[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-126175-en":3,"doc-seo-126175-105":30,"detail-sidebar-cat-0-en-105":92},{"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":11,"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},126175,3985741905716,"Rowan","https://ap-avatar.wpscdn.com/davatar_994ba38a5ba835b3df7d355c54d3ed8d",8,"Research & Report","Machine Learning for Packet Detection in Satellite Communications - Master Thesis","Master thesis exploring machine-learning approaches for packet detection in satellite communications, focusing on how common channel impairments affect reliable recognition. The work defines the scenario and system model, including channel impairments, link budget, and a detection-algorithm set combining correlation-based methods with a convolutional neural network. Dataset generation supports controlled experiments, while model tuning optimizes network and training settings. Results analyze performance under AWGN and interference, including phase offset, Doppler shift, and received power effects, concluding with directions for future development.","Machine Learning for Packet Detection in Satellite Communications  \nMaster Thesis submitted to the Faculty of the Escola T`ecnica d’Enginyeria de Telecomunicaci´o de Barcelona Universitat Polit`ecnica de Catalunya  \nby Pol Simon Campreci´os  \nIn partial fulfillment of the requirements for the master in  \nMASTER IN TELECOMMUNICATIONS ENGINEERING  \nSupervisors  \nEstefan´ıa Recayte (DLR German Aerospace Center) Andrea Munari (DLR German Aerospace Center) Giuseppe Cocco (UPC Universitat Polit`ecnica de Catalunya)  \nMunich and Barcelona, February 2024  \nContents  \nList of Figures 4  \nList of Tables 5  \nList of Algorithms 5  \n1 Introduction 10  \n1.1 Problem Description .............................. 10  \n1.2 Gantt Diagram ................................. 11  \n2 State of the Art 12  \n2.1 Packet Detection ................................ 12  \n2.1.1 Packet Detection in Satellite Communications ............ 12  \n2.2 Machine Learning ................................ 13  \n2.2.1 Neural networks ............................. 14  \n2.2.2 Machine Learning in Signal Processing ................ 15  \n3 Scenario and System Model 18  \n3.1 Scenario Description .............................. 18  \n3.1.1 Channel Impairments .......................... 19  \n3.1.2 Link Budget ............................... 22  \n3.2 Detection Algorithms .............................. 24  \n3.2.1 Correlation ............................... 25  \n3.2.2 Convolutional Neural Network ..................... 25  \n3.2.3 Performance metrics .......................... 26  \n3.3 Dataset Generation ............................... 28  \n4 Initial Setup and Validation 31  \n4.1 Model tuning .................................. 31  \n4.1.1 Network architecture .......................... 31  \n4.1.2 Convolutional layer ........................... 32  \n4.1.3 Dataset proportions ........................... 33  \n4.1.4 Dataset sizes .............................. 34  \n4.2 AWGN scenario ................................. 35  \n4.3 Interference scenario .............................. 37  \n5 Results with Channel Impairments 40  \n5.1 Phase offset ................................... 40  \n5.2 Doppler Shift .................................. 44  \n5.2.1 Bank of Correlators ........................... 46  \n5.3 Received Power Distribution .......................... 50  \n5.4 Final Results .................................. 53  \n6 Conclusions and future development 59  \nReferences 61  \nAppendices 64  \nA Satellite geometry calculations 64  \nList of Figures  \n1 Project’s Gantt diagram ............................ 11  \n2 Example of a neural network architecture................... 15  \n3 Packet structure considered........................... 18  \n4 Scenarios contemplated............................. 19  \n5 Comparison of a signal with and without random phase offset........ 20  \n6 Representation of the Doppler effect...................... 21  \n7 Link budget analysis of the scenario...................... 23  \n8 First four symbols of two preambles affected by different channel impairments. 24  \n9 Correlation output of a received signal .................... 25  \n10 A schematic representation of the architecture of the proposed CNN .... 26  \n11 Representation of the AUC metric ....................... 27  \n12 Learning curves versus the epochs of the algorithms varying their architectures ....................................... 31  \n13 Learning curves versus the epochs of the algorithms varying the convolutional layers parameters ............................ 33  \n14 Learning curves versus the epochs of the algorithms varying the training classes proportions ............................... 34  \n15 Learning curves versus the epochs of the algorithms varying the training dataset sizes ................................... 35  \n16 Visualization of received signal symbols in the I-Q plane........... 36  \n17 ROC plots considering AWGN scenario and no impairments for different SNR and generation rates............................ 