{"id":"https://openalex.org/W4389629118","doi":"https://doi.org/10.1109/icspis60075.2023.10344073","title":"Investigating The Impact of Sampling Techniques on an Imbalanced Classification Problem","display_name":"Investigating The Impact of Sampling Techniques on an Imbalanced Classification Problem","publication_year":2023,"publication_date":"2023-11-08","ids":{"openalex":"https://openalex.org/W4389629118","doi":"https://doi.org/10.1109/icspis60075.2023.10344073"},"language":"en","primary_location":{"id":"doi:10.1109/icspis60075.2023.10344073","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/icspis60075.2023.10344073","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 6th International Conference on Signal Processing and Information Security (ICSPIS)","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5050289622","display_name":"Dina Shehada","orcid":"https://orcid.org/0000-0002-7711-5389"},"institutions":[{"id":"https://openalex.org/I132806614","display_name":"University of Dubai","ror":"https://ror.org/05h0z7c09","country_code":"AE","type":"education","lineage":["https://openalex.org/I132806614"]},{"id":"https://openalex.org/I29891158","display_name":"University of Sharjah","ror":"https://ror.org/00engpz63","country_code":"AE","type":"education","lineage":["https://openalex.org/I29891158"]}],"countries":["AE"],"is_corresponding":true,"raw_author_name":"Dina Shehada","raw_affiliation_strings":["University of Sharjah,Department of Electrical Engineering,Sharjah,UAE","College of Engineering and IT, University of Dubai, Dubai, United Arab Emirates","Department of Electrical Engineering, University of Sharjah, Sharjah, UAE"],"affiliations":[{"raw_affiliation_string":"University of Sharjah,Department of Electrical Engineering,Sharjah,UAE","institution_ids":["https://openalex.org/I29891158"]},{"raw_affiliation_string":"College of Engineering and IT, University of Dubai, Dubai, United Arab Emirates","institution_ids":["https://openalex.org/I132806614"]},{"raw_affiliation_string":"Department of Electrical Engineering, University of Sharjah, Sharjah, UAE","institution_ids":["https://openalex.org/I29891158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5028235667","display_name":"Suadad Muammar","orcid":"https://orcid.org/0000-0002-4415-4445"},"institutions":[{"id":"https://openalex.org/I132806614","display_name":"University of Dubai","ror":"https://ror.org/05h0z7c09","country_code":"AE","type":"education","lineage":["https://openalex.org/I132806614"]}],"countries":["AE"],"is_corresponding":false,"raw_author_name":"Suadad Muammar","raw_affiliation_strings":["University of Dubai,College of Engineering and IT,Dubai,United Arab Emirates","College of Engineering and IT, University of Dubai, Dubai, United Arab Emirates"],"affiliations":[{"raw_affiliation_string":"University of Dubai,College of Engineering and IT,Dubai,United Arab Emirates","institution_ids":["https://openalex.org/I132806614"]},{"raw_affiliation_string":"College of Engineering and IT, University of Dubai, Dubai, United Arab Emirates","institution_ids":["https://openalex.org/I132806614"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5092316391","display_name":"Maryam Ali Amour","orcid":null},"institutions":[{"id":"https://openalex.org/I132806614","display_name":"University of Dubai","ror":"https://ror.org/05h0z7c09","country_code":"AE","type":"education","lineage":["https://openalex.org/I132806614"]}],"countries":["AE"],"is_corresponding":false,"raw_author_name":"Maryam Ali Amour","raw_affiliation_strings":["University of Dubai,College of Engineering and IT,Dubai,United Arab Emirates","College of Engineering and IT, University of Dubai, Dubai, United Arab Emirates"],"affiliations":[{"raw_affiliation_string":"University of Dubai,College of Engineering and IT,Dubai,United Arab Emirates","institution_ids":["https://openalex.org/I132806614"]},{"raw_affiliation_string":"College of Engineering and IT, University of Dubai, Dubai, United Arab Emirates","institution_ids":["https://openalex.org/I132806614"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5033623398","display_name":"Ahmed Bouridane","orcid":"https://orcid.org/0000-0002-1474-2772"},"institutions":[{"id":"https://openalex.org/I29891158","display_name":"University of Sharjah","ror":"https://ror.org/00engpz63","country_code":"AE","type":"education","lineage":["https://openalex.org/I29891158"]}],"countries":["AE"],"is_corresponding":false,"raw_author_name":"Ahmed Bouridane","raw_affiliation_strings":["University of Sharjah,Centre for Data