{"id":"https://openalex.org/W4394874587","doi":"https://doi.org/10.21203/rs.3.rs-4118656/v1","title":"Universal distances detect anomalies in big data","display_name":"Universal distances detect anomalies in big data","publication_year":2024,"publication_date":"2024-04-17","ids":{"openalex":"https://openalex.org/W4394874587","doi":"https://doi.org/10.21203/rs.3.rs-4118656/v1"},"language":"en","primary_location":{"id":"doi:10.21203/rs.3.rs-4118656/v1","doi":"https://doi.org/10.21203/rs.3.rs-4118656/v1","is_oa":true,"landing_page_url":"http://dx.doi.org/10.21203/rs.3.rs-4118656/v1","pdf_url":"https://www.researchsquare.com/article/rs-4118656/latest.pdf","source":{"id":"https://openalex.org/S4306525896","display_name":"Research Square","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Research Square","raw_type":"posted-content"},"volume":null,"type":"preprint","is_traditional":true,"indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://www.researchsquare.com/article/rs-4118656/latest.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5087745005","display_name":"Ilya Komarov","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I4210147761","display_name":"Bundesdruckerei (Germany)","ror":"https://ror.org/055jqqn57","country_code":"DE","type":"company","lineage":["https://openalex.org/I4210147761"]}],"countries":["DE"],"is_corresponding":true,"raw_author_name":"Ilya Komarov","raw_affiliation_strings":["Bundesdruckerei GmbH","Bundesdruckerei GmbH, Abteilung Innovations, Kommandantenstr. 18, 10969 Berlin, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Bundesdruckerei GmbH","institution_ids":["https://openalex.org/I4210147761"]},{"raw_affiliation_string":"Bundesdruckerei GmbH, Abteilung Innovations, Kommandantenstr. 18, 10969 Berlin, Germany","institution_ids":["https://openalex.org/I4210147761"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5095741814","display_name":"David Fabian","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I196349391","display_name":"Universit\u00e4t Ulm","ror":"https://ror.org/032000t02","country_code":"DE","type":"education","lineage":["https://openalex.org/I196349391"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"David Fabian","raw_affiliation_strings":["University of Ulm"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Ulm","institution_ids":["https://openalex.org/I196349391"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5058319854","display_name":"Olga Kulikovska","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I4210147761","display_name":"Bundesdruckerei (Germany)","ror":"https://ror.org/055jqqn57","country_code":"DE","type":"company","lineage":["https://openalex.org/I4210147761"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Olga Kulikovska","raw_affiliation_strings":["Bundesdruckerei GmbH","Bundesdruckerei GmbH, Abteilung Innovations, Kommandantenstr. 18, 10969 Berlin, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Bundesdruckerei GmbH","institution_ids":["https://openalex.org/I4210147761"]},{"raw_affiliation_string":"Bundesdruckerei GmbH, Abteilung Innovations, Kommandantenstr. 18, 10969 Berlin, Germany","institution_ids":["https://openalex.org/I4210147761"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5095741815","display_name":"Neele Kunaht-Huhsmann","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I4210147761","display_name":"Bundesdruckerei (Germany)","ror":"https://ror.org/055jqqn57","country_code":"DE","type":"company","lineage":["https://openalex.org/I4210147761"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Neele Kunaht-Huhsmann","raw_affiliation_strings":["Bundesdruckerei GmbH","Bundesdruckerei GmbH, Abteilung Innovations, Kommandantenstr. 18, 10969 Berlin, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Bundesdruckerei GmbH","institution_ids":["https://openalex.org/I4210147761"]},{"raw_affiliation_string":"Bundesdruckerei GmbH, Abteilung Innovations, Kommandantenstr. 18, 10969 Berlin, Germany","institution_ids":["https://openalex.org/I4210147761"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5015459790","display_name":"Manfred Paeschke","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I4210147761","display_name":"Bundesdruckerei (Germany)","ror":"https://ror.org/055jqqn57","country_code":"DE","type":"company","lineage":["https://openalex.org/I4210147761"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Manfred Paeschke","raw_affiliation_strings":["Bundesdruckerei GmbH","Bundesdruckerei GmbH, Abteilung Innovations, Kommandantenstr. 