{"id":"https://openalex.org/W1987652028","doi":"https://doi.org/10.1109/apccas.2014.7032862","title":"Efficient data transfer scheme using word-pair-encoding-based compression for large-scale text-data processing","display_name":"Efficient data transfer scheme using word-pair-encoding-based compression for large-scale text-data processing","publication_year":2014,"publication_date":"2014-11-01","ids":{"openalex":"https://openalex.org/W1987652028","doi":"https://doi.org/10.1109/apccas.2014.7032862","mag":"1987652028"},"language":"en","primary_location":{"id":"doi:10.1109/apccas.2014.7032862","is_oa":false,"landing_page_url":"https://doi.org/10.1109/apccas.2014.7032862","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2014 IEEE Asia Pacific Conference on Circuits and Systems (APCCAS)","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/A5058564631","display_name":"Hasitha Muthumala Waidyasooriya","orcid":"https://orcid.org/0000-0001-5108-9891"},"institutions":[{"id":"https://openalex.org/I201537933","display_name":"Tohoku University","ror":"https://ror.org/01dq60k83","country_code":"JP","type":"education","lineage":["https://openalex.org/I201537933"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Hasitha Muthumala Waidyasooriya","raw_affiliation_strings":["Graduate School of Information Sciences, Tohoku University, Sendai, Miyagi, Japan","Graduate School of Information Sciences, Tohoku University, Aoba 6-6-05, Aramaki, Aoba, Sendai, Miyagi,980-8579, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Graduate School of Information Sciences, Tohoku University, Sendai, Miyagi, Japan","institution_ids":["https://openalex.org/I201537933"]},{"raw_affiliation_string":"Graduate School of Information Sciences, Tohoku University, Aoba 6-6-05, Aramaki, Aoba, Sendai, Miyagi,980-8579, Japan","institution_ids":["https://openalex.org/I201537933"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5026520913","display_name":"Daisuke Ono","orcid":"https://orcid.org/0000-0003-0192-163X"},"institutions":[{"id":"https://openalex.org/I201537933","display_name":"Tohoku University","ror":"https://ror.org/01dq60k83","country_code":"JP","type":"education","lineage":["https://openalex.org/I201537933"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Daisuke Ono","raw_affiliation_strings":["Graduate School of Information Sciences, Tohoku University, Sendai, Miyagi, Japan","Graduate School of Information Sciences, Tohoku University, Aoba 6-6-05, Aramaki, Aoba, Sendai, Miyagi,980-8579, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Graduate School of Information Sciences, Tohoku University, Sendai, Miyagi, Japan","institution_ids":["https://openalex.org/I201537933"]},{"raw_affiliation_string":"Graduate School of Information Sciences, Tohoku University, Aoba 6-6-05, Aramaki, Aoba, Sendai, Miyagi,980-8579, Japan","institution_ids":["https://openalex.org/I201537933"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5070647966","display_name":"Masanori Hariyama","orcid":"https://orcid.org/0000-0002-1464-8807"},"institutions":[{"id":"https://openalex.org/I201537933","display_name":"Tohoku University","ror":"https://ror.org/01dq60k83","country_code":"JP","type":"education","lineage":["https://openalex.org/I201537933"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Masanori Hariyama","raw_affiliation_strings":["Graduate School of Information Sciences, Tohoku University, Sendai, Miyagi, Japan","Graduate School of Information Sciences, Tohoku University, Aoba 6-6-05, Aramaki, Aoba, Sendai, Miyagi,980-8579, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Graduate School of Information Sciences, Tohoku University, Sendai, Miyagi, Japan","institution_ids":["https://openalex.org/I201537933"]},{"raw_affiliation_string":"Graduate School of Information Sciences, Tohoku University, Aoba 6-6-05, Aramaki, Aoba, Sendai, Miyagi,980-8579, Japan","institution_ids":["https://openalex.org/I201537933"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5037191455","display_name":"Michitaka Kameyama","orcid":"https://orcid.org/0000-0002-4245-9907"},"institutions":[{"id":"https://openalex.org/I201537933","display_name":"Tohoku University","ror":"https://ror.org/01dq60k83","country_code":"JP","type":"education","lineage":["https://openalex.org/I201537933"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Michitaka Kameyama","raw_affiliation_strings":["Graduate School of Information Sciences, Tohoku University, Sendai, Miyagi, Japan","Graduate School of Information Sciences, Tohoku University, Aoba 6-6-05, Aramaki, Aoba, Sendai, Miyagi,980-8579, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Graduate School of Information Sciences, Tohoku University, Sendai, Miyagi, Japan","institution_ids":["https://openalex.org/I201537933"]},{"raw_affiliation_string":"Graduate School of Information Sciences, Tohoku University, Aoba 6-6-05, Aramaki, Aoba, Sendai, Miyagi,980-8579, Japan","institution_ids":["https://openalex.org/I201537933"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.8458,"has_fulltext":false,"cited_by_count":7,"citation_normalized_percentile":{"value":0.80461337,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":96},"biblio":{"volume":"64","issue":null,"first_page":"639","last_page":"642"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11269","display_name":"Algorithms and Data Compression","score":0.9998999834060669,"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":0.9998999834060669,"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/T11181","display_name":"Advanced Data Storage Technologies","score":0.9948999881744385,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"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/T12029","display_name":"DNA and Biological Computing","score":0.991100013256073,"subfield":{"id":"https://openalex.org/subfields/1312","display_name":"Molecular Biology"},"field":{"id":"https://openalex.org/fields/13","display_name":"Biochemistry, Genetics