{"id":"https://openalex.org/W4385481003","doi":"https://doi.org/10.3390/mti7080077","title":"Enhancing Object Detection for VIPs Using YOLOv4_Resnet101 and Text-to-Speech Conversion Model","display_name":"Enhancing Object Detection for VIPs Using YOLOv4_Resnet101 and Text-to-Speech Conversion Model","publication_year":2023,"publication_date":"2023-08-02","ids":{"openalex":"https://openalex.org/W4385481003","doi":"https://doi.org/10.3390/mti7080077"},"language":"en","primary_location":{"id":"doi:10.3390/mti7080077","is_oa":true,"landing_page_url":"https://doi.org/10.3390/mti7080077","pdf_url":"https://www.mdpi.com/2414-4088/7/8/77/pdf?version=1690968530","source":{"id":"https://openalex.org/S4210226272","display_name":"Multimodal Technologies and Interaction","issn_l":"2414-4088","issn":["2414-4088"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310310987","host_organization_name":"Multidisciplinary Digital Publishing Institute","host_organization_lineage":["https://openalex.org/P4310310987"],"host_organization_lineage_names":["Multidisciplinary Digital Publishing Institute"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Multimodal Technologies and Interaction","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://www.mdpi.com/2414-4088/7/8/77/pdf?version=1690968530","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5041891989","display_name":"Tahani Jaser Alahmadi","orcid":"https://orcid.org/0000-0002-0067-692X"},"institutions":[{"id":"https://openalex.org/I106778892","display_name":"Princess Nourah bint Abdulrahman University","ror":"https://ror.org/05b0cyh02","country_code":"SA","type":"education","lineage":["https://openalex.org/I106778892"]}],"countries":["SA"],"is_corresponding":true,"raw_author_name":"Tahani Jaser Alahmadi","raw_affiliation_strings":["Department of Information Systems, College of Computer and Information Sciences, Princess Nourah Bint Abdulrahman University (PNU), P.O. Box 84428, Riyadh 11671, Saudi Arabia"],"raw_orcid":"https://orcid.org/0000-0002-0067-692X","affiliations":[{"raw_affiliation_string":"Department of Information Systems, College of Computer and Information Sciences, Princess Nourah Bint Abdulrahman University (PNU), P.O. Box 84428, Riyadh 11671, Saudi Arabia","institution_ids":["https://openalex.org/I106778892"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101766352","display_name":"Atta Ur Rahman","orcid":"https://orcid.org/0000-0003-3569-9926"},"institutions":[{"id":"https://openalex.org/I5400463","display_name":"Ghulam Ishaq Khan Institute of Engineering Sciences and Technology","ror":"https://ror.org/01sb6ek09","country_code":"PK","type":"education","lineage":["https://openalex.org/I5400463"]}],"countries":["PK"],"is_corresponding":false,"raw_author_name":"Atta Ur Rahman","raw_affiliation_strings":["Faculty of Computer Science and Engineering, GIK Institute of Engineering Sciences and Technology, Swabi 23640, Pakistan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Faculty of Computer Science and Engineering, GIK Institute of Engineering Sciences and Technology, Swabi 23640, Pakistan","institution_ids":["https://openalex.org/I5400463"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5058485751","display_name":"Hend Khalid Alkahtani","orcid":"https://orcid.org/0000-0001-7507-5267"},"institutions":[{"id":"https://openalex.org/I106778892","display_name":"Princess Nourah bint Abdulrahman University","ror":"https://ror.org/05b0cyh02","country_code":"SA","type":"education","lineage":["https://openalex.org/I106778892"]}],"countries":["SA"],"is_corresponding":false,"raw_author_name":"Hend Khalid Alkahtani","raw_affiliation_strings":["Department of Information Systems, College of Computer and Information Sciences, Princess Nourah Bint Abdulrahman University (PNU), P.O. Box 84428, Riyadh 11671, Saudi Arabia"],"raw_orcid":"https://orcid.org/0000-0001-7507-5267","affiliations":[{"raw_affiliation_string":"Department of Information Systems, College of Computer and Information Sciences, Princess Nourah Bint Abdulrahman University (PNU), P.O. Box 84428, Riyadh 11671, Saudi