{"id":"https://openalex.org/W3013034085","doi":"https://doi.org/10.1186/s40537-020-00288-8","title":"Tracing outliers in the dataset of Drosophila suzukii records with the Isolation Forest method","display_name":"Tracing outliers in the dataset of Drosophila suzukii records with the Isolation Forest method","publication_year":2020,"publication_date":"2020-03-05","ids":{"openalex":"https://openalex.org/W3013034085","doi":"https://doi.org/10.1186/s40537-020-00288-8","mag":"3013034085"},"language":"en","primary_location":{"id":"doi:10.1186/s40537-020-00288-8","is_oa":true,"landing_page_url":"https://doi.org/10.1186/s40537-020-00288-8","pdf_url":"https://journalofbigdata.springeropen.com/track/pdf/10.1186/s40537-020-00288-8","source":{"id":"https://openalex.org/S2737955091","display_name":"Journal Of Big Data","issn_l":"2196-1115","issn":["2196-1115"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of Big Data","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://journalofbigdata.springeropen.com/track/pdf/10.1186/s40537-020-00288-8","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5076431937","display_name":"Ugo Santosuosso","orcid":"https://orcid.org/0000-0003-1802-3094"},"institutions":[{"id":"https://openalex.org/I45084792","display_name":"University of Florence","ror":"https://ror.org/04jr1s763","country_code":"IT","type":"education","lineage":["https://openalex.org/I45084792"]}],"countries":["IT"],"is_corresponding":true,"raw_author_name":"Ugo Santosuosso","raw_affiliation_strings":["Department of Clinical and Experimental Medicine, University of Florence, Largo Brambilla 3, 50134, Florence, Italy"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Clinical and Experimental Medicine, University of Florence, Largo Brambilla 3, 50134, Florence, Italy","institution_ids":["https://openalex.org/I45084792"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5052278388","display_name":"Alessandro Cini","orcid":"https://orcid.org/0000-0003-0355-2188"},"institutions":[{"id":"https://openalex.org/I45084792","display_name":"University of Florence","ror":"https://ror.org/04jr1s763","country_code":"IT","type":"education","lineage":["https://openalex.org/I45084792"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Alessandro Cini","raw_affiliation_strings":["Department of Biology, University of Florence, Via Madonna del Piano 6, 50019, Florence, Italy"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Biology, University of Florence, Via Madonna del Piano 6, 50019, Florence, Italy","institution_ids":["https://openalex.org/I45084792"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5025685078","display_name":"Alessio Papini","orcid":"https://orcid.org/0000-0001-7904-0336"},"institutions":[{"id":"https://openalex.org/I45084792","display_name":"University of Florence","ror":"https://ror.org/04jr1s763","country_code":"IT","type":"education","lineage":["https://openalex.org/I45084792"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Alessio Papini","raw_affiliation_strings":["Department of Biology, University of Florence, Via Micheli 3, Florence, 50121, Italy"],"raw_orcid":"https://orcid.org/0000-0001-7904-0336","affiliations":[{"raw_affiliation_string":"Department of Biology, University of Florence, Via Micheli 3, Florence, 50121, Italy","institution_ids":["https://openalex.org/I45084792"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5076431937"],"corresponding_institution_ids":["https://openalex.org/I45084792"],"apc_list":{"value":1060,"currency":"GBP","value_usd":1300},"apc_paid":{"value":1060,"currency":"GBP","value_usd":1300},"fwci":0.7546,"has_fulltext":true,"cited_by_count":10,"citation_normalized_percentile":{"value":0.72154061,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":"7","issue":"1","first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12043","display_name":"Insect behavior and control techniques","score":0.9998000264167786,"subfield":{"id":"https://openalex.org/subfields/1109","display_name":"Insect Science"},"field":{"id":"https://openalex.org/fields/11","display_name":"Agricultural and Biological Sciences"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},"topics":[{"id":"https://openalex.org/T12043","display_name":"Insect behavior and control