug":122},8,"Research & Report",30,"research-report",{"id":124,"doc_module":4,"doc_module_name":46,"category_name":125,"show_sort_weight":126,"slug":127},9,"Religion & Spirituality",20,"religion-spirituality",{"id":126,"doc_module":4,"doc_module_name":46,"category_name":129,"show_sort_weight":126,"slug":130},"World Cup","world-cup",{"id":132,"doc_module":4,"doc_module_name":46,"category_name":133,"show_sort_weight":132,"slug":134},10,"Lifestyle","lifestyle",{"id":136,"doc_module":4,"doc_module_name":46,"category_name":137,"show_sort_weight":106,"slug":138},19,"General","general"]