{"id":"https://openalex.org/W2809816183","doi":"https://doi.org/10.23919/mipro.2018.8400232","title":"Solution for detecting sensitive data inside a data lake","display_name":"Solution for detecting sensitive data inside a data lake","publication_year":2018,"publication_date":"2018-05-01","ids":{"openalex":"https://openalex.org/W2809816183","doi":"https://doi.org/10.23919/mipro.2018.8400232","mag":"2809816183"},"language":"en","primary_location":{"id":"doi:10.23919/mipro.2018.8400232","is_oa":false,"landing_page_url":"https://doi.org/10.23919/mipro.2018.8400232","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 41st International Convention on Information and Communication Technology, Electronics and Microelectronics (MIPRO)","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/A5049182863","display_name":"Silvija Toverni\u0107","orcid":null},"institutions":[{"id":"https://openalex.org/I4390039327","display_name":"Faculty of Electrical Engineering and Computing in Zagreb","ror":"https://ror.org/04e90ca47","country_code":null,"type":"education","lineage":["https://openalex.org/I181343428","https://openalex.org/I4390039327"]},{"id":"https://openalex.org/I181343428","display_name":"University of Zagreb","ror":"https://ror.org/00mv6sv71","country_code":"HR","type":"education","lineage":["https://openalex.org/I181343428"]}],"countries":["HR"],"is_corresponding":true,"raw_author_name":"S. Toverni\u0107","raw_affiliation_strings":["Faculty of Electrical Engineering and Computing, Zagreb, Croatia"],"affiliations":[{"raw_affiliation_string":"Faculty of Electrical Engineering and Computing, Zagreb, Croatia","institution_ids":["https://openalex.org/I181343428","https://openalex.org/I4390039327"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5059469529","display_name":"Vladimir Banovi\u0107","orcid":null},"institutions":[{"id":"https://openalex.org/I4390039327","display_name":"Faculty of Electrical Engineering and Computing in Zagreb","ror":"https://ror.org/04e90ca47","country_code":null,"type":"education","lineage":["https://openalex.org/I181343428","https://openalex.org/I4390039327"]},{"id":"https://openalex.org/I181343428","display_name":"University of Zagreb","ror":"https://ror.org/00mv6sv71","country_code":"HR","type":"education","lineage":["https://openalex.org/I181343428"]}],"countries":["HR"],"is_corresponding":false,"raw_author_name":"V. Banovi\u0107","raw_affiliation_strings":["Faculty of Electrical Engineering and Computing, Zagreb, Croatia"],"affiliations":[{"raw_affiliation_string":"Faculty of Electrical Engineering and Computing, Zagreb, Croatia","institution_ids":["https://openalex.org/I181343428","https://openalex.org/I4390039327"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5003815334","display_name":"Z. Hrastic","orcid":null},"institutions":[{"id":"https://openalex.org/I4390039327","display_name":"Faculty of Electrical Engineering and Computing in Zagreb","ror":"https://ror.org/04e90ca47","country_code":null,"type":"education","lineage":["https://openalex.org/I181343428","https://openalex.org/I4390039327"]},{"id":"https://openalex.org/I181343428","display_name":"University of Zagreb","ror":"https://ror.org/00mv6sv71","country_code":"HR","type":"education","lineage":["https://openalex.org/I181343428"]}],"countries":["HR"],"is_corresponding":false,"raw_author_name":"Z. Hrasti\u0107","raw_affiliation_strings":["Faculty of Electrical Engineering and Computing, Zagreb, Croatia"],"affiliations":[{"raw_affiliation_string":"Faculty of Electrical Engineering and Computing, Zagreb, Croatia","institution_ids":["https://openalex.org/I181343428","https://openalex.org/I4390039327"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5089592956","display_name":"Katarina Planti\u0107","orcid":null},"institutions":[{"id":"https://openalex.org/I181343428","display_name":"University of Zagreb","ror":"https://ror.org/00mv6sv71","country_code":"HR","type":"education","lineage":["https://openalex.org/I181343428"]},{"id":"https://openalex.org/I4390039327","display_name":"Faculty of Electrical Engineering and Computing in Zagreb","ror":"https://ror.org/04e90ca47","country_code":null,"type":"education","lineage":["https://openalex.org/I181343428","https://openalex.org/I4390039327"]}],"countries":["HR"],"is_corresponding":false,"raw_author_name":"K. Planti\u0107","raw_affiliation_strings":["Faculty of Electrical Engineering and Computing, Zagreb, Croatia"],"affiliations":[{"raw_affiliation_string":"Faculty of