[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-127687-en":3,"doc-seo-127687-105":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},127687,962084925782,"Ava Thompson","https://ap-avatar.wpscdn.com/davatar_9964176cb1d06d4a9deccf72a44ae3dc",8,"Research & Report","Unleashing the potential of fNIRS with machine learning - classification of fine anatomical movements to empower future brain-computer interface","The study evaluates functional near-infrared spectroscopy (fNIRS) signals combined with modern machine-learning and deep-learning models to classify fine anatomical movements for expanding control commands in a potential fNIRS-based brain-computer interface (BCI). Using a novel multi-class setting, twenty-four right-handed participants performed individual finger-tapping while signals were recorded with sixteen sources and detectors over the motor cortex. Oxygenated 1 HbO and deoxygenated 1 HbR were used as features. Ensemble methods such as RF and XGBoost outperform classical LDA, QDA, and MNLR, while the proposed DL model “Hemo-Net” achieves the highest test accuracy of 76% and shows promise for future BCI.","TYPE Original Research PUBLISHED 16 February 2024  \nDOI 10. 3389/fnhum.2024.1354143  \nOPEN ACCESS  \nEDITED BY  \nJiahui Pan,  \nSouth China Normal University, China  \nREVIEWED BY  \nXiaoou Li,  \nShanghai University of Medicine and Health Sciences, China  \nUsman Ghafoor,  \nInstitute of Space Technology, Pakistan  \n*CORRESPONDENCE  \nPeyman Mirtaheri  \n [peymanm@oslomet.no](peymanm@oslomet.no)[ ](peymanm@oslomet.no)Haroon Khan  \n [haroonkh@oslomet.no](haroonkh@oslomet.no)  \n†These authors have contributed equally to this work and share first authorship  \nRECEIVED 12 December 2023  \nACCEPTED 31 January 2024  \nPUBLISHED 16 February 2024  \nCITATION  \nKhan H, Khadka R, Sultan MS, Yazidi A, Ombao H and Mirtaheri P (2024) Unleashing the potential of fNIRS with machine learning: classification of fine anatomical movements to empower future brain-computer interface. Front. Hum. Neurosci. 18:1354143 .  \ndoi: 10.3389/fnhum.2024.1354143  \nCOPYRIGHT  \n© 2024 Khan, Khadka, Sultan, Yazidi, Ombao and Mirtaheri. This is an open-access article distributed under the terms of the Creative Commons Attribution License (CC BY) . The use, distribution or reproduction in other forums is permitted, provided the original author(s) and the copyright owner(s) are credited and that the original publication in this journal is cited, in accordance with accepted academic practice. No use, distribution or reproduction is permitted which does not comply with these terms.  \nUnleashing the potential of fNIRS with machine learning: classification of fine anatomical movements to empower future brain-computer interface  \nHaroon Khan1*†, Rabindra Khadka2†, Malik Shahid Sultan3†, Anis Yazidi2 , Hernando Ombao3 and Peyman Mirtaheri1*  \n1 Department of Mechanical, Electronics and Chemical Engineering, OsloMet-Oslo Metropolitan University, Oslo, Norway, 2 Department of Information Technology, Oslomet-Oslo Metropolitan University, Oslo, Norway, 3 Department of Computer, Electrical and Mathematical Science and Engineering, King Abdullah University of Science and Technology (KAUST), Thuwal, Saudi Arabia  \nIn this study, we explore the potential of using functional near-infrared spectroscopy (fNIRS) signals in conjunction with modern machine-learning techniques to classify specific anatomical movements to increase the number of control commands for a possible fNIRS-based brain-computer interface (BCI) applications. The study focuses on novel individual finger-tapping, a well-known task in fNIRS and fMRI studies, but limited to left/right or few fingers. Twentyfour right-handed participants performed the individual finger-tapping task. Data were recorded by using sixteen sources and detectors placed over the motor cortex according to the 10-10 international system. The event’s average oxygenated 1 HbO and deoxygenated 1 HbR hemoglobin data were utilized as features to assess the performance of diverse machine learning (ML) models in a challenging multi-class classification setting. These methods include LDA, QDA, MNLR, XGBoost, and RF. A new DL-based model named “Hemo-Net”has been proposed which consists of multiple parallel convolution layers with di􀀀erent filters to extract the features. This paper aims to explore the e􀀈cacy of using fNRIS along with ML/DL methods in a multi-class classification task. Complex models like RF, XGBoost, and Hemo-Net produce relatively higher test set accuracy when compared to LDA, MNLR, and QDA. Hemo-Net has depicted a superior performance achieving the highest test set accuracy of 76%, however, in this work, we do not aim at improving the accuracies of models rather we are interested in exploring if fNIRS has the neural signatures to help modern ML/DL methods in multi-class classification which can lead to applications like brain-computer interfaces. Multi-class classification of fine anatomical movements, such as individual finger movements, is di􀀈cult to classify with fNIRS data. Traditional ML models like MNLR and LDA show inferior performance compared to the ","cbCairhdgqqpEWud","https://ap.wps.com/l/cbCairhdgqqpEWud","pdf",1611936,1,13,"English","en",105,"# 1 Introduction\n## Functional near-infrared spectroscopy and BCI context","[{\"question\":\"What is the main goal of using fNIRS with machine learning in this work?\",\"answer\":\"To classify specific fine anatomical movements from fNIRS signals to increase the number of control commands for a future fNIRS-based brain-computer interface.\"},{\"question\":\"How was the finger-tapping task and fNIRS data acquisition set up?\",\"answer\":\"Twenty-four right-handed participants performed individual finger-tapping. Sixteen sources and detectors were placed over the motor cortex, and both oxygenated 1 HbO and deoxygenated 1 HbR were recorded.\"},{\"question\":\"Which models performed best for the multi-class classification task?\",\"answer\":\"Ensemble methods like random forest (RF) and XGBoost achieved higher test accuracy than LDA, QDA, and MNLR. The deep-learning model “Hemo-Net” performed best, reaching 76% test accuracy.\"}]","Unleashing the potential of fNIRS with machine learning - classification of fine anatomical movements to empower future brain-computer interface | PDF",1785940862,33,{"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},"unleashing-the-potential-of-fnirs-with-machine-learning-classification-of-fine-anatomical-movements-to-empower-future-brain-computer-interface","",{"@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/unleashing-the-potential-of-fnirs-with-machine-learning-classification-of-fine-anatomical-movements-to-empower-future-brain-computer-interface/127687/",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","2026-08-22","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},"What is the main goal of using fNIRS with machine learning in this work?","Question",{"text":76,"@type":77},"To classify specific fine anatomical movements from fNIRS signals to increase the number of control commands for a future fNIRS-based brain-computer interface.","Answer",{"name":79,"@type":74,"acceptedAnswer":80},"How was the finger-tapping task and fNIRS data acquisition set up?",{"text":81,"@type":77},"Twenty-four right-handed participants performed individual finger-tapping. Sixteen sources and detectors were placed over the motor cortex, and both oxygenated 1 HbO and deoxygenated 1 HbR were recorded.",{"name":83,"@type":74,"acceptedAnswer":84},"Which models performed best for the multi-class classification task?",{"text":85,"@type":77},"Ensemble methods like random forest (RF) and XGBoost achieved higher test accuracy than LDA, QDA, and MNLR. The deep-learning model “Hemo-Net” performed best, reaching 76% test accuracy.","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"]