{"id":"https://openalex.org/W3013531585","doi":"https://doi.org/10.3390/a13030071","title":"Two-Step Classification with SVD Preprocessing of Distributed Massive Datasets in Apache Spark","display_name":"Two-Step Classification with SVD Preprocessing of Distributed Massive Datasets in Apache Spark","publication_year":2020,"publication_date":"2020-03-24","ids":{"openalex":"https://openalex.org/W3013531585","doi":"https://doi.org/10.3390/a13030071","mag":"3013531585"},"language":"en","primary_location":{"id":"doi:10.3390/a13030071","is_oa":true,"landing_page_url":"https://doi.org/10.3390/a13030071","pdf_url":"https://www.mdpi.com/1999-4893/13/3/71/pdf?version=1585236692","source":{"id":"https://openalex.org/S190629608","display_name":"Algorithms","issn_l":"1999-4893","issn":["1999-4893"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310310987","host_organization_name":"Multidisciplinary Digital Publishing Institute","host_organization_lineage":["https://openalex.org/P4310310987"],"host_organization_lineage_names":["Multidisciplinary Digital Publishing Institute"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Algorithms","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://www.mdpi.com/1999-4893/13/3/71/pdf?version=1585236692","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5052189975","display_name":"A. Alexopoulos","orcid":null},"institutions":[{"id":"https://openalex.org/I174878644","display_name":"University of Patras","ror":"https://ror.org/017wvtq80","country_code":"GR","type":"education","lineage":["https://openalex.org/I174878644"]}],"countries":["GR"],"is_corresponding":false,"raw_author_name":"Athanasios Alexopoulos","raw_affiliation_strings":["Computer Engineering and Informatics Department, University of Patras, 26504 Patras, Greece"],"affiliations":[{"raw_affiliation_string":"Computer Engineering and Informatics Department, University of Patras, 26504 Patras, Greece","institution_ids":["https://openalex.org/I174878644"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5044250636","display_name":"\u0393\u03b5\u03ce\u03c1\u03b3\u03b9\u03bf\u03c2 \u0394\u03c1\u03b1\u03ba\u03cc\u03c0\u03bf\u03c5\u03bb\u03bf\u03c2","orcid":"https://orcid.org/0000-0002-0975-1877"},"institutions":[{"id":"https://openalex.org/I187792471","display_name":"Ionian University","ror":"https://ror.org/01xm4n520","country_code":"GR","type":"education","lineage":["https://openalex.org/I187792471"]}],"countries":["GR"],"is_corresponding":false,"raw_author_name":"Georgios Drakopoulos","raw_affiliation_strings":["Department of Informatics, Ionian University, 49100 Corfu, Greece"],"affiliations":[{"raw_affiliation_string":"Department of Informatics, Ionian University, 49100 Corfu, Greece","institution_ids":["https://openalex.org/I187792471"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5004664070","display_name":"Andreas Kanavos","orcid":"https://orcid.org/0000-0002-9964-4134"},"institutions":[{"id":"https://openalex.org/I174878644","display_name":"University of Patras","ror":"https://ror.org/017wvtq80","country_code":"GR","type":"education","lineage":["https://openalex.org/I174878644"]}],"countries":["GR"],"is_corresponding":true,"raw_author_name":"Andreas Kanavos","raw_affiliation_strings":["Computer Engineering and Informatics Department, University of Patras, 26504 Patras, Greece"],"affiliations":[{"raw_affiliation_string":"Computer Engineering and Informatics Department, University of Patras, 26504 Patras, Greece","institution_ids":["https://openalex.org/I174878644"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5061448936","display_name":"Phivos Mylonas","orcid":"https://orcid.org/0000-0002-6916-3129"},"institutions":[{"id":"https://openalex.org/I187792471","display_name":"Ionian University","ror":"https://ror.org/01xm4n520","country_code":"GR","type":"education","lineage":["https://openalex.org/I187792471"]}],"countries":["GR"],"is_corresponding":false,"raw_author_name":"Phivos