[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-119535-en":3,"doc-seo-119535-105":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},119535,1374391974564,"Clementine","https://ap-avatar.wpscdn.com/avatar/14000253aa45c000a9e?x-image-process=image/resize,m_fixed,w_180,h_180&k=1779874745381141002",8,"Research & Report","Machine Learning-Assisted Networking Protocols for Emerging IoT Applications - Dissertation","This dissertation investigates networking protocols for mesoscale Internet of Things (IoT) applications where link and path quality fluctuate and dedicated radio technologies may be unavailable. It develops machine learning-assisted approaches to estimate path quality and guide multi-radio selection, aiming to improve end-to-end throughput. The work also proposes COMNETS with cost-sensitive learning objectives and EDRP with enhanced dynamic relay decisions. Real-world and large-scale experiments evaluate performance, structural properties, and design insights for deploying multi-hop multi-radio IoT networks.","UC Merced  \nUC Merced Electronic Theses and Dissertations  \nTitle  \nMachine Learning-Assisted Networking Protocols for Emerging IoT Applications  \nPermalink  \n[https://escholarship.org/uc/item/8tx8s6zw](https://escholarship.org/uc/item/8tx8s6zw)  \nISBN  \n9798297603646  \nAuthor  \nShanmuga Sundaram, Jothi Prasanna  \nPublication Date  \n2025-08-08  \nPeer reviewed|Thesis/dissertation  \n[eScholarship.org](eScholarship.org) Powered by the California Digital Library  \nUniversity of California  \nUNIVERSITY OF CALIFORNIA, MERCED  \nMachine Learning-Assisted Networking Protocols for Emerging IoT  \nApplications  \nA dissertation submitted in partial satisfaction of the requirements for the degree  \nDoctor of Philosophy  \nin  \nElectrical Engineering and Computer Science  \nby  \nJothi Prasanna Shanmuga Sundaram  \nCommittee in charge:  \nProfessor Alberto Cerpa, Chair  \nProfessor Miguel ´A . Carreira-Perpi˜n´an  \nProfessor Hua Huang  \n2025  \nCopyright  \nJothi Prasanna Shanmuga Sundaram, 2025 All rights reserved.  \nThe dissertation of Jothi Prasanna Shanmuga Sundaram is approved, and it is acceptable in quality and form for publication on microfilm and electronically:  \n(Professor Miguel ´A . Carreira-Perpi˜n´an)  \n(Professor Hua Huang)  \n(Professor Alberto Cerpa, Chair)  \nUniversity of California, Merced  \n2025  \nDEDICATION  \nDedicated to my wife, sister, and parents.  \nTABLE OF CONTENTS  \nSignature Page .......................... iii  \nDedication ............................. iv  \nTable of Contents ......................... v  \nList of Figures ........................... viii  \nList of Tables ........................... x  \nAcknowledgements ........................ xi  \nVita and Publications ....................... xiii  \nAbstract .............................. xiv  \nChapter 1 Introduction ............................ 1  \n1.1 Taxonomy of mesoscale applications based on KPI .... 2  \n1.1.1 Traditional Vs. Emerging mesoscale IoT applications ......................... 2  \n1.1.2 Important metrics for mesoscale IoT applications 3  \n1.1.3 Taxonomy ...................... 5  \n1.2 Challenges faced by mesoscale IoT applications ...... 6  \n1.2.1 Mesoscale applications lack dedicated radio technologies ....................... 6  \n1.2.2 Deployment factors affecting mesoscale applications: ......................... 7  \n1.3 Contributions ........................ 8  \nChapter 2 Related work ........................... 11  \n2.1 Multi-radio systems ..................... 11  \n2.2 Cost-sensitive machine learning .............. 14  \n2.3 Data dissemination for multi-hop IoT networks ...... 17  \nChapter 3 Background ............................ 22  \n3.1 Link/Path quality metrics ................. 22  \n3.1.1 Traditional path quality estimations ........ 24  \n3.2 Decision Trees ........................ 25  \n3.3 Tree Alternating Optimization Algorithm ......... 26  \nChapter 4 MARS ............................... 29  \n4.1 Introduction ......................... 29  \n4.2 MARS System Overview .................. 31  \n4.3 A qualitative comparison of IoT radios for mesoscale applications .......................... 32  \n4.4 A quantitative comparison of potential radio candidates . 33  \n4.4.1 Single-hop experiments ............... 33  \n4.4.2 Multi-hop experiments ............... 36  \n4.5 End-to-End throughput (E2E) fluctuations in the gray region ............................ 39  \n4.6 Why multi-radio networks for mesoscale IoT applications? 