{"id":"https://openalex.org/W4406458740","doi":"https://doi.org/10.1109/bigdata62323.2024.10825319","title":"Lightweight Transformer exhibits comparable performance to LLMs for Seizure Prediction: A case for light-weight models for EEG data","display_name":"Lightweight Transformer exhibits comparable performance to LLMs for Seizure Prediction: A case for light-weight models for EEG data","publication_year":2024,"publication_date":"2024-12-15","ids":{"openalex":"https://openalex.org/W4406458740","doi":"https://doi.org/10.1109/bigdata62323.2024.10825319","pmid":"https://pubmed.ncbi.nlm.nih.gov/40041397"},"language":"en","primary_location":{"id":"doi:10.1109/bigdata62323.2024.10825319","is_oa":false,"landing_page_url":"https://doi.org/10.1109/bigdata62323.2024.10825319","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE International Conference on Big Data (BigData)","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref","pubmed"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://pmc.ncbi.nlm.nih.gov/articles/PMC11877310/pdf/nihms-2060447.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5114519469","display_name":"Paras Parani","orcid":null},"institutions":[{"id":"https://openalex.org/I19700959","display_name":"Florida International University","ror":"https://ror.org/02gz6gg07","country_code":"US","type":"education","lineage":["https://openalex.org/I19700959"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Paras Parani","raw_affiliation_strings":["Florida International University,Knight Foundation School of Computing and Information Sciences,Miami,FL,USA,33172"],"affiliations":[{"raw_affiliation_string":"Florida International University,Knight Foundation School of Computing and Information Sciences,Miami,FL,USA,33172","institution_ids":["https://openalex.org/I19700959"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5061493358","display_name":"Umair Mohammad","orcid":"https://orcid.org/0000-0002-4499-548X"},"institutions":[{"id":"https://openalex.org/I19700959","display_name":"Florida International University","ror":"https://ror.org/02gz6gg07","country_code":"US","type":"education","lineage":["https://openalex.org/I19700959"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Umair Mohammad","raw_affiliation_strings":["Florida International University,Knight Foundation School of Computing and Information Sciences,Miami,FL,USA,33172"],"affiliations":[{"raw_affiliation_string":"Florida International University,Knight Foundation School of Computing and Information Sciences,Miami,FL,USA,33172","institution_ids":["https://openalex.org/I19700959"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5102729196","display_name":"Fahad Saeed","orcid":"https://orcid.org/0000-0002-3410-9552"},"institutions":[{"id":"https://openalex.org/I19700959","display_name":"Florida International University","ror":"https://ror.org/02gz6gg07","country_code":"US","type":"education","lineage":["https://openalex.org/I19700959"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Fahad Saeed","raw_affiliation_strings":["Florida International University,Knight Foundation School of Computing and Information Sciences,Miami,FL,USA,33172"],"affiliations":[{"raw_affiliation_string":"Florida International University,Knight Foundation School of Computing and Information Sciences,Miami,FL,USA,33172","institution_ids":["https://openalex.org/I19700959"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5114519469"],"corresponding_institution_ids":["https://openalex.org/I19700959"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.26374825,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"2024","issue":null,"first_page":"4941","last_page":"4945"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10429","display_name":"EEG and Brain-Computer Interfaces","score":1.0,"subfield":{"id":"https://openalex.org/subfields/2805","display_name":"Cognitive Neuroscience"},"field":{"id":"https://openalex.org/fields/28","display_name":"Neuroscience"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},"topics":[{"id":"https://openalex.org/T10429","display_name":"EEG and Brain-Computer Interfaces","score":1.0,"subfield":{"id":"https://openalex.org/subfields/2805","display_name":"Cognitive Neuroscience"},"field":{"id":"https://openalex.org/fields/28","display_name":"Neuroscience"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},{"id":"https://openalex.org/T10241","display_name":"Functional Brain