{"id":"https://openalex.org/W4384572726","doi":"https://doi.org/10.1515/comp-2022-0278","title":"Data preprocessing impact on machine learning algorithm performance","display_name":"Data preprocessing impact on machine learning algorithm performance","publication_year":2023,"publication_date":"2023-01-01","ids":{"openalex":"https://openalex.org/W4384572726","doi":"https://doi.org/10.1515/comp-2022-0278"},"language":"en","primary_location":{"id":"doi:10.1515/comp-2022-0278","is_oa":true,"landing_page_url":"https://doi.org/10.1515/comp-2022-0278","pdf_url":"https://www.degruyter.com/document/doi/10.1515/comp-2022-0278/pdf","source":{"id":"https://openalex.org/S4210177004","display_name":"Open Computer Science","issn_l":"2299-1093","issn":["2299-1093"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310313990","host_organization_name":"De Gruyter","host_organization_lineage":["https://openalex.org/P4310313990"],"host_organization_lineage_names":["De Gruyter"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Open Computer Science","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://www.degruyter.com/document/doi/10.1515/comp-2022-0278/pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5076119559","display_name":"Alberto Amato","orcid":"https://orcid.org/0000-0002-8107-7047"},"institutions":[{"id":"https://openalex.org/I68618741","display_name":"Polytechnic University of Bari","ror":"https://ror.org/03c44v465","country_code":"IT","type":"education","lineage":["https://openalex.org/I68618741"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Alberto Amato","raw_affiliation_strings":["Department of Electrical and Information Engineering Politecnico di Bari , Bari , Italy"],"affiliations":[{"raw_affiliation_string":"Department of Electrical and Information Engineering Politecnico di Bari , Bari , Italy","institution_ids":["https://openalex.org/I68618741"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5020752895","display_name":"Vincenzo Di Lecce","orcid":"https://orcid.org/0000-0002-4878-185X"},"institutions":[{"id":"https://openalex.org/I68618741","display_name":"Polytechnic University of Bari","ror":"https://ror.org/03c44v465","country_code":"IT","type":"education","lineage":["https://openalex.org/I68618741"]}],"countries":["IT"],"is_corresponding":true,"raw_author_name":"Vincenzo Di Lecce","raw_affiliation_strings":["Department of Electrical and Information Engineering Politecnico di Bari , Bari , Italy"],"affiliations":[{"raw_affiliation_string":"Department of Electrical and Information Engineering Politecnico di Bari , Bari , Italy","institution_ids":["https://openalex.org/I68618741"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5020752895"],"corresponding_institution_ids":["https://openalex.org/I68618741"],"apc_list":{"value":1000,"currency":"EUR","value_usd":1078},"apc_paid":{"value":1000,"currency":"EUR","value_usd":1078},"fwci":4.0791,"has_fulltext":true,"cited_by_count":34,"citation_normalized_percentile":{"value":0.95372848,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":100},"biblio":{"volume":"13","issue":"1","first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10057","display_name":"Face and Expression Recognition","score":0.9993000030517578,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/T10057","display_name":"Face and Expression Recognition","score":0.9993000030517578,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/T10640","display_name":"Spectroscopy and Chemometric Analyses","score":0.9945999979972839,"subfield":{"id":"https://openalex.org/subfields/1602","display_name":"Analytical Chemistry"},"field":{"id":"https://openalex.org/fields/16","display_name":"Chemistry"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10824","display_name":"Image Retrieval and Classification Techniques","score":0.9918000102043152,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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":0.7504796981811523},{"id":"https://openalex.org/keywords/data-pre-processing","display_name":"Data pre-processing","score":0.7493131756782532},{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.7069808840751648},{"id":"https://openalex.org/keywords/preprocessor","display_name":"Preprocessor","score":0.6883307099342346},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6121964454650879},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.582497775554657},{"id":"https://openalex.org/keywords/principal-component-analysis","display_name":"Principal component analysis","score":0.5636734962463379},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.5288485288619995},{"id":"https://openalex.org/keywords/feature-selection","display_name":"Feature selection","score":0.49895310401916504},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.4825712740421295}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7504796981811523},{"id":"https://openalex.org/C10551718","wikidata":"https://www.wikidata.org/wiki/Q5227332","display_name":"Data pre-processing","level":2,"score":0.7493131756782532},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.7069808840751648},{"id":"https://openalex.org/C34736171","wikidata":"https://www.wikidata.org/wiki/Q918333","display_name":"Preprocessor","level":2,"score":0.6883307099342346},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6121964454650879},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.582497775554657},{"id":"https://openalex.org/C27438332","wikidata":"https://www.wikidata.org/wiki/Q2873","display_name":"Principal component analysis","level":2,"score":0.5636734962463379},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.5288485288619995},{"id":"https://openalex.org/C148483581","wikidata":"https://www.wikidata.org/wiki/Q446488","display_name":"Feature