[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-119595-en":3,"doc-seo-119595-105":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},119595,687197207919,"Theodora","https://ap-avatar.wpscdn.com/avatar/a000253d6f5f7c60be?x-image-process=image/resize,m_fixed,w_180,h_180&k=1779446848396160552",8,"Research & Report","Enabling SWIPT with Machine Learning-Based Multisine Signal Classification - Conference Paper Draft","This paper introduces a methodology for simultaneous wireless information and power transfer (SWIPT) that exploits bandwidth-constrained multisine waveforms, using software-defined radio tools. Information is embedded by varying the number of carriers (tones) while the receiver harvests RF energy. A comprehensive dataset is constructed by transmitting multiple waveform types and measuring harvested power across different distances. Machine-learning-based waveform classification is used to extract the encoded information and validate the dataset. Experimental results show 99.2% accuracy with multinomial logistic regression and 100% with support vector machine, enabling discrimination across both binary and multi-class signal types.","# Enabling SWIPT with Machine Learning-Based Multisine Signal Classification\n\nStylianou Petros,Faddoul Elio,Korium Mohamed Selim,Krikidis loannis  \nThis is a Final draftversion of a publicationpublished by IEEEin 2025 IEEE Wireless Power Technology Conference and Expo (WPTCE)  \nDOI:10.1109/WPTCE62521.2025.11062143  \nCopyright of the original publication:  \nC IEEE 2025  \nPlease cite the publication as follows:  \nStylianou,P.,Faddoul,E.,Korium,M.S.,Krikidis,I.(2025).Enabling SWIPT with MachineLearning-Based Multisine Signal Classification.In:2025 IEEE Wireless Power TechnologyConference and Expo (WPTCE),Rome,Italy,2025.pp.1-5.DOI:  \n10.1109/WPTCE62521.2025.11062143  \nThis is a parallel published version of an original publication.This version can differ from the original published article.  \nEnabling SWIPT with Machine Learning-BasedMultisine Signal Classification  \nMohamed Selim Korium  \nPetros Stylianou  \nElio Faddoul  \nIoannis Krikidis  \nIRIDA Research Centre forIRIDA Research Centre forLappeenranta-LahtiIRIDA Research Centre forrCommunication TechnologiesCommunication TechnologiesUniversity of TechnologyCommunication TechnologiesNicosia,CyprusNicosia,CyprusLappeenranta,FinlandNicosia,Cypruspstyi03@ucy.ac.cyefaddo01@ucy.ac.cymohamed.korium@lut.fikrikidis@ucy.ac.cy  \na new SWIPT technique that exploits bandwidth-constrainedmultisine signals for RF energy harvesting,while informationis embedded in the number of tones.Similarly,the authors in[5]introduce a multitone PSK technique in which the tones'phases are used for transmitting multiple symbols over a singlemultitone transmission.Ideally,efficient diode-based energyharvesting benefits from signals with high PAPR.However,maximizing PAPR faces additional issues,such as the limitedoutput range of digital-to-analog converters (DACs)and thenonlinearity caused by power amplifiers saturating at highamplitude peaks.These distortions can alter the time-domainwaveform envelope,potentially reducing the WPT efficiencyof multisine signals [6],[7].  \nAbstract—This paper presents a novel methodology for em-ploying multisine waveforms in simultaneous wireless informa-tion and power transfer(SWIPT)systems,utilizing software-defined radio tools.The proposed approach encodes informationby varying the number of carriers in the multisine signals,while simultaneously enabling the receiver to harvest energy.A comprehensive dataset is generated by transmitting variouswaveforms and measuring the harvested power across differentdistances.The primary objectives are to accurately classify thereceived waveforms to extract information and validate thedataset using established machine learning techniques.Exper-imental evaluations demonstrate that basic supervised machinelearning models,specifically multinomial logistic regression andsupport vector machine,achieve a high accuracy of 99.2%and100%,respectively.These results underscore the capability ofthe proposed system to effectively distinguish not only betweenbinary signal classes but also among multiple signal classes.  \nThe work presented in [4]introduces a SWIPT systemthat embeds information in the tone indices of multisinewaveforms,utilizing a linear envelope detector at the receiver.However,such an approach may be impractical in certainscenarios,due to the nonlinearities of the rectenna circuits andthe hardware constraints of the digital transceivers.Therefore,in this work,we propose a novel experimental method foremploying multisine waveforms in SWIPT systems,by uti-lizing software-defined radio(SDR)tools.In particular,theinformation is encoded by varying the number of carriers(tones)in the multisine waveforms,while having the receiversimultaneously harvest energy.The method involves gener-ating a dataset by transmitting various signals and collectingthe harvested power at different distances.A machine learningmodel is then trained on the dataset to identify the waveformsand extract information.Performance evaluation demonstratesthat multinomial log","cbCaiaoi3fg4Yzme","https://ap.wps.com/l/cbCaiaoi3fg4Yzme","pdf",1165093,1,6,"English","en",105,"# Abstract\n# I. Introduction\n# II. SWIPT Technique and Hardware System Setup","[{\"question\":\"How is information encoded in the proposed SWIPT multisine signals?\",\"answer\":\"Information is encoded by varying the number of carriers (tones) in the multisine waveforms, while the receiver simultaneously harvests energy.\"},{\"question\":\"How is the dataset for classification generated and validated?\",\"answer\":\"Various multisine waveforms are transmitted and the harvested power is measured at different distances to form the dataset. The dataset is validated using established machine learning classification techniques.\"},{\"question\":\"Which machine learning models are used and what accuracies are reported?\",\"answer\":\"Multinomial logistic regression and support vector machine are evaluated. The reported accuracies are 99.2% for multinomial logistic regression and 100% for SVM.\"}]","Enabling SWIPT with Machine Learning-Based Multisine Signal Classification - Conference Paper Draft | PDF",1785725187,15,{"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},"enabling-swipt-with-machine-learning-based-multisine-signal-classification-conference-paper-draft","",{"@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/enabling-swipt-with-machine-learning-based-multisine-signal-classification-conference-paper-draft/119595/",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","2026-08-03",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},"How is information encoded in the proposed SWIPT multisine signals?","Question",{"text":75,"@type":76},"Information is encoded by varying the number of carriers (tones) in the multisine waveforms, while the receiver simultaneously harvests energy.","Answer",{"name":78,"@type":73,"acceptedAnswer":79},"How is the dataset for classification generated and validated?",{"text":80,"@type":76},"Various multisine waveforms are transmitted and the harvested power is measured at different distances to form the dataset. The dataset is validated using established machine learning classification techniques.",{"name":82,"@type":73,"acceptedAnswer":83},"Which machine learning models are used and what accuracies are reported?",{"text":84,"@type":76},"Multinomial logistic regression and support vector machine are evaluated. The reported accuracies are 99.2% for multinomial logistic regression and 100% for SVM.","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},[93,97,101,105,110,114,119,122,127,130,134],{"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":21,"doc_module":4,"doc_module_name":46,"category_name":111,"show_sort_weight":112,"slug":113},"Technology",50,"technology",{"id":115,"doc_module":4,"doc_module_name":46,"category_name":116,"show_sort_weight":117,"slug":118},7,"Healthcare",40,"healthcare",{"id":11,"doc_module":4,"doc_module_name":46,"category_name":12,"show_sort_weight":120,"slug":121},30,"research-report",{"id":123,"doc_module":4,"doc_module_name":46,"category_name":124,"show_sort_weight":125,"slug":126},9,"Religion & Spirituality",20,"religion-spirituality",{"id":125,"doc_module":4,"doc_module_name":46,"category_name":128,"show_sort_weight":125,"slug":129},"World Cup","world-cup",{"id":131,"doc_module":4,"doc_module_name":46,"category_name":132,"show_sort_weight":131,"slug":133},10,"Lifestyle","lifestyle",{"id":135,"doc_module":4,"doc_module_name":46,"category_name":136,"show_sort_weight":106,"slug":137},19,"General","general"]