[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-126619-en":3,"doc-seo-126619-105":31,"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":21,"is_downloadable":21,"audit_status":21,"page_count":22,"language":23,"language_code":24,"site_id":25,"html_lang":24,"table_of_contents":26,"faqs":27,"seo_title":28,"seo_description":14,"update_tm":29,"read_time":30},126619,549768064622,"Anda","https://ap-avatar.wpscdn.com/davatar_6f874abed73319feea01a86fa6f0fab8",8,"Research & Report","Lightweight Machine Learning with Brain Signals","Electroencephalography (EEG) signals are increasingly used in Brain-Computer Interface (BCI) systems and neural engineering due to their portability and availability. However, scalp-wide sensory electrodes collect task-irrelevant signals, which raises overfitting risk, increases computation cost, and worsens transferability because of inter-subject variability. Existing CNN or GNN approaches also inadequately represent functional connectivity beyond physical proximity.","Lightweight Machine Learning with Brain Signals  \nAuthor:  \nLou , Haowei  \nPublication Date:  \n2023  \nDOI:  \n[https://doi.org/10.26190/unsworks/24944](https://doi.org/10.26190/unsworks/24944)  \nLicense:  \n[https://creativecommons.org/licenses/by/4.0/](https://creativecommons.org/licenses/by/4.0/)  \nLink to license to see what you are allowed to do with this resource.  \nDownloaded from [http://hdl.handle. net/1959.4/101237](http://hdl.handle. net/1959.4/101237) in [https://](https://)[ ](https://)[unsworks. unsw.edu.au](unsworks. unsw.edu.au) on 2023-09-07  \nLightweight Machine Learning with  \nBrain Signals  \nHaowei Lou  \nA thesis in fulfillment of the requirements for the degree of  \nMaster of Philosophy  \nSchool of Computer Science and Engineering Faculty of Engineering The University of New South Wales  \nFebruary 2023  \nCopyright Statement  \n‘I hereby grant the University of New South Wales or its agents the right to archive and to make available my thesis or dissertation in whole or part in the University libraries in all forms of media, now or here after known, subject to the provisions of the Copyright Act 1968 . I retain all proprietary rights, such as patent rights. I also retain the right to use in future works (such as articles or books) all or part of this thesis or dissertation.  \nI also authorise University Microfilms to use the 350 word abstract of my thesis in Dissertation Abstract International (this is applicable to doctoral theses only) .  \nI have either used no substantial portions of copyright material in my thesis or I have obtained permission to use copyright material; where permission has not been granted I have applied/will apply for a partial restriction of the digital copy of my thesis or dissertation.’  \nHaowei Lou July 10, 2023  \nAuthenticity Statement  \n‘I certify that the Library deposit digital copy is a direct equivalent of the final officially approved version of my thesis. No emendation of content has occurred and if there are any minor variations in formatting, they are the result of the conversion to digital format.’  \nHaowei Lou July 10, 2023  \nAbstract  \nElectroencephalography (EEG) signals are gaining popularity in Brain-Computer Interface (BCI) systems and neural engineering applications thanks to their portability and availability. Inevitably, the sensory electrodes on the entire scalp would collect signals irrelevant to the particular BCI task, increasing the risks of overfitting in machine learning-based predictions.  \nWhile this issue is being addressed by scaling up the EEG datasets and handcrafting the complex predictive models, this also leads to increased computation costs. Moreover, the model trained for one set of subjects cannot easily be adapted to other sets due to inter-subject variability, which creates even higher over-fitting risks. Meanwhile, despite previous studies using either convolutional neural networks (CNNs) or graph neural networks (GNNs) to determine spatial correlations between brain regions, they fail to capture brain functional connectivity beyond physical proximity.  \nTo this end, we propose 1) removing task-irrelevant noises instead of merely complicating models; 2) extracting subject-invariant discriminative EEG encodings, by taking functional connectivity into account; 3) navigating and training deep learning model with the most critical EEG channels; 4) detecting most similar EEG segments with target subject to reduce the cost of computation as well as inter-subject variability.  \nSpecifically, we construct a task-adaptive graph representation of brain network based on topological functional connectivity rather than distance-based connections. Further, non-contributory EEG channels are excluded by selecting only functional regions relevant to the corresponding intention. Lastly, contributory EEG segments are detected by several similarity estimation metrics, we then evaluate and train our proposed framework upon detected EEG segments to compare the perf","cbCaitKVYyioUSop","https://ap.wps.com/l/cbCaitKVYyioUSop","pdf",9888259,3,1,114,"English","en",105,"# Abstract\n## Motivation: overfitting, computation, inter-subject variability\n## Proposed approach (SIFT-EEG)\n## EEG task-adaptive graph representation and channel/segment selection\n## Experimental results and implications","[{\"question\":\"Why do EEG-based BCI models face overfitting challenges?\",\"answer\":\"Task-irrelevant electrode signals are collected across the scalp, which increases overfitting risk in machine learning predictions.\"},{\"question\":\"How does the proposed method address inter-subject variability?\",\"answer\":\"It extracts subject-invariant discriminative EEG encodings using functional connectivity and reduces reliance on subject-specific patterns through channel and segment selection.\"},{\"question\":\"What performance improvements are reported for SIFT-EEG?\",\"answer\":\"On motor imagery predictions, SIFT-EEG outperforms CNN-based and GNN-based models by about 4% and 7%, while maintaining similar performance using only 20% of raw EEG data and achieving high accuracy with less than 9% training data using the best metric.\"}]","Lightweight Machine Learning with Brain Signals | PDF",1785933788,287,{"code":4,"msg":32,"data":33},"ok",{"site_id":25,"language":24,"slug":34,"title":13,"keywords":35,"description":14,"schema_data":36,"social_meta":87,"head_meta":89,"extra_data":91,"updated_unix":29},"lightweight-machine-learning-with-brain-signals","",{"@graph":37,"@context":86},[38,54,69],{"@type":39,"itemListElement":40},"BreadcrumbList",[41,45,49,51],{"item":42,"name":43,"@type":44,"position":21},"https://docshare.wps.com","Home","ListItem",{"item":46,"name":47,"@type":44,"position":48},"https://docshare.wps.com/document/","Document",2,{"item":50,"name":12,"@type":44,"position":20},"https://docshare.wps.com/document/research-report/",{"item":52,"name":13,"@type":44,"position":53},"https://docshare.wps.com/document/lightweight-machine-learning-with-brain-signals/126619/",4,{"url":52,"name":13,"@type":55,"author":56,"headline":13,"publisher":58,"fileFormat":61,"inLanguage":24,"description":14,"dateModified":62,"datePublished":63,"encodingFormat":61,"isAccessibleForFree":64,"interactionStatistic":65},"DigitalDocument",{"name":9,"@type":57},"Person",{"url":42,"name":59,"@type":60},"DocShare","Organization","application/pdf","2026-08-27","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},"Why do EEG-based BCI models face overfitting challenges?","Question",{"text":76,"@type":77},"Task-irrelevant electrode signals are collected across the scalp, which increases overfitting risk in machine learning predictions.","Answer",{"name":79,"@type":74,"acceptedAnswer":80},"How does the proposed method address inter-subject variability?",{"text":81,"@type":77},"It extracts subject-invariant discriminative EEG encodings using functional connectivity and reduces reliance on subject-specific patterns through channel and segment selection.",{"name":83,"@type":74,"acceptedAnswer":84},"What performance improvements are reported for SIFT-EEG?",{"text":85,"@type":77},"On motor imagery predictions, SIFT-EEG outperforms CNN-based and GNN-based models by about 4% and 7%, while maintaining similar performance using only 20% of raw EEG data and achieving high accuracy with less than 9% training data using the best metric.","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":25},{"code":4,"msg":5,"data":93},[94,98,102,106,111,116,121,124,129,132,136],{"id":21,"doc_module":4,"doc_module_name":47,"category_name":95,"show_sort_weight":96,"slug":97},"Story & Novel",90,"story-novel",{"id":48,"doc_module":4,"doc_module_name":47,"category_name":99,"show_sort_weight":100,"slug":101},"Literature",80,"literature",{"id":53,"doc_module":4,"doc_module_name":47,"category_name":103,"show_sort_weight":104,"slug":105},"Exam",70,"exam",{"id":107,"doc_module":4,"doc_module_name":47,"category_name":108,"show_sort_weight":109,"slug":110},5,"Comic",60,"comic",{"id":112,"doc_module":4,"doc_module_name":47,"category_name":113,"show_sort_weight":114,"slug":115},6,"Technology",50,"technology",{"id":117,"doc_module":4,"doc_module_name":47,"category_name":118,"show_sort_weight":119,"slug":120},7,"Healthcare",40,"healthcare",{"id":11,"doc_module":4,"doc_module_name":47,"category_name":12,"show_sort_weight":122,"slug":123},30,"research-report",{"id":125,"doc_module":4,"doc_module_name":47,"category_name":126,"show_sort_weight":127,"slug":128},9,"Religion & Spirituality",20,"religion-spirituality",{"id":127,"doc_module":4,"doc_module_name":47,"category_name":130,"show_sort_weight":127,"slug":131},"World Cup","world-cup",{"id":133,"doc_module":4,"doc_module_name":47,"category_name":134,"show_sort_weight":133,"slug":135},10,"Lifestyle","lifestyle",{"id":137,"doc_module":4,"doc_module_name":47,"category_name":138,"show_sort_weight":107,"slug":139},19,"General","general"]