{"id":"https://openalex.org/W4312884560","doi":"https://doi.org/10.1109/tkde.2022.3218930","title":"Find Another me Across the World - Large-Scale Semantic Trajectory Analysis Using Spark","display_name":"Find Another me Across the World - Large-Scale Semantic Trajectory Analysis Using Spark","publication_year":2022,"publication_date":"2022-11-04","ids":{"openalex":"https://openalex.org/W4312884560","doi":"https://doi.org/10.1109/tkde.2022.3218930"},"language":"en","primary_location":{"id":"doi:10.1109/tkde.2022.3218930","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tkde.2022.3218930","pdf_url":null,"source":{"id":"https://openalex.org/S30698027","display_name":"IEEE Transactions on Knowledge and Data Engineering","issn_l":"1041-4347","issn":["1041-4347","1558-2191","2326-3865"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320439","host_organization_name":"IEEE Computer Society","host_organization_lineage":["https://openalex.org/P4310320439","https://openalex.org/P4310319808"],"host_organization_lineage_names":["IEEE Computer Society","Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Knowledge and Data Engineering","raw_type":"journal-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/A5010384444","display_name":"Chaoquan Cai","orcid":"https://orcid.org/0000-0003-2233-1786"},"institutions":[{"id":"https://openalex.org/I200719446","display_name":"Vanderbilt University","ror":"https://ror.org/02vm5rt34","country_code":"US","type":"education","lineage":["https://openalex.org/I200719446"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Chaoquan Cai","raw_affiliation_strings":["Computer Science Department, Vanderbilt University, Nashville, TN, USA"],"affiliations":[{"raw_affiliation_string":"Computer Science Department, Vanderbilt University, Nashville, TN, USA","institution_ids":["https://openalex.org/I200719446"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101655052","display_name":"Dan Lin","orcid":"https://orcid.org/0000-0002-3062-8240"},"institutions":[{"id":"https://openalex.org/I200719446","display_name":"Vanderbilt University","ror":"https://ror.org/02vm5rt34","country_code":"US","type":"education","lineage":["https://openalex.org/I200719446"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Dan Lin","raw_affiliation_strings":["Computer Science Department, Vanderbilt University, Nashville, TN, USA"],"affiliations":[{"raw_affiliation_string":"Computer Science Department, Vanderbilt University, Nashville, TN, USA","institution_ids":["https://openalex.org/I200719446"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5010384444"],"corresponding_institution_ids":["https://openalex.org/I200719446"],"apc_list":null,"apc_paid":null,"fwci":0.4464,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.60028653,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":95},"biblio":{"volume":"35","issue":"9","first_page":"8905","last_page":"8918"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11106","display_name":"Data Management and Algorithms","score":0.9998000264167786,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"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/T11106","display_name":"Data Management and Algorithms","score":0.9998000264167786,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"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/T11980","display_name":"Human Mobility and Location-Based Analysis","score":0.9969000220298767,"subfield":{"id":"https://openalex.org/subfields/3313","display_name":"Transportation"},"field":{"id":"https://openalex.org/fields/33","display_name":"Social Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T12205","display_name":"Time Series Analysis and Forecasting","score":0.9891999959945679,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"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/computer-science","display_name":"Computer science","score":0.8410714268684387},{"id":"https://openalex.org/keywords/spark","display_name":"SPARK (programming language)","score":0.7892427444458008},{"id":"https://openalex.org/keywords/trajectory","display_name":"Trajectory","score":0.7750356197357178},{"id":"https://openalex.org/keywords/hash-function","display_name":"Hash function","score":0.5617637634277344},{"id":"https://openalex.org/keywords/scale","display_name":"Scale (ratio)","score":0.5454394221305847},{"id":"https://openalex.org/keywords/function","display_name":"Function (biology)","score":0.5133720636367798},{"id":"https://openalex.org/keywords/semantic-analysis","display_name":"Semantic analysis (machine learning)","score":0.42972055077552795},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.3605427145957947},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.34523892402648926},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.3394746780395508},{"id":"https://openalex.org/keywords/data-science","display_name":"Data science","score":0.3326607346534729},{"id":"https://openalex.org/keywords/computer-security","display_name":"Computer security","score":0.11789149045944214}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8410714268684387},{"id":"https://openalex.org/C2781215313","wikidata":"https://www.wikidata.org/wiki/Q3493345","display_name":"SPARK (programming language)","level":2,"score":0.7892427444458008},{"id":"https://openalex.org/C13662910","wikidata":"https://www.wikidata.org/wiki/Q193139","display_name":"Trajectory","level":2,"score":0.7750356197357178},{"id":"https://openalex.org/C99138194","wikidata":"https://www.wikidata.org/wiki/Q183427","display_name":"Hash