{"id":"https://openalex.org/W2381598956","doi":"https://doi.org/10.5220/0005932703780382","title":"Sampling and Evaluating the Big Data for Knowledge Discovery","display_name":"Sampling and Evaluating the Big Data for Knowledge Discovery","publication_year":2016,"publication_date":"2016-01-01","ids":{"openalex":"https://openalex.org/W2381598956","doi":"https://doi.org/10.5220/0005932703780382","mag":"2381598956"},"language":"en","primary_location":{"id":"doi:10.5220/0005932703780382","is_oa":false,"landing_page_url":"https://doi.org/10.5220/0005932703780382","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the International Conference on Internet of Things and 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/A5027821975","display_name":"Andrew H. Sung","orcid":"https://orcid.org/0009-0005-0815-3102"},"institutions":[{"id":"https://openalex.org/I44854399","display_name":"University of Southern Mississippi","ror":"https://ror.org/0270vfa57","country_code":"US","type":"education","lineage":["https://openalex.org/I4210141039","https://openalex.org/I44854399"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Andrew H. Sung","raw_affiliation_strings":["The University of Southern Mississippi, United States"],"affiliations":[{"raw_affiliation_string":"The University of Southern Mississippi, United States","institution_ids":["https://openalex.org/I44854399"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5046882659","display_name":"Bernardete Ribeiro","orcid":"https://orcid.org/0000-0002-9770-7672"},"institutions":[{"id":"https://openalex.org/I76903346","display_name":"University of Coimbra","ror":"https://ror.org/04z8k9a98","country_code":"PT","type":"education","lineage":["https://openalex.org/I76903346"]}],"countries":["PT"],"is_corresponding":false,"raw_author_name":"Bernardete Ribeiro","raw_affiliation_strings":["University of Coimbra, Portugal"],"affiliations":[{"raw_affiliation_string":"University of Coimbra, Portugal","institution_ids":["https://openalex.org/I76903346"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100746642","display_name":"Qingzhong Liu","orcid":"https://orcid.org/0000-0002-2006-5413"},"institutions":[{"id":"https://openalex.org/I191429286","display_name":"Sam Houston State University","ror":"https://ror.org/00yh3cz06","country_code":"US","type":"education","lineage":["https://openalex.org/I191429286"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Qingzhong Liu","raw_affiliation_strings":["Sam Houston State University, United States"],"affiliations":[{"raw_affiliation_string":"Sam Houston State University, United States","institution_ids":["https://openalex.org/I191429286"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5027821975"],"corresponding_institution_ids":["https://openalex.org/I44854399"],"apc_list":null,"apc_paid":null,"fwci":2.6558744,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":{"value":0.91922767,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"378","last_page":"382"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10538","display_name":"Data Mining Algorithms and Applications","score":0.8457000255584717,"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/T10538","display_name":"Data Mining Algorithms and Applications","score":0.8457000255584717,"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/T11891","display_name":"Big Data and Business Intelligence","score":0.7523999810218811,"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"}},{"id":"https://openalex.org/T14280","display_name":"Big Data Technologies and Applications","score":0.737500011920929,"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/computer-science","display_name":"Computer science","score":0.7067528963088989},{"id":"https://openalex.org/keywords/big-data","display_name":"Big data","score":0.6494839191436768},{"id":"https://openalex.org/keywords/knowledge-extraction","display_name":"Knowledge extraction","score":0.6283677816390991},{"id":"https://openalex.org/keywords/sampling","display_name":"Sampling (signal processing)","score":0.5509042143821716},{"id":"https://openalex.org/keywords/data-science","display_name":"Data science","score":0.531791627407074},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.4400784373283386}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7067528963088989},{"id":"https://openalex.org/C75684735","wikidata":"https://www.wikidata.org/wiki/Q858810","display_name":"Big