[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-120881-en":3,"doc-seo-120881-105":30,"detail-sidebar-cat-0-en-105":83},{"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},120881,3848291630094,"Emma Wilson","https://eur-avatar.wpscdn.com/davatar_085a072bc5b1113ac321206ff7593b45",8,"Research & Report","An Ultra-low-power Real-time Machine Learning based fNIRS Motion Artefacts Detection","Machine learning for functional near-infrared spectroscopy (fNIRS) often demands significant processing and memory due to iterative matrix multiplications and gradient computations, limiting feasibility on wearable platforms. The study presents an ultralow-power, real-time machine learning module to detect fNIRS motion artefacts, reporting 97.42% classification accuracy. Implemented on an FPGA, it achieves 38,354 LUTs, 6,024 flip-flops, and 0.021 W dynamic power consumption, outperforming conventional CPU SVM and other SVM baselines. Results support embedded deployment under strict resource and power constraints while maintaining high accuracy.","This is a repository copy of An Ultra-low-power Real-time Machine Learning based fNIRS Motion Artefacts Detection.  \nWhite Rose Research Online URL for this paper:  \n[https://eprints.whiterose.ac.uk/208160/](https://eprints.whiterose.ac.uk/208160/)  \n[Version: Accepted Version](Version: Accepted Version)  \nArticle:  \nErcan, R. , Xia, Y. , Zhao, Y. et al. (3 more authors) (Accepted: 2024) An Ultra-low-power Real-time Machine Learning based fNIRS Motion Artefacts Detection. IEEE Transactions on Very Large Scale Integration (VLSI) Systems. ISSN 1063-8210 (In Press)  \n© 2024 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, forresale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works.  \nReuse  \nItems deposited in White Rose Research Online are protected by copyright, with all rights reserved unless indicated otherwise. They may be downloaded and/or printed for private study, or other acts as permitted by national copyright laws. The publisher or other rights holders may allow further reproduction and re-use of the full text version. This is indicated by the licence information on the White Rose Research Online record for the item.  \nTakedown  \nIf you consider content in White Rose Research Online to be in breach of UK law, please notify us by  \nemailing [eprints@whiterose.ac.uk](eprints@whiterose.ac.uk) including the URL of the record and the reason for the withdrawal request.  \n[eprints@whiterose.ac.uk](eprints@whiterose.ac.uk)[ ](eprints@whiterose.ac.uk)[https://eprints.whiterose.ac.uk/](https://eprints.whiterose.ac.uk/)  \n1  \n> REPLACE THIS LINE WITH YOUR MANUSCRIPT ID NUMBER (DOUBLE-CLICK HERE TO EDIT) \u003C  \nAn Ultra-low-power Real-time Machine Learning based fNIRS Motion Artefacts Detection  \nRenas Ercan, Yunjia Xia, Student Member, IEEE, Yunyi Zhao, Rui Loureiro, Member, IEEE, Shufan Yang, Senior Member, IEEE, and Hubin Zhao, Member, IEEE  \nAbstract— Due to iterative matrix multiplications or gradient computations, machine learning modules often require a large amount of processing power and memory. As a result, they are often not feasible for use in wearable devices, which have limited processing power and memory. In this study, we propose an ultralow-power and real-time machine learning-based motion artefact detection module for functional Near-Infrared Spectroscopy fNIRS systems. We achieved a high classification accuracy of 97.42%, low FPGA resource utilization of 38,354 look-up tablesand 6024 flip-flops, as well as low power consumption of 0.021 Win dynamic power. These results outperform conventional CPUSVM methods and other state-of-the-art SVM implementations. This study has demonstrated that an FPGA-based fNIRS motion artefact classifier can be exploited whilst meeting low power and resource constraints, which are crucial in embedded hardware systems while keeping high classification accuracy.  \nIndex Terms— Field-programmable gate array (FPGA), fNIRS, low power, machine learning, motion artefact detection, real-time, support vector machines (SVM)  \nI. INTRODUCTION  \nFUNCTIONAL Near-Infrared Spectroscopy (fNIRS) is  \nan emerging modality that aims to characterize cortical  \nhemoglobin fluctuations through intensity measurements of diffusely scattered near-infrared light [1,2] . It can help neuroscientists to determine which brain regions are activated during specific actions. However, pre-processing is essential for fNIRS data which can be noisy. Due to the participant’s motion, non-evoked systemic signal components in recorded fNIRS signals pose a challenge. This challenge isone of the main issues affecting fNIRS applications, as it results in motion artefacts, causing an erroneous detection of functional cortical activity [1] .  \nConventional motion detecti","cbCaig09sj2mnxZA","https://ap.wps.com/l/cbCaig09sj2mnxZA","pdf",1168799,1,12,"English","en",105,"# Introduction\n## Functional fNIRS and the motion artefact problem\n## Limits of offline and GPU-based approaches\n## Motivation for an FPGA-based low-power solution","[{\"question\":\"What performance does the proposed ultralow-power real-time detection module achieve?\",\"answer\":\"The module achieves 97.42% classification accuracy on the fNIRS motion artefact detection task, while using low FPGA resources (38,354 LUTs and 6,024 flip-flops) and low dynamic power (0.021 W).\"}]","An Ultra-low-power Real-time Machine Learning based fNIRS Motion Artefacts Detection | PDF",1785732472,30,{"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":78,"head_meta":80,"extra_data":82,"updated_unix":28},"an-ultra-low-power-real-time-machine-learning-based-fnirs-motion-artefacts-detection","",{"@graph":36,"@context":77},[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/an-ultra-low-power-real-time-machine-learning-based-fnirs-motion-artefacts-detection/120881/",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],{"name":72,"@type":73,"acceptedAnswer":74},"What performance does the proposed ultralow-power real-time detection module achieve?","Question",{"text":75,"@type":76},"The module achieves 97.42% classification accuracy on the fNIRS motion artefact detection task, while using low FPGA resources (38,354 LUTs and 6,024 flip-flops) and low dynamic power (0.021 W).","Answer","https://schema.org",{"og:url":52,"og:type":79,"og:title":13,"og:site_name":59,"og:description":14},"article",{"robots":81,"canonical":52},"index,follow",{"doc_id":7,"site_id":24},{"code":4,"msg":5,"data":84},[85,89,93,97,102,107,112,114,119,122,126],{"id":20,"doc_module":4,"doc_module_name":46,"category_name":86,"show_sort_weight":87,"slug":88},"Story & Novel",90,"story-novel",{"id":47,"doc_module":4,"doc_module_name":46,"category_name":90,"show_sort_weight":91,"slug":92},"Literature",80,"literature",{"id":53,"doc_module":4,"doc_module_name":46,"category_name":94,"show_sort_weight":95,"slug":96},"Exam",70,"exam",{"id":98,"doc_module":4,"doc_module_name":46,"category_name":99,"show_sort_weight":100,"slug":101},5,"Comic",60,"comic",{"id":103,"doc_module":4,"doc_module_name":46,"category_name":104,"show_sort_weight":105,"slug":106},6,"Technology",50,"technology",{"id":108,"doc_module":4,"doc_module_name":46,"category_name":109,"show_sort_weight":110,"slug":111},7,"Healthcare",40,"healthcare",{"id":11,"doc_module":4,"doc_module_name":46,"category_name":12,"show_sort_weight":29,"slug":113},"research-report",{"id":115,"doc_module":4,"doc_module_name":46,"category_name":116,"show_sort_weight":117,"slug":118},9,"Religion & Spirituality",20,"religion-spirituality",{"id":117,"doc_module":4,"doc_module_name":46,"category_name":120,"show_sort_weight":117,"slug":121},"World Cup","world-cup",{"id":123,"doc_module":4,"doc_module_name":46,"category_name":124,"show_sort_weight":123,"slug":125},10,"Lifestyle","lifestyle",{"id":127,"doc_module":4,"doc_module_name":46,"category_name":128,"show_sort_weight":98,"slug":129},19,"General","general"]