[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-119357-en":3,"doc-seo-119357-105":30,"detail-sidebar-cat-0-en-105":95},{"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":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},119357,1099514067415,"Rowan","https://ap-avatar.wpscdn.com/avatar/100002539d78ffe74a7?x-image-process=image/resize,m_fixed,w_180,h_180&k=1779092875211072502",8,"Research & Report","Lightly Supervised Machine Learning for Wireless Signals - dissertation","Modern wireless communication systems struggle to manage finite spectrum resources while meeting rising demands for data and connectivity. This dissertation studies machine learning methods that reduce supervision requirements using three complementary approaches: cooperative learning of compatible modulation schemes by minimally assumed radio agents, automatic calibration and metadata generation for distributed spectrum sensing via signals of opportunity, and generative models for privacy-preserving sharing of wireless datasets. Across simulations and software-defined radio experiments, the work builds more autonomous, scalable systems with robust performance and reduced human oversight.","UC Berkeley  \nUC Berkeley Electronic Theses and Dissertations  \nTitle  \nLightly Supervised Machine Learning for Wireless Signals  \nPermalink  \n[https://escholarship.org/uc/item/5zr788vt](https://escholarship.org/uc/item/5zr788vt)  \nAuthor  \nSanz, Joshua  \nPublication Date  \n2024  \nPeer reviewed|Thesis/dissertation  \n[eScholarship.org](eScholarship.org) Powered by the California Digital Library  \nUniversity of California  \nLightly Supervised Machine Learning for Wireless Signals  \nby  \nJoshua Sanz  \nA dissertation submitted in partial satisfaction of the requirements for the degree of Doctor of Philosophy  \nin  \nEngineering – Electrical Engineering and Computer Sciences  \nin the  \nGraduate Division  \nof the  \nUniversity of California, Berkeley  \nCommittee in charge:  \nProfessor Anant Sahai, Chair Professor Jiantao Jiao  \nProfessor Michael Lustig Professor Pramod Viswanath  \nFall 2024  \nLightly Supervised Machine Learning for Wireless Signals  \nCopyright 2024  \nby  \nJoshua Sanz  \n1  \nAbstract  \nLightly Supervised Machine Learning for Wireless Signals  \nby  \nJoshua Sanz  \nDoctor of Philosophy in Engineering – Electrical Engineering and Computer Sciences  \nUniversity of California, Berkeley  \nProfessor Anant Sahai, Chair  \nModern wireless communication systems face unprecedented challenges in managing finite spectrum resources while meeting growing demands for data and connectivity. This dissertation explores how machine learning techniques with reduced supervision requirements can address these challenges through three complementary approaches. First, I demonstrate that two radio agents with minimal shared assumptions can learn compatible modulation schemes through cooperative interaction, enabling communication without explicit protocol design. Careful experimentation, including simulation and implementation on software-defined radios, shows that while reduced supervision increases learning time, agents can still achieve near-optimal performance. Second, I develop techniques for automatic calibration and metadata generation in distributed spectrum sensing networks using signals of opportunity as a form of environmental supervision. These techniques enable verification of sensor characteristics like field of view and location without manual intervention, facilitating trustworthy large-scale deployments. Finally, I propose using generative models to allow the sharing of wireless datasets while preserving privacy, addressing a key barrier to advancing wireless machine learning research. The unifying theme is the development of techniques that minimize required human supervision while maintaining robust performance, enabling more autonomous and scalable wireless systems. This research is a step toward cognitive radio networks that can adaptively and cooperatively manage spectrum resources with reduced human oversight.  \ni  \nTo my advisor, Professor Anant Sahai,  \nThank you for your invaluable guidance and support throughout my time at Berkeley. I am humbled by your unfailing positivity and incisive comments and questions. I hope to emulate your example throughout my career. Thank you also to my wife, family, and friends who were essential to keeping me happy, healthy, and sane through the ups and  \ndowns of a Ph.D.  \nii  \nContents  \nContents ii  \nList of Figures iv  \nList of Tables vii  \n1 Introduction 1  \n1.1 Why ML for Wireless Communication? ..................... 2  \n1.2 Employing Machine Learning for Wireless PHY ................ 4  \n1.3 Beyond Protocols: Exploiting the Physical World ............... 7  \n1.4 Bringing Wireless Comms into the Age of Big Data .............. 10  \n2 Interactive Supervision for Learning Wireless PHY 12  \n2.1 Introduction .................................... 12  \n2.2 Related Work ................................... 15  \n2.3 Overview ...................................... 17  \n2.4 Levels of Information Sharing .......................... 20  \n2.5 Alienness of Agents ................................ 26  \n","cbCain3r97nzf21y","https://ap.wps.com/l/cbCain3r97nzf21y","pdf",37779547,1,195,"English","en",105,"# 1 Introduction\n## 1.1 Why ML for Wireless Communication?