{"id":"https://openalex.org/W2169330701","doi":"https://doi.org/10.1109/fskd.2012.6233810","title":"An optimized features extraction algorithm on VSM","display_name":"An optimized features extraction algorithm on VSM","publication_year":2012,"publication_date":"2012-05-01","ids":{"openalex":"https://openalex.org/W2169330701","doi":"https://doi.org/10.1109/fskd.2012.6233810","mag":"2169330701"},"language":"en","primary_location":{"id":"doi:10.1109/fskd.2012.6233810","is_oa":false,"landing_page_url":"https://doi.org/10.1109/fskd.2012.6233810","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2012 9th International Conference on Fuzzy Systems and Knowledge Discovery","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/A5103268322","display_name":"Kui Fang","orcid":null},"institutions":[{"id":"https://openalex.org/I52180223","display_name":"Hunan Agricultural University","ror":"https://ror.org/01dzed356","country_code":"CN","type":"education","lineage":["https://openalex.org/I52180223"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Kui Fang","raw_affiliation_strings":["College of Information Science and Technology, Hunan Agricultural University, Changsha, China"],"affiliations":[{"raw_affiliation_string":"College of Information Science and Technology, Hunan Agricultural University, Changsha, China","institution_ids":["https://openalex.org/I52180223"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5104668783","display_name":"Juan Wang","orcid":"https://orcid.org/0000-0001-5583-9944"},"institutions":[{"id":"https://openalex.org/I52180223","display_name":"Hunan Agricultural University","ror":"https://ror.org/01dzed356","country_code":"CN","type":"education","lineage":["https://openalex.org/I52180223"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Juan Wang","raw_affiliation_strings":["College of Information Science and Technology, Hunan Agricultural University, Changsha, China"],"affiliations":[{"raw_affiliation_string":"College of Information Science and Technology, Hunan Agricultural University, Changsha, China","institution_ids":["https://openalex.org/I52180223"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5103268322"],"corresponding_institution_ids":["https://openalex.org/I52180223"],"apc_list":null,"apc_paid":null,"fwci":1.4211,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.88041517,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":"14","issue":null,"first_page":"1471","last_page":"1473"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12016","display_name":"Web Data Mining and Analysis","score":0.9984999895095825,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"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/T12016","display_name":"Web Data Mining and Analysis","score":0.9984999895095825,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"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":0.9970999956130981,"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/T10824","display_name":"Image Retrieval and Classification Techniques","score":0.9836999773979187,"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":0.7245301008224487},{"id":"https://openalex.org/keywords/precision-and-recall","display_name":"Precision and recall","score":0.6551345586776733},{"id":"https://openalex.org/keywords/tf\u2013idf","display_name":"tf\u2013idf","score":0.6335960030555725},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.5492182374000549},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.5436978936195374},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.4901507794857025},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.46317464113235474},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.44669270515441895},{"id":"https://openalex.org/keywords/feature-vector","display_name":"Feature vector","score":0.42043113708496094},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3816741108894348}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7245301008224487},{"id":"https://openalex.org/C81669768","wikidata":"https://www.wikidata.org/wiki/Q2359161","display_name":"Precision and recall","level":2,"score":0.6551345586776733},{"id":"https://openalex.org/C81758059","wikidata":"https://www.wikidata.org/wiki/Q796584","display_name":"tf\u2013idf","level":3,"score":0.6335960030555725},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.5492182374000549},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.5436978936195374},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.4901507794857025},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.46317464113235474},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.44669270515441895},{"id":"https://openalex.org/C83665646","wikidata":"https://www.wikidata.org/wiki/Q42139305","display_name":"Feature vector","level":2,"score":0.42043113708496094},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3816741108894348},{"id":"https://openalex.org/C61797465","wikidata":"https://www.wikidata.org/wiki/Q1188986","display_name":"Term (time)","level":2,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/fskd.2012.6233810","is_oa":false,"landing_page_url":"https://doi.org/10.1109/fskd.2012.6233810","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2012 9th International Conference on Fuzzy Systems and Knowledge Discovery","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","score":0.550000011920929,"id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":9,"referenced_works":["https://openalex.org/W1978394996","https://openalex.org/W2041145971","https://openalex.org/W2353490606","https://openalex.org/W2361209440","https://openalex.org/W2361483642","https://openalex.org/W2372424341","https://openalex.org/W2435251607","https://openalex.org/W6660731769","https://openalex.org/W6717827561"],"related_works":["https://openalex.org/W2382433580","https://openalex.org/W2100326285","https://openalex.org/W2369751049","https://openalex.org/W2198237484","https://openalex.org/W2041122820","https://openalex.org/W2169105971","https://openalex.org/W2968390902","https://openalex.org/W116095830","https://openalex.org/W2372520056","https://openalex.org/W4390992395"],"abstract_inverted_index":{"VSM":[0],"(Vector":[1],"Space":[2],"Model)":[3],"is":[4],"one":[5],"of":[6,17,41,61,67,77,110,132],"the":[7,15,55,59,65,73,78,97,102,113,115,121,128,133,154],"important":[8],"methods":[9],"for":[10],"describing":[11],"documents.":[12],"However,":[13,53],"in":[14,45,51],"process":[16],"information":[18],"representation,":[19],"features":[20],"are":[21,39,48,136],"always":[22],"high":[23],"dimensional.":[24],"So":[25],"feature":[26,42,87],"extraction":[27,43,88],"technologies":[28],"have":[29],"to":[30,33,100],"be":[31],"used":[32,49],"reduce":[34],"dimensions.":[35],"At":[36],"present,":[37],"there":[38],"lots":[40],"algorithms,":[44],"which":[46,70,106,152],"TF-IDF,TF-IDF-IG":[47],"widely":[50],"practice.":[52],"as":[54],"two":[56],"didn't":[57],"consider":[58],"influence":[60],"text":[62],"categories":[63],"and":[64,75,123,130,142,146,148,160],"structure":[66],"HTML":[68],"sufficiently,":[69],"greatly":[71],"affects":[72],"accuracy":[74],"applicability":[76],"algorithms.":[79],"To":[80],"this":[81],"issue,":[82],"we":[83,91],"proposed":[84,116],"an":[85],"optimized":[86],"algorithm.":[89],"Meanwhile,":[90],"introduced":[92],"a":[93],"modifying":[94],"factor":[95],"into":[96],"novel":[98,155],"algorithm":[99,117,135,156],"avoid":[101],"data":[103],"imbalance":[104],"problem":[105],"results":[107],"from":[108],"magnitude":[109],"categories.":[111],"Through":[112],"experiment,":[114],"was":[118],"compared":[119],"with":[120],"TF-IDF":[122],"TF-IDF-IG.":[124],"We":[125],"found":[126],"that":[127],"precision":[129,159],"recall":[131],"new":[134],"separately":[137],"increased":[138],"more":[139],"than":[140,144,150],"10.4%":[141],"13.8%":[143],"TF-IDF,":[145],"4.6%":[147],"2.9%":[149],"TF-IDF-IG,":[151],"shows":[153],"has":[157],"better":[158],"recall.":[161]},"counts_by_year":[{"year":2023,"cited_by_count":1},{"year":2015,"cited_by_count":1},{"year":2012,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}