{"id":"https://openalex.org/W4205489943","doi":"https://doi.org/10.1109/bigdata52589.2021.9672005","title":"Scaling deep learning data management with Cassandra DB","display_name":"Scaling deep learning data management with Cassandra DB","publication_year":2021,"publication_date":"2021-12-15","ids":{"openalex":"https://openalex.org/W4205489943","doi":"https://doi.org/10.1109/bigdata52589.2021.9672005"},"language":"en","primary_location":{"id":"doi:10.1109/bigdata52589.2021.9672005","is_oa":false,"landing_page_url":"https://doi.org/10.1109/bigdata52589.2021.9672005","pdf_url":null,"source":{"id":"https://openalex.org/S4363607718","display_name":"2021 IEEE International Conference on Big Data (Big Data)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 IEEE International Conference on Big Data (Big Data)","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://zenodo.org/record/6038358","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5010522931","display_name":"Francesco Versaci","orcid":"https://orcid.org/0000-0003-2513-3590"},"institutions":[{"id":"https://openalex.org/I2800759272","display_name":"Center for Advanced Studies Research and Development in Sardinia","ror":"https://ror.org/03jdxdk20","country_code":"IT","type":"facility","lineage":["https://openalex.org/I2800759272"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Francesco Versaci","raw_affiliation_strings":["CRS4, Scalable Computing and Analytics Group, Pula, Italy"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"CRS4, Scalable Computing and Analytics Group, Pula, Italy","institution_ids":["https://openalex.org/I2800759272"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5009437460","display_name":"Giovanni Busonera","orcid":"https://orcid.org/0000-0003-3266-7857"},"institutions":[{"id":"https://openalex.org/I2800759272","display_name":"Center for Advanced Studies Research and Development in Sardinia","ror":"https://ror.org/03jdxdk20","country_code":"IT","type":"facility","lineage":["https://openalex.org/I2800759272"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Giovanni Busonera","raw_affiliation_strings":["CRS4, Scalable Computing and Analytics Group, Pula, Italy"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"CRS4, Scalable Computing and Analytics Group, Pula, Italy","institution_ids":["https://openalex.org/I2800759272"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.1268,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.39500924,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"5301","last_page":"5310"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12761","display_name":"Data Stream Mining Techniques","score":0.9983000159263611,"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/T12761","display_name":"Data Stream Mining Techniques","score":0.9983000159263611,"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/T10101","display_name":"Cloud Computing and Resource Management","score":0.9972000122070312,"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/T10273","display_name":"IoT and Edge/Fog Computing","score":0.982200026512146,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8470122814178467},{"id":"https://openalex.org/keywords/nosql","display_name":"NoSQL","score":0.8232543468475342},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.7714625597000122},{"id":"https://openalex.org/keywords/metadata","display_name":"Metadata","score":0.7184886932373047},{"id":"https://openalex.org/keywords/big-data","display_name":"Big data","score":0.6736790537834167},{"id":"https://openalex.org/keywords/pipeline","display_name":"Pipeline (software)","score":0.6562250852584839},{"id":"https://openalex.org/keywords/data-management","display_name":"Data management","score":0.547623336315155},{"id":"https://openalex.org/keywords/standardization","display_name":"Standardization","score":0.514777421951294},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.4949888586997986},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.492000550031662},{"id":"https://openalex.org/keywords/data-modeling","display_name":"Data modeling","score":0.4684109091758728},{"id":"https://openalex.org/keywords/cloud-computing","display_name":"Cloud computing","score":0.4636325538158417},{"id":"https://openalex.org/keywords/distributed-computing","display_name":"Distributed computing","score":0.38729581236839294},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.36234694719314575},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.278677761554718},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.22956541180610657}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8470122814178467},{"id":"https://openalex.org/C2779599972","wikidata":"https://www.wikidata.org/wiki/Q82231","display_name":"NoSQL","level":3,"score":0.8232543468475342},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.7714625597000122},{"id":"https://openalex.org/C93518851","wikidata":"https://www.wikidata.org/wiki/Q180160","display_name":"Metadata","level":2,"score":0.7184886932373047},{"id":"https://openalex.org/C75684735","wikidata":"https://www.wikidata.org/wiki/Q858810","display_name":"Big data","level":2,"score":0.6736790537834167},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.6562250852584839},{"id":"https://openalex.org/C1668388","wikidata":"https://www.wikidata.org/wiki/Q1149776","display_name":"Data