techniques","score":0.9998000264167786,"subfield":{"id":"https://openalex.org/subfields/1109","display_name":"Insect Science"},"field":{"id":"https://openalex.org/fields/11","display_name":"Agricultural and Biological Sciences"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},{"id":"https://openalex.org/T11691","display_name":"Forest Insect Ecology and Management","score":0.9991999864578247,"subfield":{"id":"https://openalex.org/subfields/2303","display_name":"Ecology"},"field":{"id":"https://openalex.org/fields/23","display_name":"Environmental Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11641","display_name":"Insect and Pesticide Research","score":0.9970999956130981,"subfield":{"id":"https://openalex.org/subfields/1109","display_name":"Insect Science"},"field":{"id":"https://openalex.org/fields/11","display_name":"Agricultural and Biological Sciences"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/outlier","display_name":"Outlier","score":0.7143622636795044},{"id":"https://openalex.org/keywords/voronoi-diagram","display_name":"Voronoi diagram","score":0.6787278056144714},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6719517111778259},{"id":"https://openalex.org/keywords/python","display_name":"Python (programming language)","score":0.5942599773406982},{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.5790340900421143},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.5604667067527771},{"id":"https://openalex.org/keywords/geospatial-analysis","display_name":"Geospatial analysis","score":0.5274683833122253},{"id":"https://openalex.org/keywords/partition","display_name":"Partition (number theory)","score":0.5028836131095886},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.27974414825439453},{"id":"https://openalex.org/keywords/geography","display_name":"Geography","score":0.19534844160079956},{"id":"https://openalex.org/keywords/cartography","display_name":"Cartography","score":0.19041290879249573},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.10697820782661438}],"concepts":[{"id":"https://openalex.org/C79337645","wikidata":"https://www.wikidata.org/wiki/Q779824","display_name":"Outlier","level":2,"score":0.7143622636795044},{"id":"https://openalex.org/C24881265","wikidata":"https://www.wikidata.org/wiki/Q757267","display_name":"Voronoi diagram","level":2,"score":0.6787278056144714},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6719517111778259},{"id":"https://openalex.org/C519991488","wikidata":"https://www.wikidata.org/wiki/Q28865","display_name":"Python (programming language)","level":2,"score":0.5942599773406982},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.5790340900421143},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.5604667067527771},{"id":"https://openalex.org/C9770341","wikidata":"https://www.wikidata.org/wiki/Q1938983","display_name":"Geospatial analysis","level":2,"score":0.5274683833122253},{"id":"https://openalex.org/C42812","wikidata":"https://www.wikidata.org/wiki/Q1082910","display_name":"Partition (number theory)","level":2,"score":0.5028836131095886},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.27974414825439453},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.19534844160079956},{"id":"https://openalex.org/C58640448","wikidata":"https://www.wikidata.org/wiki/Q42515","display_name":"Cartography","level":1,"score":0.19041290879249573},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.10697820782661438},{"id":"https://openalex.org/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","level":1,"score":0.0},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0}],"mesh":[],"locations_count":5,"locations":[{"id":"doi:10.1186/s40537-020-00288-8","is_oa":true,"landing_page_url":"https://doi.org/10.1186/s40537-020-00288-8","pdf_url":"https://journalofbigdata.springeropen.com/track/pdf/10.1186/s40537-020-00288-8","source":{"id":"https://openalex.org/S2737955091","display_name":"Journal Of Big Data","issn_l":"2196-1115","issn":["2196-1115"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of Big Data","raw_type":"journal-article"},{"id":"pmh:oai:arpi.unipi.it:11568/1141869","is_oa":false,"landing_page_url":"https://journalofbigdata.springeropen.com/","pdf_url":null,"source":{"id":"https://openalex.org/S4377196265","display_name":"CINECA