Arabia","institution_ids":["https://openalex.org/I106778892"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5079318114","display_name":"Hisham A. Kholidy","orcid":"https://orcid.org/0000-0002-7673-5850"},"institutions":[{"id":"https://openalex.org/I90965887","display_name":"SUNY Polytechnic Institute","ror":"https://ror.org/000fxgx19","country_code":"US","type":"education","lineage":["https://openalex.org/I90965887"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Hisham Kholidy","raw_affiliation_strings":["Department of Networks and Computer Security, SUNY Polytechnic Institute, College of Engineering, Utica, NY 13502, USA"],"raw_orcid":"https://orcid.org/0000-0002-7673-5850","affiliations":[{"raw_affiliation_string":"Department of Networks and Computer Security, SUNY Polytechnic Institute, College of Engineering, Utica, NY 13502, USA","institution_ids":["https://openalex.org/I90965887"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5041891989"],"corresponding_institution_ids":["https://openalex.org/I106778892"],"apc_list":{"value":1600,"currency":"CHF","value_usd":1782},"apc_paid":{"value":1600,"currency":"CHF","value_usd":1782},"fwci":3.6937,"has_fulltext":true,"cited_by_count":28,"citation_normalized_percentile":{"value":0.94224946,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":97,"max":99},"biblio":{"volume":"7","issue":"8","first_page":"77","last_page":"77"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10914","display_name":"Tactile and Sensory Interactions","score":0.9993000030517578,"subfield":{"id":"https://openalex.org/subfields/2805","display_name":"Cognitive Neuroscience"},"field":{"id":"https://openalex.org/fields/28","display_name":"Neuroscience"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},"topics":[{"id":"https://openalex.org/T10914","display_name":"Tactile and Sensory Interactions","score":0.9993000030517578,"subfield":{"id":"https://openalex.org/subfields/2805","display_name":"Cognitive Neuroscience"},"field":{"id":"https://openalex.org/fields/28","display_name":"Neuroscience"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":0.9987999796867371,"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/T10331","display_name":"Video Surveillance and Tracking Methods","score":0.9933000206947327,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8162969350814819},{"id":"https://openalex.org/keywords/backbone-network","display_name":"Backbone network","score":0.6486117839813232},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6246132850646973},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.5300801992416382},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.5220144391059875},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.49585995078086853},{"id":"https://openalex.org/keywords/object-detection","display_name":"Object detection","score":0.47728386521339417},{"id":"https://openalex.org/keywords/annotation","display_name":"Annotation","score":0.47017210721969604},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.45539939403533936},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.45072200894355774},{"id":"https://openalex.org/keywords/obstacle","display_name":"Obstacle","score":0.4482387602329254},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3812265396118164},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.37078458070755005},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.3481534719467163}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8162969350814819},{"id":"https://openalex.org/C88796919","wikidata":"https://www.wikidata.org/wiki/Q1142907","display_name":"Backbone network","level":2,"score":0.6486117839813232},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6246132850646973},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.5300801992416382},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.5220144391059875},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.49585995078086853},{"id":"https://openalex.org/C2776151529","wikidata":"https://www.wikidata.org/wiki/Q3045304","display_name":"Object