[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-124282-en":3,"doc-seo-124282-105":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},124282,2336464648746,"Skyler","https://ap-avatar.wpscdn.com/davatar_276721f389ce27ea32af1340a28f341c",8,"Research & Report","Generalized Machine Learning Based Network Traffic Classification - Master of Engineering Thesis","Internet traffic classification is increasingly prioritized by Internet Service Providers to adapt network behavior to customer needs while improving operational gains. Most prior machine-learning work focuses on model and algorithm choices without analyzing how the traffic capture location affects generalization across different flow capture directions. This thesis proposes approaches to generalize across environments while also targeting narrower gaming-related traffic classes under background-noise complexity. It addresses capture-direction effects via direction-wise training/testing and full-flow comparison, then evaluates multiple models on the Gaming Network Traffic Dataset, including random forest, CNN image-based models, a CNN-LSTM temporal model, and a semi-supervised stacked CNN–random-forest approach. Results show the semi-supervised architecture achieves the highest testing accuracy overall.","AMERICAN UNIVERSITY OF BEIRUT  \nGENERALIZED MACHINE LEARNING BASED NETWORK TRAFFIC CLASSIFICATION  \nby  \nJEAN PAUL GEORGES CHAIBAN  \nA thesis  \nsubmitted in partial fulfillment of the requirements for the degree of Master of Engineering to the Department of Electrical and Computer Engineering of the Faculty of Engineering and Architecture at the American University of Beirut  \nBeirut, Lebanon  \nNovember, 2022  \nAMERICAN UNIVERSITY OF BEIRUT  \nGENERALIZED MACHINE LEARNING BASED NETWORK TRAFFIC CLASSIFICATION  \nby  \nJEAN PAUL GEORGES CHAIBAN  \nApproved by:  \nSignature  \nProfessor Imad H. Elhajj, Ph.D. ECE Department  \nAdvisor  \nSignature  \nProfessor Ayman Kayssi, Ph.D. ECE Department  \nMember of Committee  \n Signature  \nAssociate Professor Hazem Hajj, Ph.D. ECE Department Member of Committee  \n______________________________________________________________________  \nDate of thesis defense: December 13, 2022  \nAMERICAN UNIVERSITY OF BEIRUT  \nTHESIS RELEASE FORM  \nStudent Name:   Chaiban  Jean Paul   Georges   \nLast First Middle  \nI authorize the American University of Beirut, to: (a) reproduce hard or electronic copies of my thesis; (b) include such copies in the archives and digital repositories of the University; and (c) make freely available such copies to third parties for research or educational purposes:  \n As of the date of submission  \n One year from the date of submission of my thesis.  \n Two years from the date of submission of my thesis.  \n Three years from the date of submission of my thesis.  \nJanuary 10, 2023  \nSignature Date  \nACKNOWLEDGEMENTS  \nIn the completion of this thesis, I am grateful to my advisor Prof. Imad Elhajj and Prof. Ayman Kayssi for their continuous support and extensive knowledge and advice leading me in the right direction in my research. I am honored to have had the chance working with them as a team. I also thank Telus for funding this research and allowing me this great opportunity.  \nI would also like to thank my mother and my late father for their encouragement and help throughout my education. I also want to thank my sister Carly, her family and my dear friends for their support especially in the pandemic lockdown and the hyperinflation crisis.  \nABSTRACT  \nOF THE THESIS OF  \nJean Paul Georges Chaiban for  Master of Engineering  \nMajor: Networks and Security  \nTitle: Generalized Machine Learning Based Network Traffic Classification  \nWith the exponential rise in online activity, Internet Service Providers (ISPs) have prioritized network traffic classification in order to dynamically adapt their networks to best serve their customers while increasing their gains. While most work on machine learning based classification studied different models and the best techniques to solve the issue, none studied the effect of the traffic capture location on the model and whether a model could be generalized to work effectively with different flow capture directions. The aim of this work is to find the best approach in creating network traffic classification models that are, from one side, capable of generalizing to different environments, while being able to target narrower classes in internet traffic and from the other side, adaptive, scalable and performant in different production environments. While most previous work attempted separating general classes such as SSH traffic, VPN traffic and [HTTP/](HTTP/)[HTTPS](HTTPS), we attempt to separate very similar classes related to gaming that use common protocols and backends with the added complexity of background noise traffic. Another contribution of this work is tackling the traffic direction problem, which is directly related to the traffic capture location. Since no multi location dataset was available, this work is limited in this regards. This problem was addressed by training and testing our models versus each of the directions ofthe flows apart followed by the full flow comparison. To this end, our approach to solve this issue is two-fold. From one","cbCaipEZ67HJ5T10","https://ap.wps.com/l/cbCaipEZ67HJ5T10","pdf",3047948,1,113,"English","en",105,"# Introduction\n## Problem Motivation and Research Gap\n## Goals and Contributions\n# Methodology\n## Capture-Direction Handling\n## Model Designs and Training Strategy\n# Experiments and Results\n## Dataset and Evaluation Setup\n## Model Comparisons and Accuracy Findings\n# Discussion and Conclusion\n## Generalization Across Datasets\n## Key Takeaways","[{\"question\":\"Why does this thesis focus on generalized network traffic classification?\",\"answer\":\"Because ISPs need traffic classification models that adapt to different environments, avoid performance drops, and remain useful when deployment conditions differ from training conditions.\"},{\"question\":\"What problem does the thesis address regarding traffic capture location?\",\"answer\":\"It addresses how flow capture direction influences model performance, using direction-wise training/testing and then comparing with full-flow results due to the lack of a multi-location dataset.\"},{\"question\":\"Which models are proposed and how do they compare in accuracy?\",\"answer\":\"The thesis evaluates random forest (baseline), CNN image-based models, a CNN-LSTM model that includes temporal information, and a semi-supervised stacked CNN–random forest. The semi-supervised stacked approach achieves the best testing accuracy overall on the Gaming Network Traffic Dataset.\"}]","Generalized Machine Learning Based Network Traffic Classification - Master of Engineering Thesis | PDF",1785821356,285,{"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},"generalized-machine-learning-based-network-traffic-classification-master-of-engineering-thesis","",{"@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/generalized-machine-learning-based-network-traffic-classification-master-of-engineering-thesis/124282/",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","2026-08-04",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},"Why does this thesis focus on generalized network traffic classification?","Question",{"text":75,"@type":76},"Because ISPs need traffic classification models that adapt to different environments, avoid performance drops, and remain useful when deployment conditions differ from training conditions.","Answer",{"name":78,"@type":73,"acceptedAnswer":79},"What problem does the thesis address regarding traffic capture location?",{"text":80,"@type":76},"It addresses how flow capture direction influences model performance, using direction-wise training/testing and then comparing with full-flow results due to the lack of a multi-location dataset.",{"name":82,"@type":73,"acceptedAnswer":83},"Which models are proposed and how do they compare in accuracy?",{"text":84,"@type":76},"The thesis evaluates random forest (baseline), CNN image-based models, a CNN-LSTM model that includes temporal information, and a semi-supervised stacked CNN–random forest. The semi-supervised stacked approach achieves the best testing accuracy overall on the Gaming Network Traffic Dataset.","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"]