{"id":"https://openalex.org/W4406814831","doi":"https://doi.org/10.1145/3704289.3704292","title":"Assessing the Effect of Data Complexity and Instance Overlap Issues on Imbalanced Learning","display_name":"Assessing the Effect of Data Complexity and Instance Overlap Issues on Imbalanced Learning","publication_year":2024,"publication_date":"2024-09-24","ids":{"openalex":"https://openalex.org/W4406814831","doi":"https://doi.org/10.1145/3704289.3704292"},"language":"en","primary_location":{"id":"doi:10.1145/3704289.3704292","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3704289.3704292","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2024 7th International Conference on Big Data and Education","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1145/3704289.3704292","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5103718998","display_name":"Mohd Alauddin Mohd Ali","orcid":"https://orcid.org/0000-0001-6423-2562"},"institutions":[{"id":"https://openalex.org/I138801177","display_name":"University of Ulster","ror":"https://ror.org/01yp9g959","country_code":"GB","type":"education","lineage":["https://openalex.org/I138801177"]}],"countries":["GB"],"is_corresponding":true,"raw_author_name":"Muhammad Asim Ali","raw_affiliation_strings":["Computer Science, Ulster University, Belfast, Antrium, United Kingdom"],"raw_orcid":"https://orcid.org/0000-0001-6423-2562","affiliations":[{"raw_affiliation_string":"Computer Science, Ulster University, Belfast, Antrium, United Kingdom","institution_ids":["https://openalex.org/I138801177"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100361707","display_name":"Jun Liu","orcid":"https://orcid.org/0000-0001-8859-5405"},"institutions":[{"id":"https://openalex.org/I138801177","display_name":"University of Ulster","ror":"https://ror.org/01yp9g959","country_code":"GB","type":"education","lineage":["https://openalex.org/I138801177"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Jun Liu","raw_affiliation_strings":["Computer Science, Ulster University, Belfast, Antrium, United Kingdom"],"raw_orcid":"https://orcid.org/0000-0001-8859-5405","affiliations":[{"raw_affiliation_string":"Computer Science, Ulster University, Belfast, Antrium, United Kingdom","institution_ids":["https://openalex.org/I138801177"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5011992029","display_name":"Samuel A. Moore","orcid":"https://orcid.org/0000-0001-7417-8248"},"institutions":[{"id":"https://openalex.org/I138801177","display_name":"University of Ulster","ror":"https://ror.org/01yp9g959","country_code":"GB","type":"education","lineage":["https://openalex.org/I138801177"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Samuel Moore","raw_affiliation_strings":["Computer Science, Ulster University, Belfast, Antrium, United Kingdom"],"raw_orcid":"https://orcid.org/0000-0001-7417-8248","affiliations":[{"raw_affiliation_string":"Computer Science, Ulster University, Belfast, Antrium, United Kingdom","institution_ids":["https://openalex.org/I138801177"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5030458751","display_name":"Omar Nibouche","orcid":"https://orcid.org/0000-0003-2149-2975"},"institutions":[{"id":"https://openalex.org/I138801177","display_name":"University of Ulster","ror":"https://ror.org/01yp9g959","country_code":"GB","type":"education","lineage":["https://openalex.org/I138801177"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Omar Nibouche","raw_affiliation_strings":["Computer Science, Ulster University, Belfast, Antrium, United Kingdom"],"raw_orcid":"https://orcid.org/0000-0003-2149-2975","affiliations":[{"raw_affiliation_string":"Computer Science, Ulster University, Belfast, Antrium, United Kingdom","institution_ids":["https://openalex.org/I138801177"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5103718998"],"corresponding_institution_ids":["https://openalex.org/I138801177"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.23486592,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"49","last_page":"56"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11652","display_name":"Imbalanced Data Classification Techniques","score":0.9995999932289124,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T11652","display_name":"Imbalanced Data Classification Techniques","score":0.9995999932289124,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T13429","display_name":"Electricity Theft Detection Techniques","score":0.9674999713897705,"subfield":{"id":"https://openalex.org/subfields/2208","display_name":"Electrical and Electronic Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T12535","display_name":"Machine Learning and Data Classification","score":0.9031999707221985,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"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/computer-science","display_name":"Computer