{"id":"https://openalex.org/W2622274540","doi":"https://doi.org/10.1145/3075564.3078886","title":"Finding the Critical Sampling of Big Datasets","display_name":"Finding the Critical Sampling of Big Datasets","publication_year":2017,"publication_date":"2017-05-15","ids":{"openalex":"https://openalex.org/W2622274540","doi":"https://doi.org/10.1145/3075564.3078886","mag":"2622274540"},"language":"en","primary_location":{"id":"doi:10.1145/3075564.3078886","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3075564.3078886","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Computing Frontiers Conference","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/A5003160587","display_name":"Jos\u00e9 Tom\u00e1s da Silva","orcid":"https://orcid.org/0000-0002-9995-8221"},"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":true,"raw_author_name":"Jos\u00e9 Silva","raw_affiliation_strings":["Department of Informatics Engineering, University of Coimbra, Coimbra, Portugal"],"affiliations":[{"raw_affiliation_string":"Department of Informatics Engineering, University of Coimbra, Coimbra, Portugal","institution_ids":["https://openalex.org/I76903346"]}]},{"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":["Department of Informatics Engineering, University of Coimbra, Coimbra, Portugal"],"affiliations":[{"raw_affiliation_string":"Department of Informatics Engineering, University of Coimbra, Coimbra, Portugal","institution_ids":["https://openalex.org/I76903346"]}]},{"author_position":"last","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":false,"raw_author_name":"Andrew H. Sung","raw_affiliation_strings":["School of Computing, The University of Southern Mississippi, Hattiesburg, Mississippi"],"affiliations":[{"raw_affiliation_string":"School of Computing, The University of Southern Mississippi, Hattiesburg, Mississippi","institution_ids":["https://openalex.org/I44854399"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5003160587"],"corresponding_institution_ids":["https://openalex.org/I76903346"],"apc_list":null,"apc_paid":null,"fwci":0.39,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":{"value":0.69290365,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"355","last_page":"360"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12535","display_name":"Machine Learning and Data Classification","score":0.9990000128746033,"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/T12535","display_name":"Machine Learning and Data Classification","score":0.9990000128746033,"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/T12072","display_name":"Machine Learning and Algorithms","score":0.9970999956130981,"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/T10538","display_name":"Data Mining Algorithms and Applications","score":0.9909999966621399,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8222960233688354},{"id":"https://openalex.org/keywords/big-data","display_name":"Big data","score":0.7950146198272705},{"id":"https://openalex.org/keywords/sampling","display_name":"Sampling (signal processing)","score":0.6185909509658813},{"id":"https://openalex.org/keywords/data-science","display_name":"Data science","score":0.5985035300254822},{"id":"https://openalex.org/keywords/analytics","display_name":"Analytics","score":0.5892088413238525},{"id":"https://openalex.org/keywords/knowledge-extraction","display_name":"Knowledge extraction","score":0.5352495312690735},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.5161095857620239},{"id":"https://openalex.org/keywords/feature-selection","display_name":"Feature selection","score":0.4600970149040222},{"id":"https://openalex.org/keywords/the-internet","display_name":"The Internet","score":0.419309139251709},{"id":"https://openalex.org/keywords/predictive-analytics","display_name":"Predictive analytics","score":0.4175504744052887},{"id":"https://openalex.org/keywords/heuristic","display_name":"Heuristic","score":0.4153258204460144},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3119348883628845},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.29391205310821533},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.1483730971813202}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8222960233688354},{"id":"https://openalex.org/C75684735","wikidata":"https://www.wikidata.org/wiki/Q858810","display_name":"Big data","level":2,"score":0.7950146198272705},{"id":"https://openalex.org/C140779682","wikidata":"https://www.wikidata.org/wiki/Q210868","display_name":"Sampling (signal processing)","level":3,"score":0.6185909509658813},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.5985035300254822},{"id":"https://openalex.org/C79158427","wikidata":"https://www.wikidata.org/wiki/Q485396","display_name":"Analytics","level":2,"score":0.5892088413238525},{"id":"https://openalex.org/C120567893","wikidata":"https://www.wikidata.org/wiki/Q1582085","display_name":"Knowledge extraction","level":2,"score":0.5352495312690735},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.5161095857620239},{"id":"https://openalex.org/C148483581","wikidata":"https://www.wikidata.org/wiki/Q446488","display_name":"Feature selection","level":2,"score":0.4600970149040222},{"id":"https://openalex.org/C110875604","wikidata":"https://www.wikidata.org/wiki/Q75","display_name":"The Internet","level":2,"score":0.419309139251709},{"id":"https://openalex.org/C83209312","wikidata":"https://www.wikidata.org/wiki/Q1053367","display_name":"Predictive analytics","level":2,"score":0.4175504744052887},{"id":"https://openalex.org/C173801870","wikidata":"https://www.wikidata.org/wiki/Q201413","display_name":"Heuristic","level":2,"score":0.4153258204460144},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3119348883628845},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.29391205310821533},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.1483730971813202},{"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:10.1145/3075564.3078886","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3075564.3078886","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Computing Frontiers Conference","raw_type":"proceedings-article"},{"id":"pmh:oai:aquila.usm.edu:fac_pubs-19685","is_oa":false,"landing_page_url":"https://aquila.usm.edu/fac_pubs/18371","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":4,"referenced_works":["https://openalex.org/W1517928879","https://openalex.org/W1751962365","https://openalex.org/W2324334594","https://openalex.org/W2381598956"],"related_works":["https://openalex.org/W2052370551","https://openalex.org/W2570647323","https://openalex.org/W2206805568","https://openalex.org/W2076942471","https://openalex.org/W2515921780","https://openalex.org/W2863268765","https://openalex.org/W3027285423","https://openalex.org/W2896245927","https://openalex.org/W4205879366","https://openalex.org/W1961101704"],"abstract_inverted_index":{"Big":[0],"Data":[1],"allied":[2],"to":[3,29,45,93],"the":[4,59,68,85,95],"Internet":[5],"of":[6,62,67,98],"Things":[7],"nowadays":[8],"provides":[9],"a":[10,90],"powerful":[11],"resource":[12],"that":[13,58],"various":[14],"organizations":[15],"are":[16,72],"increasingly":[17],"exploiting":[18],"for":[19],"applications":[20],"ranging":[21],"from":[22],"decision":[23],"support,":[24],"predictive":[25],"and":[26,32,37,79,88],"prescriptive":[27],"analytics,":[28],"knowledge":[30],"extraction":[31],"intelligence":[33],"discovery.":[34],"In":[35],"analytics":[36],"data":[38,49,60],"mining":[39],"processes,":[40],"it":[41,53],"is":[42,54,61],"usually":[43],"desirable":[44],"have":[46],"as":[47,50],"much":[48],"possible,":[51],"though":[52],"often":[55],"more":[56],"important":[57,70],"high":[63],"quality":[64],"thereby":[65],"two":[66],"most":[69],"problems":[71],"raised":[73],"when":[74],"handling":[75],"large":[76],"datasets:":[77],"sampling":[78,86],"feature":[80],"selection.":[81],"This":[82],"paper":[83],"addresses":[84],"problem":[87],"presents":[89],"heuristic":[91],"method":[92],"find":[94],"\"critical":[96],"sampling\"":[97],"big":[99],"datasets.":[100]},"counts_by_year":[{"year":2022,"cited_by_count":2},{"year":2019,"cited_by_count":1},{"year":2018,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
