{"id":"https://openalex.org/W2295483185","doi":"https://doi.org/10.1145/1835804.1835806","title":"Data winnowing","display_name":"Data winnowing","publication_year":2010,"publication_date":"2010-07-25","ids":{"openalex":"https://openalex.org/W2295483185","doi":"https://doi.org/10.1145/1835804.1835806","mag":"2295483185"},"language":"en","primary_location":{"id":"doi:10.1145/1835804.1835806","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1835804.1835806","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 16th ACM SIGKDD international conference on Knowledge discovery and data mining","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/A5072341135","display_name":"Yoav Freund","orcid":"https://orcid.org/0000-0002-3850-6184"},"institutions":[{"id":"https://openalex.org/I36258959","display_name":"University of California, San Diego","ror":"https://ror.org/0168r3w48","country_code":"US","type":"education","lineage":["https://openalex.org/I36258959"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Yoav Freund","raw_affiliation_strings":["University of California, San Diego, USA"],"affiliations":[{"raw_affiliation_string":"University of California, San Diego, USA","institution_ids":["https://openalex.org/I36258959"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5072341135"],"corresponding_institution_ids":["https://openalex.org/I36258959"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.17015616,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"3","last_page":"4"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T13937","display_name":"Genetics, Bioinformatics, and Biomedical Research","score":0.13040000200271606,"subfield":{"id":"https://openalex.org/subfields/1312","display_name":"Molecular Biology"},"field":{"id":"https://openalex.org/fields/13","display_name":"Biochemistry, Genetics and Molecular Biology"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},"topics":[{"id":"https://openalex.org/T13937","display_name":"Genetics, Bioinformatics, and Biomedical Research","score":0.13040000200271606,"subfield":{"id":"https://openalex.org/subfields/1312","display_name":"Molecular Biology"},"field":{"id":"https://openalex.org/fields/13","display_name":"Biochemistry, Genetics and Molecular Biology"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/winnowing","display_name":"Winnowing","score":0.9618369340896606},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6189990639686584},{"id":"https://openalex.org/keywords/variety","display_name":"Variety (cybernetics)","score":0.5719045996665955},{"id":"https://openalex.org/keywords/biological-data","display_name":"Biological data","score":0.5196836590766907},{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.41766250133514404},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.3582965135574341},{"id":"https://openalex.org/keywords/data-science","display_name":"Data science","score":0.3336760103702545},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.26125121116638184},{"id":"https://openalex.org/keywords/geography","display_name":"Geography","score":0.19698232412338257},{"id":"https://openalex.org/keywords/biology","display_name":"Biology","score":0.1763245165348053},{"id":"https://openalex.org/keywords/bioinformatics","display_name":"Bioinformatics","score":0.09125801920890808}],"concepts":[{"id":"https://openalex.org/C9396515","wikidata":"https://www.wikidata.org/wiki/Q961751","display_name":"Winnowing","level":2,"score":0.9618369340896606},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6189990639686584},{"id":"https://openalex.org/C136197465","wikidata":"https://www.wikidata.org/wiki/Q1729295","display_name":"Variety (cybernetics)","level":2,"score":0.5719045996665955},{"id":"https://openalex.org/C201797286","wikidata":"https://www.wikidata.org/wiki/Q4914986","display_name":"Biological data","level":2,"score":0.5196836590766907},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.41766250133514404},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.3582965135574341},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.3336760103702545},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.26125121116638184},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.19698232412338257},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.1763245165348053},{"id":"https://openalex.org/C60644358","wikidata":"https://www.wikidata.org/wiki/Q128570","display_name":"Bioinformatics","level":1,"score":0.09125801920890808},{"id":"https://openalex.org/C166957645","wikidata":"https://www.wikidata.org/wiki/Q23498","display_name":"Archaeology","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/1835804.1835806","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1835804.1835806","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 16th ACM SIGKDD international conference on Knowledge discovery and data mining","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W2056302143","https://openalex.org/W2380102103","https://openalex.org/W2808839349","https://openalex.org/W4293080099","https://openalex.org/W2383760405","https://openalex.org/W1768142643","https://openalex.org/W1428398981","https://openalex.org/W4301394113","https://openalex.org/W2361745471","https://openalex.org/W2899267400"],"abstract_inverted_index":{"Massive":[0],"quantities":[1],"of":[2,11,42,50,56,75,81],"digital":[3],"data":[4,33,52],"are":[5],"being":[6],"collected":[7],"in":[8,72,84,100],"every":[9],"aspect":[10],"modern":[12],"life.":[13],"Examples":[14],"include":[15],"Personal":[16],"photos":[17],"and":[18,21,24,87,93,105],"videos,":[19],"biological":[20],"medical":[22],"images":[23],"recordings":[25],"from":[26,78],"sensor":[27],"arrays.":[28],"To":[29],"transform":[30],"these":[31],"massive":[32],"streams":[34],"into":[35],"useful":[36],"information":[37],"we":[38],"use":[39],"a":[40,73],"sequence":[41],"\"winnowing\"":[43],"stages.":[44],"Each":[45],"step":[46],"reduces":[47],"the":[48,51,59,62,79],"size":[49],"by":[53],"an":[54],"order":[55],"magnitude;":[57],"extracting":[58],"wheat":[60],"form":[61],"chaff.":[63],"In":[64],"this":[65,70],"talk":[66],"I":[67],"will":[68],"describe":[69],"approach":[71],"variety":[74],"contexts,":[76],"ranging":[77],"analysis":[80],"genetic":[82],"pathways":[83],"fruit-fly":[85],"embryos":[86],"C-Elegans":[88],"worms":[89],"to":[90],"counting":[91],"birds":[92],"helping":[94],"elderly":[95],"people":[96],"living":[97],"alone":[98],"keep":[99],"touch":[101],"with":[102],"their":[103],"family":[104],"caregivers.":[106]},"counts_by_year":[],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2016-06-24T00:00:00"}
