{"id":"https://openalex.org/W2025406780","doi":"https://doi.org/10.1109/bigdata.2014.7004388","title":"Duplicate drug discovery using Hadoop","display_name":"Duplicate drug discovery using Hadoop","publication_year":2014,"publication_date":"2014-10-01","ids":{"openalex":"https://openalex.org/W2025406780","doi":"https://doi.org/10.1109/bigdata.2014.7004388","mag":"2025406780"},"language":"en","primary_location":{"id":"doi:10.1109/bigdata.2014.7004388","is_oa":false,"landing_page_url":"https://doi.org/10.1109/bigdata.2014.7004388","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2014 IEEE International Conference on Big Data (Big Data)","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/A5112519217","display_name":"Cheng Shao","orcid":null},"institutions":[{"id":"https://openalex.org/I3141939062","display_name":"Institute for Information Industry","ror":"https://ror.org/01d8kr740","country_code":"TW","type":"nonprofit","lineage":["https://openalex.org/I3141939062"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Shao Hua Cheng","raw_affiliation_strings":["Advanced Research Institute Institute for Information Industry, Taipei, Taiwan, ROC","Advanced Research Institute, Institute for Information Industry, Taipei, Taiwan, ROC"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Advanced Research Institute Institute for Information Industry, Taipei, Taiwan, ROC","institution_ids":["https://openalex.org/I3141939062"]},{"raw_affiliation_string":"Advanced Research Institute, Institute for Information Industry, Taipei, Taiwan, ROC","institution_ids":["https://openalex.org/I3141939062"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5081727166","display_name":"Yu Shian Chiu","orcid":null},"institutions":[{"id":"https://openalex.org/I3141939062","display_name":"Institute for Information Industry","ror":"https://ror.org/01d8kr740","country_code":"TW","type":"nonprofit","lineage":["https://openalex.org/I3141939062"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Yu Shian Chiu","raw_affiliation_strings":["Advanced Research Institute Institute for Information Industry, Taipei, Taiwan, ROC","Advanced Research Institute, Institute for Information Industry, Taipei, Taiwan, ROC"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Advanced Research Institute Institute for Information Industry, Taipei, Taiwan, ROC","institution_ids":["https://openalex.org/I3141939062"]},{"raw_affiliation_string":"Advanced Research Institute, Institute for Information Industry, Taipei, Taiwan, ROC","institution_ids":["https://openalex.org/I3141939062"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5003313140","display_name":"Shih Yao Dai","orcid":null},"institutions":[{"id":"https://openalex.org/I3141939062","display_name":"Institute for Information Industry","ror":"https://ror.org/01d8kr740","country_code":"TW","type":"nonprofit","lineage":["https://openalex.org/I3141939062"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Shih Yao Dai","raw_affiliation_strings":["Advanced Research Institute Institute for Information Industry, Taipei, Taiwan, ROC","Advanced Research Institute, Institute for Information Industry, Taipei, Taiwan, ROC"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Advanced Research Institute Institute for Information Industry, Taipei, Taiwan, ROC","institution_ids":["https://openalex.org/I3141939062"]},{"raw_affiliation_string":"Advanced Research Institute, Institute for Information Industry, Taipei, Taiwan, ROC","institution_ids":["https://openalex.org/I3141939062"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5075510577","display_name":"Hui-I Hsiao","orcid":null},"institutions":[{"id":"https://openalex.org/I3141939062","display_name":"Institute for Information Industry","ror":"https://ror.org/01d8kr740","country_code":"TW","type":"nonprofit","lineage":["https://openalex.org/I3141939062"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Hui-I Hsiao","raw_affiliation_strings":["Advanced Research Institute Institute for Information Industry, Taipei, Taiwan, ROC","Advanced Research Institute, Institute for Information Industry, Taipei, Taiwan, ROC"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Advanced Research Institute Institute for Information Industry, Taipei, Taiwan, ROC","institution_ids":["https://openalex.org/I3141939062"]},{"raw_affiliation_string":"Advanced Research Institute, Institute for Information Industry, Taipei, Taiwan, ROC","institution_ids":["https://openalex.org/I3141939062"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.4202,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.69427023,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"24","last_page":"26"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11719","display_name":"Data Quality and Management","score":0.9950000047683716,"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":0.9950000047683716,"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/T11396","display_name":"Artificial Intelligence in Healthcare","score":0.9528999924659729,"subfield":{"id":"https://openalex.org/subfields/3605","display_name":"Health Information Management"},"field":{"id":"https://openalex.org/fields/36","display_name":"Health Professions"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}},{"id":"https://openalex.org/T11891","display_name":"Big