selection","level":2,"score":0.49895310401916504},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.4825712740421295}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1515/comp-2022-0278","is_oa":true,"landing_page_url":"https://doi.org/10.1515/comp-2022-0278","pdf_url":"https://www.degruyter.com/document/doi/10.1515/comp-2022-0278/pdf","source":{"id":"https://openalex.org/S4210177004","display_name":"Open Computer Science","issn_l":"2299-1093","issn":["2299-1093"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310313990","host_organization_name":"De Gruyter","host_organization_lineage":["https://openalex.org/P4310313990"],"host_organization_lineage_names":["De Gruyter"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Open Computer Science","raw_type":"journal-article"},{"id":"pmh:oai:doaj.org/article:3f01021396994b03a1992fd52f9c1267","is_oa":true,"landing_page_url":"https://doaj.org/article/3f01021396994b03a1992fd52f9c1267","pdf_url":null,"source":{"id":"https://openalex.org/S112646816","display_name":"SHILAP Revista de lepidopterolog\u00eda","issn_l":"0300-5267","issn":["0300-5267","2340-4078"],"is_oa":true,"is_in_doaj":true,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Open Computer Science, Vol 13, Iss 1, Pp pp. 175-180 (2023)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.1515/comp-2022-0278","is_oa":true,"landing_page_url":"https://doi.org/10.1515/comp-2022-0278","pdf_url":"https://www.degruyter.com/document/doi/10.1515/comp-2022-0278/pdf","source":{"id":"https://openalex.org/S4210177004","display_name":"Open Computer Science","issn_l":"2299-1093","issn":["2299-1093"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310313990","host_organization_name":"De Gruyter","host_organization_lineage":["https://openalex.org/P4310313990"],"host_organization_lineage_names":["De Gruyter"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Open Computer Science","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4384572726.pdf"},"referenced_works_count":31,"referenced_works":["https://openalex.org/W1508363294","https://openalex.org/W1510073064","https://openalex.org/W1987971958","https://openalex.org/W1990044052","https://openalex.org/W1990368529","https://openalex.org/W1995450389","https://openalex.org/W1995918092","https://openalex.org/W2003711267","https://openalex.org/W2019432911","https://openalex.org/W2033403400","https://openalex.org/W2044304288","https://openalex.org/W2053186076","https://openalex.org/W2093010960","https://openalex.org/W2093402979","https://openalex.org/W2097308346","https://openalex.org/W2130660124","https://openalex.org/W2132582398","https://openalex.org/W2156838815","https://openalex.org/W2475392251","https://openalex.org/W2733722625","https://openalex.org/W2919748712","https://openalex.org/W3041913137","https://openalex.org/W3092532049","https://openalex.org/W3092603928","https://openalex.org/W3093854333","https://openalex.org/W3118612008","https://openalex.org/W3127591480","https://openalex.org/W3138440964","https://openalex.org/W4285115492","https://openalex.org/W4292023222","https://openalex.org/W6600820135"],"related_works":["https://openalex.org/W2989490741","https://openalex.org/W1629127207","https://openalex.org/W138569904","https://openalex.org/W2367545121","https://openalex.org/W4248881655","https://openalex.org/W2482165163","https://openalex.org/W3010890513","https://openalex.org/W3092506759","https://openalex.org/W2390914021","https://openalex.org/W2389417819"],"abstract_inverted_index":{"Abstract":[0],"The":[1,120,153,162],"popularity":[2],"of":[3,20,25,35,41,62,104,127,132],"artificial":[4],"intelligence":[5],"applications":[6,27],"is":[7,65,88,155],"on":[8,30,129,157],"the":[9,23,31,39,59,63,102,125,130,150,166,180],"rise,":[10],"and":[11,33,94,137],"they":[12],"are":[13],"producing":[14],"better":[15,56],"outcomes":[16,171],"in":[17,47,116],"numerous":[18],"fields":[19],"research.":[21],"However,":[22],"effectiveness":[24],"these":[26],"relies":[28],"heavily":[29],"quantity":[32],"quality":[34],"data":[36,42,64,75,114],"used.":[37],"While":[38],"volume":[40],"available":[43,160],"has":[44,108],"increased":[45],"significantly":[46],"recent":[48],"years,":[49],"this":[50],"does":[51],"not":[52,109],"always":[53],"lead":[54],"to":[55,71,113,123,141,173],"results,":[57],"as":[58,96,149],"information":[60],"content":[61],"also":[66],"important.":[67],"This":[68,86],"study":[69,121],"aims":[70,122],"evaluate":[72,124],"a":[73,97],"new":[74],"preprocessing":[76,115,151],"technique":[77,87],"called":[78],"semi-pivoted":[79],"QR":[80],"(SPQR)":[81],"approximation":[82],"for":[83,90],"machine":[84,117],"learning.":[85],"designed":[89],"approximating":[91],"sparse":[92],"matrices":[93],"acts":[95],"feature":[98],"selection":[99],"algorithm.":[100,152],"To":[101],"best":[103],"our":[105],"knowledge,":[106],"it":[107],"been":[110],"previously":[111],"applied":[112],"learning":[118],"algorithms.":[119],"impact":[126],"SPQR":[128,167],"performance":[131],"an":[133],"unsupervised":[134],"clustering":[135],"algorithm":[136,168],"compare":[138],"its":[139],"results":[140],"those":[142,174],"obtained":[143],"using":[144,176],"principal":[145],"component":[146],"analysis":[147],"(PCA)":[148],"evaluation":[154],"conducted":[156],"various":[158],"publicly":[159],"datasets.":[161],"findings":[163],"suggest":[164],"that":[165],"can":[169],"produce":[170],"comparable":[172],"achieved":[175],"PCA":[177],"without":[178],"altering":[179],"original":[181],"dataset.":[182]},"counts_by_year":[{"year":2026,"cited_by_count":5},{"year":2025,"cited_by_count":17},{"year":2024,"cited_by_count":11},{"year":2023,"cited_by_count":1}],"updated_date":"2026-04-03T22:45:19.894376","created_date":"2023-07-18T00:00:00"}