{"id":"https://openalex.org/W2203470973","doi":"https://doi.org/10.1109/bigdata.2015.7363882","title":"Open research challenges with Big Data \u2014 A data-scientist's perspective","display_name":"Open research challenges with Big Data \u2014 A data-scientist's perspective","publication_year":2015,"publication_date":"2015-10-01","ids":{"openalex":"https://openalex.org/W2203470973","doi":"https://doi.org/10.1109/bigdata.2015.7363882","mag":"2203470973"},"language":"en","primary_location":{"id":"doi:10.1109/bigdata.2015.7363882","is_oa":false,"landing_page_url":"https://doi.org/10.1109/bigdata.2015.7363882","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2015 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/A5079418386","display_name":"Sreenivas R. Sukumar","orcid":"https://orcid.org/0000-0003-4031-2888"},"institutions":[{"id":"https://openalex.org/I1289243028","display_name":"Oak Ridge National Laboratory","ror":"https://ror.org/01qz5mb56","country_code":"US","type":"facility","lineage":["https://openalex.org/I1289243028","https://openalex.org/I1330989302","https://openalex.org/I39565521","https://openalex.org/I4210159294"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Sreenivas R. Sukumar","raw_affiliation_strings":["Computational Sciences and Engineering Division, Oak Ridge National Laboratory, Oak Ridge, TN, USA"],"affiliations":[{"raw_affiliation_string":"Computational Sciences and Engineering Division, Oak Ridge National Laboratory, Oak Ridge, TN, USA","institution_ids":["https://openalex.org/I1289243028"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5079418386"],"corresponding_institution_ids":["https://openalex.org/I1289243028"],"apc_list":null,"apc_paid":null,"fwci":0.4314,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":{"value":0.7693867,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":95},"biblio":{"volume":"2","issue":null,"first_page":"1272","last_page":"1278"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12535","display_name":"Machine Learning and Data Classification","score":0.9995999932289124,"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":0.9995999932289124,"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/T12761","display_name":"Data Stream Mining Techniques","score":0.9983999729156494,"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/T11512","display_name":"Anomaly Detection Techniques and Applications","score":0.998199999332428,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/big-data","display_name":"Big data","score":0.8032208681106567},{"id":"https://openalex.org/keywords/data-science","display_name":"Data science","score":0.7809817790985107},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7626051902770996},{"id":"https://openalex.org/keywords/leverage","display_name":"Leverage (statistics)","score":0.6213634014129639},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.593352735042572},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.4911322295665741},{"id":"https://openalex.org/keywords/variety","display_name":"Variety (cybernetics)","score":0.4826505780220032},{"id":"https://openalex.org/keywords/cyberinfrastructure","display_name":"Cyberinfrastructure","score":0.4271274209022522},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.41851380467414856},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4089462161064148},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.24411919713020325},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.12322473526000977}],"concepts":[{"id":"https://openalex.org/C75684735","wikidata":"https://www.wikidata.org/wiki/Q858810","display_name":"Big data","level":2,"score":0.8032208681106567},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.7809817790985107},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7626051902770996},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.6213634014129639},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.593352735042572},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.4911322295665741},{"id":"https://openalex.org/C136197465","wikidata":"https://www.wikidata.org/wiki/Q1729295","display_name":"Variety (cybernetics)","level":2,"score":0.4826505780220032},{"id":"https://openalex.org/C2776397876","wikidata":"https://www.wikidata.org/wiki/Q1450531","display_name":"Cyberinfrastructure","level":2,"score":0.4271274209022522},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.41851380467414856},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4089462161064148},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.24411919713020325},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.12322473526000977},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/bigdata.2015.7363882","is_oa":false,"landing_page_url":"https://doi.org/10.1109/bigdata.2015.7363882","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2015 