{"id":"https://openalex.org/W4404739773","doi":"https://doi.org/10.1109/isncc62547.2024.10758939","title":"Balancing the Complexity of Data Pipeline Engineering: A Technological Landscape Where Human Expertise Meets Large Language Models","display_name":"Balancing the Complexity of Data Pipeline Engineering: A Technological Landscape Where Human Expertise Meets Large Language Models","publication_year":2024,"publication_date":"2024-10-22","ids":{"openalex":"https://openalex.org/W4404739773","doi":"https://doi.org/10.1109/isncc62547.2024.10758939"},"language":"en","primary_location":{"id":"doi:10.1109/isncc62547.2024.10758939","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/isncc62547.2024.10758939","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 International Symposium on Networks, Computers and Communications (ISNCC)","raw_type":"proceedings-article"},"type":"conference-paper","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/A5066083180","display_name":"Rim Moussa","orcid":"https://orcid.org/0000-0002-5011-1695"},"institutions":[{"id":"https://openalex.org/I179097149","display_name":"University of Carthage","ror":"https://ror.org/057x6za15","country_code":"TN","type":"education","lineage":["https://openalex.org/I179097149"]}],"countries":["TN"],"is_corresponding":false,"raw_author_name":"Rim Moussa","raw_affiliation_strings":["ENI-Carthage, University of Carthage,Tunisia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"ENI-Carthage, University of Carthage,Tunisia","institution_ids":["https://openalex.org/I179097149"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5079374330","display_name":"Tarek Bejaoui","orcid":"https://orcid.org/0000-0003-2501-8939"},"institutions":[{"id":"https://openalex.org/I179097149","display_name":"University of Carthage","ror":"https://ror.org/057x6za15","country_code":"TN","type":"education","lineage":["https://openalex.org/I179097149"]}],"countries":["TN"],"is_corresponding":false,"raw_author_name":"Tarek Bejaoui","raw_affiliation_strings":["University of Carthage,Faculty of Sciences of Bizerte,Tunisia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Carthage,Faculty of Sciences of Bizerte,Tunisia","institution_ids":["https://openalex.org/I179097149"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I179097149"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.22705877,"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":"6"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10215","display_name":"Semantic Web and Ontologies","score":0.8125,"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/T10215","display_name":"Semantic Web and Ontologies","score":0.8125,"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/pipeline","display_name":"Pipeline (software)","score":0.7066146731376648},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7062035202980042},{"id":"https://openalex.org/keywords/data-modeling","display_name":"Data modeling","score":0.46074381470680237},{"id":"https://openalex.org/keywords/data-science","display_name":"Data science","score":0.40964001417160034},{"id":"https://openalex.org/keywords/software-engineering","display_name":"Software engineering","score":0.3865935802459717},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.2169492542743683}],"concepts":[{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.7066146731376648},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7062035202980042},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.46074381470680237},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.40964001417160034},{"id":"https://openalex.org/C115903868","wikidata":"https://www.wikidata.org/wiki/Q80993","display_name":"Software engineering","level":1,"score":0.3865935802459717},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.2169492542743683}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/isncc62547.2024.10758939","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/isncc62547.2024.10758939","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 International Symposium on Networks, Computers and Communications (ISNCC)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.46000000834465027,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":13,"referenced_works":["https://openalex.org/W4200151996","https://openalex.org/W4286432951","https://openalex.org/W4312349237","https://openalex.org/W4312867851","https://openalex.org/W4386493427","https://openalex.org/W4386797617","https://openalex.org/W4387263124","https://openalex.org/W4389539730","https://openalex.org/W4396669430","https://openalex.org/W6758269923","https://openalex.org/W6797711835","https://openalex.org/W6858978762","https://openalex.org/W6870161493"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W4391913857","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W4396696052"],"abstract_inverted_index":{"Data":[0],"pipeline":[1,66,74,87,116],"engineering":[2],"plays":[3],"a":[4,29,43,59,71,101],"critical":[5],"role":[6],"in":[7,28,113],"managing":[8],"cost":[9],"optimization,":[10],"scalability,":[11],"reliability,":[12],"and":[13,26,31,37,50,95],"data":[14,21,65,73,86,91,115],"governance":[15],"challenges":[16],"by":[17],"ensuring":[18],"that":[19],"big":[20,90],"can":[22],"be":[23],"ingested,":[24],"processed,":[25],"stored":[27],"scalable":[30],"reliable":[32],"way,":[33],"to":[34,76],"enable":[35],"analysis":[36],"insights.":[38],"Addressing":[39],"these":[40],"obstacles":[41],"necessitates":[42],"combination":[44],"of":[45,61,104,107],"human":[46],"expertise,":[47],"suitable":[48,89],"technologies,":[49],"custom":[51],"hardware":[52],"resources.":[53],"In":[54],"this":[55],"paper":[56],"we":[57,69],"present":[58],"survey":[60],"existing":[62],"research":[63],"on":[64],"engineering.":[67,117],"Subsequently,":[68],"introduce":[70],"complex":[72],"designed":[75],"infer":[77],"aircraft":[78],"flights":[79],"from":[80],"crowdsourced":[81],"networks.":[82],"We":[83,98],"implement":[84],"the":[85,105],"using":[88],"frameworks":[92],"Apache":[93,96],"Spark":[94],"Sedona.":[97],"also":[99],"provide":[100],"comprehensive":[102],"review":[103],"capabilities":[106],"prominent":[108],"Large":[109],"Language":[110],"Models":[111],"(LLMs)":[112],"assisting":[114]},"counts_by_year":[],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}