18, 10969 Berlin, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Bundesdruckerei GmbH","institution_ids":["https://openalex.org/I4210147761"]},{"raw_affiliation_string":"Bundesdruckerei GmbH, Abteilung Innovations, Kommandantenstr. 18, 10969 Berlin, Germany","institution_ids":["https://openalex.org/I4210147761"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5095741816","display_name":"Peter Palm","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Peter Palm","raw_affiliation_strings":["Cortex Innovations GmbH"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Cortex Innovations GmbH","institution_ids":[]}]},{"author_position":"middle","author":{"id":null,"display_name":"Andreas Wilke","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I4210147761","display_name":"Bundesdruckerei (Germany)","ror":"https://ror.org/055jqqn57","country_code":"DE","type":"company","lineage":["https://openalex.org/I4210147761"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Andreas Wilke","raw_affiliation_strings":["Bundesdruckerei GmbH","Bundesdruckerei GmbH, Abteilung Innovations, Kommandantenstr. 18, 10969 Berlin, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Bundesdruckerei GmbH","institution_ids":["https://openalex.org/I4210147761"]},{"raw_affiliation_string":"Bundesdruckerei GmbH, Abteilung Innovations, Kommandantenstr. 18, 10969 Berlin, Germany","institution_ids":["https://openalex.org/I4210147761"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5047214535","display_name":"Wolfgang P. Schleich","orcid":"https://orcid.org/0000-0002-9693-8882","observed_orcids":["https://orcid.org/0000-0002-9693-8882"]},"institutions":[{"id":"https://openalex.org/I196349391","display_name":"Universit\u00e4t Ulm","ror":"https://ror.org/032000t02","country_code":"DE","type":"education","lineage":["https://openalex.org/I196349391"]},{"id":"https://openalex.org/I91045830","display_name":"Texas A&M University","ror":"https://ror.org/01f5ytq51","country_code":"US","type":"education","lineage":["https://openalex.org/I91045830"]}],"countries":["DE","US"],"is_corresponding":false,"raw_author_name":"Wolfgang Schleich","raw_affiliation_strings":["University of Ulm","Hagler Institute for Advanced Study and Department of Physics and Astronomy, Institute for Quantum Science and Engineering, Texas A&M University, College Station, Texas 77843-4242, USA","Texas A&M AgriLife Research, Texas A&M University, College Station, Texas 77843-4242, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Ulm","institution_ids":["https://openalex.org/I196349391"]},{"raw_affiliation_string":"Hagler Institute for Advanced Study and Department of Physics and Astronomy, Institute for Quantum Science and Engineering, Texas A&M University, College Station, Texas 77843-4242, USA","institution_ids":["https://openalex.org/I91045830"]},{"raw_affiliation_string":"Texas A&M AgriLife Research, Texas A&M University, College Station, Texas 77843-4242, USA","institution_ids":["https://openalex.org/I91045830"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5087745005"],"corresponding_institution_ids":["https://openalex.org/I4210147761"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11512","display_name":"Anomaly Detection Techniques and Applications","score":0.9994999766349792,"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/T11512","display_name":"Anomaly Detection Techniques and Applications","score":0.9994999766349792,"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/T12127","display_name":"Software System Performance and Reliability","score":0.0,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"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/T11871","display_name":"Advanced Statistical Methods and Models","score":0.0,"subfield":{"id":"https://openalex.org/subfields/2613","display_name":"Statistics and Probability"},"field":{"id":"https://openalex.org/fields/26","display_name":"Mathematics"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/anomaly-detection","display_name":"anomaly detection","score":0.996999979019165},{"id":"https://openalex.org/keywords/big-data","display_name":"big data","score":0.7590000033378601},{"id":"https://openalex.org/keywords/key-value-pairs","display_name":"key-value pairs","score":0.5960000157356262},{"id":"https://openalex.org/keywords/set-distance","display_name":"set distance","score":0.5770000219345093},{"id":"https://openalex.org/keywords/heat-maps","display_name":"heatmaps","score":0.8899999856948853},{"id":"https://openalex.org/keywords/tabular-data","display_name":"tabular data","score":0.8579999804496765},{"id":"https://openalex.org/keywords/data-integrity","display_name":"data