{"id":"W4416922229","doi":"10.1109/access.2025.3639410","title":"DSConvNet: A Lightweight Architecture for Extracting Image Features From Depthwise Separable Convolution Network for Edge Devices","year":2025,"lang":"en","type":"article","venue":"IEEE Access","topic":"Advanced Neural Network Applications","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"McMaster University","funders":"","keywords":"Convolution (computer science); Benchmark (surveying); Convolutional neural network; Block (permutation group theory); Image (mathematics); Feature (linguistics); Separable space; Enhanced Data Rates for GSM Evolution; Object (grammar)","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001566759,0.000242473,0.0002731842,0.00009084689,0.0005814466,0.0004750431,0.001598709,0.0001247244,0.000003815929],"category_scores_gemma":[0.00005955184,0.0002252961,0.0001353523,0.0006558715,0.00004991645,0.001051053,0.0001869392,0.0002112789,0.000005573947],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005745476,"about_ca_system_score_gemma":0.00008087564,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00004240909,"about_ca_topic_score_gemma":0.0003513091,"domain_scores_codex":[0.9982498,0.00004354406,0.0003175079,0.0007278466,0.0001286288,0.0005326441],"domain_scores_gemma":[0.9973495,0.001495745,0.0002405871,0.0006603576,0.0001700774,0.00008373961],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.0005376629,0.0003498817,0.003082108,0.0004983804,0.0004321517,0.00001283976,0.0008439359,0.1001196,0.03874529,0.07607387,0.447994,0.3313103],"study_design_scores_gemma":[0.002103982,0.00009111103,0.01018231,0.0003784764,0.0001583056,0.000009860592,0.00002331857,0.1593323,0.09449287,0.3983322,0.3338742,0.001021112],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.00680033,0.001759343,0.9855939,0.002231058,0.001145132,0.001467472,0.00005067333,0.0003010946,0.0006510326],"genre_scores_gemma":[0.449811,0.00005585868,0.5423986,0.002845382,0.001729347,0.00207197,0.00009792647,0.00004442867,0.0009455543],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.4431953,"threshold_uncertainty_score":0.918731,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0218541881762299,"score_gpt":0.3318302541726655,"score_spread":0.3099760659964356,"validation_status":"score_only:v0-immature-baseline","note":"Baseline scores from an immature model (maturity gate not passed). Scores rank; they never assert a category."}}