Electrical Engineering and Computing, Zagreb, Croatia","institution_ids":["https://openalex.org/I181343428","https://openalex.org/I4390039327"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5051166639","display_name":"Agneza Sandic","orcid":null},"institutions":[{"id":"https://openalex.org/I181343428","display_name":"University of Zagreb","ror":"https://ror.org/00mv6sv71","country_code":"HR","type":"education","lineage":["https://openalex.org/I181343428"]},{"id":"https://openalex.org/I4390039327","display_name":"Faculty of Electrical Engineering and Computing in Zagreb","ror":"https://ror.org/04e90ca47","country_code":null,"type":"education","lineage":["https://openalex.org/I181343428","https://openalex.org/I4390039327"]}],"countries":["HR"],"is_corresponding":false,"raw_author_name":"A. \u0160andi\u0107","raw_affiliation_strings":["Faculty of Electrical Engineering and Computing, Zagreb, Croatia"],"affiliations":[{"raw_affiliation_string":"Faculty of Electrical Engineering and Computing, Zagreb, Croatia","institution_ids":["https://openalex.org/I181343428","https://openalex.org/I4390039327"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5056642319","display_name":"Mirta Baranovi\u0107","orcid":"https://orcid.org/0000-0002-8941-5485"},"institutions":[{"id":"https://openalex.org/I181343428","display_name":"University of Zagreb","ror":"https://ror.org/00mv6sv71","country_code":"HR","type":"education","lineage":["https://openalex.org/I181343428"]},{"id":"https://openalex.org/I4390039327","display_name":"Faculty of Electrical Engineering and Computing in Zagreb","ror":"https://ror.org/04e90ca47","country_code":null,"type":"education","lineage":["https://openalex.org/I181343428","https://openalex.org/I4390039327"]}],"countries":["HR"],"is_corresponding":false,"raw_author_name":"M. Baranovi\u0107","raw_affiliation_strings":["Faculty of Electrical Engineering and Computing, Zagreb, Croatia"],"affiliations":[{"raw_affiliation_string":"Faculty of Electrical Engineering and Computing, Zagreb, Croatia","institution_ids":["https://openalex.org/I181343428","https://openalex.org/I4390039327"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5049182863"],"corresponding_institution_ids":["https://openalex.org/I181343428","https://openalex.org/I4390039327"],"apc_list":null,"apc_paid":null,"fwci":1.2936,"has_fulltext":false,"cited_by_count":7,"citation_normalized_percentile":{"value":0.83096518,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"1284","last_page":"1288"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11891","display_name":"Big Data and Business Intelligence","score":0.8847000002861023,"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"}},"topics":[{"id":"https://openalex.org/T11891","display_name":"Big Data and Business Intelligence","score":0.8847000002861023,"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/T10538","display_name":"Data Mining Algorithms and Applications","score":0.8439000248908997,"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/T11719","display_name":"Data Quality and Management","score":0.8382999897003174,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/dashboard","display_name":"Dashboard","score":0.7744956016540527},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7737452387809753},{"id":"https://openalex.org/keywords/master-data","display_name":"Master data","score":0.6004194617271423},{"id":"https://openalex.org/keywords/identification","display_name":"Identification (biology)","score":0.574663519859314},{"id":"https://openalex.org/keywords/cloud-computing","display_name":"Cloud computing","score":0.5641179084777832},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.5213559865951538},{"id":"https://openalex.org/keywords/analytics","display_name":"Analytics","score":0.5194075107574463},{"id":"https://openalex.org/keywords/data-stream-mining","display_name":"Data stream mining","score":0.5093115568161011},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.45044130086898804},{"id":"https://openalex.org/keywords/big-data","display_name":"Big data","score":0.4403301179409027},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.43543705344200134},{"id":"https://openalex.org/keywords/data-science","display_name":"Data science","score":0.3971814811229706},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.17519620060920715}],"concepts":[{"id":"https://openalex.org/C33499554","wikidata":"https://www.wikidata.org/wiki/Q1417134","display_name":"Dashboard","level":2,"score":0.7744956016540527},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7737452387809753},{"id":"https://openalex.org/C61871575","wikidata":"https://www.wikidata.org/wiki/Q384093","display_name":"Master