{"id":"https://openalex.org/W3200450977","doi":"https://doi.org/10.26599/bdma.2021.9020012","title":"Intelligent and adaptive web data extraction system using convolutional and long short-term memory deep learning networks","display_name":"Intelligent and adaptive web data extraction system using convolutional and long short-term memory deep learning networks","publication_year":2021,"publication_date":"2021-08-26","ids":{"openalex":"https://openalex.org/W3200450977","doi":"https://doi.org/10.26599/bdma.2021.9020012","mag":"3200450977"},"language":"en","primary_location":{"id":"doi:10.26599/bdma.2021.9020012","is_oa":true,"landing_page_url":"https://doi.org/10.26599/bdma.2021.9020012","pdf_url":"https://ieeexplore.ieee.org/ielx7/8254253/9523493/09523501.pdf","source":{"id":"https://openalex.org/S4210209060","display_name":"Big Data Mining and Analytics","issn_l":"2096-0654","issn":["2096-0654"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310311901","host_organization_name":"Tsinghua University Press","host_organization_lineage":["https://openalex.org/P4310311901"],"host_organization_lineage_names":["Tsinghua University Press"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Big Data Mining and Analytics","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"diamond","oa_url":"https://ieeexplore.ieee.org/ielx7/8254253/9523493/09523501.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5081513560","display_name":"Sudhir Kumar Patnaik","orcid":"https://orcid.org/0000-0001-6069-1091"},"institutions":[{"id":"https://openalex.org/I302410947","display_name":"M S Ramaiah University of Applied Sciences","ror":"https://ror.org/02anh8x74","country_code":"IN","type":"education","lineage":["https://openalex.org/I302410947"]}],"countries":["IN"],"is_corresponding":true,"raw_author_name":"Sudhir Kumar Patnaik","raw_affiliation_strings":["Department of Computer Science and Engineering, M. S. Ramaiah University of Applied Sciences, Bangalore 560054, India; Gibraltar India Solutions LLP, Bangalore 560103, India","Gibraltar India Solutions LLP, Bangalore, India"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering, M. S. Ramaiah University of Applied Sciences, Bangalore 560054, India; Gibraltar India Solutions LLP, Bangalore 560103, India","institution_ids":["https://openalex.org/I302410947"]},{"raw_affiliation_string":"Gibraltar India Solutions LLP, Bangalore, India","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5112598534","display_name":"C. Narendra Babu","orcid":null},"institutions":[{"id":"https://openalex.org/I302410947","display_name":"M S Ramaiah University of Applied Sciences","ror":"https://ror.org/02anh8x74","country_code":"IN","type":"education","lineage":["https://openalex.org/I302410947"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"C. Narendra Babu","raw_affiliation_strings":["Department of Computer Science and Engineering, M. S. Ramaiah University of Applied Sciences, Bangalore 560054, India"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering, M. S. Ramaiah University of Applied Sciences, Bangalore 560054, India","institution_ids":["https://openalex.org/I302410947"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5024757458","display_name":"Mukul Bhave","orcid":null},"institutions":[{"id":"https://openalex.org/I4210146516","display_name":"OnApp (Gibraltar)","ror":"https://ror.org/046y0et18","country_code":"GI","type":"company","lineage":["https://openalex.org/I4210146516"]}],"countries":["GI"],"is_corresponding":false,"raw_author_name":"Mukul Bhave","raw_affiliation_strings":["Gibraltar India Solutions LLP, Bangalore 560103, India"],"affiliations":[{"raw_affiliation_string":"Gibraltar India Solutions LLP, Bangalore 560103, India","institution_ids":["https://openalex.org/I4210146516"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5081513560"],"corresponding_institution_ids":["https://openalex.org/I302410947"],"apc_list":null,"apc_paid":null,"fwci":10.8109,"has_fulltext":true,"cited_by_count":47,"citation_normalized_percentile":{"value":0.98308012,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":"4","issue":"4","first_page":"279","last_page":"297"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12016","display_name":"Web Data Mining and Analysis","score":1.0,"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"}},"topics":[{"id":"https://openalex.org/T12016","display_name":"Web Data Mining and