[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-121881-en":3,"doc-seo-121881-105":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},121881,4810365810221,"Aurora","https://ap-avatar.wpscdn.com/davatar_155a257f0dc6eb9ab79c44ca47cae57d",8,"Research & Report","A benchmarking framework for improving machine learning with fNIRS neuroimaging data - PhD Thesis","Functional near-infrared spectroscopy (fNIRS) enables non-invasive neuroimaging with a favorable balance of temporal resolution, spatial resolution, and portability, and it is relatively robust to motion in naturalistic experiments. It is widely used to study working memory and mental workload, yet it remains less standardized than EEG or fMRI, leaving uncertainty about best practices for machine learning usage and analysis. This thesis introduces BenchNIRS, an open-source benchmarking framework for training, evaluating, and comparing fNIRS classification models using open datasets, reducing time and improving methodological rigor.","University of Nottingham School of Computer Science  \nA benchmarking framework for improving machine learning with fNIRS neuroimaging data  \nThesis  \nPhD in Computer Science  \nJohann Benerradi  \nSupervisors  \nDr Max L. Wilson Prof Michel F. Valstar Dr Jeremie Clos  \nExaminers  \nDr Paola Pinti Dr Jamie Twycross  \nNovember 2023  \nAbstract  \nFunctional near-infrared spectroscopy (fNIRS) is a non-invasive neuroimaging technology that presents attractive advantages such as a good compromise between temporal resolution, spatial resolution, and portability. Thanks to its properties and relative robustness to motion, it is often used in naturalistic settings and one of its key domains of application is the study of working memory and mental workload. However fNIRS is less popular and tested than other technologies such as electroencephalography (EEG) or functional magnetic resonance imaging (fMRI) which can nowadays be used in a clinical context. As such, there is no real consensus yet in the research community as to how fNIRS data should be used and analysed. While efforts to establish best practices with fNIRS have been published, there are still no community standards for using machine learning with fNIRS data. Moreover, the lack of open source benchmarks and standard expectations for reporting means that published works often claim high generalisation capabilities, but with poor methodology practices or reporting with missing details. These issues make it hard to evaluate the performance of models when it comes to choosing them for brain-computer interface (BCI) applications.  \nIn this thesis, we present the creation of an open-source benchmarking framework called BenchNIRS to establish a best practice machine learning methodology to develop, evaluate, and compare models for classification from fNIRS data, using open-access datasets from the literature. This framework makes the implementation of a robust machine learning methodology for fNIRS much simpler and less time-consuming.  \nWe demonstrate the utility of the framework by presenting a benchmarking of 6 baseline machine learning models (linear discriminant analysis (LDA), support vector machine (SVM), k-nearest neighbours (kNN), artificial neural network (ANN), convolutional neural network (CNN) and long short-term memory (LSTM)) on 5 open-access datasets and investigate the influence of different factors on the classification performance. Those benchmarks set a solid basis for future comparisons of machine learning approaches for fNIRS classification and reveal that most models have lower performances than expected when evaluating them in an unbiased way.  \nWe then go on to use the framework in a specific challenging use case, the classification of mental workload, and demonstrate how it is used to develop machine learning models tailored to a specific task or dataset. We show that models using as inputs longer durations of fNIRS recordings did not necessarily predict n-back levels better and that the classification from fNIRS data on this task is relatively challenging, despite the tailoring of deep learning models to specific device configurations being promising.  \nFinally, we go beyond supervised learning and extend the framework to study how unlabelled segments of the data can be used to improve classification. This leads us to perform transfer learning with a self-supervised representation learning pretext task and study to what extent it can be useful to fNIRS data classification. We explore the use of opposite hemoglobin type reconstruction as a pretext task and extend the framework to support the exploration of more pretext tasks for transfer learning in the future.  \nThank you. ..  \nTo my examiners, who so benevolently challenged me.  \nTo my supervisors, who so kindly guided me. To my mentors, who so greatly inspired me. To my dear colleagues, who so pedagogically helped me. To my friends, who so generously supported me. To my family, who so unconditionally loved me.  \nContents  ","cbCaijzOAprYubZp","https://ap.wps.com/l/cbCaijzOAprYubZp","pdf",6576678,1,141,"English","en",105,"# Introduction\n## Introduction of the topic\n## Functional near-infrared spectroscopy\n## Brain-computer interfaces\n## Application to mental workload\n## Problem statement and research questions\n## Summary of the contributions\n## Publications\n## Literature Review\n## fNIRS signal processing\n## Mental workload\n## Machine learning with fNIRS","[{\"question\":\"What problem does the thesis address about machine learning with fNIRS data?\",\"answer\":\"The research community lacks community standards for how to use and analyze fNIRS data in machine learning. Limited open-source benchmarks and inconsistent reporting make it difficult to judge model performance, especially for BCI applications.\"},{\"question\":\"What is BenchNIRS and what does it provide?\",\"answer\":\"BenchNIRS is an open-source benchmarking framework designed to establish best-practice machine learning methodology for fNIRS. It supports developing, evaluating, and comparing classification models using open-access literature datasets.\"},{\"question\":\"How does the thesis evaluate model performance and what key finding emerges?\",\"answer\":\"The thesis benchmarks six baseline machine learning models across five open-access datasets and studies factors affecting classification performance. It finds that many models perform worse than expected when evaluated in an unbiased way.\"}]","A benchmarking framework for improving machine learning with fNIRS neuroimaging data - PhD Thesis | PDF",1785807434,355,{"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},"a-benchmarking-framework-for-improving-machine-learning-with-fnirs-neuroimaging-data-phd-thesis","",{"@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/a-benchmarking-framework-for-improving-machine-learning-with-fnirs-neuroimaging-data-phd-thesis/121881/",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","2026-08-04",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},"What problem does the thesis address about machine learning with fNIRS data?","Question",{"text":75,"@type":76},"The research community lacks community standards for how to use and analyze fNIRS data in machine learning. Limited open-source benchmarks and inconsistent reporting make it difficult to judge model performance, especially for BCI applications.","Answer",{"name":78,"@type":73,"acceptedAnswer":79},"What is BenchNIRS and what does it provide?",{"text":80,"@type":76},"BenchNIRS is an open-source benchmarking framework designed to establish best-practice machine learning methodology for fNIRS. It supports developing, evaluating, and comparing classification models using open-access literature datasets.",{"name":82,"@type":73,"acceptedAnswer":83},"How does the thesis evaluate model performance and what key finding emerges?",{"text":84,"@type":76},"The thesis benchmarks six baseline machine learning models across five open-access datasets and studies factors affecting classification performance. It finds that many models perform worse than expected when evaluated in an unbiased way.","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},[93,97,101,105,110,115,120,123,128,131,135],{"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":111,"doc_module":4,"doc_module_name":46,"category_name":112,"show_sort_weight":113,"slug":114},6,"Technology",50,"technology",{"id":116,"doc_module":4,"doc_module_name":46,"category_name":117,"show_sort_weight":118,"slug":119},7,"Healthcare",40,"healthcare",{"id":11,"doc_module":4,"doc_module_name":46,"category_name":12,"show_sort_weight":121,"slug":122},30,"research-report",{"id":124,"doc_module":4,"doc_module_name":46,"category_name":125,"show_sort_weight":126,"slug":127},9,"Religion & Spirituality",20,"religion-spirituality",{"id":126,"doc_module":4,"doc_module_name":46,"category_name":129,"show_sort_weight":126,"slug":130},"World Cup","world-cup",{"id":132,"doc_module":4,"doc_module_name":46,"category_name":133,"show_sort_weight":132,"slug":134},10,"Lifestyle","lifestyle",{"id":136,"doc_module":4,"doc_module_name":46,"category_name":137,"show_sort_weight":106,"slug":138},19,"General","general"]