{"id":"https://openalex.org/W2117404929","doi":"https://doi.org/10.1145/2666310.2666373","title":"A system for efficient cleaning and transformation of geospatial data attributes","display_name":"A system for efficient cleaning and transformation of geospatial data attributes","publication_year":2014,"publication_date":"2014-11-04","ids":{"openalex":"https://openalex.org/W2117404929","doi":"https://doi.org/10.1145/2666310.2666373","mag":"2117404929"},"language":"en","primary_location":{"id":"doi:10.1145/2666310.2666373","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2666310.2666373","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 22nd ACM SIGSPATIAL International Conference on Advances in Geographic Information Systems","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/A5045786247","display_name":"Yao\u2010Yi Chiang","orcid":"https://orcid.org/0000-0002-8923-0130"},"institutions":[{"id":"https://openalex.org/I1174212","display_name":"University of Southern California","ror":"https://ror.org/03taz7m60","country_code":"US","type":"education","lineage":["https://openalex.org/I1174212"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Yao-Yi Chiang","raw_affiliation_strings":["University of Southern California, Los Angeles, CA","University of Southern California,,,Los Angeles,CA,"],"affiliations":[{"raw_affiliation_string":"University of Southern California, Los Angeles, CA","institution_ids":["https://openalex.org/I1174212"]},{"raw_affiliation_string":"University of Southern California,,,Los Angeles,CA,","institution_ids":["https://openalex.org/I1174212"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5084693607","display_name":"Bo Wu","orcid":"https://orcid.org/0000-0002-0214-234X"},"institutions":[{"id":"https://openalex.org/I1174212","display_name":"University of Southern California","ror":"https://ror.org/03taz7m60","country_code":"US","type":"education","lineage":["https://openalex.org/I1174212"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Bo Wu","raw_affiliation_strings":["University of Southern California, Los Angeles, CA","University of Southern California,,,Los Angeles,CA,"],"affiliations":[{"raw_affiliation_string":"University of Southern California, Los Angeles, CA","institution_ids":["https://openalex.org/I1174212"]},{"raw_affiliation_string":"University of Southern California,,,Los Angeles,CA,","institution_ids":["https://openalex.org/I1174212"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101888188","display_name":"Akshay Anand","orcid":"https://orcid.org/0000-0001-9003-3532"},"institutions":[{"id":"https://openalex.org/I1174212","display_name":"University of Southern California","ror":"https://ror.org/03taz7m60","country_code":"US","type":"education","lineage":["https://openalex.org/I1174212"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Akshay Anand","raw_affiliation_strings":["University of Southern California, Los Angeles, CA","University of Southern California,,,Los Angeles,CA,"],"affiliations":[{"raw_affiliation_string":"University of Southern California, Los Angeles, CA","institution_ids":["https://openalex.org/I1174212"]},{"raw_affiliation_string":"University of Southern California,,,Los Angeles,CA,","institution_ids":["https://openalex.org/I1174212"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5090010441","display_name":"Ketan Akade","orcid":null},"institutions":[{"id":"https://openalex.org/I1174212","display_name":"University of Southern California","ror":"https://ror.org/03taz7m60","country_code":"US","type":"education","lineage":["https://openalex.org/I1174212"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ketan Akade","raw_affiliation_strings":["University of Southern California, Los Angeles, CA","University of Southern California,,,Los Angeles,CA,"],"affiliations":[{"raw_affiliation_string":"University of Southern California, Los Angeles, CA","institution_ids":["https://openalex.org/I1174212"]},{"raw_affiliation_string":"University of Southern California,,,Los Angeles,CA,","institution_ids":["https://openalex.org/I1174212"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5089542402","display_name":"Craig A. Knoblock","orcid":"https://orcid.org/0000-0002-6371-4807"},"institutions":[{"id":"https://openalex.org/I1174212","display_name":"University of Southern California","ror":"https://ror.org/03taz7m60","country_code":"US","type":"education","lineage":["https://openalex.org/I1174212"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Craig A. Knoblock","raw_affiliation_strings":["University of Southern California, Los Angeles, CA","University of Southern California,,,Los Angeles,CA,"],"affiliations":[{"raw_affiliation_string":"University of Southern California, Los Angeles, CA","institution_ids":["https://openalex.org/I1174212"]},{"raw_affiliation_string":"University of Southern California,,,Los