Data and Business Intelligence","score":0.9262999892234802,"subfield":{"id":"https://openalex.org/subfields/1404","display_name":"Management Information Systems"},"field":{"id":"https://openalex.org/fields/14","display_name":"Business, Management and Accounting"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/health-care","display_name":"Health care","score":0.6172623634338379},{"id":"https://openalex.org/keywords/variety","display_name":"Variety (cybernetics)","score":0.611082136631012},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6040016412734985},{"id":"https://openalex.org/keywords/medical-prescription","display_name":"Medical prescription","score":0.5256867408752441},{"id":"https://openalex.org/keywords/prescription-drug","display_name":"Prescription drug","score":0.45574143528938293},{"id":"https://openalex.org/keywords/data-science","display_name":"Data science","score":0.41804179549217224},{"id":"https://openalex.org/keywords/business","display_name":"Business","score":0.35452190041542053},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.11182644963264465},{"id":"https://openalex.org/keywords/medicine","display_name":"Medicine","score":0.1093207597732544},{"id":"https://openalex.org/keywords/economics","display_name":"Economics","score":0.08030211925506592}],"concepts":[{"id":"https://openalex.org/C160735492","wikidata":"https://www.wikidata.org/wiki/Q31207","display_name":"Health care","level":2,"score":0.6172623634338379},{"id":"https://openalex.org/C136197465","wikidata":"https://www.wikidata.org/wiki/Q1729295","display_name":"Variety (cybernetics)","level":2,"score":0.611082136631012},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6040016412734985},{"id":"https://openalex.org/C2426938","wikidata":"https://www.wikidata.org/wiki/Q3355478","display_name":"Medical prescription","level":2,"score":0.5256867408752441},{"id":"https://openalex.org/C2778858636","wikidata":"https://www.wikidata.org/wiki/Q1643563","display_name":"Prescription drug","level":3,"score":0.45574143528938293},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.41804179549217224},{"id":"https://openalex.org/C144133560","wikidata":"https://www.wikidata.org/wiki/Q4830453","display_name":"Business","level":0,"score":0.35452190041542053},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.11182644963264465},{"id":"https://openalex.org/C71924100","wikidata":"https://www.wikidata.org/wiki/Q11190","display_name":"Medicine","level":0,"score":0.1093207597732544},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.08030211925506592},{"id":"https://openalex.org/C98274493","wikidata":"https://www.wikidata.org/wiki/Q128406","display_name":"Pharmacology","level":1,"score":0.0},{"id":"https://openalex.org/C50522688","wikidata":"https://www.wikidata.org/wiki/Q189833","display_name":"Economic growth","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/bigdata.2014.7004388","is_oa":false,"landing_page_url":"https://doi.org/10.1109/bigdata.2014.7004388","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2014 IEEE International Conference on Big Data (Big Data)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320336958","display_name":"Institute for Information Industry, Ministry of Science and Technology, Taiwan","ror":"https://ror.org/01d8kr740"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W2361820086","https://openalex.org/W4388487825","https://openalex.org/W2368224867","https://openalex.org/W3029903131","https://openalex.org/W3111030087","https://openalex.org/W2341334583","https://openalex.org/W2385685139","https://openalex.org/W3151315576","https://openalex.org/W1960377041","https://openalex.org/W2413810328"],"abstract_inverted_index":{"Rising":[0],"healthcare":[1,33,37,56],"costs":[2],"in":[3,94],"recent":[4],"years":[5],"has":[6,41],"become":[7,42],"a":[8,31,43,68,80,92,122],"major":[9],"issue":[10],"for":[11,46],"many":[12,47],"countries.":[13],"This":[14],"is":[15,67],"especially":[16],"prominent":[17],"as":[18],"baby":[19],"boomers":[20],"reaching":[21],"their":[22],"retirement":[23],"age":[24],"and":[25,51],"thus":[26],"demanding":[27],"large":[28,53],"shares":[29],"of":[30,55,60,109],"country's":[32],"resources.":[34],"Consequently,":[35],"reducing":[36],"cost":[38,64],"or":[39],"waste":[40],"top":[44],"priority":[45],"governments.":[48],"However,":[49],"integrating":[50],"analyzing":[52],"amount":[54],"data":[57,127],"with":[58],"variety":[59],"formats":[61],"to":[62,116,121],"identify":[63],"saving":[65],"opportunities":[66],"very":[69],"complex":[70],"problem.":[71],"To":[72],"help":[73],"addressing":[74],"the":[75],"problem,":[76],"this":[77],"paper":[78],"proposes":[79],"Hadoop":[81],"based":[82],"approach":[83,105,124],"that":[84,103],"can":[85,106],"efficiently":[86],"discover":[87,107],"duplicate":[88,110],"drug":[89,111],"usage":[90],"by":[91],"patient":[93],"any":[95],"given":[96],"time":[97],"period.":[98],"Our":[99],"experiment":[100],"results":[101],"show":[102],"our":[104],"cases":[108],"prescription":[112],"much":[113],"faster,":[114,119],"up":[115],"100":[117],"times":[118],"compared":[120],"traditional":[123],"using":[125],"relational":[126],"warehouse.":[128]},"counts_by_year":[{"year":2020,"cited_by_count":1},{"year":2018,"cited_by_count":1},{"year":2017,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}