41  \n4.7 Building a machine learning model ............ 44  \n4.7.1 Problem formulation ................ 45  \n4.7.2 Prediction methods and results .......... 47  \n4.8 Realizing TAO-CART on end devices ........... 49  \n4.8.1 Traditional path quality estimations are not instantaneous ..................... 51  \n4.8.2 DT-based path quality estimation ......... 52  \n4.9 Large-scale experimental results .............. 54  \n4.9.1 Performance evaluation ............... 56  \n4.10 Discussion .......................... 59  \n4.11 Conclusion ....................","cbCaitICsmKK3CHR","https://ap.wps.com/l/cbCaitICsmKK3CHR","pdf",6739528,1,129,"English","en",105,"# Chapter 1 Introduction\n## Taxonomy of mesoscale applications based on KPI\n## Challenges faced by mesoscale IoT applications\n## Contributions\n# Chapter 2 Related work\n## Multi-radio systems\n## Cost-sensitive machine learning\n## Data dissemination for multi-hop IoT networks\n# Chapter 3 Background\n## Link/Path quality metrics\n## Decision Trees\n## Tree Alternating Optimization Algorithm\n# Chapter 4 MARS\n## System overview\n## Radio comparisons for mesoscale applications\n## Machine learning model and predictions\n## TAO-CART on end devices\n## Large-scale experimental results\n# Chapter 5 COMNETS\n## Cost-sensitive loss and ML model\n## Structural stability property\n## Large-scale evaluations\n# Chapter 6 EDRP\n## Enhanced Dynamic Relay Point Protocol\n## LQ-CSMA and ML-BSS components\n## Real-world evaluations\n# Chapter 7 Conclusions and Future work","[{\"question\":\"What problem does the dissertation target in mesoscale IoT networking?\",\"answer\":\"It targets mesoscale IoT scenarios where link/path quality metrics are hard to estimate instantaneously and where dedicated radio technologies may be lacking, causing networking performance challenges.\"},{\"question\":\"How does MARS use machine learning in the proposed networking approach?\",\"answer\":\"MARS builds and applies a machine learning model to estimate path quality and supports radio selection, including DT-based path quality estimation and TAO-CART realization on end devices.\"},{\"question\":\"What are COMNETS and EDRP focused on?\",\"answer\":\"COMNETS focuses on optimizing a cost-sensitive loss using an ML model for multi-radio/cost-aware objectives, while EDRP enhances dynamic relay decisions using components such as LQ-CSMA and an ML-based block size selection algorithm for rateless coding.\"}]","Machine Learning-Assisted Networking Protocols for Emerging IoT Applications - Dissertation | PDF",1785724831,325,{"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-assisted-networking-protocols-for-emerging-iot-applications-dissertation","",{"@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/research-report/",3,{"item":52,"name":13,"@type":43,"position":53},"https://docshare.wps.com/document/machine-learning-assisted-networking-protocols-for-emerging-iot-applications-dissertation/119535/",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","2026-08-03",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 dissertation target in mesoscale IoT networking?","Question",{"text":75,"@type":76},"It targets mesoscale IoT scenarios where link/path quality metrics are hard to estimate instantaneously and where dedicated radio technologies may be lacking, causing networking performance challenges.","Answer",{"name":78,"@type":73,"acceptedAnswer":79},"How does MARS use machine learning in the proposed networking approach?",{"text":80,"@type":76},"MARS builds and applies a machine learning model to estimate path quality and supports radio selection, including DT-based path quality estimation and TAO-CART realization on end devices.",{"name":82,"@type":73,"acceptedAnswer":83},"What are COMNETS and EDRP focused on?",{"text":84,"@type":76},"COMNETS focuses on optimizing a cost-sensitive loss using an ML model for multi-radio/cost-aware objectives, while EDRP enhances dynamic relay decisions using components such as LQ-CSMA and an ML-based block size selection algorithm for rateless coding.","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},[93,97,101,105,110,115,120,123,128,131,135],{"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":116,"doc_module":4,"doc_module_name":46,"category_name":117,"show_sort_weight":118,"slug":119},7,"Healthcare",40,"healthcare",{"id":11,"doc_module":4,"doc_module_name":46,"category_name":12,"show_sort_weight":121,"slug":122},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"]