data","level":2,"score":0.6494839191436768},{"id":"https://openalex.org/C120567893","wikidata":"https://www.wikidata.org/wiki/Q1582085","display_name":"Knowledge extraction","level":2,"score":0.6283677816390991},{"id":"https://openalex.org/C140779682","wikidata":"https://www.wikidata.org/wiki/Q210868","display_name":"Sampling (signal processing)","level":3,"score":0.5509042143821716},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.531791627407074},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.4400784373283386},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.0},{"id":"https://openalex.org/C106131492","wikidata":"https://www.wikidata.org/wiki/Q3072260","display_name":"Filter (signal processing)","level":2,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.5220/0005932703780382","is_oa":false,"landing_page_url":"https://doi.org/10.5220/0005932703780382","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the International Conference on Internet of Things and Big Data","raw_type":"proceedings-article"},{"id":"pmh:oai:aquila.usm.edu:fac_pubs-21065","is_oa":false,"landing_page_url":"https://aquila.usm.edu/fac_pubs/19738","pdf_url":null,"source":{"id":"https://openalex.org/S4306402529","display_name":"Aquila Digital Community (University of Southern Mississippi)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I44854399","host_organization_name":"University of Southern Mississippi","host_organization_lineage":["https://openalex.org/I44854399"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Faculty Publications","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W4322629366","https://openalex.org/W2808989540","https://openalex.org/W2397053934","https://openalex.org/W1039292361","https://openalex.org/W2551093110","https://openalex.org/W2148016376","https://openalex.org/W4237919137","https://openalex.org/W3184179822","https://openalex.org/W3095362084","https://openalex.org/W3003361536"],"abstract_inverted_index":{"The":[0],"era":[1],"of":[2,4,39,82,102,124,170,179,182],"Internet":[3],"Things":[5],"and":[6,13,26,47,118,160,189],"big":[7,31,115,127,193],"data":[8,18,32,69,85,116,128,158,194],"has":[9],"seen":[10],"individuals,":[11],"businesses,":[12],"organizations":[14],"increasingly":[15,54],"rely":[16],"on":[17],"for":[19,64,71,91,129],"routine":[20],"operations,":[21],"decision":[22],"making,":[23],"intelligence":[24],"gathering,":[25],"knowledge":[27,72,190],"discovery.":[28],"As":[29],"the":[30,60,77,93,100,111,122,126,177,180],"is":[33,52,86,131,134,165,173],"being":[34,55],"generated":[35],"by":[36],"all":[37],"sorts":[38],"sources":[40],"at":[41],"accelerated":[42],"velocity,":[43],"in":[44,59,114,157,192],"increasing":[45],"volumes,":[46],"with":[48,184],"unprecedented":[49],"variety,":[50],"it":[51,133],"also":[53],"traded":[56],"as":[57],"commodity":[58],"new":[61],"\"data":[62],"economy\"":[63],"utilization.":[65],"With":[66],"regard":[67],"to":[68,76,175,186],"analytics":[70,117,130],"discovery,":[73],"this":[74,106],"leads":[75],"question,":[78],"among":[79],"various":[80],"others,":[81],"how":[83],"much":[84],"really":[87],"necessary":[88],"and/or":[89],"sufficient":[90],"getting":[92],"analytic":[94],"results":[95],"that":[96,120],"will":[97],"reasonably":[98],"satisfy":[99],"requirements":[101],"an":[103],"application.":[104],"In":[105],"work-in-progress":[107],"paper,":[108],"we":[109],"address":[110],"sampling":[112,125],"problem":[113,123,138],"propose":[119],"(1)":[121],"\"hard\"-specifically,":[132],"a":[135,161,168],"theoretically":[136],"intractable":[137],"when":[139],"formal":[140],"measures":[141],"are":[142,154],"incorporated":[143],"into":[144],"performance":[145],"evaluation;":[146],"therefore,":[147],"(2)":[148],"heuristic,":[149],"rather":[150],"than":[151],"algorithmic,":[152],"methods":[153],"necessarily":[155],"needed":[156],"sampling,":[159],"plausible":[162],"heuristic":[163],"method":[164],"proposed":[166,174],"(3)":[167],"measure":[169],"dataset":[171],"quality":[172],"facilitate":[176],"evaluation":[178],"worthiness":[181],"datasets":[183],"respect":[185],"model":[187],"building":[188],"discovery":[191],"analytics.":[195]},"counts_by_year":[{"year":2022,"cited_by_count":1},{"year":2018,"cited_by_count":1},{"year":2017,"cited_by_count":3}],"updated_date":"2026-02-09T09:26:11.010843","created_date":"2025-10-10T00:00:00"}