detection","level":3,"score":0.47728386521339417},{"id":"https://openalex.org/C2776321320","wikidata":"https://www.wikidata.org/wiki/Q857525","display_name":"Annotation","level":2,"score":0.47017210721969604},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.45539939403533936},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.45072200894355774},{"id":"https://openalex.org/C2776650193","wikidata":"https://www.wikidata.org/wiki/Q264661","display_name":"Obstacle","level":2,"score":0.4482387602329254},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3812265396118164},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.37078458070755005},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.3481534719467163},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","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},{"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/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.3390/mti7080077","is_oa":true,"landing_page_url":"https://doi.org/10.3390/mti7080077","pdf_url":"https://www.mdpi.com/2414-4088/7/8/77/pdf?version=1690968530","source":{"id":"https://openalex.org/S4210226272","display_name":"Multimodal Technologies and Interaction","issn_l":"2414-4088","issn":["2414-4088"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310310987","host_organization_name":"Multidisciplinary Digital Publishing Institute","host_organization_lineage":["https://openalex.org/P4310310987"],"host_organization_lineage_names":["Multidisciplinary Digital Publishing Institute"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Multimodal Technologies and Interaction","raw_type":"journal-article"},{"id":"pmh:oai:doaj.org/article:3e2203c5496148d6aea6d7983f5d8209","is_oa":true,"landing_page_url":"https://doaj.org/article/3e2203c5496148d6aea6d7983f5d8209","pdf_url":null,"source":{"id":"https://openalex.org/S4306401280","display_name":"DOAJ (DOAJ: Directory of Open Access Journals)","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":"repository"},"license":"cc-by-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Multimodal Technologies and Interaction, Vol 7, Iss 8, p 77 (2023)","raw_type":"article"},{"id":"pmh:oai:mdpi.com:/2414-4088/7/8/77/","is_oa":true,"landing_page_url":"https://dx.doi.org/10.3390/mti7080077","pdf_url":null,"source":{"id":"https://openalex.org/S4306400947","display_name":"MDPI (MDPI AG)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I4210097602","host_organization_name":"Multidisciplinary Digital Publishing Institute (Switzerland)","host_organization_lineage":["https://openalex.org/I4210097602"],"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":"Multimodal Technologies and Interaction; Volume 7; Issue 8; Pages: 77","raw_type":"Text"}],"best_oa_location":{"id":"doi:10.3390/mti7080077","is_oa":true,"landing_page_url":"https://doi.org/10.3390/mti7080077","pdf_url":"https://www.mdpi.com/2414-4088/7/8/77/pdf?version=1690968530","source":{"id":"https://openalex.org/S4210226272","display_name":"Multimodal Technologies and Interaction","issn_l":"2414-4088","issn":["2414-4088"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310310987","host_organization_name":"Multidisciplinary Digital Publishing Institute","host_organization_lineage":["https://openalex.org/P4310310987"],"host_organization_lineage_names":["Multidisciplinary Digital Publishing Institute"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Multimodal Technologies and Interaction","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G6826428883","display_name":null,"funder_award_id":"KSRG-2023-021","funder_id":"https://openalex.org/F4320330363","funder_display_name":"King Salman Center for Disability Research"}],"funders":[{"id":"https://openalex.org/F4320330363","display_name":"King Salman Center for Disability