[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-124745-en":3,"doc-seo-124745-105":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":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},124745,16904993612988,"Olivia Brown","https://ap-avatar.wpscdn.com/davatar_a8503ba1806abce46bf441b54a3ca4cd",8,"Research & Report","5G Throughput Prediction Using Machine Learning","5G Throughput Prediction Using Machine Learning presents a machine learning workflow to estimate 5G network throughput by analyzing dataset structure, performing data preprocessing, and tuning model hyperparameters. Multiple learning approaches are implemented and evaluated, including GBDT, Seq2Seq, RF, SVR, and XGBoost, with explicit procedures to detect and adjust overfitting using training/testing error behavior. Feature contributions are interpreted through SHAP, followed by a comparative study and an ensemble meta-model strategy to improve robustness and predictive accuracy.","5G Throughput Prediction Using Machine Learning  \nby  \nDaeyoo Kim  \nA Creative Component submitted to the graduate faculty  \nin partial fulfillment of the requirements for the degree of  \nMASTER OF SCIENCE  \nMajor: Electrical Engineering (Communications and Signal Processing)  \nProgram of Study Committee:  \nJoseph Zambreno, Major Professor  \nThe student author, whose presentation of the scholarship herein was approved by the program of study committee, is solely responsible for the content of this report. The Graduate College will ensure this report is globally accessible and will not permit alterations after a degree is conferred.  \nIowa State University  \nAmes, Iowa  \n2023  \nCopyright © Daeyoo Kim, 2023. All rights reserved.  \nii  \nTABLE OF CONTENTS  \nPage  \nLIST OF TABLES .......................................... iv  \nLIST OF FIGURES ......................................... v  \n[ACKNOWLEDGMENTS ......................................](ACKNOWLEDGMENTS ...................................... vi)[ vi](ACKNOWLEDGMENTS ...................................... vi)  \n[ABSTRACT .............................................](ABSTRACT ............................................. vii)[ vii](ABSTRACT ............................................. vii)  \n[CHAPTER 1. Introduction .....................................](CHAPTER 1. Introduction ..................................... 1)[ 1](CHAPTER 1. Introduction ..................................... 1)  \n[CHAPTER 2. REVIEW OF LITERATURE ...........................](CHAPTER 2. REVIEW OF LITERATURE ........................... 3)[ 3](CHAPTER 2. REVIEW OF LITERATURE ........................... 3)  \n[2.1 The Importance of Throughput Prediction in 5G Networks ..............](2.1 The Importance of Throughput Prediction in 5G Networks .............. 3)[ 3](2.1 The Importance of Throughput Prediction in 5G Networks .............. 3)  \n[2.2 Understanding the Various Factors Influencing 5G Throughput ............](2.2 Understanding the Various Factors Influencing 5G Throughput ............ 4)[ 4](2.2 Understanding the Various Factors Influencing 5G Throughput ............ 4)  \n[2.3 Introduction to Concepts and Key Technologies of Machine Learning and Deep](2.3 Introduction to Concepts and Key Technologies of Machine Learning and Deep)[ ](2.3 Introduction to Concepts and Key Technologies of Machine Learning and Deep)Learning for 5G Throughput Prediction ......................... 5  \nCHAPTER 3 . METHODS AND PROCEDURES ........................ 9  \n3.1 Dataset ........................................... 9  \n3.1.1 Dataset Analysis .................................. 9  \n3.1.2 Data Preprocessing ................................. 13  \n3.2 Model Implementation ................................... 14  \n3.2.1 Hyperparameter Tuning .............................. 14  \n3.2.2 Model Implementation on GBDT, Seq2Seq, RF, SVR, and XGBoost ..... 19  \n3.3 Overfitting ......................................... 21  \n3.4 Feature Importance through SHAP ............................ 24  \n3.5 Ensemble Model ...................................... 26  \nCHAPTER 4 . RESULTS ...................................... 28  \n4.1 Comparative Analysis of Results from Models with Hyperparameter Tuning ..... 28  \n4.2 Observation and Adjustment of Overfitting in All Models ............... 30  \n4.2.1 Observation of Overfitting in All Models ..................... 30  \n4.2.2 Adjustment of Overfitting in All Models ..................... 34  \n4.3 Analysis of Feature Importance Obtained through SHAP ............... 37  \n4.3.1 Performance of Models Applied with Feature Importance ........... 40  \n4.4 Ensemble Model Results .................................. 44  \nCHAPTER 5 . SUMMARY AND DISCUSSION ......................... 46  \niii  \nBIBLIOGRAPHY .......................................... 48  \niv  \nLIST OF TABLES  \nPage  \nTable 4.1 Evaluation of Models: Hyperparameters and Performance Metrics ...... 29  \n4.2 Training and Testing RMSE Comparisons Across Mac","cbCaifw3xkS1PDGH","https://ap.wps.com/l/cbCaifw3xkS1PDGH","pdf",772205,1,57,"English","en",105,"# LIST OF TABLES\n# LIST OF FIGURES\n# CHAPTER 1. Introduction\n# CHAPTER 2. REVIEW OF LITERATURE\n## The Importance of Throughput Prediction in 5G Networks\n## Understanding the Various Factors Influencing 5G Throughput\n# CHAPTER 3 . METHODS AND PROCEDURES\n## Dataset\n## Model Implementation\n## Ensemble Model\n# CHAPTER 4 . RESULTS\n## Comparative Analysis of Results from Models with Hyperparameter Tuning\n## Analysis of Feature Importance Obtained through SHAP\n## Ensemble Model Results\n# CHAPTER 5 . SUMMARY AND DISCUSSION\n# BIBLIOGRAPHY","[{\"question\":\"What machine learning models are used for 5G throughput prediction?\",\"answer\":\"The study implements GBDT, Seq2Seq, RF, SVR, and XGBoost, evaluates them with tuned hyperparameters, and compares their performance using error metrics.\"},{\"question\":\"How does the report handle overfitting during training?\",\"answer\":\"It observes overfitting by comparing training and testing RMSE/MAE behavior, then applies adjustments in all models to reduce the gap between training and testing performance.\"},{\"question\":\"How are feature effects analyzed and interpreted in the models?\",\"answer\":\"Feature importance is derived using SHAP, enabling analysis of which inputs contribute most to predictions and supporting experiments with features removed based on low importance.\"}]","5G Throughput Prediction Using Machine Learning | PDF",1785894257,144,{"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},"5g-throughput-prediction-using-machine-learning","",{"@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/5g-throughput-prediction-using-machine-learning/124745/",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","2026-08-05",true,{"@type":65,"interactionType":66,"userInteractionCount":20},"InteractionCounter",{"@type":67},"ViewAction",{"@type":69,"mainEntity":70},"FAQPage",[71,77,81],{"name":72,"@type":73,"acceptedAnswer":74},"What machine learning models are used for 5G throughput prediction?","Question",{"text":75,"@type":76},"The study implements GBDT, Seq2Seq, RF, SVR, and XGBoost, evaluates them with tuned hyperparameters, and compares their performance using error metrics.","Answer",{"name":78,"@type":73,"acceptedAnswer":79},"How does the report handle overfitting during training?",{"text":80,"@type":76},"It observes overfitting by comparing training and testing RMSE/MAE behavior, then applies adjustments in all models to reduce the gap between training and testing performance.",{"name":82,"@type":73,"acceptedAnswer":83},"How are feature effects analyzed and interpreted in the models?",{"text":84,"@type":76},"Feature importance is derived using SHAP, enabling analysis of which inputs contribute most to predictions and supporting experiments with features removed based on low importance.","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"]