[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-128203-en":3,"doc-seo-128203-105":31,"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":20,"is_deleted":4,"is_public":21,"is_downloadable":21,"audit_status":21,"page_count":22,"language":23,"language_code":24,"site_id":25,"html_lang":24,"table_of_contents":26,"faqs":27,"seo_title":28,"seo_description":14,"update_tm":29,"read_time":30},128203,2336475104042,"Skyler","https://ap-avatar.wpscdn.com/avatar/22000c4c32af1715be0?x-image-process=image/resize,m_fixed,w_180,h_180&k=1786537525561427321",8,"Research & Report","Development of Machine Learning Based Models for Detecting GNSS Signal Jamming in Real-World Scenarios Using AGC Data - Master’s Thesis","GNSS enables high-precision positioning in favorable conditions but remains vulnerable to intentional radio frequency interference because received ground-level signal power is low and jamming devices are increasingly available. Fixed-threshold jamming detection methods are often inefficient in dynamic real-world settings. This master’s thesis develops machine learning approaches that detect GNSS jamming using AGC-derived multidimensional features. It evaluates a supervised XGBoost classifier and an unsupervised Isolation Forest anomaly detector trained and validated on data from a controlled jamming test in Norway under varied conditions. Sliding-window feature extraction preserves temporal and spectral dynamics across frequency bands. Results show effective detection, strong performance especially for G1-band features, and interpretable insights through feature-importance analysis. The proposed methods reduce manual threshold tuning and can scale toward real-time deployment in GNSS receivers.","Ashika Ruwanthi  \nDevelopment of Machine Learning Based Models for Detecting GNSS Signal Jamming in Real-World Scenarios Using AGC Data  \nSchool of Technology and Innovations Master’s Thesis  \nSustainable and Autonomous Systems  \n\n| UNIVERSITY OF VAASA\u003Cbr>School of Technology and Innovations\u003Cbr>Author: Ashika Ruwanthi\u003Cbr>Title of the thesis: Development of Machine Learning Based Models for Detecting\u003Cbr>GNSS Signal Jamming in Real-World Scenarios Using AGC Data\u003Cbr>Degree: Master of Computer Science\u003Cbr>Discipline: Sustainable and Autonomous Systems\u003Cbr>Supervisor: Heidi Kuusniemi\u003Cbr>Evaluator Petri Välisuo\u003Cbr>Year: 2025 Pages: 71 |\n| --- |\n| ABSTRACT:\u003Cbr>Although Global Navigation Satellite Systems (GNSS) provide high-precision positioning under optimal situations, they remain vulnerable to intentional Radio Frequency Interference (RFI) due to the low signal power received at ground level and the increasing availability of jamming devices. Previous studies have demonstrated that traditional jamming detection methods, such as fixed-threshold-based detection, are limited in handling dynamic scenarios and therefore remain less efficient under real-world conditions. This study addresses these limitations by applying machine learning (ML) techniques to detect GNSS jamming using AGC data.\u003Cbr>The primary objective of the study is to analyse supervised and unsupervised machine learning (ML) models for detecting jamming using multidimensional features derived from AGC signals. The theoretical foundation is based on anomaly detection, statistical learning, and time-series signal analysis. Two machine learning models were applied: a supervised classifier (XGBoost) and an unsupervised anomaly detector (Isolation Forest) . Both were trained and validated on AGC data measured during a controlled jamming test in Norway. The experiment is conducted under various jamming conditions, which enable realistic and reproducible data collection in a dynamic vehicular environment.