management","level":2,"score":0.547623336315155},{"id":"https://openalex.org/C188087704","wikidata":"https://www.wikidata.org/wiki/Q369577","display_name":"Standardization","level":2,"score":0.514777421951294},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.4949888586997986},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.492000550031662},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.4684109091758728},{"id":"https://openalex.org/C79974875","wikidata":"https://www.wikidata.org/wiki/Q483639","display_name":"Cloud computing","level":2,"score":0.4636325538158417},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.38729581236839294},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.36234694719314575},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.278677761554718},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.22956541180610657}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/bigdata52589.2021.9672005","is_oa":false,"landing_page_url":"https://doi.org/10.1109/bigdata52589.2021.9672005","pdf_url":null,"source":{"id":"https://openalex.org/S4363607718","display_name":"2021 IEEE International Conference on Big Data (Big Data)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 IEEE International Conference on Big Data (Big Data)","raw_type":"proceedings-article"},{"id":"pmh:oai:zenodo.org:6038358","is_oa":true,"landing_page_url":"https://zenodo.org/record/6038358","pdf_url":null,"source":{"id":"https://openalex.org/S4306400562","display_name":"Zenodo (CERN European Organization for Nuclear Research)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I67311998","host_organization_name":"European Organization for Nuclear Research","host_organization_lineage":["https://openalex.org/I67311998"],"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":"","raw_type":"info:eu-repo/semantics/conferencePaper"}],"best_oa_location":{"id":"pmh:oai:zenodo.org:6038358","is_oa":true,"landing_page_url":"https://zenodo.org/record/6038358","pdf_url":null,"source":{"id":"https://openalex.org/S4306400562","display_name":"Zenodo (CERN European Organization for Nuclear Research)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I67311998","host_organization_name":"European Organization for Nuclear Research","host_organization_lineage":["https://openalex.org/I67311998"],"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":"","raw_type":"info:eu-repo/semantics/conferencePaper"},"sustainable_development_goals":[{"display_name":"Industry, innovation and infrastructure","id":"https://metadata.un.org/sdg/9","score":0.46000000834465027}],"awards":[],"funders":[{"id":"https://openalex.org/F4320320300","display_name":"European Commission","ror":"https://ror.org/00k4n6c32"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":28,"referenced_works":["https://openalex.org/W174317439","https://openalex.org/W1985667642","https://openalex.org/W2000075256","https://openalex.org/W2087946700","https://openalex.org/W2097438121","https://openalex.org/W2117539524","https://openalex.org/W2144174917","https://openalex.org/W2194775991","https://openalex.org/W2542459869","https://openalex.org/W2788193959","https://openalex.org/W2799845958","https://openalex.org/W2800277550","https://openalex.org/W2805886241","https://openalex.org/W2869909795","https://openalex.org/W2900042580","https://openalex.org/W2952046647","https://openalex.org/W2953809131","https://openalex.org/W2955152335","https://openalex.org/W2976292093","https://openalex.org/W2977730164","https://openalex.org/W2997111522","https://openalex.org/W3000374705","https://openalex.org/W3105067168","https://openalex.org/W3162829015","https://openalex.org/W3206418153","https://openalex.org/W4288289119","https://openalex.org/W6767917410","https://openalex.org/W6912823979"],"related_works":["https://openalex.org/W2799973158","https://openalex.org/W2419153746","https://openalex.org/W2514636569","https://openalex.org/W2553396476","https://openalex.org/W2064004856","https://openalex.org/W2519462635","https://openalex.org/W2115553997","https://openalex.org/W1976221100","https://openalex.org/W298027295","https://openalex.org/W4225748383"],"abstract_inverted_index":{"Deep":[0],"learning":[1,122],"(DL)":[2],"algorithms":[3],"require,":[4],"to":[5,30,63],"be":[6],"fully":[7],"effective,":[8],"harvesting":[9],"an":[10],"increasingly":[11],"large":[12],"amount":[13],"of":[14,22,38,54],"data.":[15],"These":[16],"data,":[17],"typically":[18],"organized":[19],"as":[20],"millions":[21],"small":[23],"files,":[24],"stress":[25],"filesystems":[26],"and":[27,41,57,77,86,103,107,112,116],"are":[28],"difficult":[29],"manage.":[31],"In":[32],"fact,":[33],"despite":[34],"the":[35,65,84],"huge":[36],"development":[37],"DL":[39,48,93],"tools":[40],"specialized":[42],"hardware,":[43],"data":[44,66,76,89,101,114,118],"loading":[45,67],"pipeline":[46],"for":[47,73,91,120],"still":[49],"lacks":[50],"behind":[51],"in":[52],"ease":[53],"use,":[55],"standardization":[56],"scalability.In":[58],"this":[59],"work":[60],"we":[61],"try":[62],"rethink":[64],"pipeline,":[68],"by":[69],"leveraging":[70],"NoSQL":[71],"DBs":[72],"storing":[74],"both":[75],"metadata,":[78],"making":[79],"them":[80],"efficiently":[81],"available":[82],"through":[83],"network,":[85],"allowing":[87],"easier":[88],"distribution":[90,119],"parallel":[92,121],"training.":[94],"We":[95],"present":[96],"our":[97],"open-source,":[98],"Apache":[99],"Cassandra-based":[100],"loader":[102],"illustrate":[104],"its":[105],"use":[106],"performance,":[108],"which":[109],"enable":[110],"easy":[111],"efficient":[113],"management":[115],"decentralized":[117],"applications.":[123]},"counts_by_year":[{"year":2022,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}