{"id":"https://openalex.org/W2945346640","doi":"https://doi.org/10.1145/3316615.3316641","title":"An Improved Over-sampling Algorithm based on iForest and SMOTE","display_name":"An Improved Over-sampling Algorithm based on iForest and SMOTE","publication_year":2019,"publication_date":"2019-02-19","ids":{"openalex":"https://openalex.org/W2945346640","doi":"https://doi.org/10.1145/3316615.3316641","mag":"2945346640"},"language":"en","primary_location":{"id":"doi:10.1145/3316615.3316641","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3316615.3316641","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2019 8th International Conference on Software and Computer Applications","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/A5017426295","display_name":"Yifeng Zheng","orcid":"https://orcid.org/0000-0001-9884-2481"},"institutions":[{"id":"https://openalex.org/I204553293","display_name":"China University of Petroleum, Beijing","ror":"https://ror.org/041qf4r12","country_code":"CN","type":"education","lineage":["https://openalex.org/I204553293"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Yifeng Zheng","raw_affiliation_strings":["College of Information Science and Engineering, China University of Petroleum, Beijing, China, Beijing Key Lab of Data Mining for Petroleum Data, China University of Petroleum, Beijing, China"],"affiliations":[{"raw_affiliation_string":"College of Information Science and Engineering, China University of Petroleum, Beijing, China, Beijing Key Lab of Data Mining for Petroleum Data, China University of Petroleum, Beijing, China","institution_ids":["https://openalex.org/I204553293"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102844195","display_name":"Guohe Li","orcid":"https://orcid.org/0009-0008-9982-4478"},"institutions":[{"id":"https://openalex.org/I204553293","display_name":"China University of Petroleum, Beijing","ror":"https://ror.org/041qf4r12","country_code":"CN","type":"education","lineage":["https://openalex.org/I204553293"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Guohe Li","raw_affiliation_strings":["College of Information Science and Engineering, China University of Petroleum, Beijing, China, Beijing Key Lab of Data Mining for Petroleum Data, China University of Petroleum, Beijing, China"],"affiliations":[{"raw_affiliation_string":"College of Information Science and Engineering, China University of Petroleum, Beijing, China, Beijing Key Lab of Data Mining for Petroleum Data, China University of Petroleum, Beijing, China","institution_ids":["https://openalex.org/I204553293"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100372518","display_name":"Teng Zhang","orcid":"https://orcid.org/0000-0003-1870-1051"},"institutions":[{"id":"https://openalex.org/I204553293","display_name":"China University of Petroleum, Beijing","ror":"https://ror.org/041qf4r12","country_code":"CN","type":"education","lineage":["https://openalex.org/I204553293"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Teng Zhang","raw_affiliation_strings":["College of Information Science and Engineering, China University of Petroleum, Beijing, China, Beijing Key Lab of Data Mining for Petroleum Data, China University of Petroleum, Beijing, China"],"affiliations":[{"raw_affiliation_string":"College of Information Science and Engineering, China University of Petroleum, Beijing, China, Beijing Key Lab of Data Mining for Petroleum Data, China University of Petroleum, Beijing, China","institution_ids":["https://openalex.org/I204553293"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5017426295"],"corresponding_institution_ids":["https://openalex.org/I204553293"],"apc_list":null,"apc_paid":null,"fwci":0.4201,"has_fulltext":false,"cited_by_count":8,"citation_normalized_percentile":{"value":0.69957023,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"75","last_page":"80"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11652","display_name":"Imbalanced Data Classification Techniques","score":0.9997000098228455,"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":0.9997000098228455,"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/T11512","display_name":"Anomaly Detection Techniques and Applications","score":0.9815000295639038,"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/T11550","display_name":"Text and Document Classification Technologies","score":0.9732000231742859,"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/sample","display_name":"Sample (material)","score":0.7293784618377686},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6879932880401611},{"id":"https://openalex.org/keywords/oversampling","display_name":"Oversampling","score":0.6652891039848328},{"id":"https://openalex.org/keywords/interpolation","display_name":"Interpolation (computer graphics)","score":0.628436803817749},{"id":"https://openalex.org/keywords/roulette","display_name":"Roulette","score":0.6207706928253174},{"id":"https://openalex.org/keywords/sampling","display_name":"Sampling (signal processing)","score":0.6053047180175781},{"id":"https://openalex.org/keywords/selection","display_name":"Selection (genetic algorithm)","score":0.5556850433349609},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5505212545394897},{"id":"https://openalex.org/keywords/sampling-distribution","display_name":"Sampling distribution","score":0.5036892294883728},{"id":"https://openalex.org/keywords/class","display_name":"Class (philosophy)","score":0.4926500916481018},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.45820310711860657},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.4505399763584137},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.44115710258483887},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.42592933773994446},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.3825869560241699},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.21557852625846863},{"id":"https://openalex.org/keywords/filter","display_name":"Filter (signal