Research","ror":"https://ror.org/01ht2b307"}],"has_content":{"grobid_xml":false,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4385481003.pdf"},"referenced_works_count":33,"referenced_works":["https://openalex.org/W1483870316","https://openalex.org/W1861492603","https://openalex.org/W2083044905","https://openalex.org/W2102605133","https://openalex.org/W2700061640","https://openalex.org/W2742792558","https://openalex.org/W2766459852","https://openalex.org/W2927635115","https://openalex.org/W2945042256","https://openalex.org/W2962970995","https://openalex.org/W2980838178","https://openalex.org/W3001112922","https://openalex.org/W3020972710","https://openalex.org/W3034024180","https://openalex.org/W3091895534","https://openalex.org/W3113276149","https://openalex.org/W3127646871","https://openalex.org/W3166010309","https://openalex.org/W3197025345","https://openalex.org/W3216761206","https://openalex.org/W3217492189","https://openalex.org/W4210319364","https://openalex.org/W4210459336","https://openalex.org/W4220755807","https://openalex.org/W4280538133","https://openalex.org/W4296629864","https://openalex.org/W4309978326","https://openalex.org/W4317624365","https://openalex.org/W6769053239","https://openalex.org/W6779368119","https://openalex.org/W6790290745","https://openalex.org/W6809441643","https://openalex.org/W7074091645"],"related_works":["https://openalex.org/W2794103424","https://openalex.org/W1996530509","https://openalex.org/W3028317537","https://openalex.org/W2389515972","https://openalex.org/W4245435724","https://openalex.org/W2361861616","https://openalex.org/W2894651257","https://openalex.org/W3200590620","https://openalex.org/W4200172193","https://openalex.org/W4303926741"],"abstract_inverted_index":{"Vision":[0],"impairment":[1],"affects":[2],"an":[3,181],"individual\u2019s":[4],"quality":[5],"of":[6,50,54,69,118,126,160,183,196,203],"life,":[7],"posing":[8],"challenges":[9],"for":[10,42],"visually":[11],"impaired":[12],"people":[13],"(VIPs)":[14],"in":[15,45,82,95,100,139,175],"various":[16],"aspects":[17],"such":[18],"as":[19,71],"object":[20,55,77,127],"recognition":[21],"and":[22,48,105,154],"daily":[23,61],"tasks.":[24],"Previous":[25],"research":[26],"has":[27],"focused":[28],"on":[29,75,185],"developing":[30],"visual":[31,120],"navigation":[32],"systems":[33],"to":[34,79,88,149,173],"assist":[35,80,174],"VIPs,":[36],"but":[37],"there":[38],"is":[39,132],"a":[40,51,66,92,103,199],"need":[41],"further":[43],"improvements":[44],"accuracy,":[46],"speed,":[47],"inclusion":[49],"wider":[52],"range":[53],"categories":[56],"that":[57],"may":[58],"obstruct":[59],"VIPs\u2019":[60],"lives.":[62],"This":[63],"study":[64],"presents":[65],"modified":[67],"version":[68],"YOLOv4_Resnet101":[70,101],"backbone":[72,93,99],"networks":[73],"trained":[74],"multiple":[76],"classes":[78],"VIPs":[81,169],"navigating":[83],"their":[84],"surroundings.":[85],"In":[86],"comparison":[87],"the":[89,97,124,135,151,186,191],"Darknet,":[90],"with":[91,170,198],"utilized":[94],"YOLOv4,":[96],"ResNet-101":[98],"offers":[102],"deeper":[104],"more":[106],"powerful":[107],"feature":[108],"extraction":[109],"network.":[110],"The":[111,129,163,178],"ResNet-101\u2019s":[112],"greater":[113],"capacity":[114],"enables":[115],"better":[116],"representation":[117],"complex":[119],"patterns,":[121],"which":[122],"increases":[123],"accuracy":[125,182],"detection.":[128],"proposed":[130],"model":[131,179],"validated":[133],"using":[134],"Microsoft":[136],"Common":[137],"Objects":[138],"Context":[140],"(MS":[141],"COCO)":[142],"dataset.":[143],"Image":[144],"pre-processing":[145],"techniques":[146],"are":[147],"employed":[148],"enhance":[150],"training":[152],"process,":[153],"manual":[155],"annotation":[156],"ensures":[157],"accurate":[158],"labeling":[159],"all":[161],"images.":[162],"module":[164],"incorporates":[165],"text-to-speech":[166],"conversion,":[167],"providing":[168],"auditory":[171],"information":[172],"obstacle":[176],"recognition.":[177],"achieves":[180],"96.34%":[184],"test":[187],"images":[188],"obtained":[189],"from":[190],"dataset":[192],"after":[193],"4000":[194],"iterations":[195],"training,":[197],"loss":[200],"error":[201],"rate":[202],"0.073%.":[204]},"counts_by_year":[{"year":2026,"cited_by_count":4},{"year":2025,"cited_by_count":11},{"year":2024,"cited_by_count":8},{"year":2023,"cited_by_count":5}],"updated_date":"2026-07-22T07:51:19.307946","created_date":"2025-10-10T00:00:00"}