Mylonas","raw_affiliation_strings":["Department of Informatics, Ionian University, 49100 Corfu, Greece"],"affiliations":[{"raw_affiliation_string":"Department of Informatics, Ionian University, 49100 Corfu, Greece","institution_ids":["https://openalex.org/I187792471"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5055730804","display_name":"Gerasimos Vonitsanos","orcid":"https://orcid.org/0000-0001-9555-4775"},"institutions":[{"id":"https://openalex.org/I174878644","display_name":"University of Patras","ror":"https://ror.org/017wvtq80","country_code":"GR","type":"education","lineage":["https://openalex.org/I174878644"]}],"countries":["GR"],"is_corresponding":false,"raw_author_name":"Gerasimos Vonitsanos","raw_affiliation_strings":["Computer Engineering and Informatics Department, University of Patras, 26504 Patras, Greece"],"affiliations":[{"raw_affiliation_string":"Computer Engineering and Informatics Department, University of Patras, 26504 Patras, Greece","institution_ids":["https://openalex.org/I174878644"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5004664070"],"corresponding_institution_ids":["https://openalex.org/I174878644"],"apc_list":{"value":1400,"currency":"CHF","value_usd":1515},"apc_paid":{"value":1400,"currency":"CHF","value_usd":1515},"fwci":1.1724,"has_fulltext":false,"cited_by_count":19,"citation_normalized_percentile":{"value":0.80716878,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":"13","issue":"3","first_page":"71","last_page":"71"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12292","display_name":"Graph Theory and Algorithms","score":0.9990000128746033,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/T12292","display_name":"Graph Theory and Algorithms","score":0.9990000128746033,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/T10101","display_name":"Cloud Computing and Resource Management","score":0.9887999892234802,"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/T11106","display_name":"Data Management and Algorithms","score":0.9858999848365784,"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":0.8320226669311523},{"id":"https://openalex.org/keywords/spark","display_name":"SPARK (programming language)","score":0.6133188605308533},{"id":"https://openalex.org/keywords/big-data","display_name":"Big data","score":0.606821596622467},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5093227624893188},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.5070562362670898},{"id":"https://openalex.org/keywords/preprocessor","display_name":"Preprocessor","score":0.49649888277053833},{"id":"https://openalex.org/keywords/architecture","display_name":"Architecture","score":0.4519384801387787},{"id":"https://openalex.org/keywords/singular-value-decomposition","display_name":"Singular value decomposition","score":0.44096338748931885},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.3620039224624634}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8320226669311523},{"id":"https://openalex.org/C2781215313","wikidata":"https://www.wikidata.org/wiki/Q3493345","display_name":"SPARK (programming language)","level":2,"score":0.6133188605308533},{"id":"https://openalex.org/C75684735","wikidata":"https://www.wikidata.org/wiki/Q858810","display_name":"Big data","level":2,"score":0.606821596622467},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5093227624893188},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5070562362670898},{"id":"https://openalex.org/C34736171","wikidata":"https://www.wikidata.org/wiki/Q918333","display_name":"Preprocessor","level":2,"score":0.49649888277053833},{"id":"https://openalex.org/C123657996","wikidata":"https://www.wikidata.org/wiki/Q12271","display_name":"Architecture","level":2,"score":0.4519384801387787},{"id":"https://openalex.org/C22789450","wikidata":"https://www.wikidata.org/wiki/Q420904","display_name":"Singular value