{"id":"https://openalex.org/W3138422672","doi":"https://doi.org/10.4018/ijossp.2020070101","title":"Efficient Algorithms for Cleaning and Indexing of Graph data","display_name":"Efficient Algorithms for Cleaning and Indexing of Graph data","publication_year":2020,"publication_date":"2020-07-01","ids":{"openalex":"https://openalex.org/W3138422672","doi":"https://doi.org/10.4018/ijossp.2020070101","mag":"3138422672"},"language":"en","primary_location":{"id":"doi:10.4018/ijossp.2020070101","is_oa":false,"landing_page_url":"https://doi.org/10.4018/ijossp.2020070101","pdf_url":null,"source":{"id":"https://openalex.org/S171397936","display_name":"International Journal of Open Source Software and Processes","issn_l":"1942-3926","issn":["1942-3926","1942-3934"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320424","host_organization_name":"IGI Global","host_organization_lineage":["https://openalex.org/P4310320424"],"host_organization_lineage_names":["IGI Global"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"International Journal of Open Source Software and Processes","raw_type":"journal-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/A5054471482","display_name":"D. K. Santhosh Kumar","orcid":"https://orcid.org/0000-0002-9179-3864"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Santhosh Kumar D. K.","raw_affiliation_strings":["Canara Engineering College, India"],"affiliations":[{"raw_affiliation_string":"Canara Engineering College, India","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5088837614","display_name":"Demian Antony D\u2019Mello","orcid":"https://orcid.org/0000-0001-7184-6853"},"institutions":[{"id":"https://openalex.org/I65674248","display_name":"Visvesvaraya Technological University","ror":"https://ror.org/00ha14p11","country_code":"IN","type":"education","lineage":["https://openalex.org/I65674248"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Demain Antony DMello","raw_affiliation_strings":["Canara Engineering College, Visvesvaraya Technological University (VTU), Belagavi, India"],"affiliations":[{"raw_affiliation_string":"Canara Engineering College, Visvesvaraya Technological University (VTU), Belagavi, India","institution_ids":["https://openalex.org/I65674248"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5054471482"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.359,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.67825105,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":96},"biblio":{"volume":"11","issue":"3","first_page":"1","last_page":"19"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11719","display_name":"Data Quality and Management","score":0.9997000098228455,"subfield":{"id":"https://openalex.org/subfields/1803","display_name":"Management Science and Operations Research"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},"topics":[{"id":"https://openalex.org/T11719","display_name":"Data Quality and Management","score":0.9997000098228455,"subfield":{"id":"https://openalex.org/subfields/1803","display_name":"Management Science and Operations Research"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T12292","display_name":"Graph Theory and Algorithms","score":0.996999979019165,"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/T10317","display_name":"Advanced Database Systems and Queries","score":0.9912999868392944,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"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":0.8148695230484009},{"id":"https://openalex.org/keywords/search-engine-indexing","display_name":"Search engine indexing","score":0.7897592782974243},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.7296245694160461},{"id":"https://openalex.org/keywords/graph-database","display_name":"Graph database","score":0.6152231097221375},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.6037463545799255},{"id":"https://openalex.org/keywords/graph","display_name":"Graph","score":0.6028356552124023},{"id":"https://openalex.org/keywords/big-data","display_name":"Big data","score":0.5106526017189026},{"id":"https://openalex.org/keywords/computation","display_name":"Computation","score":0.48440366983413696},{"id":"https://openalex.org/keywords/data-structure","display_name":"Data structure","score":0.4161060154438019},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.3903816342353821},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.3854001760482788},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.3308437466621399},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.29956483840942383}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8148695230484009},{"id":"https://openalex.org/C75165309","wikidata":"https://www.wikidata.org/wiki/Q2258979","display_name":"Search engine