{"id":"https://openalex.org/W4393141664","doi":"https://doi.org/10.1109/ants59832.2023.10469018","title":"A Comparative Study of Unsupervised Learning Techniques and Natural Language Processing in Network Traffic Classification","display_name":"A Comparative Study of Unsupervised Learning Techniques and Natural Language Processing in Network Traffic Classification","publication_year":2023,"publication_date":"2023-12-17","ids":{"openalex":"https://openalex.org/W4393141664","doi":"https://doi.org/10.1109/ants59832.2023.10469018"},"language":"en","primary_location":{"id":"doi:10.1109/ants59832.2023.10469018","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ants59832.2023.10469018","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 IEEE International Conference on Advanced Networks and Telecommunications Systems (ANTS)","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/A5102021037","display_name":"Yayathi Pavan Kumar S","orcid":null},"institutions":[{"id":"https://openalex.org/I119241673","display_name":"Indian Institute of Technology Ropar","ror":"https://ror.org/02qkhhn56","country_code":"IN","type":"education","lineage":["https://openalex.org/I119241673"]}],"countries":["IN"],"is_corresponding":true,"raw_author_name":"Yayathi Pavan Kumar S","raw_affiliation_strings":["Indian Institute of Technology, Ropar,Rupnagar,India"],"affiliations":[{"raw_affiliation_string":"Indian Institute of Technology, Ropar,Rupnagar,India","institution_ids":["https://openalex.org/I119241673"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5055393595","display_name":"Sudeepta Mishra","orcid":"https://orcid.org/0000-0003-4821-4318"},"institutions":[{"id":"https://openalex.org/I119241673","display_name":"Indian Institute of Technology Ropar","ror":"https://ror.org/02qkhhn56","country_code":"IN","type":"education","lineage":["https://openalex.org/I119241673"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Sudeepta Mishra","raw_affiliation_strings":["Indian Institute of Technology, Ropar,Rupnagar,India"],"affiliations":[{"raw_affiliation_string":"Indian Institute of Technology, Ropar,Rupnagar,India","institution_ids":["https://openalex.org/I119241673"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5031257926","display_name":"V. K. Chaithanya Manam","orcid":"https://orcid.org/0000-0003-3653-1279"},"institutions":[{"id":"https://openalex.org/I219193219","display_name":"Purdue University West Lafayette","ror":"https://ror.org/02dqehb95","country_code":"US","type":"education","lineage":["https://openalex.org/I219193219"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"V. K. Chaithanya Manam","raw_affiliation_strings":["Purdue University,West Lafayette,Indiana,USA"],"affiliations":[{"raw_affiliation_string":"Purdue University,West Lafayette,Indiana,USA","institution_ids":["https://openalex.org/I219193219"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5102021037"],"corresponding_institution_ids":["https://openalex.org/I119241673"],"apc_list":null,"apc_paid":null,"fwci":1.037,"has_fulltext":false,"cited_by_count":6,"citation_normalized_percentile":{"value":0.82236717,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":95,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"138","last_page":"143"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11598","display_name":"Internet Traffic Analysis and Secure E-voting","score":0.9984999895095825,"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/T11598","display_name":"Internet Traffic Analysis and Secure E-voting","score":0.9984999895095825,"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/T12262","display_name":"Hate Speech and Cyberbullying Detection","score":0.9783999919891357,"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/T10400","display_name":"Network Security and Intrusion Detection","score":0.9617000222206116,"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":0.755914568901062},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5617173314094543},{"id":"https://openalex.org/keywords/unsupervised-learning","display_name":"Unsupervised learning","score":0.5355576872825623},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5194551348686218},{"id":"https://openalex.org/keywords/traffic-classification","display_name":"Traffic classification","score":0.41402214765548706},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.15733852982521057},{"id":"https://openalex.org/keywords/the-internet","display_name":"The Internet","score":0.06758308410644531}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.755914568901062},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5617173314094543},{"id":"https://openalex.org/C8038995","wikidata":"https://www.wikidata.org/wiki/Q1152135","display_name":"Unsupervised