\u003Cbr>Feature extraction was performed using the sliding-window approach across various GNSS frequency bands, retaining the temporal and spectral dynamics of AGC. The supervised model was trained on labelled samples to distinguish normal and jammed windows, while the unsupervised model was trained on normal data only to identify anomalies. The test consisted of typical classification metrics and interpretability methods, such as feature importance analysis, to understand the model's decisions.\u003Cbr>Both models demonstrated the ability to detect jamming effectively. The supervised model showed strong performance, revealing that AGC features from specific frequency bands, particularly the G1 band, were most indicative of jamming. The unsupervised model performed reliably on normal data, although it generated some false predictions, which may be attributed to sudden variations in positioning data. Visual analysis offers a deeper understanding of the relationship between prediction results and the behavior of positioning parameters.\u003Cbr>The proposed ML-based approaches provide better adaptability, eliminate the need for manual threshold tuning, and scale effectively across various conditions. They are well-suited for realtime deployment in GNSS receivers. Future work may enhance these models by combining them to provide a total localization solution. |\n\nKEYWORDS: (GNSS, Jamming, Detection, Isolation Forest, XGBoost, AGC, Machine Learning)  \nContents  \n1 Introduction 8  \n1.1 Background and Motivation 8  \n1.1.1 Jammertest 11  \n1.1.2 Motivation 11  \n1.2 Research Problems 13  \n1.3 Research Objectives 13  \n1.4 Scope of Work 14  \n1.5 Thesis Structure 14  \n2 Literature Review 16  \n2.1 Overview of GNSS 16  \n2.2 GNSS Errors and Vulnerabilities for Navigation 18  \n2.2.1 Jamming in GNSS Navigation 19  \n2.3 GNSS Jamming Detection Methods 21  \n2.3.1 Traditional Approaches for Jamming Detection 21  \n2.3.2 Machine Learning for GNSS Jamming Detection 23  \n2.4 Mitigation Techniques for GNSS Jamming 26  \n","cbCaid73Fe6gWZH7","https://ap.wps.com/l/cbCaid73Fe6gWZH7","pdf",2632631,4,1,71,"English","en",105,"# Introduction\n## Background and Motivation\n## Research Problems\n## Research Objectives\n## Scope of Work\n## Thesis Structure\n# Literature Review\n## Overview of GNSS\n## GNSS Errors and Vulnerabilities for Navigation\n## GNSS Jamming Detection Methods\n## Mitigation Techniques for GNSS Jamming\n## Smartphone Sensors and Sensor Fusion in GNSS Navigation\n## Chapter Summary and Research Gaps\n# Methodology\n## Research Design and Approach\n## Data Collection\n## Preprocessing and Labelling\n## Feature Selection and Extraction\n## Machine Learning Model Development\n## Performance and Evaluation Metrics\n## Summary\n# Analysis and Results\n## Overview of the Dataset and Experimental Setup\n## Performance Evaluation\n## Feature Importance for XGBoost Model\n## Summary\n# Discussion\n# Conclusions and Future Works","[{\"question\":\"Why are traditional fixed-threshold GNSS jamming detection methods insufficient in real-world scenarios?\",\"answer\":\"They struggle to handle dynamic conditions efficiently, which lowers effectiveness when the environment and signal characteristics change during real operations.\"},{\"question\":\"Which machine learning models are used to detect GNSS jamming in this thesis?\",\"answer\":\"A supervised XGBoost classifier distinguishes normal versus jammed windows, and an unsupervised Isolation Forest anomaly detector identifies anomalies using normal data only.\"},{\"question\":\"How is AGC data processed to extract features for the models?\",\"answer\":\"A sliding-window approach extracts multidimensional features across multiple GNSS frequency bands, preserving temporal and spectral dynamics relevant to jamming behavior.