{"id":"https://openalex.org/W4410192498","doi":"https://doi.org/10.1145/3696673.3723060","title":"From Baselines to DenseNet: A Deep Learning Framework for CNN Optimization and Augmentation","display_name":"From Baselines to DenseNet: A Deep Learning Framework for CNN Optimization and Augmentation","publication_year":2025,"publication_date":"2025-04-24","ids":{"openalex":"https://openalex.org/W4410192498","doi":"https://doi.org/10.1145/3696673.3723060"},"language":"en","primary_location":{"id":"doi:10.1145/3696673.3723060","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3696673.3723060","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3696673.3723060","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2025 ACM Southeast Conference","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3696673.3723060","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5074663163","display_name":"Hazim Shatnawi","orcid":"https://orcid.org/0009-0006-8456-5288"},"institutions":[{"id":"https://openalex.org/I193531525","display_name":"George Washington University","ror":"https://ror.org/00y4zzh67","country_code":"US","type":"education","lineage":["https://openalex.org/I193531525"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Hazim Shatnawi","raw_affiliation_strings":["The George Washington University, Washington, D.C., USA"],"raw_orcid":"https://orcid.org/0009-0006-8456-5288","affiliations":[{"raw_affiliation_string":"The George Washington University, Washington, D.C., USA","institution_ids":["https://openalex.org/I193531525"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5117476950","display_name":"Mahmoud Abusaqer","orcid":null},"institutions":[{"id":"https://openalex.org/I119942284","display_name":"Missouri State University","ror":"https://ror.org/01d2sez20","country_code":"US","type":"education","lineage":["https://openalex.org/I119942284"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Mahmoud Abusaqer","raw_affiliation_strings":["Missouri State University, Springfield, MO, USA"],"raw_orcid":"https://orcid.org/0009-0006-2850-6566","affiliations":[{"raw_affiliation_string":"Missouri State University, Springfield, MO, USA","institution_ids":["https://openalex.org/I119942284"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5078131344","display_name":"Jamil Saquer","orcid":"https://orcid.org/0009-0006-7948-8409"},"institutions":[{"id":"https://openalex.org/I119942284","display_name":"Missouri State University","ror":"https://ror.org/01d2sez20","country_code":"US","type":"education","lineage":["https://openalex.org/I119942284"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jamil Saquer","raw_affiliation_strings":["Missouri State University, Springfield, MO, USA"],"raw_orcid":"https://orcid.org/0009-0006-7948-8409","affiliations":[{"raw_affiliation_string":"Missouri State University, Springfield, MO, USA","institution_ids":["https://openalex.org/I119942284"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5074663163"],"corresponding_institution_ids":["https://openalex.org/I193531525"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.07464981,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"2","last_page":"11"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":0.9998000264167786,"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"}},"topics":[{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":0.9998000264167786,"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/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.9958999752998352,"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/T11512","display_name":"Anomaly Detection Techniques and Applications","score":0.9958000183105469,"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":0.7635667324066162},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5306046605110168},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.5272366404533386},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.4171026945114136},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3270120918750763}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7635667324066162},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5306046605110168},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.5272366404533386},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.4171026945114136},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3270120918750763}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3696673.3723060","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3696673.3723060","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3696673.3723060","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2025 ACM Southeast Conference","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3696673.3723060","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3696673.3723060","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3696673.3723060","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2025 ACM Southeast Conference","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4410192498.pdf","grobid_xml":"https://content.openalex.org/works/W4410192498.grobid-xml"},"referenced_works_count":10,"referenced_works":["https://openalex.org/W114517082","https://openalex.org/W398859631","https://openalex.org/W2108598243","https://openalex.org/W2194775991","https://openalex.org/W2949736877","https://openalex.org/W2954996726","https://openalex.org/W2963446712","https://openalex.org/W4240768087","https://openalex.org/W6600679772","https://openalex.org/W6824197019"],"related_works":["https://openalex.org/W2731899572","https://openalex.org/W4226493464","https://openalex.org/W2961085424","https://openalex.org/W3215138031","https://openalex.org/W4306674287","https://openalex.org/W3133861977","https://openalex.org/W3009238340","https://openalex.org/W4360585206","https://openalex.org/W4321369474","https://openalex.org/W4285208911"],"abstract_inverted_index":{"This":[0],"paper":[1],"presents":[2],"a":[3,142],"systematic":[4],"investigation":[5],"into":[6],"the":[7,100,106,119],"interplay":[8],"among":[9],"convolutional":[10],"neural":[11],"network":[12],"(CNN)":[13],"architectures,":[14],"optimization":[15],"algorithms,":[16],"and":[17,30,42,54,59,74,94,105,124,134,149],"data":[18],"augmentation":[19],"strategies.":[20],"Our":[21,77,137],"study":[22,138],"examines":[23],"three":[24],"widely":[25],"used":[26],"architectures---Baseline":[27],"CNN,":[28],"ResNet-50,":[29],"DenseNet-121---across":[31],"four":[32,49],"datasets":[33],"representing":[34],"distinct":[35],"domains:":[36],"CIFAR-10,":[37],"FashionMNIST,":[38,104],"PathMNIST":[39],"(from":[40],"MedMNIST),":[41],"Street":[43],"View":[44],"House":[45],"Numbers.":[46],"We":[47],"evaluated":[48],"optimizers":[50],"(SGD,":[51],"Adam,":[52],"RMSprop,":[53],"AdamW)":[55],"under":[56],"both":[57,146],"augmented":[58],"non-augmented":[60],"conditions":[61],"over":[62],"100":[63],"training":[64],"epochs,":[65],"measuring":[66],"performance":[67,91],"in":[68],"terms":[69],"of":[70,121],"validation":[71],"accuracy,":[72],"loss,":[73],"execution":[75],"time.":[76],"experiments":[78],"reveal":[79],"that":[80],"optimal":[81],"configurations":[82],"vary":[83],"by":[84],"dataset:":[85],"DenseNet-121":[86,96],"with":[87,97,109],"AdamW":[88],"demonstrates":[89],"exceptional":[90],"on":[92,103,114],"CIFAR-10":[93],"SVHN,":[95],"Adam":[98,110],"achieves":[99],"highest":[101],"accuracy":[102],"Baseline":[107],"CNN":[108],"is":[111],"most":[112],"efficient":[113],"PathMNIST.":[115],"These":[116],"findings":[117],"underscore":[118],"importance":[120],"dataset-specific":[122],"tuning":[123],"provide":[125],"actionable":[126],"insights":[127],"for":[128,145],"balancing":[129],"model":[130],"complexity,":[131],"computational":[132],"cost,":[133],"predictive":[135],"performance.":[136],"thus":[139],"serves":[140],"as":[141],"practical":[143],"guide":[144],"academic":[147],"research":[148],"real-world":[150],"applications.":[151]},"counts_by_year":[],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}