Angeles,CA,","institution_ids":["https://openalex.org/I1174212"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5045786247"],"corresponding_institution_ids":["https://openalex.org/I1174212"],"apc_list":null,"apc_paid":null,"fwci":1.0344,"has_fulltext":false,"cited_by_count":6,"citation_normalized_percentile":{"value":0.81032107,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"577","last_page":"580"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10317","display_name":"Advanced Database Systems and Queries","score":0.9994999766349792,"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"}},"topics":[{"id":"https://openalex.org/T10317","display_name":"Advanced Database Systems and Queries","score":0.9994999766349792,"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"}},{"id":"https://openalex.org/T11719","display_name":"Data Quality and Management","score":0.9984999895095825,"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/T11986","display_name":"Scientific Computing and Data Management","score":0.9979000091552734,"subfield":{"id":"https://openalex.org/subfields/1802","display_name":"Information Systems and Management"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/geospatial-analysis","display_name":"Geospatial analysis","score":0.864189624786377},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.836000919342041},{"id":"https://openalex.org/keywords/scripting-language","display_name":"Scripting language","score":0.7207791805267334},{"id":"https://openalex.org/keywords/geographic-information-system","display_name":"Geographic information system","score":0.6712812185287476},{"id":"https://openalex.org/keywords/transformation","display_name":"Transformation (genetics)","score":0.6339849233627319},{"id":"https://openalex.org/keywords/focus","display_name":"Focus (optics)","score":0.5780455470085144},{"id":"https://openalex.org/keywords/data-transformation","display_name":"Data transformation","score":0.5704273581504822},{"id":"https://openalex.org/keywords/am/fm/gis","display_name":"AM/FM/GIS","score":0.5689870119094849},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.5605359673500061},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5075587034225464},{"id":"https://openalex.org/keywords/spatial-analysis","display_name":"Spatial analysis","score":0.5057930946350098},{"id":"https://openalex.org/keywords/gis-file-format","display_name":"GIS file format","score":0.502152681350708},{"id":"https://openalex.org/keywords/component","display_name":"Component (thermodynamics)","score":0.4509083032608032},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.4035700857639313},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.3657621741294861},{"id":"https://openalex.org/keywords/gis-applications","display_name":"GIS applications","score":0.34235745668411255},{"id":"https://openalex.org/keywords/remote-sensing","display_name":"Remote sensing","score":0.110088050365448},{"id":"https://openalex.org/keywords/data-warehouse","display_name":"Data warehouse","score":0.09509167075157166},{"id":"https://openalex.org/keywords/geography","display_name":"Geography","score":0.09235867857933044},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.06902042031288147},{"id":"https://openalex.org/keywords/systems-engineering","display_name":"Systems engineering","score":0.06781160831451416}],"concepts":[{"id":"https://openalex.org/C9770341","wikidata":"https://www.wikidata.org/wiki/Q1938983","display_name":"Geospatial analysis","level":2,"score":0.864189624786377},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.836000919342041},{"id":"https://openalex.org/C61423126","wikidata":"https://www.wikidata.org/wiki/Q187432","display_name":"Scripting language","level":2,"score":0.7207791805267334},{"id":"https://openalex.org/C41856607","wikidata":"https://www.wikidata.org/wiki/Q483130","display_name":"Geographic information system","level":2,"score":0.6712812185287476},{"id":"https://openalex.org/C204241405","wikidata":"https://www.wikidata.org/wiki/Q461499","display_name":"Transformation (genetics)","level":3,"score":0.6339849233627319},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.5780455470085144},{"id":"https://openalex.org/C150670458","wikidata":"https://www.wikidata.org/wiki/Q4272815","display_name":"Data transformation","level":3,"score":0.5704273581504822},{"id":"https://openalex.org/C148162668","wikidata":"https://www.wikidata.org/wiki/Q483130","display_name":"AM/FM/GIS","level":4,"score":0.5689870119094849},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.5605359673500061},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5075587034225464},{"id":"https://openalex.org/C159620131","wikidata":"https://www.wikidata.org/wiki/Q1938983","display_name":"Spatial analysis","level":2,"score":0.5057930946350098},{"id":"https://openalex.org/C59994114","wikidata":"https://www.wikidata.org/wiki/Q1485661","display_name":"GIS file