Analysis","score":1.0,"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/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.9793000221252441,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/T11269","display_name":"Algorithms and Data Compression","score":0.9682000279426575,"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":0.8261837959289551},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.5273597836494446},{"id":"https://openalex.org/keywords/web-page","display_name":"Web page","score":0.5216915011405945},{"id":"https://openalex.org/keywords/term","display_name":"Term (time)","score":0.5135071873664856},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.49614986777305603},{"id":"https://openalex.org/keywords/data-extraction","display_name":"Data extraction","score":0.4857361912727356},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.47354239225387573},{"id":"https://openalex.org/keywords/big-data","display_name":"Big data","score":0.4711657464504242},{"id":"https://openalex.org/keywords/dynamic-web-page","display_name":"Dynamic web page","score":0.41108593344688416},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.38675689697265625},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.36565154790878296},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.25403517484664917}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8261837959289551},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.5273597836494446},{"id":"https://openalex.org/C21959979","wikidata":"https://www.wikidata.org/wiki/Q36774","display_name":"Web page","level":2,"score":0.5216915011405945},{"id":"https://openalex.org/C61797465","wikidata":"https://www.wikidata.org/wiki/Q1188986","display_name":"Term (time)","level":2,"score":0.5135071873664856},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.49614986777305603},{"id":"https://openalex.org/C2777466982","wikidata":"https://www.wikidata.org/wiki/Q5227287","display_name":"Data extraction","level":3,"score":0.4857361912727356},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.47354239225387573},{"id":"https://openalex.org/C75684735","wikidata":"https://www.wikidata.org/wiki/Q858810","display_name":"Big data","level":2,"score":0.4711657464504242},{"id":"https://openalex.org/C100158260","wikidata":"https://www.wikidata.org/wiki/Q1650567","display_name":"Dynamic web page","level":3,"score":0.41108593344688416},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.38675689697265625},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.36565154790878296},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.25403517484664917},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C2779473830","wikidata":"https://www.wikidata.org/wiki/Q1540899","display_name":"MEDLINE","level":2,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.26599/bdma.2021.9020012","is_oa":true,"landing_page_url":"https://doi.org/10.26599/bdma.2021.9020012","pdf_url":"https://ieeexplore.ieee.org/ielx7/8254253/9523493/09523501.pdf","source":{"id":"https://openalex.org/S4210209060","display_name":"Big Data Mining and Analytics","issn_l":"2096-0654","issn":["2096-0654"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310311901","host_organization_name":"Tsinghua University Press","host_organization_lineage":["https://openalex.org/P4310311901"],"host_organization_lineage_names":["Tsinghua University Press"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Big Data Mining and Analytics","raw_type":"journal-article"},{"id":"pmh:oai:doaj.org/article:a826c864be2d4aa081bc5069b7b2b972","is_oa":true,"landing_page_url":"https://doaj.org/article/a826c864be2d4aa081bc5069b7b2b972","pdf_url":null,"source":{"id":"https://openalex.org/S112646816","display_name":"SHILAP Revista de lepidopterolog\u00eda","issn_l":"0300-5267","issn":["0300-5267","2340-4078"],"is_oa":true,"is_in_doaj":true,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":"cc-by-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Big Data Mining and Analytics, Vol 4, Iss 4, Pp 279-297 (2021)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.26599/bdma.2021.9020012","is_oa":true,"landing_page_url":"https://doi.org/10.26599/bdma.2021.9020012","pdf_url":"https://ieeexplore.ieee.org/ielx7/8254253/9523493/09523501.pdf","source":{"id":"https://openalex.org/S4210209060","display_name":"Big Data Mining and