{"id":"https://openalex.org/W2769171239","doi":"https://doi.org/10.1109/infcomw.2017.8116481","title":"A data-driven preprocessing scheme on anomaly detection in big data applications","display_name":"A data-driven preprocessing scheme on anomaly detection in big data applications","publication_year":2017,"publication_date":"2017-05-01","ids":{"openalex":"https://openalex.org/W2769171239","doi":"https://doi.org/10.1109/infcomw.2017.8116481","mag":"2769171239"},"language":"en","primary_location":{"id":"doi:10.1109/infcomw.2017.8116481","is_oa":false,"landing_page_url":"https://doi.org/10.1109/infcomw.2017.8116481","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2017 IEEE Conference on Computer Communications Workshops (INFOCOM WKSHPS)","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/A5024969203","display_name":"Shengjie Xu","orcid":"https://orcid.org/0000-0003-2019-5186"},"institutions":[{"id":"https://openalex.org/I114395901","display_name":"University of Nebraska\u2013Lincoln","ror":"https://ror.org/043mer456","country_code":"US","type":"education","lineage":["https://openalex.org/I114395901"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Shengjie Xu","raw_affiliation_strings":["Department of Electrical and Computer Engineering, University of Nebraska-Lincoln, Omaha, NE"],"affiliations":[{"raw_affiliation_string":"Department of Electrical and Computer Engineering, University of Nebraska-Lincoln, Omaha, NE","institution_ids":["https://openalex.org/I114395901"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5073527013","display_name":"Yi Qian","orcid":"https://orcid.org/0000-0001-5671-916X"},"institutions":[{"id":"https://openalex.org/I114395901","display_name":"University of Nebraska\u2013Lincoln","ror":"https://ror.org/043mer456","country_code":"US","type":"education","lineage":["https://openalex.org/I114395901"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yi Qian","raw_affiliation_strings":["Department of Electrical and Computer Engineering, University of Nebraska-Lincoln, Omaha, NE"],"affiliations":[{"raw_affiliation_string":"Department of Electrical and Computer Engineering, University of Nebraska-Lincoln, Omaha, NE","institution_ids":["https://openalex.org/I114395901"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5057118326","display_name":"Rose Qingyang Hu","orcid":"https://orcid.org/0000-0002-1571-3631"},"institutions":[{"id":"https://openalex.org/I121980950","display_name":"Utah State University","ror":"https://ror.org/00h6set76","country_code":"US","type":"education","lineage":["https://openalex.org/I121980950"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Rose Qingyang Hu","raw_affiliation_strings":["Department of Electrical and Computer Engineering, Utah State University, Logan, Utah"],"affiliations":[{"raw_affiliation_string":"Department of Electrical and Computer Engineering, Utah State University, Logan, Utah","institution_ids":["https://openalex.org/I121980950"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5024969203"],"corresponding_institution_ids":["https://openalex.org/I114395901"],"apc_list":null,"apc_paid":null,"fwci":2.5353,"has_fulltext":false,"cited_by_count":21,"citation_normalized_percentile":{"value":0.92021841,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":91,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"814","last_page":"819"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11512","display_name":"Anomaly Detection Techniques and Applications","score":0.9998999834060669,"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/T11512","display_name":"Anomaly Detection Techniques and Applications","score":0.9998999834060669,"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/T11871","display_name":"Advanced Statistical Methods and Models","score":0.9976999759674072,"subfield":{"id":"https://openalex.org/subfields/2613","display_name":"Statistics and Probability"},"field":{"id":"https://openalex.org/fields/26","display_name":"Mathematics"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10876","display_name":"Fault Detection and Control Systems","score":0.9973000288009644,"subfield":{"id":"https://openalex.org/subfields/2207","display_name":"Control and Systems Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/anomaly-detection","display_name":"Anomaly detection","score":0.7927188277244568},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7739928960800171},{"id":"https://openalex.org/keywords/preprocessor","display_name":"Preprocessor","score":0.623049259185791},{"id":"https://openalex.org/keywords/outlier","display_name":"Outlier","score":0.6186085343360901},{"id":"https://openalex.org/keywords/dimensionality-reduction","display_name":"Dimensionality reduction","score":0.600063145160675},{"id":"https://openalex.org/keywords/big-data","display_name":"Big data","score":0.5776814818382263},{"id":"https://openalex.org/keywords/data-pre-processing","display_name":"Data pre-processing","score":0.5739127993583679},{"id":"https://openalex.org/keywords/scheme","display_name":"Scheme (mathematics)","score":0.5706192255020142},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.5682525038719177},{"id":"https://openalex.org/keywords/data-modeling","display_name":"Data modeling","score":0.46158507466316223},{"id":"https://openalex.org/keywords/data-set","display_name":"Data set","score":0.4405686855316162},{"id":"https://openalex.org/keywords/curse-of-dimensionality","display_name":"Curse of