format","level":5,"score":0.502152681350708},{"id":"https://openalex.org/C168167062","wikidata":"https://www.wikidata.org/wiki/Q1117970","display_name":"Component (thermodynamics)","level":2,"score":0.4509083032608032},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.4035700857639313},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.3657621741294861},{"id":"https://openalex.org/C56321713","wikidata":"https://www.wikidata.org/wiki/Q483130","display_name":"GIS applications","level":3,"score":0.34235745668411255},{"id":"https://openalex.org/C62649853","wikidata":"https://www.wikidata.org/wiki/Q199687","display_name":"Remote sensing","level":1,"score":0.110088050365448},{"id":"https://openalex.org/C135572916","wikidata":"https://www.wikidata.org/wiki/Q193351","display_name":"Data warehouse","level":2,"score":0.09509167075157166},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.09235867857933044},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.06902042031288147},{"id":"https://openalex.org/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"score":0.06781160831451416},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0},{"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/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","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/C120665830","wikidata":"https://www.wikidata.org/wiki/Q14620","display_name":"Optics","level":1,"score":0.0},{"id":"https://openalex.org/C97355855","wikidata":"https://www.wikidata.org/wiki/Q11473","display_name":"Thermodynamics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/2666310.2666373","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2666310.2666373","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 22nd ACM SIGSPATIAL International Conference on Advances in Geographic Information Systems","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Industry, innovation and infrastructure","score":0.46000000834465027,"id":"https://metadata.un.org/sdg/9"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":8,"referenced_works":["https://openalex.org/W1492324553","https://openalex.org/W1792831685","https://openalex.org/W2064766209","https://openalex.org/W2106895292","https://openalex.org/W2132525863","https://openalex.org/W2171972164","https://openalex.org/W4237412827","https://openalex.org/W6629601088"],"related_works":["https://openalex.org/W821612863","https://openalex.org/W1891814256","https://openalex.org/W3092407084","https://openalex.org/W2209631380","https://openalex.org/W2954210378","https://openalex.org/W3204173350","https://openalex.org/W2600938714","https://openalex.org/W1529647666","https://openalex.org/W2381551043","https://openalex.org/W1539890788"],"abstract_inverted_index":{"A":[0],"significant":[1],"challenge":[2],"in":[3,28,95,139],"handling":[4,92],"geographic":[5,69,114],"datasets":[6,10,24,94],"is":[7,44,108,123],"that":[8,166],"the":[9,47,52,65,78,89,161,173],"can":[11,25],"come":[12],"from":[13,146],"heterogeneous":[14],"sources":[15],"with":[16],"various":[17],"data":[18,49,53,80,104,130,137,178],"qualities":[19],"and":[20,50,71,101,135,151,171,180],"formats.":[21,163],"Before":[22],"these":[23,153],"be":[26],"used":[27],"a":[29,41,55,85,96,140,147],"Geographic":[30],"Information":[31],"System":[32],"(GIS)":[33],"for":[34,76,91,111,175],"spatial":[35,66],"analysis":[36],"or":[37],"to":[38,45,132,155],"create":[39],"maps,":[40],"typical":[42],"task":[43],"clean":[46,134],"attribute":[48,79,103,158],"transform":[51,136,156],"into":[54,160],"uniform":[56],"format.":[57],"However,":[58],"conventional":[59],"GIS":[60,97],"products":[61],"focus":[62],"on":[63,125,129],"manipulating":[64],"component":[67],"of":[68,113],"features":[70],"only":[72],"offer":[73],"basic":[74],"tools":[75],"editing":[77,100],"(e.g.,":[81],"one":[82],"row":[83],"at":[84],"time).":[86],"This":[87],"limits":[88],"capability":[90],"large":[93],"since":[98],"manually":[99],"transforming":[102],"between":[105],"different":[106],"formats":[107],"not":[109],"practical":[110],"thousands":[112],"features.":[115],"In":[116],"this":[117],"demo,":[118],"we":[119],"present":[120],"ArcKarma,":[121],"which":[122],"built":[124],"our":[126],"previous":[127],"work":[128],"transformation,":[131],"efficiently":[133],"attributes":[138],"GIS.":[141],"ArcKarma":[142,167],"generates":[143],"transformation":[144],"programs":[145,154],"few":[148],"user-provided":[149],"examples":[150],"applies":[152],"individual":[157],"columns":[159],"desired":[162],"We":[164],"show":[165],"produces":[168],"accurate":[169],"results":[170],"eliminates":[172],"need":[174],"laborious":[176],"manual":[177],"cleaning":[179],"scripting":[181],"tasks.":[182]},"counts_by_year":[{"year":2021,"cited_by_count":2},{"year":2018,"cited_by_count":1},{"year":2017,"cited_by_count":1},{"year":2016,"cited_by_count":1},{"year":2015,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