and Molecular Biology"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8447116613388062},{"id":"https://openalex.org/keywords/decoding-methods","display_name":"Decoding methods","score":0.7550573348999023},{"id":"https://openalex.org/keywords/bottleneck","display_name":"Bottleneck","score":0.7512884140014648},{"id":"https://openalex.org/keywords/encoding","display_name":"Encoding (memory)","score":0.658708930015564},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.6525236368179321},{"id":"https://openalex.org/keywords/transfer","display_name":"Transfer (computing)","score":0.5816435813903809},{"id":"https://openalex.org/keywords/data-compression","display_name":"Data compression","score":0.5654770731925964},{"id":"https://openalex.org/keywords/field-programmable-gate-array","display_name":"Field-programmable gate array","score":0.4778934717178345},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.3774920403957367},{"id":"https://openalex.org/keywords/computer-hardware","display_name":"Computer hardware","score":0.31555038690567017},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.26286882162094116},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.20966681838035583},{"id":"https://openalex.org/keywords/embedded-system","display_name":"Embedded system","score":0.1387597918510437}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8447116613388062},{"id":"https://openalex.org/C57273362","wikidata":"https://www.wikidata.org/wiki/Q576722","display_name":"Decoding methods","level":2,"score":0.7550573348999023},{"id":"https://openalex.org/C2780513914","wikidata":"https://www.wikidata.org/wiki/Q18210350","display_name":"Bottleneck","level":2,"score":0.7512884140014648},{"id":"https://openalex.org/C125411270","wikidata":"https://www.wikidata.org/wiki/Q18653","display_name":"Encoding (memory)","level":2,"score":0.658708930015564},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.6525236368179321},{"id":"https://openalex.org/C2776175482","wikidata":"https://www.wikidata.org/wiki/Q1195816","display_name":"Transfer (computing)","level":2,"score":0.5816435813903809},{"id":"https://openalex.org/C78548338","wikidata":"https://www.wikidata.org/wiki/Q2493","display_name":"Data compression","level":2,"score":0.5654770731925964},{"id":"https://openalex.org/C42935608","wikidata":"https://www.wikidata.org/wiki/Q190411","display_name":"Field-programmable gate array","level":2,"score":0.4778934717178345},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.3774920403957367},{"id":"https://openalex.org/C9390403","wikidata":"https://www.wikidata.org/wiki/Q3966","display_name":"Computer hardware","level":1,"score":0.31555038690567017},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.26286882162094116},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.20966681838035583},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.1387597918510437},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/apccas.2014.7032862","is_oa":false,"landing_page_url":"https://doi.org/10.1109/apccas.2014.7032862","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2014 IEEE Asia Pacific Conference on Circuits and Systems (APCCAS)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320320912","display_name":"Ministry of Education, Culture, Sports, Science and Technology","ror":"https://ror.org/048rj2z13"},{"id":"https://openalex.org/F4320334764","display_name":"Japan Society for the Promotion of Science","ror":"https://ror.org/00hhkn466"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":13,"referenced_works":["https://openalex.org/W46679369","https://openalex.org/W1993074222","https://openalex.org/W2019334886","https://openalex.org/W2103441770","https://openalex.org/W2133531097","https://openalex.org/W2158322625","https://openalex.org/W2161488606","https://openalex.org/W2164364358","https://openalex.org/W2554162996","https://openalex.org/W6601894380","https://openalex.org/W6683030939","https://openalex.org/W6683504902","https://openalex.org/W6730253985"],"related_works":["https://openalex.org/W2595172197","https://openalex.org/W2084856301","https://openalex.org/W2127970246","https://openalex.org/W2885125400","https://openalex.org/W1001352512","https://openalex.org/W1989889224","https://openalex.org/W4382618745","https://openalex.org/W1973775000","https://openalex.org/W2748922771","https://openalex.org/W4301373716"],"abstract_inverted_index":{"Large-scale":[0],"data":[1,32,58,68,79,86,102],"processing":[2],"is":[3,42],"very":[4],"common":[5],"in":[6],"many":[7],"fields":[8],"such":[9,17],"as":[10],"data-mining,":[11],"genome":[12],"mapping,":[13],"etc.":[14],"To":[15],"accelerate":[16],"processing,":[18],"Graphic":[19],"Accelerator":[20],"Units":[21],"(GPU)":[22],"and":[23,38,104],"FPGAs":[24],"(Feild-Programmable":[25],"Gate-Array)":[26],"are":[27],"used.":[28],"However,":[29],"the":[30,36,39,57,77,84,101],"large":[31],"transfer":[33,105],"time":[34,106],"between":[35],"accelerator":[37],"host":[40],"computer":[41],"a":[43,52],"huge":[44],"performance":[45],"bottleneck.":[46],"In":[47],"this":[48],"paper,":[49],"we":[50,98],"use":[51],"word-pair-encoding":[53],"method":[54],"to":[55,60],"compress":[56],"down":[59],"25%":[61],"of":[62],"its":[63],"original":[64],"size.":[65],"The":[66],"encoded":[67,85],"can":[69,87,107],"be":[70,88,108],"decoded":[71],"from":[72],"any":[73],"position":[74],"without":[75,90],"decoding":[76],"whole":[78],"file.":[80],"For":[81],"some":[82],"algorithms,":[83],"processed":[89],"decoding.":[91],"Using":[92],"Burrows-Wheeler":[93],"algorithm":[94],"based":[95],"text":[96],"search,":[97],"show":[99],"that":[100],"amount":[103],"reduced":[109],"by":[110],"over":[111],"70%.":[112]},"counts_by_year":[{"year":2023,"cited_by_count":2},{"year":2021,"cited_by_count":1},{"year":2019,"cited_by_count":1},{"year":2018,"cited_by_count":1},{"year":2016,"cited_by_count":1},{"year":2015,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}