Connectivity Studies","score":0.9925000071525574,"subfield":{"id":"https://openalex.org/subfields/2805","display_name":"Cognitive Neuroscience"},"field":{"id":"https://openalex.org/fields/28","display_name":"Neuroscience"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},{"id":"https://openalex.org/T11447","display_name":"Blind Source Separation Techniques","score":0.9923999905586243,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.7231584787368774},{"id":"https://openalex.org/keywords/electroencephalography","display_name":"Electroencephalography","score":0.6384930610656738},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.44922250509262085},{"id":"https://openalex.org/keywords/electrical-engineering","display_name":"Electrical engineering","score":0.1812903881072998},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.17985373735427856},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.15631723403930664},{"id":"https://openalex.org/keywords/neuroscience","display_name":"Neuroscience","score":0.12127092480659485},{"id":"https://openalex.org/keywords/voltage","display_name":"Voltage","score":0.07552477717399597}],"concepts":[{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.7231584787368774},{"id":"https://openalex.org/C522805319","wikidata":"https://www.wikidata.org/wiki/Q179965","display_name":"Electroencephalography","level":2,"score":0.6384930610656738},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.44922250509262085},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.1812903881072998},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.17985373735427856},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.15631723403930664},{"id":"https://openalex.org/C169760540","wikidata":"https://www.wikidata.org/wiki/Q207011","display_name":"Neuroscience","level":1,"score":0.12127092480659485},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.07552477717399597}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/bigdata62323.2024.10825319","is_oa":false,"landing_page_url":"https://doi.org/10.1109/bigdata62323.2024.10825319","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE International Conference on Big Data (BigData)","raw_type":"proceedings-article"},{"id":"pmid:40041397","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/40041397","pdf_url":null,"source":{"id":"https://openalex.org/S4306525036","display_name":"PubMed","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings : ... IEEE International Conference on Big Data. IEEE International Conference on Big Data","raw_type":null},{"id":"pmh:oai:pubmedcentral.nih.gov:11877310","is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/11877310","pdf_url":"https://pmc.ncbi.nlm.nih.gov/articles/PMC11877310/pdf/nihms-2060447.pdf","source":{"id":"https://openalex.org/S2764455111","display_name":"PubMed Central","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Proc IEEE Int Conf Big Data","raw_type":"Text"}],"best_oa_location":{"id":"pmh:oai:pubmedcentral.nih.gov:11877310","is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/11877310","pdf_url":"https://pmc.ncbi.nlm.nih.gov/articles/PMC11877310/pdf/nihms-2060447.pdf","source":{"id":"https://openalex.org/S2764455111","display_name":"PubMed Central","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Proc IEEE Int Conf Big Data","raw_type":"Text"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G2304404479","display_name":null,"funder_award_id":"OAC-2312599","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G4895449648","display_name":"PFI-TT: Artificial Intelligence-enabled Real-time System for Early Epileptic Seizure Detection and Prediction","funder_award_id":"2213951","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G5558737376","display_name":"OAC Core: High Performance Computing Algorithms and Software for large-scale Mass Spectrometry based Omics","funder_award_id":"2312599","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G848032724","display_name":null,"funder_award_id":"Science","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G8932077419","display_name":null,"funder_award_id":"R35GM153434","funder_id":"https://openalex.org/F4320332161","funder_display_name":"National Institutes of Health"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320332161","display_name":"National Institutes of