36  ","cbCaikHRbrvbIfxj","https://ap.wps.com/l/cbCaikHRbrvbIfxj","pdf",2533169,1,65,"English","en",105,"# Contents\n## List of Figures\n## List of Tables\n## List of Algorithms\n# 1 Introduction\n## 1.1 Problem Description\n## 1.2 Gantt Diagram\n# 2 State of the Art\n## 2.1 Packet Detection\n## 2.1.1 Packet Detection in Satellite Communications\n## 2.2 Machine Learning\n## 2.2.1 Neural networks\n## 2.2.2 Machine Learning in Signal Processing\n# 3 Scenario and System Model\n## 3.1 Scenario Description\n## 3.1.1 Channel Impairments\n## 3.1.2 Link Budget\n## 3.2 Detection Algorithms\n## 3.2.1 Correlation\n## 3.2.2 Convolutional Neural Network\n## 3.3 Dataset Generation\n# 4 Initial Setup and Validation\n## 4.1 Model tuning\n## 4.1.1 Network architecture\n## 4.1.2 Convolutional layer\n## 4.1.3 Dataset proportions\n## 4.1.4 Dataset sizes\n## 4.2 AWGN scenario\n## 4.3 Interference scenario\n# 5 Results with Channel Impairments\n## 5.1 Phase offset\n## 5.2 Doppler Shift\n## 5.2.1 Bank of Correlators\n## 5.3 Received Power Distribution\n## 5.4 Final Results\n# 6 Conclusions and future development\n# References\n# Appendices","[{\"question\":\"What problem does the thesis address in satellite communications?\",\"answer\":\"It addresses packet detection under realistic satellite channel conditions, where impairments can degrade detection reliability.\"},{\"question\":\"Which detection approaches are compared in the study?\",\"answer\":\"The thesis considers correlation-based detection and a convolutional neural network, with correlations used as a baseline for comparison.\"},{\"question\":\"How are channel impairments evaluated in the results?\",\"answer\":\"Performance is evaluated across AWGN and interference scenarios, covering phase offset, Doppler shift, and received power distribution, using metrics such as ROC-related measures.\"}]","Machine Learning for Packet Detection in Satellite Communications - Master Thesis | PDF",1785903591,164,{"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":87,"head_meta":89,"extra_data":91,"updated_unix":28},"machine-learning-for-packet-detection-in-satellite-communications-master-thesis","",{"@graph":36,"@context":86},[37,54,69],{"@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-for-packet-detection-in-satellite-communications-master-thesis/126175/",4,{"url":52,"name":13,"@type":55,"author":56,"headline":13,"publisher":58,"fileFormat":61,"inLanguage":23,"description":14,"dateModified":62,"datePublished":63,"encodingFormat":61,"isAccessibleForFree":64,"interactionStatistic":65},"DigitalDocument",{"name":9,"@type":57},"Person",{"url":41,"name":59,"@type":60},"DocShare","Organization","application/pdf","2026-08-23","2026-08-05",true,{"@type":66,"interactionType":67,"userInteractionCount":11},"InteractionCounter",{"@type":68},"ViewAction",{"@type":70,"mainEntity":71},"FAQPage",[72,78,82],{"name":73,"@type":74,"acceptedAnswer":75},"What problem does the thesis address in satellite communications?","Question",{"text":76,"@type":77},"It addresses packet detection under realistic satellite channel conditions, where impairments can degrade detection reliability.","Answer",{"name":79,"@type":74,"acceptedAnswer":80},"Which detection approaches are compared in the study?",{"text":81,"@type":77},"The thesis considers correlation-based detection and a convolutional neural network, with correlations used as a baseline for comparison.",{"name":83,"@type":74,"acceptedAnswer":84},"How are channel impairments evaluated in the results?",{"text":85,"@type":77},"Performance is evaluated across AWGN and interference scenarios, covering phase offset, Doppler shift, and received power distribution, using metrics such as ROC-related measures.","https://schema.org",{"og:url":52,"og:type":88,"og:title":13,"og:site_name":59,"og:description":14},"article",{"robots":90,"canonical":52},"index,follow",{"doc_id":7,"site_id":24},{"code":4,"msg":5,"data":93},[94,98,102,106,111,116,121,124,129,132,136],{"id":20,"doc_module":4,"doc_module_name":46,"category_name":95,"show_sort_weight":96,"slug":97},"Story & Novel",90,"story-novel",{"id":47,"doc_module":4,"doc_module_name":46,"category_name":99,"show_sort_weight":100,"slug":101},"Literature",80,"literature",{"id":53,"doc_module":4,"doc_module_name":46,"category_name":103,"show_sort_weight":104,"slug":105},"Exam",70,"exam",{"id":107,"doc_module":4,"doc_module_name":46,"category_name":108,"show_sort_weight":109,"slug":110},5,"Comic",60,"comic",{"id":112,"doc_module":4,"doc_module_name":46,"category_name":113,"show_sort_weight":114,"slug":115},6,"Technology",50,"technology",{"id":117,"doc_module":4,"doc_module_name":46,"category_name":118,"show_sort_weight":119,"slug":120},7,"Healthcare",40,"healthcare",{"id":11,"doc_module":4,"doc_module_name":46,"category_name":12,"show_sort_weight":122,"slug":123},30,"research-report",{"id":125,"doc_module":4,"doc_module_name":46,"category_name":126,"show_sort_weight":127,"slug":128},9,"Religion & Spirituality",20,"religion-spirituality",{"id":127,"doc_module":4,"doc_module_name":46,"category_name":130,"show_sort_weight":127,"slug":131},"World Cup","world-cup",{"id":133,"doc_module":4,"doc_module_name":46,"category_name":134,"show_sort_weight":133,"slug":135},10,"Lifestyle","lifestyle",{"id":137,"doc_module":4,"doc_module_name":46,"category_name":138,"show_sort_weight":107,"slug":139},19,"General","general"]