integrity","score":0.492000013589859}],"concepts":[{"id":"https://openalex.org/C75684735","wikidata":"https://www.wikidata.org/wiki/Q858810","display_name":"Big data","level":2,"score":0.5415009260177612},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.4023084044456482},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.25791966915130615}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.21203/rs.3.rs-4118656/v1","doi":"https://doi.org/10.21203/rs.3.rs-4118656/v1","is_oa":true,"landing_page_url":"http://dx.doi.org/10.21203/rs.3.rs-4118656/v1","pdf_url":"https://www.researchsquare.com/article/rs-4118656/latest.pdf","source":{"id":"https://openalex.org/S4306525896","display_name":"Research Square","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Research Square","raw_type":"posted-content"}],"best_oa_location":{"id":"doi:10.21203/rs.3.rs-4118656/v1","doi":"https://doi.org/10.21203/rs.3.rs-4118656/v1","is_oa":true,"landing_page_url":"http://dx.doi.org/10.21203/rs.3.rs-4118656/v1","pdf_url":"https://www.researchsquare.com/article/rs-4118656/latest.pdf","source":{"id":"https://openalex.org/S4306525896","display_name":"Research Square","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Research Square","raw_type":"posted-content"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[{"id":"https://openalex.org/F4303701741","display_name":"Bundesministerium f\u00fcr Wirtschaft und Klimaschutz","ror":"https://ror.org/02vgg2808"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4394874587.pdf","grobid_xml":"https://content.openalex.org/works/W4394874587.grobid-xml"},"referenced_works_count":30,"referenced_works":["https://openalex.org/W125869453","https://openalex.org/W572368116","https://openalex.org/W655089096","https://openalex.org/W1604458106","https://openalex.org/W1673310716","https://openalex.org/W1965787203","https://openalex.org/W2003048487","https://openalex.org/W2004131797","https://openalex.org/W2048110439","https://openalex.org/W2056638635","https://openalex.org/W2061240327","https://openalex.org/W2076758681","https://openalex.org/W2084512860","https://openalex.org/W2163952039","https://openalex.org/W2483617729","https://openalex.org/W2512536179","https://openalex.org/W2549969552","https://openalex.org/W2583888926","https://openalex.org/W2594899909","https://openalex.org/W2597511167","https://openalex.org/W2978726144","https://openalex.org/W2980650841","https://openalex.org/W2997590552","https://openalex.org/W2998758436","https://openalex.org/W3006372827","https://openalex.org/W3039222472","https://openalex.org/W3158805797","https://openalex.org/W4205471456","https://openalex.org/W4231701532","https://openalex.org/W4240144763"],"related_works":["https://openalex.org/W7045420749","https://openalex.org/W826482099","https://openalex.org/W2900259179","https://openalex.org/W7018385848","https://openalex.org/W2515622810","https://openalex.org/W3083297424","https://openalex.org/W6941202194","https://openalex.org/W2170902455","https://openalex.org/W1551503668","https://openalex.org/W2028637253"],"abstract_inverted_index":{"Abstract":[0],"The":[1],"detection":[2],"of":[3,8,22,37,47,55,63,69,104,113],"anomalies":[4,119],"in":[5,14,18,120],"a":[6,11,19,45,70],"set":[7],"data":[9,49],"represents":[10],"ubiquitous":[12],"challenge":[13],"computer":[15],"science":[16],"emerging":[17],"wide":[20],"range":[21],"fields":[23],"such":[24],"as":[25],"financial":[26],"transactions,":[27],"particle":[28],"physics":[29],"and":[30,73,76,107,126],"communication":[31],"traffic.":[32],"At":[33],"the":[34,48,67,111,121],"very":[35],"heart":[36],"our":[38,114],"method":[39,91],"to":[40,82],"attack":[41],"this":[42],"problem":[43],"lies":[44],"representation":[46],"by":[50,116],"key-value":[51,64],"pairs":[52,65],"with":[53,66,85,97],"sets":[54,62],"associated":[56,74],"identifiers.":[57],"We":[58,109],"compute":[59],"distances":[60,79],"between":[61],"help":[68],"reference":[71],"key":[72],"identifiers,":[75],"visualize":[77],"these":[78],"using":[80],"heatmaps":[81],"bring":[83],"out":[84],"few":[86],"prior":[87],"assumptions":[88],"anomalies.":[89],"Our":[90],"is":[92],"universal":[93],"since":[94],"it":[95],"works":[96],"any":[98],"tabular":[99],"or":[100],"document-oriented":[101],"data,":[102],"independent":[103],"their":[105],"content":[106],"form.":[108],"demonstrate":[110],"power":[112],"technique":[115],"identifying":[117],"three":[118],"New":[122],"York":[123],"City":[124],"Taxi":[125],"Limousine":[127],"Commission":[128],"Trip":[129],"Record":[130],"Data.":[131]},"counts_by_year":[],"updated_date":"2026-11-09T13:22:03.289127","created_date":"2024-04-18T00:00:00"}