IRIS Institutial research information system (University of Pisa)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I108290504","host_organization_name":"University of Pisa","host_organization_lineage":["https://openalex.org/I108290504"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"info:eu-repo/semantics/article"},{"id":"pmh:oai:doaj.org/article:4fa5ca1bb3bf4c80934a969a45bf9747","is_oa":true,"landing_page_url":"https://doaj.org/article/4fa5ca1bb3bf4c80934a969a45bf9747","pdf_url":null,"source":{"id":"https://openalex.org/S112646816","display_name":"SHILAP Revista de lepidopterolog\u00eda","issn_l":"0300-5267","issn":["0300-5267","2340-4078"],"is_oa":true,"is_in_doaj":true,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":"cc-by-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Journal of Big Data, Vol 7, Iss 1, Pp 1-11 (2020)","raw_type":"article"},{"id":"pmh:oai:eprints.ucl.ac.uk.OAI2:10094695","is_oa":false,"landing_page_url":"https://discovery.ucl.ac.uk/id/eprint/10094695/","pdf_url":null,"source":{"id":"https://openalex.org/S4306400024","display_name":"UCL Discovery (University College London)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I45129253","host_organization_name":"University College London","host_organization_lineage":["https://openalex.org/I45129253"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"   Journal of Big Data , 7     , Article 14. (2020)      ","raw_type":"Article"},{"id":"pmh:oai:flore.unifi.it:2158/1185232","is_oa":true,"landing_page_url":"http://hdl.handle.net/2158/1185232","pdf_url":null,"source":{"id":"https://openalex.org/S4306402033","display_name":"Florence Research (University of Florence)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I45084792","host_organization_name":"University of Florence","host_organization_lineage":["https://openalex.org/I45084792"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"info:eu-repo/semantics/article"}],"best_oa_location":{"id":"doi:10.1186/s40537-020-00288-8","is_oa":true,"landing_page_url":"https://doi.org/10.1186/s40537-020-00288-8","pdf_url":"https://journalofbigdata.springeropen.com/track/pdf/10.1186/s40537-020-00288-8","source":{"id":"https://openalex.org/S2737955091","display_name":"Journal Of Big Data","issn_l":"2196-1115","issn":["2196-1115"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of Big Data","raw_type":"journal-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/15","score":0.6800000071525574,"display_name":"Life in Land"}],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3013034085.pdf","grobid_xml":"https://content.openalex.org/works/W3013034085.grobid-xml"},"referenced_works_count":44,"referenced_works":["https://openalex.org/W171895998","https://openalex.org/W1870652839","https://openalex.org/W1967005434","https://openalex.org/W1971784203","https://openalex.org/W1987971958","https://openalex.org/W1995443851","https://openalex.org/W2007287082","https://openalex.org/W2007982581","https://openalex.org/W2011301426","https://openalex.org/W2011430131","https://openalex.org/W2014896269","https://openalex.org/W2021833436","https://openalex.org/W2026146969","https://openalex.org/W2045551512","https://openalex.org/W2045740345","https://openalex.org/W2061719079","https://openalex.org/W2079440320","https://openalex.org/W2101234009","https://openalex.org/W2103777983","https://openalex.org/W2105023945","https://openalex.org/W2109959130","https://openalex.org/W2116964561","https://openalex.org/W2119820191","https://openalex.org/W2163191590","https://openalex.org/W2240245417","https://openalex.org/W2296719434","https://openalex.org/W2319660501","https://openalex.org/W2415799561","https://openalex.org/W2474164161","https://openalex.org/W2553696195","https://openalex.org/W2585773615","https://openalex.org/W2779733582","https://openalex.org/W2883173194","https://openalex.org/W2902539404","https://openalex.org/W2904362928","https://openalex.org/W2905532182","https://openalex.org/W2916056239","https://openalex.org/W2964088199","https://openalex.org/W2983029853","https://openalex.org/W2986384279","https://openalex.org/W2995662243","https://openalex.org/W4232845540","https://openalex.org/W6649126050","https://openalex.org/W6770641979"],"related_works":["https://openalex.org