[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-117537-en":3,"doc-seo-117537-105":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},117537,687197207057,"Sage","https://ap-avatar.wpscdn.com/davatar_29158cc5080c5b710cf443261637dec0",8,"Research & Report","Effects of Lossy Compression Data on Machine Learning Models - Dissertation","Machine learning is a foundational technology used across academic research and industry, but training requires large datasets that are costly to store and move. Lossy compression reduces file size by encoding data and discarding some information, lowering data quality. This dissertation examines how lossy-compressed data changes machine learning performance, focusing on prediction accuracy across tasks such as object detection, image classification, and pixel-level labeling, and how models can be adapted to remain reliable under distortion.","Clemson University  \nClemson OPEN  \n\n| All Dissertations | Dissertations |\n| --- | --- |\n| 8-2025\u003Cbr>Effects of Lossy Compression Data on Machine Learning Models\u003Cbr>Max H. Faykus III\u003Cbr>Clemson University, [mfaykus@g.clemson.edu](mfaykus@g.clemson.edu)\u003Cbr>Follow this and additional works at: [https://open.clemson.edu/all_dissertations](https://open.clemson.edu/all_dissertations)\u003Cbr> Part of the Other Computer Engineering Commons |  |\n\nRecommended Citation  \nFaykus, Max H. III, \"Effects of Lossy Compression Data on Machine Learning Models\" (2025) . All Dissertations. 3995.  \n[https://open.clemson.edu/all_dissertations/3995](https://open.clemson.edu/all_dissertations/3995)  \nThis Dissertation is brought to you for free and open access by the Dissertations at Clemson OPEN. It has been accepted for inclusion in All Dissertations by an authorized administrator of Clemson OPEN. For more information, please contact [kokeefe@clemson.edu](kokeefe@clemson.edu).  \nEffects of Lossy Compression Data on Machine Learning  \nModels  \n\n| A Dissertation\u003Cbr>Presented to\u003Cbr>the Graduate School of\u003Cbr>Clemson University |\n| --- |\n| In Partial Fulfillment\u003Cbr>of the Requirements for the Degree\u003Cbr>Doctor of Philosophy\u003Cbr>Computer Engineering |\n| by\u003Cbr>Max H Faykus III\u003Cbr>August 2025 |\n\nAccepted by:  \nDr. Melissa C. Smith, Committee Chair Dr. Jon C. Calhoun Dr. Jerome L. McClendon Dr. Fatemeh Afghah  \nPlain Language Abstract  \nMachine learning is a powerful technology that is used in nearly every domain from academic research to industry. This technology requires a large amount of data to train models that are capable of learning patterns and make decisions without being specifically programmed to do so. However, storing and handling large datasets is a difficult and expensive task. To manage this many systems use lossy compression, which is a method for reducing file size and removes some information which lowers the quality of the data.  \nThis dissertation investigates how machine learning models perform when the data has been lossy compressed. Specifically this study focuses on how compression affects the models performance, which means how accurately it can make predictions. The predictions is task depended such as object detection, classifying images or labeling the pixels in a image. This study examines how different models find patterns in input data that has been distorted due to the compression and how can these models be modified or adjusted to better handle distorted data.  \nAbstract  \nMachine learning is a fundamental tool that is incorporated in every field across academia and other industries. Due to the large amount of data needed for training machine learning models, lossy compression plays a crucial role in storing data. Machine learning involves the use of algorithms and models to learn patterns in data. This allows the AI to make decisions without specific programming. On the other hand, compression utilizes encoding and decoding techniques to reduce the size of files. Compression is either lossy or lossless, lossy causes a loss of data while lossless preserves the data.  \nThis dissertation will explore the performance of machine learning when working with data that has undergone lossy compression. The performance metrics that are being studied looks at how accurate the model’s inference will perform (i.e. accuracy, intersection over union) depending on the task. The issues with machine learning performances on lossy data involve the following: data storage, data transfer bandwidth, and processing on the intersection between machine learning and lossy compression. Over these various tasks, machine learning in different domains will be examined to investigate how meaningful patterns in the distorted data is extracted.  \nOne approach explored in this work involves the analysis and design of various neural network models allowing the research to manage lossy compressed data in an isolated format. The primary focus will be on machine lear","cbCaieJQlp2i4jIp","https://ap.wps.com/l/cbCaieJQlp2i4jIp","pdf",17232442,1,124,"English","en",105,"# Introduction\n## Background: machine learning and data requirements\n## Lossy compression: encoding, decoding, and quality loss\n## Research focus: effects on inference performance\n## Evaluation approach and performance metrics\n## Neural network models for robust handling of distorted image data","[{\"question\":\"What problem does the dissertation study regarding machine learning and data storage?\",\"answer\":\"The work studies how the need to store and handle large datasets leads systems to use lossy compression, and how this affects the performance of machine learning models.\"},{\"question\":\"How does the dissertation define the impact of compression on model performance?\",\"answer\":\"It evaluates how accurately models can make predictions on lossy-compressed inputs, using task-relevant performance metrics such as accuracy and intersection over union.\"},{\"question\":\"What image-focused tasks are considered in the research?\",\"answer\":\"The dissertation examines compression effects for image data tasks including object detection, semantic segmentation, and image classification.\"}]","Effects of Lossy Compression Data on Machine Learning Models - Dissertation | PDF",1785676776,312,{"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},"effects-of-lossy-compression-data-on-machine-learning-models-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/effects-of-lossy-compression-data-on-machine-learning-models-dissertation/117537/",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","2026-08-02",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 study regarding machine learning and data storage?","Question",{"text":75,"@type":76},"The work studies how the need to store and handle large datasets leads systems to use lossy compression, and how this affects the performance of machine learning models.","Answer",{"name":78,"@type":73,"acceptedAnswer":79},"How does the dissertation define the impact of compression on model performance?",{"text":80,"@type":76},"It evaluates how accurately models can make predictions on lossy-compressed inputs, using task-relevant performance metrics such as accuracy and intersection over union.",{"name":82,"@type":73,"acceptedAnswer":83},"What image-focused tasks are considered in the research?",{"text":84,"@type":76},"The dissertation examines compression effects for image data tasks including object detection, semantic segmentation, and image classification.","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"]