data","level":2,"score":0.6004194617271423},{"id":"https://openalex.org/C116834253","wikidata":"https://www.wikidata.org/wiki/Q2039217","display_name":"Identification (biology)","level":2,"score":0.574663519859314},{"id":"https://openalex.org/C79974875","wikidata":"https://www.wikidata.org/wiki/Q483639","display_name":"Cloud computing","level":2,"score":0.5641179084777832},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.5213559865951538},{"id":"https://openalex.org/C79158427","wikidata":"https://www.wikidata.org/wiki/Q485396","display_name":"Analytics","level":2,"score":0.5194075107574463},{"id":"https://openalex.org/C89198739","wikidata":"https://www.wikidata.org/wiki/Q3079880","display_name":"Data stream mining","level":2,"score":0.5093115568161011},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.45044130086898804},{"id":"https://openalex.org/C75684735","wikidata":"https://www.wikidata.org/wiki/Q858810","display_name":"Big data","level":2,"score":0.4403301179409027},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.43543705344200134},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.3971814811229706},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.17519620060920715},{"id":"https://openalex.org/C59822182","wikidata":"https://www.wikidata.org/wiki/Q441","display_name":"Botany","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.23919/mipro.2018.8400232","is_oa":false,"landing_page_url":"https://doi.org/10.23919/mipro.2018.8400232","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 41st International Convention on Information and Communication Technology, Electronics and Microelectronics (MIPRO)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Industry, innovation and infrastructure","score":0.6399999856948853,"id":"https://metadata.un.org/sdg/9"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":1,"referenced_works":["https://openalex.org/W2530589556"],"related_works":["https://openalex.org/W2607236244","https://openalex.org/W2382083831","https://openalex.org/W4390608645","https://openalex.org/W4247566972","https://openalex.org/W2960264696","https://openalex.org/W3090563135","https://openalex.org/W2908411463","https://openalex.org/W4286750062","https://openalex.org/W2901307568","https://openalex.org/W3127124381"],"abstract_inverted_index":{"This":[0,55],"paper":[1],"is":[2,112,134,150],"the":[3,49,65,104,119],"result":[4],"of":[5,12,24,51,75,106,117],"a":[6,10,58,71,122],"project":[7],"realized":[8],"by":[9,129],"team":[11,18,120],"current":[13],"master's":[14],"degree":[15],"students.":[16],"The":[17,132],"created":[19,121],"an":[20],"algorithm":[21,37,79],"for":[22,46,60,67,82,144],"recognition":[23],"sensitive":[25,53,107],"data,":[26],"primarily":[27],"name,":[28],"surname":[29],"and":[30,43,95,109,147],"OIB":[31],"(Croatian":[32],"personal":[33,68],"identification":[34],"number).":[35],"Same":[36],"iterates":[38],"across":[39,114],"given":[40],"unstructured":[41],"texts":[42],"appoints":[44],"tags":[45],"documents":[47,118],"considering":[48],"existence":[50],"specific":[52],"data.":[54,77],"process":[56],"offers":[57],"way":[59],"companies":[61],"to":[62],"narrow":[63],"down":[64],"search":[66],"information":[69,108],"if":[70],"client":[72],"demands":[73],"removal":[74],"his":[76],"Similar":[78],"was":[80],"implemented":[81],"working":[83],"with":[84],"server":[85],"logs":[86],"as":[87,92],"well,":[88],"which":[89,149],"are":[90],"represented":[91],"data":[93,127,145],"streams":[94],"analysed":[96],"in":[97],"real":[98],"time.":[99],"To":[100],"provide":[101],"insight":[102],"on":[103,136,152],"quantity":[105],"how":[110],"it":[111],"distributed":[113],"different":[115],"types":[116],"dashboard":[123],"that":[124],"shows":[125],"statistical":[126],"accumulated":[128],"developed":[130],"algorithms.":[131],"solution":[133],"stored":[135],"Cloudera,":[137],"Apache":[138],"Hadoop-based":[139],"open":[140],"source":[141],"platform":[142],"designed":[143],"management":[146],"analytics,":[148],"deployed":[151],"Microsoft":[153],"Azure":[154],"cloud":[155],"infrastructure.":[156]},"counts_by_year":[{"year":2024,"cited_by_count":2},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":2},{"year":2019,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
