{"id":"https://openalex.org/W4200364695","doi":"https://doi.org/10.1109/hpec49654.2021.9622810","title":"Large Scale String Analytics in Arkouda","display_name":"Large Scale String Analytics in Arkouda","publication_year":2021,"publication_date":"2021-09-20","ids":{"openalex":"https://openalex.org/W4200364695","doi":"https://doi.org/10.1109/hpec49654.2021.9622810"},"language":"en","primary_location":{"id":"doi:10.1109/hpec49654.2021.9622810","is_oa":false,"landing_page_url":"https://doi.org/10.1109/hpec49654.2021.9622810","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 IEEE High Performance Extreme Computing Conference (HPEC)","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/A5100685313","display_name":"Zhihui Du","orcid":"https://orcid.org/0000-0002-8435-1611"},"institutions":[{"id":"https://openalex.org/I118118575","display_name":"New Jersey Institute of Technology","ror":"https://ror.org/05e74xb87","country_code":"US","type":"education","lineage":["https://openalex.org/I118118575"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Zhihui Du","raw_affiliation_strings":["New Jersey Institute of Technology, Newark, New Jersey, US"],"affiliations":[{"raw_affiliation_string":"New Jersey Institute of Technology, Newark, New Jersey, US","institution_ids":["https://openalex.org/I118118575"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5070173078","display_name":"Oliver Alvarado Rodriguez","orcid":null},"institutions":[{"id":"https://openalex.org/I118118575","display_name":"New Jersey Institute of Technology","ror":"https://ror.org/05e74xb87","country_code":"US","type":"education","lineage":["https://openalex.org/I118118575"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Oliver Alvarado Rodriguez","raw_affiliation_strings":["New Jersey Institute of Technology, Newark, New Jersey, US"],"affiliations":[{"raw_affiliation_string":"New Jersey Institute of Technology, Newark, New Jersey, US","institution_ids":["https://openalex.org/I118118575"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5076610730","display_name":"David A. Bader","orcid":"https://orcid.org/0000-0002-7380-5876"},"institutions":[{"id":"https://openalex.org/I118118575","display_name":"New Jersey Institute of Technology","ror":"https://ror.org/05e74xb87","country_code":"US","type":"education","lineage":["https://openalex.org/I118118575"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"David A. Bader","raw_affiliation_strings":["New Jersey Institute of Technology, Newark, New Jersey, US"],"affiliations":[{"raw_affiliation_string":"New Jersey Institute of Technology, Newark, New Jersey, US","institution_ids":["https://openalex.org/I118118575"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5100685313"],"corresponding_institution_ids":["https://openalex.org/I118118575"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.19092923,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"7"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11269","display_name":"Algorithms and Data Compression","score":1.0,"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/T11269","display_name":"Algorithms and Data Compression","score":1.0,"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/T12326","display_name":"Network Packet Processing and Optimization","score":0.9926000237464905,"subfield":{"id":"https://openalex.org/subfields/1708","display_name":"Hardware and Architecture"},"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9775999784469604,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8480154871940613},{"id":"https://openalex.org/keywords/compressed-suffix-array","display_name":"Compressed suffix array","score":0.8457401394844055},{"id":"https://openalex.org/keywords/suffix-tree","display_name":"Suffix tree","score":0.775923490524292},{"id":"https://openalex.org/keywords/generalized-suffix-tree","display_name":"Generalized suffix tree","score":0.6359696388244629},{"id":"https://openalex.org/keywords/suffix-array","display_name":"Suffix array","score":0.6204976439476013},{"id":"https://openalex.org/keywords/suffix","display_name":"Suffix","score":0.6048306822776794},{"id":"https://openalex.org/keywords/python","display_name":"Python (programming language)","score":0.5219647288322449},{"id":"https://openalex.org/keywords/string","display_name":"String (physics)","score":0.5138011574745178},{"id":"https://openalex.org/keywords/data-structure","display_name":"Data structure","score":0.48236316442489624},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.4246140122413635},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.3982965052127838},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.37475115060806274},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.21430110931396484},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.08382627367973328}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8480154871940613},{"id":"https://openalex.org/C100903775","wikidata":"https://www.wikidata.org/wiki/Q5157028","display_name":"Compressed suffix array","level":4,"score":0.8457401394844055},{"id":"https://openalex.org/C2781166958","wikidata":"https://www.wikidata.org/wiki/Q1426863","display_name":"Suffix tree","level":3,"score":0.775923490524292},{"id":"https://openalex.org/C118146561","wikidata":"https://www.wikidata.org/wiki/Q5532514","display_name":"Generalized suffix tree","level":4,"score":0.6359696388244629},{"id":"https://openalex.org/C2779259728","wikidata":"https://www.wikidata.org/wiki/Q281472","display_name":"Suffix array","level":3,"score":0.6204976439476013},{"id":"https://openalex.org/C2779804580","wikidata":"https://www.wikidata.org/wiki/Q102047","display_name":"Suffix","level":2,"score":0.6048306822776794},{"id":"https://openalex.org/C519991488","wikidata":"https://www.wikidata.org/wiki/Q28865","display_name":"Python (programming language)","level":2,"score":0.5219647288322449},{"id":"https://openalex.org/C157486923","wikidata":"https://www.wikidata.org/wiki/Q1376436","display_name":"String (physics)","level":2,"score":0.5138011574745178},{"id":"https://openalex.org/C162319229","wikidata":"https://www.wikidata.org/wiki/Q175263","display_name":"Data structure","level":2,"score":0.48236316442489624},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.4246140122413635},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.3982965052127838},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.37475115060806274},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.21430110931396484},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.08382627367973328},{"id":"https://openalex.org/C37914503","wikidata":"https://www.wikidata.org/wiki/Q156495","display_name":"Mathematical physics","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/hpec49654.2021.9622810","is_oa":false,"landing_page_url":"https://doi.org/10.1109/hpec49654.2021.9622810","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 IEEE High Performance Extreme Computing Conference (HPEC)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Decent work and economic growth","score":0.5799999833106995,"id":"https://metadata.un.org/sdg/8"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":43,"referenced_works":["https://openalex.org/W12026041","https://openalex.org/W938539187","https://openalex.org/W1485516007","https://openalex.org/W1485847476","https://openalex.org/W1503805697","https://openalex.org/W1976682045","https://openalex.org/W1985704385","https://openalex.org/W1993399552","https://openalex.org/W2030359179","https://openalex.org/W2044127221","https://openalex.org/W2044824397","https://openalex.org/W2064184672","https://openalex.org/W2072731885","https://openalex.org/W2098297530","https://openalex.org/W2105633925","https://openalex.org/W2109062349","https://openalex.org/W2111217142","https://openalex.org/W2118703123","https://openalex.org/W2130564474","https://openalex.org/W2133732112","https://openalex.org/W2134283755","https://openalex.org/W2137346250","https://openalex.org/W2141238531","https://openalex.org/W2158874082","https://openalex.org/W2160962794","https://openalex.org/W2263407306","https://openalex.org/W2275023529","https://openalex.org/W2335962142","https://openalex.org/W2402980768","https://openalex.org/W2519490418","https://openalex.org/W2539361505","https://openalex.org/W2604604482","https://openalex.org/W2799438998","https://openalex.org/W2806788989","https://openalex.org/W2964320652","https://openalex.org/W2973738211","https://openalex.org/W3045950232","https://openalex.org/W4243001025","https://openalex.org/W4294239945","https://openalex.org/W6630059933","https://openalex.org/W6633630531","https://openalex.org/W6692951507","https://openalex.org/W6694616088"],"related_works":["https://openalex.org/W2003608043","https://openalex.org/W2405892617","https://openalex.org/W153119118","https://openalex.org/W2583658747","https://openalex.org/W4293529780","https://openalex.org/W2158874082","https://openalex.org/W1575722140","https://openalex.org/W2073921136","https://openalex.org/W1965532872","https://openalex.org/W3092594492"],"abstract_inverted_index":{"Large":[0],"scale":[1],"data":[2,27,39,46,85,181],"sets":[3,47],"from":[4,205],"the":[5,49,62,67,71,76,158,161,169,176],"web,":[6],"social":[7],"networks,":[8],"and":[9,14,21,36,88,167,185,203],"bioinformatics":[10],"are":[11,24,91,200],"widely":[12],"available":[13,204],"can":[15,179],"often":[16],"be":[17],"rep-resented":[18],"by":[19],"strings":[20,128],"suffix":[22,83,95,105,118,134,163,190],"arrays":[23,191],"highly":[25],"efficient":[26,82,186],"structures":[28],"enabling":[29],"string":[30],"analysis.":[31],"But,":[32],"our":[33,198],"personal":[34],"devices":[35],"corresponding":[37,152],"exploratory":[38],"analysis":[40],"(EDA)":[41],"tools":[42],"cannot":[43],"handle":[44],"big":[45],"beyond":[48],"local":[50],"memory.":[51],"Arkouda":[52,115],"is":[53,107,139,154],"a":[54],"framework":[55,138],"under":[56],"early":[57],"development":[58],"that":[59,175],"brings":[60],"together":[61],"productivity":[63],"of":[64,73,102,160],"Python":[65],"at":[66,75],"user":[68],"side":[69],"with":[70,192],"high-performance":[72],"Chapel":[74],"server-side.":[77],"In":[78],"this":[79],"paper,":[80],"an":[81,183],"array":[84,96,119,135,164],"structure":[86],"design":[87],"integration":[89,99,165],"method":[90,100,166,187],"given":[92,140],"first.":[93],"A":[94,132,151],"algorithm":[97,106,137],"library":[98],"instead":[101],"one":[103],"single":[104],"presented":[108],"to":[109,141,156,188],"enable":[110],"runtime":[111],"performance":[112,194],"optimization":[113],"in":[114,129,149,195],"since":[116],"different":[117,124],"algorithms":[120],"may":[121],"have":[122],"very":[123],"practical":[125],"performances":[126],"for":[127],"various":[130],"applications.":[131],"parallel":[133],"construction":[136],"further":[142],"exploit":[143],"hierarchical":[144],"parallelism":[145],"on":[146],"multiple":[147],"locales":[148],"Chapel.":[150],"benchmark":[153],"developed":[155],"evaluate":[157],"feasibility":[159],"provided":[162],"measure":[168],"end-to-end":[170],"performance.":[171],"Experimental":[172],"results":[173],"show":[174],"proposed":[177],"solution":[178],"provide":[180],"scientists":[182],"easy":[184],"build":[189],"high":[193],"Python.":[196],"All":[197],"codes":[199],"open":[201],"source":[202],"GitHub":[206],"(https://github.com/Bader-Research/arkouda/tree/string-suffix-array-functionality).":[207]},"counts_by_year":[],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}