[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-121624-en":3,"doc-seo-121624-105":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":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},121624,1099513958607,"Jiven","https://ap-avatar.wpscdn.com/avatar/100002390cf8733938c?x-image-process=image/resize,m_fixed,w_180,h_180&k=1778829742770036399",8,"Research & Report","Signal classification at discrete frequencies using machine learning - PhD thesis","Incidents such as the 2018 Gatwick Airport shutdown caused by a small UAS airfield incursion demonstrate the lack of routine, consistent methods for detecting and classifying unwanted signals. The work addresses early-warning detection of GNSS jamming RF signal types and small commercially available UAS RF signals using machine learning. It reduces data-collection burdens by applying transfer learning from object detection and representing signals in frequency/time domains. Results show high-accuracy classification, including whether a small UAS is flying or stationary, with Raspberry Pi and SDR enabling low-cost deployment.","Signal classification at discrete frequencies using machine learning  \nC. J. Swinney  \nA thesis submitted for the degree of  \nDoctor of Philosophy  \nRoyal Air Force  \nDepartment of Computer Science and Electronics Engineering  \nUniversity of Essex  \nDate of submission for examination August 2022  \nAcknowledgements  \nFirst, I would like to express my thanks to my supervisor Dr. John C. Woods. Without his extensive experience, academic support and unwavering dedication for the amount of experiments we have achieved, this work would not have been possible. This was even more paramount during the COVID-19 pandemic whereby progress could have been hindered due to lockdown restrictions. With Dr. Woods continuous support throughout that time, both pastorally and academically, the pandemic did not affect the output. I would also like to extend my thanks to Professor Reinhold Scherer, University of Essex, for the continued support and expertise, in particular with regards to machine learning and cross validation techniques. A special thank you is also extended to UAS Pilot Jim Pullen who has given up his time to fly all the UAS experiments details in this thesis and for the production of the DroneDetect dataset.  \nI would like to extend my thanks to the Royal Air Force Engineering and Cyberspace Profession, and Chief of Staff Support, for the sponsorship of this PhD. A special thank you to the Royal Air Force 591 Signals Unit for the use of their facilities for a number of the experiments in this thesis. In terms of Royal Air Force support, this PhD would not have been possible without the unwavering support of the Air and Space Warfare Centre (ASWC) in everything that has been achieved with this work. The ASWC have gone out of their way to make sure I have had all the support necessary to make this work count both academically and for the benefit of wider Defence. They have also taken special care to ensure I have been supported pastorally through every stage of the PhD and throughout the pandemic, which is something I am most grateful for. Without their support to me and this work it would not have happened. My deepest gratitude is extended to my hierarchy in the ASWC. Lastly I will extend my thanks to my family who always support all of my endeavors in every way.  \nAbstract  \nIncidents such as the 2018 shut down of Gatwick Airport due to a small Unmanned Aerial System (UAS) airfield incursion, have shown that we don’t have routine and consistent detection and classification methods in place to recognise unwanted signals in an airspace. Today, incidents ofthis nature are taking place around the world regularly. The first stage in mitigating a threat is to know whether a threat is present. This thesis focuses on the detection and classification of Global Navigation Satellite Systems (GNSS) jamming radio frequency (RF) signal types and small commercially available UAS RF signals using machine learning for early warning systems. RF signals can be computationally heavy and sometimes sensitive to collect. With neural networks requiring a lot of information to train from scratch, the thesis explores the use of transfer learning from the object detection field to lessen this burden by using graphical representations ofthe signal in the frequency and time domain. The thesis shows that utilising the benefits of transfer learning with both supervised and unsupervised learning and graphical signal representations, can provide high accuracy detection and classification, down to the fidelity of whether a small UAS is flying or stationary. By treating the classification of RF signals as an image classification problem, this thesis has shown that transfer learning through CNN feature extraction reduces the need for large datasets while still providing high accuracy results. CNN feature extraction and transfer learning was also shown to improve accuracy as a precursor to unsupervised learning but at a cost of time, while raw images provided a good o","cbCaiiaPs50SWFd3","https://ap.wps.com/l/cbCaiiaPs50SWFd3","pdf",12994350,1,399,"English","en",105,"# Chapter 1 - Introduction\n## Research Problem and Scope\n## Contribution of the Research\n## Background","[{\"question\":\"What problem does the thesis target for early warning systems?\",\"answer\":\"It targets the absence of routine, consistent detection and classification methods for recognizing unwanted signals in airspace, such as GNSS jamming and small UAS RF signals.\"},{\"question\":\"How does the thesis reduce the need for large training datasets?\",\"answer\":\"It uses transfer learning by leveraging graphical representations of RF signals in the frequency and time domains, treating RF classification as an image classification task with CNN feature extraction.\"},{\"question\":\"How are machine learning models deployed for low-cost early warning?\",\"answer\":\"The thesis demonstrates implementation using a Raspberry Pi combined with software defined radio (SDR) as a viable low-cost platform.\"}]","Signal classification at discrete frequencies using machine learning - PhD thesis | PDF",1785805773,1005,{"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},"signal-classification-at-discrete-frequencies-using-machine-learning-phd-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/signal-classification-at-discrete-frequencies-using-machine-learning-phd-thesis/121624/",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","2026-08-05","2026-08-04",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},"What problem does the thesis target for early warning systems?","Question",{"text":76,"@type":77},"It targets the absence of routine, consistent detection and classification methods for recognizing unwanted signals in airspace, such as GNSS jamming and small UAS RF signals.","Answer",{"name":79,"@type":74,"acceptedAnswer":80},"How does the thesis reduce the need for large training datasets?",{"text":81,"@type":77},"It uses transfer learning by leveraging graphical representations of RF signals in the frequency and time domains, treating RF classification as an image classification task with CNN feature extraction.",{"name":83,"@type":74,"acceptedAnswer":84},"How are machine learning models deployed for low-cost early warning?",{"text":85,"@type":77},"The thesis demonstrates implementation using a Raspberry Pi combined with software defined radio (SDR) as a viable low-cost platform.","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"]