{"id":"https://openalex.org/W2901028997","doi":"https://doi.org/10.1145/3274895.3274923","title":"Detecting skewness of big spatial data in SpatialHadoop","display_name":"Detecting skewness of big spatial data in SpatialHadoop","publication_year":2018,"publication_date":"2018-11-06","ids":{"openalex":"https://openalex.org/W2901028997","doi":"https://doi.org/10.1145/3274895.3274923","mag":"2901028997"},"language":"en","primary_location":{"id":"doi:10.1145/3274895.3274923","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3274895.3274923","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 26th ACM SIGSPATIAL International Conference on Advances in Geographic Information Systems","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/A5048471838","display_name":"Alberto Belussi","orcid":"https://orcid.org/0000-0003-3023-8020"},"institutions":[{"id":"https://openalex.org/I119439378","display_name":"University of Verona","ror":"https://ror.org/039bp8j42","country_code":"IT","type":"education","lineage":["https://openalex.org/I119439378"]}],"countries":["IT"],"is_corresponding":true,"raw_author_name":"Alberto Belussi","raw_affiliation_strings":["University of Verona, Italy"],"affiliations":[{"raw_affiliation_string":"University of Verona, Italy","institution_ids":["https://openalex.org/I119439378"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5042554325","display_name":"Sara Migliorini","orcid":"https://orcid.org/0000-0003-3675-7243"},"institutions":[{"id":"https://openalex.org/I119439378","display_name":"University of Verona","ror":"https://ror.org/039bp8j42","country_code":"IT","type":"education","lineage":["https://openalex.org/I119439378"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Sara Migliorini","raw_affiliation_strings":["University of Verona, Italy"],"affiliations":[{"raw_affiliation_string":"University of Verona, Italy","institution_ids":["https://openalex.org/I119439378"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5091292625","display_name":"Ahmed Eldawy","orcid":"https://orcid.org/0000-0002-6584-1455"},"institutions":[{"id":"https://openalex.org/I103635307","display_name":"University of California, Riverside","ror":"https://ror.org/03nawhv43","country_code":"US","type":"education","lineage":["https://openalex.org/I103635307"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ahmed Eldawy","raw_affiliation_strings":["University of California Riverside"],"affiliations":[{"raw_affiliation_string":"University of California Riverside","institution_ids":["https://openalex.org/I103635307"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5048471838"],"corresponding_institution_ids":["https://openalex.org/I119439378"],"apc_list":null,"apc_paid":null,"fwci":2.8074,"has_fulltext":false,"cited_by_count":25,"citation_normalized_percentile":{"value":0.91951203,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":91,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"432","last_page":"435"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11106","display_name":"Data Management and Algorithms","score":0.9950000047683716,"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":0.9950000047683716,"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":0.9544000029563904,"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/T10757","display_name":"Geographic Information Systems Studies","score":0.954200029373169,"subfield":{"id":"https://openalex.org/subfields/3305","display_name":"Geography, Planning and Development"},"field":{"id":"https://openalex.org/fields/33","display_name":"Social Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/skewness","display_name":"Skewness","score":0.7323325872421265},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6736906170845032},{"id":"https://openalex.org/keywords/big-data","display_name":"Big data","score":0.5618234276771545},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.3809112012386322},{"id":"https://openalex.org/keywords/data-science","display_name":"Data science","score":0.33533620834350586},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.2440783679485321},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.11450836062431335}],"concepts":[{"id":"https://openalex.org/C122342681","wikidata":"https://www.wikidata.org/wiki/Q330828","display_name":"Skewness","level":2,"score":0.7323325872421265},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6736906170845032},{"id":"https://openalex.org/C75684735","wikidata":"https://www.wikidata.org/wiki/Q858810","display_name":"Big data","level":2,"score":0.5618234276771545},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3809112012386322},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.33533620834350586},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.2440783679485321},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.11450836062431335}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3274895.3274923","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3274895.3274923","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 26th ACM SIGSPATIAL International Conference on Advances in Geographic Information Systems","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320334079","display_name":"Gruppo Nazionale per il Calcolo Scientifico","ror":null}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":13,"referenced_works":["https://openalex.org/W1504344674","https://openalex.org/W1568832590","https://openalex.org/W2079348595","https://openalex.org/W2088521060","https://openalex.org/W2127436290","https://openalex.org/W2171419575","https://openalex.org/W2187025990","https://openalex.org/W2197411628","https://openalex.org/W2280230190","https://openalex.org/W2436533802","https://openalex.org/W2586720796","https://openalex.org/W2888876219","https://openalex.org/W4244655266"],"related_works":["https://openalex.org/W4322629366","https://openalex.org/W2808989540","https://openalex.org/W2397053934","https://openalex.org/W1039292361","https://openalex.org/W2551093110","https://openalex.org/W2148016376","https://openalex.org/W4237919137","https://openalex.org/W3184179822","https://openalex.org/W3095362084","https://openalex.org/W3003361536"],"abstract_inverted_index":{"In":[0,22],"recent":[1],"years":[2],"several":[3],"extensions":[4],"of":[5,61,117,119,133,162],"Hadoop":[6],"system":[7],"have":[8,96],"been":[9],"proposed":[10],"for":[11,71,113],"dealing":[12],"with":[13],"spatial":[14,121],"data":[15,33],"and":[16,36,93,135],"SpatialHadoop":[17],"belongs":[18],"to":[19,97,106,145,150,154],"this":[20],"group.":[21],"the":[23,38,45,49,52,59,68,90,115,125,131,160],"MapReduce":[24],"paradigm":[25],"a":[26,62,84,120,139],"task":[27],"can":[28,56],"be":[29,89,98],"parallelized":[30],"by":[31],"partitioning":[32,54,148],"into":[34],"chunks":[35],"performing":[37],"same":[39],"operation":[40],"on":[41,124],"them,":[42],"eventually":[43],"combining":[44],"partial":[46],"results":[47],"at":[48],"end.":[50],"Thus,":[51],"applied":[53],"technique":[55,149],"tremendously":[57],"affect":[58],"performance":[60,161],"parallel":[63],"execution,":[64],"since":[65],"it":[66],"is":[67,141],"key":[69],"point":[70],"obtaining":[72],"balanced":[73],"map":[74],"tasks.":[75],"However,":[76],"when":[77],"skewed":[78],"distributed":[79],"datasets":[80],"are":[81,103],"considered,":[82],"using":[83],"regular":[85],"grid":[86],"might":[87],"not":[88],"right":[91],"choice":[92],"other":[94],"techniques":[95],"applied,":[99],"which":[100,147],"in":[101,143,152],"turn":[102],"more":[104],"expensive":[105],"build.":[107],"This":[108],"paper":[109],"illustrates":[110],"an":[111],"approach":[112],"detecting":[114],"degree":[116,132],"skewness":[118,134],"dataset,":[122],"based":[123],"box":[126],"counting":[127],"function.":[128],"Moreover,":[129],"given":[130],"some":[136],"experimental":[137],"observations,":[138],"heuristic":[140],"sketched":[142],"order":[144,153],"decide":[146],"apply":[151],"improve":[155],"as":[156,158],"much":[157],"possible":[159],"subsequent":[163],"operations.":[164]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":4},{"year":2022,"cited_by_count":4},{"year":2021,"cited_by_count":3},{"year":2020,"cited_by_count":8},{"year":2019,"cited_by_count":5}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}