[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-123037-en":3,"doc-seo-123037-105":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},123037,8796095461564,"Liam","https://ap-avatar.wpscdn.com/davatar_155a257f0dc6eb9ab79c44ca47cae57d",8,"Research & Report","Exploring Novel Methodological Approaches for the Analysis of Electroencephalogram Data - Machine Learning and Group Iterative Multiple Model Estimation","Machine learning, especially Support Vector Machines (SVM), has been widely used in electroencephalogram (EEG) studies to detect informative time points related to stimuli, yet alternative models may achieve comparable performance. This thesis reanalyzes datasets from Bae and Luck (2018, 2019b) using K-Nearest Neighbors, Naïve Bayes, Random Forest, and Adaptive Boosting, addressing gaps between behavioral and decoding outcomes in the 2019 motion perception experiment. It also applies Group Iterative Multiple Model Estimation (GIMME) to probe connectivity differences involving spatial attention and working memory. Results suggest GIMME complements traditional decoding models by revealing connectivity effects not evident in accuracy alone, while noting measurement-model and estimation singularity challenges to be resolved in future work.","Baral 1  \nExploring Novel Methodological Approaches for the Analysis of Electroencephalogram Data: Machine Learning and Group Iterative Multiple Model Estimation  \nBy  \nSuryadyuti Baral  \nFaculty Advisors:  \nDr. Joseph Hopfinger & Dr. Kathleen Gates  \nSenior Honors Thesis  \nDepartment of Psychology and Neuroscience  \nThe University of North Carolina at Chapel Hill  \nMarch 25, 2024  \nBaral 2  \nAbstract  \nMachine learning, particularly Support Vector Machines (SVM), has been widely utilized in Electroencephalogram (EEG) research to identify significant information within time points related to stimuli. However, alternative models may offer comparable performance. In the present study, we re-analyzed datasets from experiments by Bae & Luck (2018, 2019b) using K-Nearest Neighbors, Naïve Bayes, Random Forest and Adaptive Boosting. We address discrepancies between behavioral outcomes and decoding results in Bae and Luck’s motion perception study from 2019. We replicated the results from Bae and Luck's 2018 study using the other algorithms and explored the possibility of one model outperforming the others. While no single model emerged superior based solely on decoding accuracy, converging results from multiple models helped reconcile discrepancies in the 2019 experiment. Additionally, for Bae and Luck’s 2018 study, we explored neural mechanisms underlying significant time point clusters identified by our machine learning algorithms. Implementing Group Iterative Multiple Model Estimation (GIMME) in EEG research for the first time, we probed differences in connectivity between spatial attention and working memory using the paradigm. Our findings suggest that GIMME complements traditional machine learning models, uncovering connectivity differences not apparent in decoding results. However, challenges remain in establishing a proper measurement model and addressing estimation singularities. Successful resolution of these issues in future research will lead to a more robust exploration of effective neural connectivity using EEG.  \nKeywords: EEG, Machine Learning, GIMME, Motion perception, Attention, Memory  \nIntroduction  \nBehaviorists ofthe early 20th century would have been surprised at the current focus of the field of psychology. In 1913, J.B. Watson's publication, \"Psychology as the behaviorist  \nBaral 3  \nviews it,\" unequivocally rejected introspection and the exploration of internal cognitive processes as essential tools for understanding the human mind. At the time, his stance was warranted, as the technological limitations of that era hindered their ability to delve into brain function and use it to decode behavior effectively. However, in 2024, that is no longer the case. The brain and its processes have taken center stage in research endeavors. We haveneuroimaging methods like Electroencephalogram (EEG) that give us brain activity with millisecond precision. Recent leaps in computational power have ushered in a new era of machine learning methods, enabling us to predict human behavior with remarkable accuracy. We have come a long way and our academic ancestors would be proud of the progress in psychology. Yet, the brain and its associated cognitive processes pose innumerable unsolved mysteries.  \nThe brain is a three-pound jelly-like organ that is believed to house consciousness of a living organism. To understand consciousness and thereby human behavior better, it is essential to solve the mysteries posed by it. Human cognition is interesting from an academic standpoint, but its applications in real life can alter the world. Neuroimaging techniques like EEG that have the potential to provide glimpses into the workings ofthe mind in real time, are driving the development of the field of Brain-Computer Interface (BCI). By employing machine learning algorithms to analyze neuroimaging data, a future may be envisioned where individuals suffering from paralysis can regain control of their limbs and those with speech disorders can ","cbCaii0kyls0lLI9","https://ap.wps.com/l/cbCaii0kyls0lLI9","pdf",2123755,1,69,"English","en",105,"# Abstract\n# Introduction\n## Background of behaviorism and neuroimaging\n## Relevance to Brain-Computer Interface and cognitive neuroscience\n# Electroencephalogram (EEG)\n## Origins and principles of EEG signals\n## Event-Related Potentials (ERPs) and signal-to-noise enhancement","[{\"question\":\"Which machine learning algorithms were used to reanalyze the EEG datasets?\",\"answer\":\"The thesis reanalyzed Bae and Luck’s datasets using K-Nearest Neighbors, Naïve Bayes, Random Forest, and Adaptive Boosting (in addition to comparing against the commonly used SVM approach).\"},{\"question\":\"How did the study address discrepancies between behavioral outcomes and decoding results?\",\"answer\":\"It replicated the 2018 results using multiple alternative algorithms and used converging outputs across models to reconcile discrepancies observed in the 2019 motion perception experiment.\"},{\"question\":\"What does Group Iterative Multiple Model Estimation (GIMME) add beyond standard decoding?\",\"answer\":\"GIMME is used in EEG research to probe connectivity differences between spatial attention and working memory, revealing connectivity effects that are not apparent from decoding accuracy alone.\"}]","Exploring Novel Methodological Approaches for the Analysis of Electroencephalogram Data - Machine Learning and Group Iterative Multiple Model Estimation | PDF",1785814320,174,{"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},"exploring-novel-methodological-approaches-for-the-analysis-of-electroencephalogram-data-machine-learning-and-group-iterative-multiple-model-estimation","",{"@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/exploring-novel-methodological-approaches-for-the-analysis-of-electroencephalogram-data-machine-learning-and-group-iterative-multiple-model-estimation/123037/",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},"Which machine learning algorithms were used to reanalyze the EEG datasets?","Question",{"text":75,"@type":76},"The thesis reanalyzed Bae and Luck’s datasets using K-Nearest Neighbors, Naïve Bayes, Random Forest, and Adaptive Boosting (in addition to comparing against the commonly used SVM approach).","Answer",{"name":78,"@type":73,"acceptedAnswer":79},"How did the study address discrepancies between behavioral outcomes and decoding results?",{"text":80,"@type":76},"It replicated the 2018 results using multiple alternative algorithms and used converging outputs across models to reconcile discrepancies observed in the 2019 motion perception experiment.",{"name":82,"@type":73,"acceptedAnswer":83},"What does Group Iterative Multiple Model Estimation (GIMME) add beyond standard decoding?",{"text":84,"@type":76},"GIMME is used in EEG research to probe connectivity differences between spatial attention and working memory, revealing connectivity effects that are not apparent from decoding accuracy alone.","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"]