indexing","level":2,"score":0.7897592782974243},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.7296245694160461},{"id":"https://openalex.org/C176225458","wikidata":"https://www.wikidata.org/wiki/Q595971","display_name":"Graph database","level":3,"score":0.6152231097221375},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.6037463545799255},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.6028356552124023},{"id":"https://openalex.org/C75684735","wikidata":"https://www.wikidata.org/wiki/Q858810","display_name":"Big data","level":2,"score":0.5106526017189026},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.48440366983413696},{"id":"https://openalex.org/C162319229","wikidata":"https://www.wikidata.org/wiki/Q175263","display_name":"Data structure","level":2,"score":0.4161060154438019},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.3903816342353821},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.3854001760482788},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.3308437466621399},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.29956483840942383},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.4018/ijossp.2020070101","is_oa":false,"landing_page_url":"https://doi.org/10.4018/ijossp.2020070101","pdf_url":null,"source":{"id":"https://openalex.org/S171397936","display_name":"International Journal of Open Source Software and Processes","issn_l":"1942-3926","issn":["1942-3926","1942-3934"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320424","host_organization_name":"IGI Global","host_organization_lineage":["https://openalex.org/P4310320424"],"host_organization_lineage_names":["IGI Global"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"International Journal of Open Source Software and Processes","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.5299999713897705,"display_name":"Industry, innovation and infrastructure","id":"https://metadata.un.org/sdg/9"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":13,"referenced_works":["https://openalex.org/W1963617357","https://openalex.org/W2031792675","https://openalex.org/W2035543557","https://openalex.org/W2072534270","https://openalex.org/W2080224910","https://openalex.org/W2087183379","https://openalex.org/W2137077706","https://openalex.org/W2142965177","https://openalex.org/W2165663045","https://openalex.org/W2473778837","https://openalex.org/W2766773547","https://openalex.org/W2800958090","https://openalex.org/W2807714896"],"related_works":["https://openalex.org/W4390608645","https://openalex.org/W4247566972","https://openalex.org/W2960264696","https://openalex.org/W3090563135","https://openalex.org/W2497432351","https://openalex.org/W4206777497","https://openalex.org/W3024364549","https://openalex.org/W4233347783","https://openalex.org/W2910064364","https://openalex.org/W4255224757"],"abstract_inverted_index":{"Information":[0],"extraction":[1],"and":[2,50,56,79,143,150,169],"analysis":[3],"from":[4],"the":[5,13,43,48,70,98,105,121,136,145],"enormous":[6],"graph":[7,71,86,130,171],"data":[8,31,39,60,64,72,87,131,146,154],"is":[9,16,52,57,113],"expanding":[10],"rapidly.":[11],"From":[12],"survey,":[14],"it":[15,112],"observed":[17],"that":[18],"80%":[19],"of":[20,26,45,85,92,100,175],"researchers":[21],"spend":[22],"more":[23],"than":[24],"40%":[25],"their":[27],"project":[28],"time":[29],"in":[30],"cleaning.":[32,40],"This":[33,123],"signifies":[34],"a":[35,89],"huge":[36],"need":[37],"for":[38],"Due":[41],"to":[42,68,116,119,134,165],"characteristics":[44],"big":[46],"data,":[47],"storage":[49],"retrieval":[51],"another":[53],"major":[54],"concern":[55],"addressed":[58],"by":[59,128,147],"indexing.":[61],"The":[62,83,156],"existing":[63],"cleaning":[65,84,132],"techniques":[66],"try":[67],"clean":[69,117,144],"based":[73,152,162],"on":[74,88,153,163,173],"information":[75,93,138],"like":[76],"structural":[77],"attributes":[78],"event":[80],"log":[81],"sequences.":[82],"single":[90],"piece":[91],"alone":[94],"will":[95],"not":[96],"increase":[97],"performance":[99],"computation.":[101],"Along":[102],"with":[103,140],"node,":[104],"label":[106],"can":[107],"also":[108],"be":[109],"inconsistent,":[110],"so":[111],"highly":[114],"desirable":[115],"both":[118],"improve":[120],"performance.":[122],"paper":[124],"addresses":[125],"aforesaid":[126],"issue":[127],"proposing":[129],"algorithm":[133,161],"detect":[135],"unstructured":[137],"along":[139],"inconsistent":[141],"labeling":[142],"applying":[148],"rules":[149],"verify":[151],"inconsistency.":[155],"authors":[157],"propose":[158],"an":[159,167],"indexing":[160,172],"CSS-tree":[164],"build":[166],"efficient":[168],"scalable":[170],"top":[174],"Hadoop.":[176]},"counts_by_year":[{"year":2022,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