science","score":0.7162247896194458},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.5260767340660095},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5209023356437683},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.3243541121482849}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7162247896194458},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5260767340660095},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5209023356437683},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3243541121482849}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3704289.3704292","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3704289.3704292","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2024 7th International Conference on Big Data and Education","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3704289.3704292","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3704289.3704292","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2024 7th International Conference on Big Data and Education","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":19,"referenced_works":["https://openalex.org/W43871266","https://openalex.org/W142793689","https://openalex.org/W1993220166","https://openalex.org/W2045042261","https://openalex.org/W2125877832","https://openalex.org/W2148143831","https://openalex.org/W2902777483","https://openalex.org/W2973136425","https://openalex.org/W2992345747","https://openalex.org/W3112652185","https://openalex.org/W3199816041","https://openalex.org/W3217799297","https://openalex.org/W4220717373","https://openalex.org/W4224023078","https://openalex.org/W4243367342","https://openalex.org/W4310064572","https://openalex.org/W4365395051","https://openalex.org/W4385740286","https://openalex.org/W4389513437"],"related_works":["https://openalex.org/W2961085424","https://openalex.org/W4306674287","https://openalex.org/W4387369504","https://openalex.org/W3046775127","https://openalex.org/W4394896187","https://openalex.org/W3170094116","https://openalex.org/W4386462264","https://openalex.org/W3107602296","https://openalex.org/W4364306694","https://openalex.org/W4312192474"],"abstract_inverted_index":{"Most":[0],"machine":[1,118],"learning":[2,119],"(ML)":[3],"algorithms":[4,233],"work":[5],"best":[6],"when":[7],"the":[8,24,35,60,67,71,82,109,126,140,171,183,187,197,218,223,238],"samples":[9,22,65,89],"in":[10,59,90,117,142],"each":[11],"class":[12,62,69],"are":[13,48,73,114],"almost":[14],"equal.":[15],"However,":[16,75],"if":[17],"a":[18,29,41,91,112,129,178],"dataset":[19,83,92,104,141,207],"has":[20],"imbalanced":[21,206,213],"then":[23],"ML":[25,232],"model":[26],"can":[27,80,138],"achieve":[28],"high":[30,42],"accuracy":[31,203],"by":[32,55,85,107,153],"just":[33],"predicting":[34],"majority":[36,68],"of":[37,111,128,144,222],"classes":[38,72],"and":[39,98,147,167,186,190,231],"achieving":[40],"classifier":[43],"performance.":[44],"Different":[45],"resampling":[46,78,136,184],"methods":[47,79,137,185,230],"used":[49,116],"to":[50,124,159,211,217],"handle":[51],"this":[52],"imbalance":[53],"issue":[54],"creating":[56,86],"synthetic":[57,87],"data":[58,88,100,160],"minority":[61],"or":[63],"removing":[64],"from":[66,96,164,170],"until":[70],"balanced.":[74],"using":[76],"these":[77],"harm":[81],"performance":[84],"that":[93,196,228],"already":[94],"suffers":[95],"overlap":[97],"other":[99,219],"intrinsic":[101,122,220],"issues.":[102],"Recently,":[103],"complexity":[105,161,189],"measures,":[106],"observing":[108],"characteristics":[110,221],"dataset,":[113],"often":[115],"tasks":[120],"as":[121],"descriptors":[123],"calculate":[125],"difficulty":[127],"classification":[130,148,191,202],"problem.":[131],"This":[132,150],"study":[133],"investigates":[134],"how":[135],"affect":[139],"terms":[143],"complexity,":[145],"overlapping,":[146],"accuracy.":[149,192],"is":[151,208],"achieved":[152],"monitoring":[154],"22":[155],"different":[156],"measurements":[157],"related":[158],"measures":[162],"obtained":[163],"20":[165],"public":[166],"pre-processed":[168],"datasets":[169],"KEEL":[172],"repository.":[173],"Our":[174],"empirical":[175],"findings":[176],"demonstrate":[177],"strong":[179],"positive":[180],"correlation":[181],"between":[182],"dataset's":[188,239],"We":[193],"also":[194],"posit":[195],"main":[198],"reason":[199],"for":[200],"poor":[201],"on":[204,237,246],"an":[205,247],"not":[209],"due":[210,216],"its":[212],"nature":[214],"but":[215],"dataset.":[224],"Finally,":[225],"we":[226],"advocate":[227],"pre-processing":[229],"should":[234],"be":[235],"based":[236],"specific":[240],"properties,":[241],"rather":[242],"than":[243],"being":[244],"chosen":[245],"ad":[248],"hoc":[249],"basis.":[250]},"counts_by_year":[],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}