[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-121809-en":3,"doc-seo-121809-105":30,"detail-sidebar-cat-0-en-105":95},{"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},121809,16904993612988,"Olivia Brown","https://ap-avatar.wpscdn.com/davatar_a8503ba1806abce46bf441b54a3ca4cd",8,"Research & Report","Machine Learning Strategies to Improve Cross-Subject and Cross-Session Generalization in EEG-Based Emotion Recognition - A Systematic Review","A systematic review evaluates machine-learning strategies designed to improve generalization in electroencephalography (EEG)-based emotion recognition, with special focus on cross-subject and cross-session generalization. EEG non-stationarity is highlighted as a key driver of the Dataset Shift problem, motivating architectures and methods that primarily rely on transfer learning. From 418 retrieved papers across Scopus, IEEE Xplore, and PubMed, 75 studies meet eligibility criteria after excluding insufficient validation schemes and approaches using other biosignals. A taxonomy of ML methods is proposed and top-performing strategies are identified, showing transfer learning advantages alongside discussion of emotion models and participant screening effects on classification accuracy.","POLITECNICO DI TORINO  \nRepository ISTITUZIONALE  \nMachine Learning Strategies to Improve Cross-Subject and Cross-Session Generalization in EEGBased Emotion Recognition: A Systematic Review  \nOriginal  \nMachine Learning Strategies to Improve Cross-Subject and Cross-Session Generalization in EEG-Based Emotion Recognition: A Systematic Review / Arpaia, Pasquale; Apicella, Andrea; D’Errico, Giovanni; Marocco, Davide; Mastrati, Giovanna; Moccaldi, Nicola; Prevete, Roberto.. -In: NEUROCOMPUTING. -ISSN 0925-2312. - (2023) .[10.2139/ssrn.4474510]  \nAvailability:  \nThis version is available at: 11583/2981926 .25 since: 2023-09-11T10:29:47Z  \nPublisher: Elsevier  \nPublished  \nDOI:10.2139/ssrn.4474510  \nTerms of use:  \nThis article is made available under terms and conditions as specified in the corresponding bibliographic description in the repository  \nPublisher copyright  \n(Article begins on next page)  \n08 November 2024  \nGraphical Abstract  \nMachine Learning Strategies to Improve  \nCross-Subject and Cross-Session Generalization  \nin EEG-based Emotion Recognition:  \na Systematic Review 1  \nAndrea Apicella, Pasquale Arpaia, Giovanni D’Errico, Davide Marocco, Giovanna Mastrati, Nicola Moccaldi, Roberto Prevete  \n1 This work has been submitted possible publication. Copyright may be transferred without notice.  \nThis preprint research paper has not been peer reviewed. Electronic copy available at: [https://ssrn.com/abstract=4474510](https://ssrn.com/abstract=4474510)  \nHighlights  \nMachine Learning Strategies to Improve  \nCross-Subject and Cross-Session Generalization  \nin EEG-based Emotion Recognition:  \na Systematic Review 2  \nAndrea Apicella, Pasquale Arpaia, Giovanni D’Errico, Davide Marocco, Giovanna Mastrati, Nicola Moccaldi, Roberto Prevete  \n• The non-stationarity of EEG signals can lead to the Dataset Shift problem.  \n• Transfer learning methods improve generalizability in EEG-based emotion classification.  \n• Adaptive feature extraction also in combination with transfer learning are promising for generalization.  \n2 This work has been submitted possible publication. Copyright may be transferred without notice.  \nThis preprint research paper has not been peer reviewed. Electronic copy available at: [https://ssrn.com/abstract=4474510](https://ssrn.com/abstract=4474510)  \nMachine Learning Strategies to Improve Cross-Subject and Cross-Session Generalization in EEG-based Emotion Recognition:  \na Systematic Review 1  \nAndrea Apicellaa , Pasquale Arpaiaa,d , Giovanni D’Erricob , Davide Maroccoc , Giovanna Mastratia , Nicola Moccaldia , Roberto Prevetea  \na Department of Electrical Engineering and Information Technology, University of Naples Federico II, Via Claudio, 21, Naples, 80138, Italy, b Department of Applied Science and Technology, Polytechnic University of  \nTurin, , Turin, 10129,, Italy  \nc Natural and Artificial Cognition Laboratory, University of Naples Federico  \nII, , Naples, 80133,, Italy  \nd Interdepartmental Research Center in Health Management and Innovation in Healthcare  \n(CIRMIS), University of Naples Federico II, Naples, 80138,, Italy  \nAbstract  \nA systematic review on machine-learning strategies for improving generalization in electroencephalography-based emotion classification was realized. In particular, cross-subject and cross-session generalization was focused. In this context, the non-stationarity of electroencephalographic (EEG) signals is a critical issue and can lead to the Dataset Shift problem. Several architectures and methods have been proposed to address this issue, mainly based on transfer learning methods. In this review, 418 papers were retrieved from the Scopus, IEEE Xplore, and PubMed databases through a search query focusing on modern machine learning techniques for generalization in EEGbased emotion assessment. Among these papers, 75 were found eligible based on their relevance to the problem. Studies lacking a specific cross-subject or cross-session validation strategy, or making use of oth","cbCaidpLVylIq0Ge","https://ap.wps.com/l/cbCaidpLVylIq0Ge","pdf",572325,1,66,"English","en",105,"# Introduction\n## Affective computing and emotion recognition\n# Problem Setting: Cross-subject and cross-session generalization\n## EEG non-stationarity and dataset shift\n# Systematic Review Methodology\n## Paper retrieval and eligibility criteria\n# Analysis Framework\n## Taxonomy of machine-learning approaches\n# Findings and Discussion\n## Classification accuracy and best-performing strategies\n## Impact of emotion models and participant screening","[{\"question\":\"What challenge does the review address in EEG-based emotion recognition?