[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-120215-en":3,"doc-seo-120215-105":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},120215,7971461740886,"Theodore","https://ap-avatar.wpscdn.com/davatar_3d24733baf745e90a7e4bdd5f77d97b2",8,"Research & Report","Machine Learning as a Service (MLaaS) Selection for IoT Environments","Machine Learning as a Service (MLaaS) streamlines the deployment of machine learning models by delivering tools, infrastructure, and algorithms as cloud-based services. Effective MLaaS adoption for organisations requires choosing providers aligned with business and user needs, yet provider selection becomes difficult when complete QoS information and latent features are unavailable. The challenge increases in Internet of Things (IoT) settings, where contextual dimensions such as preferences, locations, device capabilities, and application requirements continually change. This MPhil research develops an MLaaS service selection framework using incomplete QoS disclosure, bias detection with Explainable (B-XAI), and nearest-neighbour provider selection, then extends to context-aware selection via SVM-based context change analysis, contextual bandits, and skyline queries.","School of Electrical Engineering, Computing and Mathematical Sciences  \nMachine Learning as a Service (MLaaS) Selection for IoT  \nEnvironments  \nKeyaben Mukeshbhai Patel  \n0000-0003-3987-9828  \nThis thesis is presented for the Degree of  \nMaster of Philosophy  \nOf  \nCurtin University  \nOctober 2024  \nDeclaration  \nTo the best of my knowledge and belief, this thesis contains no material previously published by any other person except where due acknowledgment has been made.  \nThis thesis contains no material which has been accepted for the award of any other degree or diploma in any university.  \nKeya Patel  \nSchool of Electrical, Computing, and Mathematical Sciences Curtin University  \nSignature:……………………  \n07 October 2024  \nAcknowledgements  \nI would like to express my sincere gratitude to my supervisor, Dr. Sajib Mistry, for his invaluable guidance, feedback, and support throughout my research. His profound knowledge and experience were instrumental in the shaping of this thesis. Iam especially grateful for his willingness to offer unconditional meetings whenever I needed guidance. His impact on refining my critical thinking, writing, and presentation skills has been exceptional. Dr. Sajib Mistry is among the most inspiring mentors I have ever encountered.  \nI am also extremely thankful to my co-supervisor, A/Prof. Aneesh Krishna, for his insightful suggestions and motivation in helping me enter the research field. His mentorship provided me with the foundational knowledge and confidence needed to navigate the complexities of academic research.  \nI am deeply grateful to Co-Author, Deepak for his significant contributions in helping me develop the preliminary experiments. His expertise, commitment, and collaborative efforts were instrumental in shaping the direction of this research. I deeply appreciate his support and contributions throughout this process.  \nI must acknowledge my husband and greatest supporter, Bhavin, whose unwavering encouragement, love, and understanding empowered me to pursue my dream of completing my MPhil. I want to thank my most diligent daughter, Khushi and caring son, Happy; your smiles, laughter, and endless energy have been a constant reminder of the joy and purpose in life. I am very thankful for your patience and for always brightening my days. This thesis is much yours as it is mine. Furthermore, I am very grateful to my parents and parents-in-law, brother-in-law, and sister-in-law for their kind support.  \nThis research is supported by an Australian Government Research Training Program (RTP) Scholarship. The partial project is supported by a grant from the Defence Science Centre under the Research Higher Degree Student Grant program.  \nAuthorship Acknowledgment  \nThe main results presented in this thesis are based on works that were published in conference proceedings or submitted during the author’s MPhil study. They are listed as follows:  \n• Patel, K., Mistry, S., Kanneganti, S. K. D., & Krishna, A. (2023) . Machine Learning as a Service (MLaaS) Selection with Incomplete QoS Information. [https://aisel.aisnet.org/acis2023/39/](https://aisel.aisnet.org/acis2023/39/)  \n(ERA ranking: A, Acceptance rate: 24%)  \n• Patel, K., Mistry, S., Kanneganti, S. K. D., & Krishna, A. (2024) . ContextAware Selection of Machine Learning as a Service (MLaaS)in an IoT Environment. Web Information Systems Engineering (WISE) . (Submitted) .  \nThe copyright information to reuse the published work has been provided in Appendix A.  \nAbstract  \nMachine Learning as a Service (MLaaS) holds significant importance in technology and business due to its pivotal role in democratising and simplifying the deployment of machine learning models. MLaaS refers to providing machine learning tools, infrastructure, and algorithms as cloud-based services, allowing users to build, train, deploy and manage machine learning models without needing to handle the underlying technical complexities. Selecting the right Machine Learning as a Se","cbCailtjuQ85jqbS","https://ap.wps.com/l/cbCailtjuQ85jqbS","pdf",1993258,1,85,"English","en",105,"# Abstract\n# Acknowledgements\n## Research support and grants\n# Authorship Acknowledgment\n## Published and submitted works","[{\"question\":\"What does MLaaS enable for organisations and users?\",\"answer\":\"MLaaS provides machine learning tools, infrastructure, and algorithms as cloud-based services, helping users build, train, deploy, and manage models without managing underlying technical complexities.\"},{\"question\":\"Why is selecting an MLaaS provider challenging?\",\"answer\":\"Selection is complex when QoS information is incomplete and when latent quality-related features such as accuracy, explainability, and intrinsic biases cannot be fully observed.\"},{\"question\":\"How does the research address MLaaS selection in IoT environments?\",\"answer\":\"It proposes context-aware selection that optimizes interactions between IoT user activities and ML services, using context change analysis with SVM, and contextual bandit plus skyline queries to map abstract services to concrete QoS outcomes.\"}]","Machine Learning as a Service (MLaaS) Selection for IoT Environments | PDF",1785728763,214,{"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-as-a-service-mlaas-selection-for-iot-environments","",{"@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-as-a-service-mlaas-selection-for-iot-environments/120215/",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 does MLaaS enable for organisations and users?","Question",{"text":75,"@type":76},"MLaaS provides machine learning tools, infrastructure, and algorithms as cloud-based services, helping users build, train, deploy, and manage models without managing underlying technical complexities.","Answer",{"name":78,"@type":73,"acceptedAnswer":79},"Why is selecting an MLaaS provider challenging?",{"text":80,"@type":76},"Selection is complex when QoS information is incomplete and when latent quality-related features such as accuracy, explainability, and intrinsic biases cannot be fully observed.",{"name":82,"@type":73,"acceptedAnswer":83},"How does the research address MLaaS selection in IoT environments?",{"text":84,"@type":76},"It proposes context-aware selection that optimizes interactions between IoT user activities and ML services, using context change analysis with SVM, and contextual bandit plus skyline queries to map abstract services to concrete QoS outcomes.","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"]