Health","ror":"https://ror.org/01cwqze88"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4406458740.pdf","grobid_xml":"https://content.openalex.org/works/W4406458740.grobid-xml"},"referenced_works_count":21,"referenced_works":["https://openalex.org/W2962984603","https://openalex.org/W3015468748","https://openalex.org/W3127389222","https://openalex.org/W3185809598","https://openalex.org/W3206153821","https://openalex.org/W4200479248","https://openalex.org/W4221091728","https://openalex.org/W4225868465","https://openalex.org/W4312349930","https://openalex.org/W4381327766","https://openalex.org/W4382203064","https://openalex.org/W4387385719","https://openalex.org/W4390204163","https://openalex.org/W4398787758","https://openalex.org/W6680455596","https://openalex.org/W6776048684","https://openalex.org/W6784333009","https://openalex.org/W6797399245","https://openalex.org/W6846872050","https://openalex.org/W6870184644","https://openalex.org/W6873445898"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2922348724","https://openalex.org/W200322357","https://openalex.org/W2390279801","https://openalex.org/W2130428257","https://openalex.org/W4391913857","https://openalex.org/W4308951944","https://openalex.org/W2358668433"],"abstract_inverted_index":{"Predicting":[0],"seizures":[1,65],"ahead":[2],"of":[3,69,88,99,104,165,218,228],"time":[4],"will":[5,111],"have":[6,52],"a":[7,129,144,174,180,186],"significant":[8],"positive":[9],"clinical":[10],"impact":[11],"for":[12,221,249,265],"people":[13],"with":[14,55,173,224],"epilepsy.":[15],"Advances":[16],"in":[17,116,137,152,158,216],"machine":[18],"learning/artificial":[19],"intelligence":[20],"(ML/AI)":[21],"has":[22],"provided":[23],"us":[24],"the":[25,42,67,78,86,138,159,163,198,213,232,237,243],"tools":[26],"needed":[27,149],"to":[28,113,150,155,231,236,242],"perform":[29,114],"such":[30,40],"predictive":[31],"tasks.":[32],"To":[33,123,161],"date,":[34],"advanced":[35],"deep":[36],"learning":[37],"(DL)":[38],"architectures":[39],"as":[41],"convolutional":[43],"neural":[44,177],"network":[45,178],"(CNN)":[46],"and":[47,95,102,140,143,185,239,246],"long":[48],"short-term":[49],"memory":[50],"(LSTM)":[51],"been":[53],"used":[54],"mixed":[56],"results.":[57],"However,":[58],"highly":[59],"connected":[60],"activity":[61],"exhibited":[62],"by":[63],"epileptic":[64],"necessitates":[66],"design":[68],"more":[70],"complex":[71,79],"ML":[72],"techniques":[73],"which":[74,196],"can":[75],"better":[76],"capture":[77],"interconnected":[80],"neurological":[81],"processes.":[82],"Other":[83],"challenges":[84],"include":[85],"variability":[87],"EEG":[89],"sensor":[90],"data":[91],"quality,":[92],"different":[93],"epilepsy":[94],"seizure":[96,201,268],"profiles,":[97],"lack":[98],"annotated":[100],"datasets":[101],"absence":[103],"ML-ready":[105],"benchmarks.":[106,206,251],"In":[107],"addition,":[108],"successful":[109],"models":[110,264],"need":[112],"inference":[115],"almost":[117],"real-time":[118,153,266],"using":[119],"limited":[120],"hardware":[121],"compute-capacity.":[122],"address":[124],"these":[125],"challenges,":[126],"we":[127,169],"propose":[128],"lightweight":[130,167,256],"architecture,":[131],"called":[132],"<i>ESPFormer</i>,":[133],"whose":[134],"novelty":[135],"lies":[136],"simple":[139],"smaller":[141],"model-size":[142],"lower":[145],"computational":[146],"load":[147],"footprint":[148],"infer":[151],"compared":[154,170,230,235,241],"other":[156,250],"works":[157],"literature.":[160],"quantify":[162],"performance":[164,172,215],"this":[166],"model,":[168],"its":[171],"custom-designed":[175],"residual":[176],"(ResNet),":[179],"pre-trained":[181,187],"vision":[182],"transformer":[183,257],"(ViT)":[184],"large-language":[188],"model":[189],"(LLM).":[190],"We":[191],"tested":[192],"ESPFormer":[193,211],"on":[194],"MLSPred-Bench":[195],"is":[197],"largest":[199],"patient-independent":[200],"prediction":[202,219],"dataset":[203],"comprising":[204],"12":[205],"Our":[207,252],"results":[208,248,253],"demonstrate":[209],"that":[210,255],"provides":[212],"best":[214],"terms":[217],"accuracy":[220],"4/12":[222],"benchmarks":[223],"an":[225],"average":[226],"improvement":[227],"2.65%":[229],"LLM,":[233],"3.35%":[234],"ViT":[238],"17.65%":[240],"ResNet":[244],"-":[245],"comparable":[247],"indicate":[254],"architecture":[258],"may":[259],"outperform":[260],"resource-intensive":[261],"LLM":[262],"based":[263],"EEG-based":[267],"predictions.":[269]},"counts_by_year":[],"updated_date":"2026-04-10T15:06:20.359241","created_date":"2025-10-10T00:00:00"}