decomposition","level":2,"score":0.44096338748931885},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3620039224624634},{"id":"https://openalex.org/C153349607","wikidata":"https://www.wikidata.org/wiki/Q36649","display_name":"Visual arts","level":1,"score":0.0},{"id":"https://openalex.org/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","level":0,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.3390/a13030071","is_oa":true,"landing_page_url":"https://doi.org/10.3390/a13030071","pdf_url":"https://www.mdpi.com/1999-4893/13/3/71/pdf?version=1585236692","source":{"id":"https://openalex.org/S190629608","display_name":"Algorithms","issn_l":"1999-4893","issn":["1999-4893"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310310987","host_organization_name":"Multidisciplinary Digital Publishing Institute","host_organization_lineage":["https://openalex.org/P4310310987"],"host_organization_lineage_names":["Multidisciplinary Digital Publishing Institute"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Algorithms","raw_type":"journal-article"},{"id":"pmh:oai:doaj.org/article:eb6d53ce90134872be50de4575dec6f5","is_oa":true,"landing_page_url":"https://doaj.org/article/eb6d53ce90134872be50de4575dec6f5","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":"Algorithms, Vol 13, Iss 3, p 71 (2020)","raw_type":"article"},{"id":"pmh:oai:mdpi.com:/1999-4893/13/3/71/","is_oa":true,"landing_page_url":"http://dx.doi.org/10.3390/a13030071","pdf_url":null,"source":{"id":"https://openalex.org/S4306400947","display_name":"MDPI (MDPI AG)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I4210097602","host_organization_name":"Multidisciplinary Digital Publishing Institute (Switzerland)","host_organization_lineage":["https://openalex.org/I4210097602"],"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":"Algorithms","raw_type":"Text"}],"best_oa_location":{"id":"doi:10.3390/a13030071","is_oa":true,"landing_page_url":"https://doi.org/10.3390/a13030071","pdf_url":"https://www.mdpi.com/1999-4893/13/3/71/pdf?version=1585236692","source":{"id":"https://openalex.org/S190629608","display_name":"Algorithms","issn_l":"1999-4893","issn":["1999-4893"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310310987","host_organization_name":"Multidisciplinary Digital Publishing Institute","host_organization_lineage":["https://openalex.org/P4310310987"],"host_organization_lineage_names":["Multidisciplinary Digital Publishing Institute"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Algorithms","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3013531585.pdf","grobid_xml":"https://content.openalex.org/works/W3013531585.grobid-xml"},"referenced_works_count":54,"referenced_works":["https://openalex.org/W68800318","https://openalex.org/W410850256","https://openalex.org/W1495984639","https://openalex.org/W1521624597","https://openalex.org/W1547087245","https://openalex.org/W1599861493","https://openalex.org/W1873332500","https://openalex.org/W2005838333","https://openalex.org/W2013246060","https://openalex.org/W2016501084","https://openalex.org/W2026297770","https://openalex.org/W2026678899","https://openalex.org/W2074935284","https://openalex.org/W2079957645","https://openalex.org/W2091825929","https://openalex.org/W2096544401","https://openalex.org/W2100830825","https://openalex.org/W2116762767","https://openalex.org/W2119738171","https://openalex.org/W2121555320","https://openalex.org/W2121834718","https://openalex.org/W2125621954","https://openalex.org/W2126379392","https://openalex.org/W2132987852","https://openalex.org/W2133990480","https://openalex.org/W2161132813","https://openalex.org/W2163598528","https://openalex.org/W2170616854","https://openalex.org/W2173213060","https://openalex.org/W2190012392","https://openalex.org/W2542459869","https://openalex.org/W2592794863","https://openalex.org/W2607171102","https://openalex.org/W2607400399","https://openalex.org/W2613161123","https://openalex.org/W2764800686","https://openalex.org/W2785046580","https://openalex.org/W2803852943","https