function","level":2,"score":0.5617637634277344},{"id":"https://openalex.org/C2778755073","wikidata":"https://www.wikidata.org/wiki/Q10858537","display_name":"Scale (ratio)","level":2,"score":0.5454394221305847},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.5133720636367798},{"id":"https://openalex.org/C2777946921","wikidata":"https://www.wikidata.org/wiki/Q7449044","display_name":"Semantic analysis (machine learning)","level":2,"score":0.42972055077552795},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.3605427145957947},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.34523892402648926},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3394746780395508},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.3326607346534729},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.11789149045944214},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C1276947","wikidata":"https://www.wikidata.org/wiki/Q333","display_name":"Astronomy","level":1,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C78458016","wikidata":"https://www.wikidata.org/wiki/Q840400","display_name":"Evolutionary biology","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tkde.2022.3218930","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tkde.2022.3218930","pdf_url":null,"source":{"id":"https://openalex.org/S30698027","display_name":"IEEE Transactions on Knowledge and Data Engineering","issn_l":"1041-4347","issn":["1041-4347","1558-2191","2326-3865"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320439","host_organization_name":"IEEE Computer Society","host_organization_lineage":["https://openalex.org/P4310320439","https://openalex.org/P4310319808"],"host_organization_lineage_names":["IEEE Computer Society","Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Knowledge and Data Engineering","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":45,"referenced_works":["https://openalex.org/W1544466327","https://openalex.org/W1568832590","https://openalex.org/W1626398438","https://openalex.org/W1976062966","https://openalex.org/W2011968383","https://openalex.org/W2012580531","https://openalex.org/W2022749020","https://openalex.org/W2023279748","https://openalex.org/W2060829616","https://openalex.org/W2075190119","https://openalex.org/W2114797768","https://openalex.org/W2128953738","https://openalex.org/W2133046526","https://openalex.org/W2136317921","https://openalex.org/W2140251882","https://openalex.org/W2143394441","https://openalex.org/W2147880780","https://openalex.org/W2156404870","https://openalex.org/W2157521848","https://openalex.org/W2158320444","https://openalex.org/W2162756694","https://openalex.org/W2167686542","https://openalex.org/W2186751573","https://openalex.org/W2189465200","https://openalex.org/W2355706562","https://openalex.org/W2436533802","https://openalex.org/W2614171007","https://openalex.org/W2735735528","https://openalex.org/W2739859529","https://openalex.org/W2765456220","https://openalex.org/W2765816511","https://openalex.org/W2798903611","https://openalex.org/W2888325465","https://openalex.org/W2915600555","https://openalex.org/W2951096868","https://openalex.org/W2953695928","https://openalex.org/W2955329215","https://openalex.org/W3029721461","https://openalex.org/W3034784236","https://openalex.org/W3045820751","https://openalex.org/W3147178137","https://openalex.org/W4200239770","https://openalex.org/W6636500457","https://openalex.org/W6683175271","https://openalex.org/W6687322159"],"related_works":["https://openalex.org/W3015859229","https://openalex.org/W2230552005","https://openalex.org/W1975949872","https://openalex.org/W3159871278","https://openalex.org/W2905242764","https://openalex.org/W3109411864","https://openalex.org/W3017846737","https://openalex.org/W3003280185","https://openalex.org/W4379407450","https://openalex.org/W2613379984"],"abstract_inverted_index":{"In":[0,60],"today's":[1],"society,":[2],"location-based":[3],"services":[4],"are":[5,43,48],"widely":[6],"used":[7],"which":[8],"collect":[9],"a":[10,65,77],"huge":[11],"amount":[12],"of":[13,19,96],"human":[14],"trajectories.":[15],"Analyzing":[16],"semantic":[17,41,68,90],"meanings":[18],"these":[20],"trajectories":[21,42],"can":[22,87],"benefit":[23],"numerous":[24],"real-world":[25],"applications,":[26],"such":[27],"as":[28],"product":[29],"advertisement,":[30],"friend":[31],"recommendation,":[32],"and":[33,93],"social":[34],"behavior":[35,100],"analysis.":[36],"However,":[37],"existing":[38],"works":[39],"on":[40],"mostly":[44],"centralized":[45,118],"approaches":[46,119],"that":[47,86,108],"not":[49],"able":[50],"to":[51],"keep":[52],"up":[53],"with":[54,82,98],"the":[55,102],"rapidly":[56],"growing":[57],"trajectory":[58,69,91],"collections.":[59],"this":[61],"paper,":[62],"we":[63],"propose":[64],"novel":[66],"large-scale":[67],"analysis":[70],"algorithm":[71],"in":[72],"Apache":[73],"Spark.":[74],"We":[75],"design":[76],"new":[78],"hash":[79],"function":[80],"along":[81],"efficient":[83],"distributed":[84],"algorithms":[85],"quickly":[88],"compute":[89],"similarities":[92],"identify":[94],"communities":[95],"people":[97],"similar":[99],"across":[101],"world.":[103],"The":[104],"experimental":[105],"results":[106],"show":[107],"our":[109],"approach":[110],"is":[111],"more":[112],"than":[113,117],"30":[114],"times":[115],"faster":[116],"without":[120],"sacrificing":[121],"any":[122],"accuracy":[123],"like":[124],"other":[125],"parallel":[126],"approaches.":[127]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}