\"}]","Development of Machine Learning Based Models for Detecting GNSS Signal Jamming in Real-World Scenarios Using AGC Data - Master’s Thesis | PDF",1785945549,179,{"code":4,"msg":32,"data":33},"ok",{"site_id":25,"language":24,"slug":34,"title":13,"keywords":35,"description":14,"schema_data":36,"social_meta":87,"head_meta":89,"extra_data":91,"updated_unix":29},"development-of-machine-learning-based-models-for-detecting-gnss-signal-jamming-in-real-world-scenarios-using-agc-data-masters-thesis","",{"@graph":37,"@context":86},[38,54,69],{"@type":39,"itemListElement":40},"BreadcrumbList",[41,45,49,52],{"item":42,"name":43,"@type":44,"position":21},"https://docshare.wps.com","Home","ListItem",{"item":46,"name":47,"@type":44,"position":48},"https://docshare.wps.com/document/","Document",2,{"item":50,"name":12,"@type":44,"position":51},"https://docshare.wps.com/document/research-report/",3,{"item":53,"name":13,"@type":44,"position":20},"https://docshare.wps.com/document/development-of-machine-learning-based-models-for-detecting-gnss-signal-jamming-in-real-world-scenarios-using-agc-data-masters-thesis/128203/",{"url":53,"name":13,"@type":55,"author":56,"headline":13,"publisher":58,"fileFormat":61,"inLanguage":24,"description":14,"dateModified":62,"datePublished":63,"encodingFormat":61,"isAccessibleForFree":64,"interactionStatistic":65},"DigitalDocument",{"name":9,"@type":57},"Person",{"url":42,"name":59,"@type":60},"DocShare","Organization","application/pdf","2026-08-27","2026-08-05",true,{"@type":66,"interactionType":67,"userInteractionCount":20},"InteractionCounter",{"@type":68},"ViewAction",{"@type":70,"mainEntity":71},"FAQPage",[72,78,82],{"name":73,"@type":74,"acceptedAnswer":75},"Why are traditional fixed-threshold GNSS jamming detection methods insufficient in real-world scenarios?","Question",{"text":76,"@type":77},"They struggle to handle dynamic conditions efficiently, which lowers effectiveness when the environment and signal characteristics change during real operations.","Answer",{"name":79,"@type":74,"acceptedAnswer":80},"Which machine learning models are used to detect GNSS jamming in this thesis?",{"text":81,"@type":77},"A supervised XGBoost classifier distinguishes normal versus jammed windows, and an unsupervised Isolation Forest anomaly detector identifies anomalies using normal data only.",{"name":83,"@type":74,"acceptedAnswer":84},"How is AGC data processed to extract features for the models?",{"text":85,"@type":77},"A sliding-window approach extracts multidimensional features across multiple GNSS frequency bands, preserving temporal and spectral dynamics relevant to jamming behavior.","https://schema.org",{"og:url":53,"og:type":88,"og:title":13,"og:site_name":59,"og:description":14},"article",{"robots":90,"canonical":53},"index,follow",{"doc_id":7,"site_id":25},{"code":4,"msg":5,"data":93},[94,98,102,106,111,116,121,124,129,132,136],{"id":21,"doc_module":4,"doc_module_name":47,"category_name":95,"show_sort_weight":96,"slug":97},"Story & Novel",90,"story-novel",{"id":48,"doc_module":4,"doc_module_name":47,"category_name":99,"show_sort_weight":100,"slug":101},"Literature",80,"literature",{"id":20,"doc_module":4,"doc_module_name":47,"category_name":103,"show_sort_weight":104,"slug":105},"Exam",70,"exam",{"id":107,"doc_module":4,"doc_module_name":47,"category_name":108,"show_sort_weight":109,"slug":110},5,"Comic",60,"comic",{"id":112,"doc_module":4,"doc_module_name":47,"category_name":113,"show_sort_weight":114,"slug":115},6,"Technology",50,"technology",{"id":117,"doc_module":4,"doc_module_name":47,"category_name":118,"show_sort_weight":119,"slug":120},7,"Healthcare",40,"healthcare",{"id":11,"doc_module":4,"doc_module_name":47,"category_name":12,"show_sort_weight":122,"slug":123},30,"research-report",{"id":125,"doc_module":4,"doc_module_name":47,"category_name":126,"show_sort_weight":127,"slug":128},9,"Religion & Spirituality",20,"religion-spirituality",{"id":127,"doc_module":4,"doc_module_name":47,"category_name":130,"show_sort_weight":127,"slug":131},"World Cup","world-cup",{"id":133,"doc_module":4,"doc_module_name":47,"category_name":134,"show_sort_weight":133,"slug":135},10,"Lifestyle","lifestyle",{"id":137,"doc_module":4,"doc_module_name":47,"category_name":138,"show_sort_weight":107,"slug":139},19,"General","general"]