Analytics","issn_l":"2096-0654","issn":["2096-0654"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310311901","host_organization_name":"Tsinghua University Press","host_organization_lineage":["https://openalex.org/P4310311901"],"host_organization_lineage_names":["Tsinghua University Press"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Big Data Mining and Analytics","raw_type":"journal-article"},"sustainable_development_goals":[{"display_name":"Industry, innovation and infrastructure","id":"https://metadata.un.org/sdg/9","score":0.5199999809265137}],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3200450977.pdf","grobid_xml":"https://content.openalex.org/works/W3200450977.grobid-xml"},"referenced_works_count":38,"referenced_works":["https://openalex.org/W639708223","https://openalex.org/W1553229631","https://openalex.org/W2008481957","https://openalex.org/W2065568440","https://openalex.org/W2071628657","https://openalex.org/W2096806473","https://openalex.org/W2102605133","https://openalex.org/W2134172329","https://openalex.org/W2136072238","https://openalex.org/W2137235842","https://openalex.org/W2138396769","https://openalex.org/W2143309843","https://openalex.org/W2148317291","https://openalex.org/W2167435152","https://openalex.org/W2517903345","https://openalex.org/W2548485934","https://openalex.org/W2570343428","https://openalex.org/W2735778951","https://openalex.org/W2766389674","https://openalex.org/W2775036586","https://openalex.org/W2783940359","https://openalex.org/W2798843784","https://openalex.org/W2799081297","https://openalex.org/W2811122304","https://openalex.org/W2946615908","https://openalex.org/W2949817882","https://openalex.org/W2962970995","https://openalex.org/W2963037989","https://openalex.org/W2972149141","https://openalex.org/W3008750864","https://openalex.org/W3014183340","https://openalex.org/W3041046342","https://openalex.org/W3081987387","https://openalex.org/W3122396520","https://openalex.org/W4233962457","https://openalex.org/W4287773354","https://openalex.org/W4301510055","https://openalex.org/W6601065604"],"related_works":["https://openalex.org/W2368657441","https://openalex.org/W2392829923","https://openalex.org/W2389737178","https://openalex.org/W2374659546","https://openalex.org/W2167278502","https://openalex.org/W2346384915","https://openalex.org/W237064923","https://openalex.org/W406631474","https://openalex.org/W4200180345","https://openalex.org/W2479887749"],"abstract_inverted_index":{"Data":[0],"are":[1,18,83],"crucial":[2],"to":[3,35,61,78,105],"the":[4,36,68],"growth":[5],"of":[6,11,127,138,144],"e-commerce":[7],"in":[8,39,108],"today's":[9],"world":[10],"highly":[12],"demanding":[13],"hyper-personalized":[14],"consumer":[15],"experiences,":[16],"which":[17,82],"collected":[19],"using":[20,67],"advanced":[21],"web":[22,49,64,88],"scraping":[23],"technologies.":[24],"However,":[25],"core":[26,97],"data":[27,50,98],"extraction":[28,51,99,124],"engines":[29],"fail":[30],"because":[31],"they":[32],"cannot":[33],"adapt":[34,104],"dynamic":[37,106],"changes":[38,107],"website":[40,109],"content.":[41],"This":[42,90],"study":[43],"investigates":[44],"an":[45,118,141],"intelligent":[46],"and":[47,55,75,101,122,129],"adaptive":[48],"system":[52,92],"with":[53,140],"convolutional":[54],"Long":[56],"Short-Term":[57],"Memory":[58],"(LSTM)":[59],"networks":[60],"enable":[62],"automated":[63],"page":[65],"detection":[66,120],"You":[69],"only":[70],"look":[71],"once":[72],"(Yolo)":[73],"algorithm":[74],"Tesseract":[76],"LSTM":[77],"extract":[79],"product":[80],"details,":[81],"detected":[84],"as":[85],"images":[86],"from":[87],"pages.":[89],"state-of-the-art":[91],"does":[93],"not":[94],"need":[95],"a":[96,134],"engine,":[100],"thus":[102],"can":[103],"layout.":[110],"Experiments":[111],"conducted":[112],"on":[113],"real-world":[114],"retail":[115],"cases":[116],"demonstrate":[117],"image":[119],"(precision)":[121,126],"character":[123],"accuracy":[125],"97%":[128],"99%,":[130],"respectively.":[131],"In":[132],"addition,":[133],"mean":[135],"average":[136],"precision":[137],"74%,":[139],"input":[142],"dataset":[143],"45":[145],"objects":[146],"or":[147],"images,":[148],"is":[149],"obtained.":[150]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":7},{"year":2024,"cited_by_count":14},{"year":2023,"cited_by_count":12},{"year":2022,"cited_by_count":11},{"year":2021,"cited_by_count":1}],"updated_date":"2026-04-02T15:55:50.835912","created_date":"2025-10-10T00:00:00"}