://openalex.org/W2884843966","https://openalex.org/W2911964244","https://openalex.org/W2917336158","https://openalex.org/W2953384591","https://openalex.org/W2963288913","https://openalex.org/W2971438928","https://openalex.org/W2972108677","https://openalex.org/W2977525883","https://openalex.org/W3105340263","https://openalex.org/W4232337901","https://openalex.org/W4251315812","https://openalex.org/W6613812410","https://openalex.org/W6614148910","https://openalex.org/W6639175750","https://openalex.org/W6684327724","https://openalex.org/W6713134421"],"related_works":["https://openalex.org/W4390608645","https://openalex.org/W2960264696","https://openalex.org/W3090563135","https://openalex.org/W2497432351","https://openalex.org/W4206777497","https://openalex.org/W2766461310","https://openalex.org/W4247566972","https://openalex.org/W4388692845","https://openalex.org/W3202731209","https://openalex.org/W3211874991"],"abstract_inverted_index":{"At":[0],"the":[1,4,32,45,49,67,79,120,126,153,157,162,176,184,200,216,234,240,244,253],"dawn":[2],"of":[3,16,37,44,133,161,169,178,183,199,202,219],"10V":[5,55],"or":[6],"big":[7,51],"data":[8,9,46,52,56,163],"era,":[10],"there":[11],"are":[12],"a":[13,41,84,96,130,145,167,193],"considerable":[14],"number":[15,132],"sources":[17],"such":[18,77],"as":[19,29,31,78,95],"smart":[20,26],"phones,":[21],"IoT":[22],"devices,":[23],"social":[24],"media,":[25],"city":[27],"sensors,":[28],"well":[30],"health":[33],"care":[34],"system,":[35],"all":[36],"which":[38,172],"constitute":[39],"but":[40],"small":[42],"portion":[43],"lakes":[47],"feeding":[48],"entire":[50],"ecosystem.":[53,81,128],"This":[54,108],"growth":[57],"poses":[58],"two":[59,113,138],"primary":[60],"challenges,":[61],"namely":[62,140],"storing":[63],"and":[64,94,142,205,226,252],"processing.":[65],"Concerning":[66],"latter,":[68],"new":[69],"frameworks":[70],"have":[71,101],"been":[72,102],"developed":[73,103],"including":[74],"distributed":[75,92],"platforms":[76,93],"Hadoop":[80,127],"Classification":[82],"is":[83,135,148,187],"major":[85],"machine":[86,122],"learning":[87,123],"task":[88],"typically":[89],"executed":[90],"on":[91,115,233],"consequence":[97],"many":[98],"algorithmic":[99],"techniques":[100],"tailored":[104],"for":[105,125],"these":[106],"platforms.":[107],"article":[109],"extensively":[110],"relies":[111],"in":[112,118,173],"ways":[114],"classifiers":[116,134,177,246],"implemented":[117],"MLlib,":[119],"main":[121],"library":[124],"First,":[129],"vast":[131],"applied":[136],"to":[137,152,188,224,249],"datasets,":[139],"Higgs":[141],"PAMAP.":[143],"Second,":[144],"two-step":[146],"classification":[147],"ab":[149],"ovo":[150],"performed":[151],"same":[154,235],"datasets.":[155],"Specifically,":[156],"singular":[158],"value":[159],"decomposition":[160],"matrix":[164],"determines":[165],"first":[166],"set":[168],"transformed":[170],"attributes":[171],"turn":[174],"drive":[175],"MLlib.":[179],"The":[180,209,230],"twofold":[181],"purpose":[182],"proposed":[185,241],"architecture":[186,242],"reduce":[189],"complexity":[190,251],"while":[191],"maintaining":[192],"similar":[194],"if":[195],"not":[196],"better":[197],"level":[198],"metrics":[201],"accuracy,":[203],"recall,":[204],"F":[206],"1":[207],".":[208],"intuition":[210],"behind":[211],"this":[212],"approach":[213],"stems":[214],"from":[215],"engineering":[217],"principle":[218],"breaking":[220],"down":[221],"complex":[222],"problems":[223],"simpler":[225],"more":[227],"manageable":[228],"tasks.":[229],"experiments":[231],"based":[232],"Spark":[236],"cluster":[237],"indicate":[238],"that":[239],"outperforms":[243],"individual":[245],"with":[247],"respect":[248],"both":[250],"abovementioned":[254],"metrics.":[255]},"counts_by_year":[{"year":2024,"cited_by_count":7},{"year":2023,"cited_by_count":3},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":4},{"year":2020,"cited_by_count":4}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}