processing)","score":0.21239310503005981},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.1358337700366974},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.09963035583496094},{"id":"https://openalex.org/keywords/bandwidth","display_name":"Bandwidth (computing)","score":0.08669203519821167}],"concepts":[{"id":"https://openalex.org/C198531522","wikidata":"https://www.wikidata.org/wiki/Q485146","display_name":"Sample (material)","level":2,"score":0.7293784618377686},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6879932880401611},{"id":"https://openalex.org/C197323446","wikidata":"https://www.wikidata.org/wiki/Q331222","display_name":"Oversampling","level":3,"score":0.6652891039848328},{"id":"https://openalex.org/C137800194","wikidata":"https://www.wikidata.org/wiki/Q11713455","display_name":"Interpolation (computer graphics)","level":3,"score":0.628436803817749},{"id":"https://openalex.org/C195502155","wikidata":"https://www.wikidata.org/wiki/Q2810237","display_name":"Roulette","level":2,"score":0.6207706928253174},{"id":"https://openalex.org/C140779682","wikidata":"https://www.wikidata.org/wiki/Q210868","display_name":"Sampling (signal processing)","level":3,"score":0.6053047180175781},{"id":"https://openalex.org/C81917197","wikidata":"https://www.wikidata.org/wiki/Q628760","display_name":"Selection (genetic algorithm)","level":2,"score":0.5556850433349609},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5505212545394897},{"id":"https://openalex.org/C167723999","wikidata":"https://www.wikidata.org/wiki/Q3773214","display_name":"Sampling distribution","level":2,"score":0.5036892294883728},{"id":"https://openalex.org/C2777212361","wikidata":"https://www.wikidata.org/wiki/Q5127848","display_name":"Class (philosophy)","level":2,"score":0.4926500916481018},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.45820310711860657},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.4505399763584137},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.44115710258483887},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.42592933773994446},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.3825869560241699},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.21557852625846863},{"id":"https://openalex.org/C106131492","wikidata":"https://www.wikidata.org/wiki/Q3072260","display_name":"Filter (signal processing)","level":2,"score":0.21239310503005981},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.1358337700366974},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.09963035583496094},{"id":"https://openalex.org/C2776257435","wikidata":"https://www.wikidata.org/wiki/Q1576430","display_name":"Bandwidth (computing)","level":2,"score":0.08669203519821167},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"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/C43617362","wikidata":"https://www.wikidata.org/wiki/Q170050","display_name":"Chromatography","level":1,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0},{"id":"https://openalex.org/C104114177","wikidata":"https://www.wikidata.org/wiki/Q79782","display_name":"Motion (physics)","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3316615.3316641","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3316615.3316641","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2019 8th International Conference on Software and Computer Applications","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.4099999964237213,"id":"https://metadata.un.org/sdg/15","display_name":"Life in Land"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":15,"referenced_works":["https://openalex.org/W66251415","https://openalex.org/W169052826","https://openalex.org/W1565050238","https://openalex.org/W2055095649","https://openalex.org/W2099454382","https://openalex.org/W2124685890","https://openalex.org/W2132791018","https://openalex.org/W2158698691","https://openalex.org/W2165466912","https://openalex.org/W2305347498","https://openalex.org/W2382640810","https://openalex.org/W2472223596","https://openalex.org/W2585528949","https://openalex.org/W6600882715","https://openalex.org/W6606879723"],"related_works":["https://openalex.org/W4248131312","https://openalex.org/W2766503024","https://openalex.org/W2781247653","https://openalex.org/W4206637278","https://openalex.org/W2152863486","https://openalex.org/W129898351","https://openalex.org/W4383227007","https://openalex.org/W2068369387","https://openalex.org/W3128679398","https://openalex.org/W4245258405"],"abstract_inverted_index":{"Imbalance":[0],"learning":[1],"is":[2,64,88,99],"one":[3],"of":[4,70,118,133],"the":[5,68,92,115,131,134],"most":[6],"challenging":[7],"problems":[8],"in":[9,78],"supervised":[10],"learning,":[11],"so":[12],"many":[13],"different":[14],"strategies":[15],"are":[16],"designed":[17],"to":[18,66,90,101],"tackle":[19],"balanced":[20,30],"sample":[21,72,123],"distribution.":[22],"The":[23,106],"over-sampling":[24,47],"techniques":[25],"which":[26],"achieve":[27],"a":[28,103],"relatively":[29],"class":[31,61,120],"distribution":[32,117],"through":[33],"synthesizing":[34],"samples":[35,121],"receive":[36],"more":[37,39],"and":[38,54,122],"attention.":[40],"In":[41],"this":[42],"paper,":[43],"we":[44],"present":[45],"an":[46],"approach":[48,98,111],"based":[49,73,85],"on":[50,74,86],"isolation":[51],"Forest":[52],"(iForest)":[53],"SMOTE,":[55],"called":[56],"iForest-SMOTE.":[57],"Firstly,":[58],"for":[59],"minority":[60,119],"samples,":[62],"iForest-score":[63,87],"employed":[65,100],"assess":[67],"importance":[69],"each":[71,79],"iForest":[75],"model.":[76,136],"Then,":[77],"SMOTE":[80],"process,":[81],"roulette":[82],"wheel":[83],"selection":[84],"utilized":[89],"select":[91],"neighbor":[93],"sample.":[94,105],"Finally,":[95],"M-dimensional-sphere":[96],"interpolation":[97],"generate":[102],"new":[104],"experiments":[107],"illustrate":[108],"that":[109],"our":[110],"takes":[112],"into":[113],"account":[114],"spatial":[116],"synthetic":[124],"simultaneously.":[125],"Therefore,":[126],"iForest-SMOTE":[127],"can":[128],"effectively":[129],"improve":[130],"performance":[132],"classification":[135]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":3},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}