learning","level":2,"score":0.5355576872825623},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5194551348686218},{"id":"https://openalex.org/C169988225","wikidata":"https://www.wikidata.org/wiki/Q7832484","display_name":"Traffic classification","level":3,"score":0.41402214765548706},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.15733852982521057},{"id":"https://openalex.org/C110875604","wikidata":"https://www.wikidata.org/wiki/Q75","display_name":"The Internet","level":2,"score":0.06758308410644531}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/ants59832.2023.10469018","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ants59832.2023.10469018","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 IEEE International Conference on Advanced Networks and Telecommunications Systems (ANTS)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.8199999928474426,"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":22,"referenced_works":["https://openalex.org/W1971776783","https://openalex.org/W2031088030","https://openalex.org/W2035734658","https://openalex.org/W2053550965","https://openalex.org/W2053901313","https://openalex.org/W2062401262","https://openalex.org/W2575148973","https://openalex.org/W2759910885","https://openalex.org/W2772996140","https://openalex.org/W2784189955","https://openalex.org/W2810973780","https://openalex.org/W2824027552","https://openalex.org/W2900853407","https://openalex.org/W2901008672","https://openalex.org/W2921646839","https://openalex.org/W2953231656","https://openalex.org/W2963516518","https://openalex.org/W2969984724","https://openalex.org/W3043280294","https://openalex.org/W3092122204","https://openalex.org/W3165205057","https://openalex.org/W4290927694"],"related_works":["https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W2358668433","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W2382290278","https://openalex.org/W3204019825","https://openalex.org/W2086288008","https://openalex.org/W4236526390","https://openalex.org/W2974523378"],"abstract_inverted_index":{"In":[0],"order":[1],"to":[2,39,45,79,111,223],"achieve":[3],"the":[4,14,40,49,73,84,103,139,164,172,180,186,190,225],"best":[5,154,165],"utilization":[6,85],"of":[7,16,43,51,75,86,138,141,156,169,193,206,213,227],"resources,":[8],"contemporary":[9],"methods":[10],"aimed":[11],"at":[12],"enhancing":[13],"categorization":[15],"network":[17,132],"traffic":[18,133],"for":[19,160,171,178,209],"optimal":[20,191,204],"prioritization":[21],"often":[22],"depend":[23],"on":[24,121],"port":[25],"identification":[26],"and":[27,48,59,67,123,144,153,176,195,201],"deep":[28,60],"packet":[29],"inspection":[30],"(DPI).":[31],"However,":[32],"these":[33,76,96],"techniques":[34,55],"have":[35,127],"become":[36],"outdated":[37],"due":[38],"unpredictable":[41],"assignment":[42],"ports":[44],"new":[46],"applications":[47],"existence":[50],"concealed":[52],"traffic.":[53,216],"Modern":[54],"leveraging":[56,148],"machine":[57],"learning":[58,61],"extract":[62],"numerous":[63],"features":[64],"from":[65],"networks":[66],"subsequently":[68],"produce":[69],"offline":[70],"analyses.":[71],"Unfortunately,":[72],"results":[74,183,198],"approaches":[77,146],"lead":[78],"substantial":[80],"computational":[81],"burdens.":[82],"Consequently,":[83],"labeled":[87,228],"datasets":[88,97],"containing":[89],"network-specific":[90],"attributes":[91],"has":[92],"been":[93,128],"adopted,":[94],"but":[95],"remain":[98],"limited":[99],"in":[100,230],"availability.":[101],"Additionally,":[102],"models":[104,120],"developed":[105],"using":[106],"such":[107],"network-centric":[108,114],"findings":[109],"tend":[110],"be":[112],"inherently":[113],"themselves.In":[115],"this":[116,231],"paper,":[117],"network-independent":[118],"data-centric":[119],"payloads":[122,124],"with":[125,135,163,174],"headers":[126],"built":[129],"by":[130],"performing":[131],"classification":[134],"a":[136,210],"comparison":[137],"efficacy":[140],"KMeans,":[142],"DBSCAN,":[143],"NLP":[145],"(by":[147],"topic":[149,161,166,187],"modeling).":[150],"The":[151],"optimum":[152],"number":[155,192,205],"clusters":[157,194,207],"were":[158],"obtained":[159],"modelling,":[162],"coherence":[167],"score":[168],"0.8069":[170],"payload":[173],"header":[175],"0.8000":[177],"only":[179],"payload.":[181],"Our":[182,217],"show":[184],"that":[185],"model":[188],"obtains":[189],"produces":[196],"better":[197],"than":[199],"KMeans":[200],"DBSCAN.":[202],"This":[203],"allows":[208],"simple":[211],"method":[212],"detecting":[214],"abnormal":[215],"study":[218],"could":[219],"potentially":[220],"create":[221],"avenues":[222],"address":[224],"scarcity":[226],"data":[229],"specific":[232],"research":[233],"domain.":[234]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":3}],"updated_date":"2026-04-10T15:06:20.359241","created_date":"2025-10-10T00:00:00"}