dimensionality","score":0.4369063973426819},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.403972327709198},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.39947667717933655},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.08661651611328125},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.07832911610603333}],"concepts":[{"id":"https://openalex.org/C739882","wikidata":"https://www.wikidata.org/wiki/Q3560506","display_name":"Anomaly detection","level":2,"score":0.7927188277244568},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7739928960800171},{"id":"https://openalex.org/C34736171","wikidata":"https://www.wikidata.org/wiki/Q918333","display_name":"Preprocessor","level":2,"score":0.623049259185791},{"id":"https://openalex.org/C79337645","wikidata":"https://www.wikidata.org/wiki/Q779824","display_name":"Outlier","level":2,"score":0.6186085343360901},{"id":"https://openalex.org/C70518039","wikidata":"https://www.wikidata.org/wiki/Q16000077","display_name":"Dimensionality reduction","level":2,"score":0.600063145160675},{"id":"https://openalex.org/C75684735","wikidata":"https://www.wikidata.org/wiki/Q858810","display_name":"Big data","level":2,"score":0.5776814818382263},{"id":"https://openalex.org/C10551718","wikidata":"https://www.wikidata.org/wiki/Q5227332","display_name":"Data pre-processing","level":2,"score":0.5739127993583679},{"id":"https://openalex.org/C77618280","wikidata":"https://www.wikidata.org/wiki/Q1155772","display_name":"Scheme (mathematics)","level":2,"score":0.5706192255020142},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.5682525038719177},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.46158507466316223},{"id":"https://openalex.org/C58489278","wikidata":"https://www.wikidata.org/wiki/Q1172284","display_name":"Data set","level":2,"score":0.4405686855316162},{"id":"https://openalex.org/C111030470","wikidata":"https://www.wikidata.org/wiki/Q1430460","display_name":"Curse of dimensionality","level":2,"score":0.4369063973426819},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.403972327709198},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.39947667717933655},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.08661651611328125},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.07832911610603333},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/infcomw.2017.8116481","is_oa":false,"landing_page_url":"https://doi.org/10.1109/infcomw.2017.8116481","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2017 IEEE Conference on Computer Communications Workshops (INFOCOM WKSHPS)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":22,"referenced_works":["https://openalex.org/W1562171576","https://openalex.org/W1963821364","https://openalex.org/W1989898472","https://openalex.org/W2054892625","https://openalex.org/W2112440119","https://openalex.org/W2127414816","https://openalex.org/W2157954477","https://openalex.org/W2169487163","https://openalex.org/W2177696067","https://openalex.org/W2199905070","https://openalex.org/W2248058375","https://openalex.org/W2277593997","https://openalex.org/W2470262141","https://openalex.org/W2487770199","https://openalex.org/W2582743722","https://openalex.org/W2955173751","https://openalex.org/W2983170364","https://openalex.org/W3120740533","https://openalex.org/W4214736747","https://openalex.org/W4229530126","https://openalex.org/W6677274844","https://openalex.org/W6694686555"],"related_works":["https://openalex.org/W1995622179","https://openalex.org/W1484111231","https://openalex.org/W4391160746","https://openalex.org/W1552543208","https://openalex.org/W2074396517","https://openalex.org/W2166963679","https://openalex.org/W2187269125","https://openalex.org/W1641615907","https://openalex.org/W3089231081","https://openalex.org/W2093956241"],"abstract_inverted_index":{"Efficient":[0],"anomaly":[1,28],"detection":[2,29,85],"mechanisms":[3],"are":[4,133],"becoming":[5],"an":[6,113],"urgent":[7],"and":[8,36,56],"critical":[9,72],"topic":[10],"in":[11],"the":[12,52,71,88,136,148,151,154],"presence":[13,89],"of":[14,51,74,90,116,138,150,153],"big":[15,43],"data":[16,44,54,59,65,106,110,117],"applications.":[17,45],"In":[18],"this":[19,139],"paper,":[20],"we":[21,47],"propose":[22],"a":[23,32,38,57,83],"data-driven":[24],"preprocessing":[25,55,66],"scheme":[26,67],"on":[27,112],"that":[30,108],"incorporates":[31],"dimensionality":[33,75],"reduction":[34,76],"algorithm":[35],"present":[37],"real-time":[39,58,93],"learning":[40,60,94,111,120],"idea":[41],"for":[42,77,135],"Specifically,":[46],"make":[48,123],"extensive":[49],"use":[50],"robust":[53,64,84],"approach.":[61],"The":[62,92],"proposed":[63,155],"not":[68],"only":[69],"preserves":[70],"property":[73],"high-dimensional":[78],"data,":[79],"but":[80],"also":[81],"introduces":[82],"boundary":[86],"to":[87,122,146],"outliers.":[91],"method":[95],"is":[96,144],"inspired":[97],"by":[98],"online":[99],"learning,":[100],"which":[101],"differs":[102],"from":[103],"batch":[104,115],"based":[105],"processing":[107],"performs":[109],"entire":[114],"set.":[118],"Real-time":[119],"aims":[121],"progress":[124],"with":[125],"each":[126],"example":[127],"it":[128],"looks":[129],"at.":[130],"Detailed":[131],"discussions":[132],"provided":[134],"justification":[137],"scheme.":[140,156],"A":[141],"case":[142],"study":[143],"presented":[145],"demonstrate":[147],"feasibility":[149],"application":[152]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2022,"cited_by_count":3},{"year":2021,"cited_by_count":4},{"year":2020,"cited_by_count":4},{"year":2019,"cited_by_count":5},{"year":2018,"cited_by_count":4}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}