\n## 1.2 Employing Machine Learning for Wireless PHY\n## 1.3 Beyond Protocols: Exploiting the Physical World\n## 1.4 Bringing Wireless Comms into the Age of Big Data\n# 2 Interactive Supervision for Learning Wireless PHY\n## 2.1 Introduction\n## 2.2 Related Work\n## 2.3 Overview\n## 2.4 Levels of Information Sharing\n## 2.5 Alienness of Agents\n## 2.6 Experiments\n## 2.7 Results\n## 2.8 Implementation in Software-Defined Radios\n## 2.9 Conclusion\n# 3 Environmental Supervision for Automatic Sensing and Calibration\n## 3.1 Introduction\n## 3.2 Related Work\n## 3.3 Signal Sources\n## 3.4 Automatic Sensor Evaluation and Calibration\n## 3.5 Automatic Metadata Generation\n## 3.6 Conclusion\n# 4 Towards Synthetic Datasets for Data-Scarce Domains\n## 4.1 Introduction\n## 4.2 Related Work\n## 4.3 Methods\n## 4.4 Results\n## 4.5 Conclusions\n# 5 Concluding Thoughts","[{\"question\":\"What problem does the dissertation address in wireless communications?\",\"answer\":\"It targets the challenge of managing finite spectrum resources while meeting growing requirements for data and connectivity, where conventional wireless systems need assistance from learning methods.\"},{\"question\":\"How does interactive supervision enable learning of wireless physical-layer tasks?\",\"answer\":\"It uses cooperative interaction between radio agents with minimal shared assumptions to learn compatible modulation schemes, demonstrated via simulation and software-defined radio experiments.\"},{\"question\":\"What is meant by environmental supervision in distributed spectrum sensing?\",\"answer\":\"The work uses signals of opportunity as a form of environmental supervision to automatically calibrate sensors and generate metadata, enabling verification of sensor characteristics without manual intervention.\"},{\"question\":\"How does the dissertation support privacy-preserving sharing of wireless datasets?\",\"answer\":\"It proposes using generative models to share wireless datasets while preserving privacy, addressing a key barrier to advancing wireless machine learning research.\"}]","Lightly Supervised Machine Learning for Wireless Signals - dissertation | PDF",1785723895,491,{"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":90,"head_meta":92,"extra_data":94,"updated_unix":28},"lightly-supervised-machine-learning-for-wireless-signals-dissertation","",{"@graph":36,"@context":89},[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/lightly-supervised-machine-learning-for-wireless-signals-dissertation/119357/",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":20},"InteractionCounter",{"@type":67},"ViewAction",{"@type":69,"mainEntity":70},"FAQPage",[71,77,81,85],{"name":72,"@type":73,"acceptedAnswer":74},"What problem does the dissertation address in wireless communications?","Question",{"text":75,"@type":76},"It targets the challenge of managing finite spectrum resources while meeting growing requirements for data and connectivity, where conventional wireless systems need assistance from learning methods.","Answer",{"name":78,"@type":73,"acceptedAnswer":79},"How does interactive supervision enable learning of wireless physical-layer tasks?",{"text":80,"@type":76},"It uses cooperative interaction between radio agents with minimal shared assumptions to learn compatible modulation schemes, demonstrated via simulation and software-defined radio experiments.",{"name":82,"@type":73,"acceptedAnswer":83},"What is meant by environmental supervision in distributed spectrum sensing?",{"text":84,"@type":76},"The work uses signals of opportunity as a form of environmental supervision to automatically calibrate sensors and generate metadata, enabling verification of sensor characteristics without manual intervention.",{"name":86,"@type":73,"acceptedAnswer":87},"How does the dissertation support privacy-preserving sharing of wireless datasets?",{"text":88,"@type":76},"It proposes using generative models to share wireless datasets while preserving privacy, addressing a key barrier to advancing wireless machine learning research.","https://schema.org",{"og:url":52,"og:type":91,"og:title":13,"og:site_name":59,"og:description":14},"article",{"robots":93,"canonical":52},"index,follow",{"doc_id":7,"site_id":24},{"code":4,"msg":5,"data":96},[97,101,105,109,114,119,124,127,132,135,139],{"id":20,"doc_module":4,"doc_module_name":46,"category_name":98,"show_sort_weight":99,"slug":100},"Story & Novel",90,"story-novel",{"id":47,"doc_module":4,"doc_module_name":46,"category_name":102,"show_sort_weight":103,"slug":104},"Literature",80,"literature",{"id":53,"doc_module":4,"doc_module_name":46,"category_name":106,"show_sort_weight":107,"slug":108},"Exam",70,"exam",{"id":110,"doc_module":4,"doc_module_name":46,"category_name":111,"show_sort_weight":112,"slug":113},5,"Comic",60,"comic",{"id":115,"doc_module":4,"doc_module_name":46,"category_name":116,"show_sort_weight":117,"slug":118},6,"Technology",50,"technology",{"id":120,"doc_module":4,"doc_module_name":46,"category_name":121,"show_sort_weight":122,"slug":123},7,"Healthcare",40,"healthcare",{"id":11,"doc_module":4,"doc_module_name":46,"category_name":12,"show_sort_weight":125,"slug":126},30,"research-report",{"id":128,"doc_module":4,"doc_module_name":46,"category_name":129,"show_sort_weight":130,"slug":131},9,"Religion & Spirituality",20,"religion-spirituality",{"id":130,"doc_module":4,"doc_module_name":46,"category_name":133,"show_sort_weight":130,"slug":134},"World Cup","world-cup",{"id":136,"doc_module":4,"doc_module_name":46,"category_name":137,"show_sort_weight":136,"slug":138},10,"Lifestyle","lifestyle",{"id":140,"doc_module":4,"doc_module_name":46,"category_name":141,"show_sort_weight":110,"slug":142},19,"General","general"]