IEEE International Conference on Big Data (Big Data)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/9","score":0.49000000953674316,"display_name":"Industry, innovation and infrastructure"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320306084","display_name":"U.S. Department of Energy","ror":"https://ror.org/01bj3aw27"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":38,"referenced_works":["https://openalex.org/W41478905","https://openalex.org/W603723648","https://openalex.org/W1548849615","https://openalex.org/W1959000896","https://openalex.org/W1968573882","https://openalex.org/W2004798878","https://openalex.org/W2010030599","https://openalex.org/W2016089260","https://openalex.org/W2044849727","https://openalex.org/W2055681363","https://openalex.org/W2060747549","https://openalex.org/W2072128103","https://openalex.org/W2081580037","https://openalex.org/W2085869645","https://openalex.org/W2087931821","https://openalex.org/W2108598243","https://openalex.org/W2109722477","https://openalex.org/W2110764733","https://openalex.org/W2121082877","https://openalex.org/W2130903752","https://openalex.org/W2145525236","https://openalex.org/W2155803963","https://openalex.org/W2162390675","https://openalex.org/W2231104193","https://openalex.org/W2282290820","https://openalex.org/W2620485168","https://openalex.org/W2799061466","https://openalex.org/W3120740533","https://openalex.org/W4205687621","https://openalex.org/W4231109964","https://openalex.org/W4242732001","https://openalex.org/W6601671229","https://openalex.org/W6676367512","https://openalex.org/W6678286823","https://openalex.org/W6679734692","https://openalex.org/W6683722107","https://openalex.org/W6695682035","https://openalex.org/W6788247690"],"related_works":["https://openalex.org/W273500195","https://openalex.org/W2043019925","https://openalex.org/W4236056781","https://openalex.org/W4399254454","https://openalex.org/W4293768956","https://openalex.org/W2773781927","https://openalex.org/W2184477657","https://openalex.org/W90628286","https://openalex.org/W1696735061","https://openalex.org/W2152811545"],"abstract_inverted_index":{"In":[0,61],"this":[1],"paper,":[2],"we":[3,64],"discuss":[4,98],"data-driven":[5],"discovery":[6,122],"challenges":[7,102],"of":[8,30,36,108,126,164,173,204,211],"the":[9,56,68,77,95,104,139,143,161,168,184,190],"Big":[10,119],"Data":[11,120],"era.":[12],"We":[13,90,114,206],"observe":[14],"that":[15,62],"recent":[16,92],"innovations":[17],"in":[18,94,103],"being":[19],"able":[20],"to":[21,79,97,132,170,192],"collect,":[22],"access,":[23],"organize,":[24],"integrate,":[25],"and":[26,44,50,66,81,100,106,130,150,180,182,195,202,213],"query":[27],"massive":[28],"amounts":[29],"data":[31,37,42,57,72,174],"from":[32,55,117],"a":[33,209],"wide":[34],"variety":[35],"sources":[38],"have":[39],"brought":[40],"statistical":[41],"mining":[43,73],"machine":[45,109,155,177],"learning":[46,110,156,178],"under":[47],"more":[48],"scrutiny":[49],"evaluation":[51],"for":[52,154,215],"gleaning":[53],"insights":[54],"than":[58],"ever":[59],"before.":[60],"context,":[63],"pose":[65],"debate":[67],"question":[69],"-":[70,147,167,189],"Are":[71],"algorithms":[74,111,179],"scaling":[75],"with":[76,197,208],"ability":[78,169,191],"store":[80],"compute?":[82],"If":[83,86],"yes,":[84],"how?":[85],"not,":[87],"why":[88],"not?":[89],"survey":[91],"developments":[93],"state-of-the-art":[96],"emerging":[99],"outstanding":[101],"design":[105],"implementation":[107],"at":[112],"scale.":[113],"leverage":[115],"experience":[116],"real-world":[118],"knowledge":[121],"projects":[123],"across":[124],"domains":[125],"national":[127],"security,":[128],"healthcare":[129],"manufacturing":[131],"suggest":[133],"our":[134],"efforts":[135],"be":[136],"focused":[137],"along":[138],"following":[140],"axes:":[141],"(i)":[142],"`data":[144],"science'":[145],"challenge":[146,166,188],"designing":[148],"scalable":[149],"flexible":[151],"computational":[152],"architectures":[153],"(beyond":[157],"just":[158],"data-retrieval);":[159],"(ii)":[160],"`":[162],"science":[163],"data'":[165],"understand":[171],"characteristics":[172],"before":[175],"applying":[176],"tools;":[181],"(iii)":[183],"`scalable":[185],"predictive":[186],"functions'":[187],"construct,":[193],"learn":[194],"infer":[196],"increasing":[198],"sample":[199],"size,":[200],"dimensionality,":[201],"categories":[203],"labels.":[205],"conclude":[207],"discussion":[210],"opportunities":[212],"directions":[214],"future":[216],"research.":[217]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2021,"cited_by_count":2},{"year":2019,"cited_by_count":1},{"year":2016,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}