/W3020555194","https://openalex.org/W2793256277","https://openalex.org/W2348235448","https://openalex.org/W4360958759","https://openalex.org/W2116218375","https://openalex.org/W2389906634","https://openalex.org/W288156810","https://openalex.org/W176898926","https://openalex.org/W1562406979","https://openalex.org/W2962797788"],"abstract_inverted_index":{"Abstract":[0],"The":[1,55,180,321],"analysis":[2,87,287],"of":[3,16,27,36,48,57,86,96,116,131,172,174,246,278,281,286,295,302,308,324,358],"big":[4],"data":[5,17,24,39,47,97],"is":[6,25,41],"a":[7,71,84,117,136,163,170,188,351],"fundamental":[8],"challenge":[9],"for":[10],"the":[11,28,45,52,109,113,127,132,141,150,156,166,177,185,201,206,216,224,235,238,249,254,276,282,292,300,306,325,332,339],"current":[12],"and":[13,107,271,347],"future":[14,114,293],"stream":[15],"coming":[18],"from":[19,267],"many":[20],"different":[21],"sources.":[22],"Geospatial":[23],"one":[26],"sources":[29],"currently":[30],"less":[31],"investigated.":[32],"A":[33],"typical":[34],"example":[35],"always":[37],"increasing":[38],"set":[40],"that":[42,88,192,263,338],"produced":[43],"by":[44],"distribution":[46],"invasive":[49,326],"species":[50],"on":[51,140,162,184,197],"concerned":[53],"territories.":[54],"dataset":[56],"Drosophila":[58],"suzuki":[59],"invasion":[60],"sites":[61],"in":[62,98,205,220,305],"Europe":[63,221],"up":[64],"to":[65,69,74,82,92,100,105,125,154,212,243,265,290,319,331,349,354],"2011":[66],"was":[67,81],"used":[68,148],"test":[70],"possible":[72],"method":[73,85,153,168,257,342,353],"pinpoint":[75],"its":[76],"outliers":[77,250,333],"(anomalies).":[78],"Our":[79],"aim":[80],"find":[83],"would":[89,258],"be":[90,223,241,344,350],"able":[91],"treat":[93,355],"large":[94,356],"amount":[95],"order":[99],"produce":[101],"easily":[102],"readable":[103],"outputs":[104],"summarize":[106],"predict":[108],"status":[110],"and,":[111],"possibly,":[112],"development":[115],"biological":[118],"invasion.":[119,283],"To":[120],"do":[121],"that,":[122],"we":[123],"aimed":[124],"identify":[126,259,291],"so":[128],"called":[129],"anomalies":[130],"dataset,":[133,165],"identified":[134],"with":[135,187,253,317],"Python":[137],"script":[138],"based":[139,161],"machine":[142],"learning":[143],"algorithm":[144],"\u201cIsolation":[145],"Forest\u201d.":[146],"We":[147],"also":[149],"K-Means":[151],"clustering":[152],"partition":[155],"dataset.":[157],"In":[158],"our":[159],"test,":[160],"real":[164],"Silhouette":[167],"yielded":[169],"number":[171],"clusters":[173,181,194],"10":[175],"as":[176,304],"best":[178],"result.":[179],"were":[182,195,204],"drawn":[183],"map":[186],"Voronoi":[189],"tessellation,":[190],"showing":[191],"8":[193],"centered":[196],"industrial":[198],"harbours,":[199],"while":[200],"last":[202],"two":[203],"hinterland.":[207],"This":[208,284],"fact":[209],"led":[210],"us":[211],"guess":[213],"that:":[214],"(1)":[215],"main":[217],"entrance":[218],"mechanisms":[219],"may":[222,240],"wares":[225],"import":[226],"fluxes":[227],"through":[228],"ports,":[229],"occurring":[230],"apparently":[231],"several":[232],"times;":[233],"(2)":[234],"spreading":[236,280],"into":[237],"inland":[239],"due":[242],"road":[244],"transportation":[245],"wares;":[247],"(3)":[248],"(anomalies)":[251],"found":[252],"isolation":[255,340],"forest":[256,341],"individuals":[260],"or":[261],"populations":[262],"tend":[264],"detach":[266],"their":[268],"original":[269],"cluster":[270],"hence":[272,289],"represent":[273],"indications":[274],"about":[275],"lines":[277],"further":[279],"type":[285],"aims":[288],"direction":[294],"an":[296,336],"invasion,":[297],"rather":[298],"than":[299],"center":[301],"origin":[303],"case":[307],"geographic":[309],"profiling.":[310],"Isolation":[311],"Forest":[312],"provides":[313],"therefore":[314],"complimentary":[315],"results":[316],"respect":[318],"PGP.":[320],"recent":[322],"records":[323],"species,":[327],"mainly":[328],"localized":[329],"close":[330],"position,":[334],"are":[335],"indication":[337],"can":[343],"considered":[345],"predictive":[346],"proved":[348],"useful":[352],"datasets":[357],"geospatial":[359],"data.":[360]},"counts_by_year":[{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":3},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}