\",\"answer\":\"The review targets the Dataset Shift problem caused by EEG non-stationarity, emphasizing generalization across different subjects and different recording sessions.\"},{\"question\":\"How were papers selected for inclusion in the systematic review?\",\"answer\":\"A search across Scopus, IEEE Xplore, and PubMed retrieved 418 papers, and 75 were included after applying relevance-based eligibility criteria, excluding studies without proper cross-subject or cross-session validation and those relying on other biosignals.\"},{\"question\":\"Which methods are reported to perform best for cross-subject and cross-session generalization?\",\"answer\":\"The review identifies transfer learning approaches as generally performing better than other strategies in terms of average classification accuracy.\"},{\"question\":\"What factors are discussed as influencing classifier performance?\",\"answer\":\"The discussion covers the impact of emotion theoretical models and psychological screening of the experimental sample on classifier performances.\"}]","Machine Learning Strategies to Improve Cross-Subject and Cross-Session Generalization in EEG-Based Emotion Recognition - A Systematic Review | PDF",1785806972,166,{"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":90,"head_meta":92,"extra_data":94,"updated_unix":28},"machine-learning-strategies-to-improve-cross-subject-and-cross-session-generalization-in-eeg-based-emotion-recognition-a-systematic-review","",{"@graph":36,"@context":89},[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/machine-learning-strategies-to-improve-cross-subject-and-cross-session-generalization-in-eeg-based-emotion-recognition-a-systematic-review/121809/",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",[71,77,81,85],{"name":72,"@type":73,"acceptedAnswer":74},"What challenge does the review address in EEG-based emotion recognition?","Question",{"text":75,"@type":76},"The review targets the Dataset Shift problem caused by EEG non-stationarity, emphasizing generalization across different subjects and different recording sessions.","Answer",{"name":78,"@type":73,"acceptedAnswer":79},"How were papers selected for inclusion in the systematic review?",{"text":80,"@type":76},"A search across Scopus, IEEE Xplore, and PubMed retrieved 418 papers, and 75 were included after applying relevance-based eligibility criteria, excluding studies without proper cross-subject or cross-session validation and those relying on other biosignals.",{"name":82,"@type":73,"acceptedAnswer":83},"Which methods are reported to perform best for cross-subject and cross-session generalization?",{"text":84,"@type":76},"The review identifies transfer learning approaches as generally performing better than other strategies in terms of average classification accuracy.",{"name":86,"@type":73,"acceptedAnswer":87},"What factors are discussed as influencing classifier performance?",{"text":88,"@type":76},"The discussion covers the impact of emotion theoretical models and psychological screening of the experimental sample on classifier performances.","https://schema.org",{"og:url":52,"og:type":91,"og:title":13,"og:site_name":59,"og:description":14},"article",{"robots":93,"canonical":52},"index,follow",{"doc_id":7,"site_id":24},{"code":4,"msg":5,"data":96},[97,101,105,109,114,119,124,127,132,135,139],{"id":20,"doc_module":4,"doc_module_name":46,"category_name":98,"show_sort_weight":99,"slug":100},"Story & Novel",90,"story-novel",{"id":47,"doc_module":4,"doc_module_name":46,"category_name":102,"show_sort_weight":103,"slug":104},"Literature",80,"literature",{"id":53,"doc_module":4,"doc_module_name":46,"category_name":106,"show_sort_weight":107,"slug":108},"Exam",70,"exam",{"id":110,"doc_module":4,"doc_module_name":46,"category_name":111,"show_sort_weight":112,"slug":113},5,"Comic",60,"comic",{"id":115,"doc_module":4,"doc_module_name":46,"category_name":116,"show_sort_weight":117,"slug":118},6,"Technology",50,"technology",{"id":120,"doc_module":4,"doc_module_name":46,"category_name":121,"show_sort_weight":122,"slug":123},7,"Healthcare",40,"healthcare",{"id":11,"doc_module":4,"doc_module_name":46,"category_name":12,"show_sort_weight":125,"slug":126},30,"research-report",{"id":128,"doc_module":4,"doc_module_name":46,"category_name":129,"show_sort_weight":130,"slug":131},9,"Religion & Spirituality",20,"religion-spirituality",{"id":130,"doc_module":4,"doc_module_name":46,"category_name":133,"show_sort_weight":130,"slug":134},"World Cup","world-cup",{"id":136,"doc_module":4,"doc_module_name":46,"category_name":137,"show_sort_weight":136,"slug":138},10,"Lifestyle","lifestyle",{"id":140,"doc_module":4,"doc_module_name":46,"category_name":141,"show_sort_weight":110,"slug":142},19,"General","general"]