Analytics and Cybersecurity,Sharjah,UAE","Centre for Data Analytics and Cybersecurity, University of Sharjah, Sharjah, UAE"],"affiliations":[{"raw_affiliation_string":"University of Sharjah,Centre for Data Analytics and Cybersecurity,Sharjah,UAE","institution_ids":["https://openalex.org/I29891158"]},{"raw_affiliation_string":"Centre for Data Analytics and Cybersecurity, University of Sharjah, Sharjah, UAE","institution_ids":["https://openalex.org/I29891158"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5050289622"],"corresponding_institution_ids":["https://openalex.org/I132806614","https://openalex.org/I29891158"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.17092653,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"39","last_page":"44"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11652","display_name":"Imbalanced Data Classification Techniques","score":0.9998000264167786,"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":0.9998000264167786,"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":0.9778000116348267,"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/T11396","display_name":"Artificial Intelligence in Healthcare","score":0.9598000049591064,"subfield":{"id":"https://openalex.org/subfields/3605","display_name":"Health Information Management"},"field":{"id":"https://openalex.org/fields/36","display_name":"Health Professions"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/random-forest","display_name":"Random forest","score":0.7545307874679565},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6750407218933105},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6451712250709534},{"id":"https://openalex.org/keywords/sampling","display_name":"Sampling (signal processing)","score":0.5786665081977844},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.546721339225769},{"id":"https://openalex.org/keywords/confusion-matrix","display_name":"Confusion matrix","score":0.5462424755096436},{"id":"https://openalex.org/keywords/oversampling","display_name":"Oversampling","score":0.533701479434967},{"id":"https://openalex.org/keywords/statistical-classification","display_name":"Statistical classification","score":0.5293011665344238},{"id":"https://openalex.org/keywords/logistic-regression","display_name":"Logistic regression","score":0.5079541802406311},{"id":"https://openalex.org/keywords/class","display_name":"Class (philosophy)","score":0.5039400458335876},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.5034360289573669},{"id":"https://openalex.org/keywords/binary-classification","display_name":"Binary classification","score":0.48973870277404785},{"id":"https://openalex.org/keywords/support-vector-machine","display_name":"Support vector machine","score":0.44815054535865784},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.3971412777900696},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.3225136995315552},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.2534193992614746},{"id":"https://openalex.org/keywords/bandwidth","display_name":"Bandwidth (computing)","score":0.0702829658985138}],"concepts":[{"id":"https://openalex.org/C169258074","wikidata":"https://www.wikidata.org/wiki/Q245748","display_name":"Random forest","level":2,"score":0.7545307874679565},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6750407218933105},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6451712250709534},{"id":"https://openalex.org/C140779682","wikidata":"https://www.wikidata.org/wiki/Q210868","display_name":"Sampling (signal processing)","level":3,"score":0.5786665081977844},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.546721339225769},{"id":"https://openalex.org/C138602881","wikidata":"https://www.wikidata.org/wiki/Q2709591","display_name":"Confusion matrix","level":2,"score":0.5462424755096436},{"id":"https://openalex.org/C197323446","wikidata":"https://www.wikidata.org/wiki/Q331222","display_name":"Oversampling","level":3,"score":0.533701479434967},{"id":"https://openalex.org/C110083411","wikidata":"https://www.wikidata.org/wiki/Q1744628","display_name":"Statistical classification","level":2,"score":0.5293011665344238},{"id":"https://openalex.org/C151956035","wikidata":"https://www.wikidata.org/wiki/Q1132755","display_name":"Logistic regression","level":2,"score":0.5079541802406311},{"id":"https://openalex.org/C2777212361","wikidata":"https://www.wikidata.org/wiki/Q5127848","display_name":"Class (philosophy)","level":2,"score":0.5039400458335876},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5034360289573669},{"id":"https://openalex.org/C66905080","wikidata":"https://www.wikidata.org/wiki/Q17005494","display_name":"Binary classification","level":3,"score":0.48973870277404785},{"id":"https://openalex.org/C12267149","wikidata":"https://www.wikidata.org/wiki/Q282453","display_name":"Support vector machine","level":2,"score":0.44815054535865784},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3971412777900696},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.3225136995315552},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.2534193992614746},{"id":"https://openalex.org/C2776257435","wikidata":"https://www.wikidata.org/wiki/Q1576430","display_name":"Bandwidth (computing)","level":2,"score":0.0702829658985138},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.0},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.0},{"id":"https://openalex.org/C106131492","wikidata":"https://www.wikidata.org/wiki/Q3072260","display_name":"Filter (signal processing)","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icspis60075.2023.10344073","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/icspis60075.2023.10344073","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 6th International Conference on Signal Processing and Information Security (ICSPIS)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":16,"referenced_works":["https://openalex.org/W1590481709","https://openalex.org/W1831729862","https://openalex.org/W2151356078","https://openalex.org/W2767067603","https://openalex.org/W2903362744","https://openalex.org/W2944160380","https://openalex.org/W3001069493","https://openalex.org/W3021580884","https://openalex.org/W3022860870","https://openalex.org/W3026915425","https://openalex.org/W3137097829","https://openalex.org/W3210673220","https://openalex.org/W4200584662","https://openalex.org/W4214927009","https://openalex.org/W4221101983","https://openalex.org/W6601269736"],"related_works":["https://openalex.org/W4401045170","https://openalex.org/W3172259201","https://openalex.org/W2903618681","https://openalex.org/W3184937791","https://openalex.org/W4401052546","https://openalex.org/W4205685985","https://openalex.org/W4288025700","https://openalex.org/W4386210978","https://openalex.org/W3011239835","https://openalex.org/W4401361218"],"abstract_inverted_index":{"Classification":[0],"with":[1,29,37,62],"imbalanced":[2,21,53,59,89,119,171],"datasets":[3],"can":[4,10,19],"be":[5],"quite":[6],"challenging":[7],"as":[8],"it":[9],"make":[11],"classifiers":[12,185],"biased":[13],"towards":[14],"the":[15,30,43,46,52,66,70,77,82,88,116,125,134,170,188,195],"majority":[16],"class.":[17,32,84],"This":[18,33],"cause":[20],"classification,":[22],"which":[23,147],"indicates":[24],"poor":[25],"predictive":[26],"performance,":[27],"particularly":[28],"minority":[31],"paper":[34],"is":[35,137,141],"concerned":[36],"a":[38],"comparative":[39],"study":[40],"to":[41,50,73,81,114,193],"investigate":[42],"impact":[44,86],"of":[45,56,69,87,118,124,127],"different":[47],"sampling":[48,135],"techniques":[49,136],"address":[51],"classification":[54,95,175],"problem":[55,117],"an":[57],"extremely":[58],"binary":[60],"dataset":[61,90],"284,807":[63],"instances.":[64],"In":[65],"dataset,":[67],"99.83%":[68],"samples":[71],"belong":[72,80],"one":[74],"class":[75],"and":[76,101,109,131,156,182],"remaining":[78],"0.17%":[79],"other":[83],"The":[85,139,173],"was":[91,166],"studied":[92],"on":[93,144],"three":[94],"algorithms:":[96],"Logistic":[97,164],"Regression,":[98],"K-Nearest":[99,180],"Neighbor,":[100],"Random":[102,183,189],"Forest.":[103],"Moreover,":[104],"Over":[105,190],"Sampling,":[106,108,111],"Under":[107,158],"Hybrid":[110],"were":[112,177],"applied":[113],"tackle":[115],"classification.":[120],"A":[121],"detailed":[122],"evaluation":[123],"performance":[126,140],"each":[128],"algorithm,":[129],"before":[130],"after":[132],"applying":[133,187],"provided.":[138],"evaluated":[142],"based":[143],"six":[145],"metrics":[146],"are:":[148],"Confusion":[149],"Matrix,":[150],"Accuracy,":[151],"Recall,":[152],"Precision,":[153],"F1":[154],"Score,":[155],"Area":[157],"Precision-Recall":[159],"Curve.":[160],"Results":[161],"showed":[162],"that":[163],"Regression":[165],"heavily":[167],"impacted":[168],"by":[169,179],"dataset.":[172,196],"best":[174],"results":[176],"achieved":[178],"Neighbor":[181],"Forest":[184],"when":[186],"Sampling":[191],"technique":[192],"balance":[194]},"counts_by_year":[],"updated_date":"2025-12-19T19:40:27.379048","created_date":"2025-10-10T00:00:00"}