{"id":"W4412937902","doi":"10.1038/s41598-025-06848-3","title":"Optimizing FCN for devices with limited resources using quantization and sparsity enhancement","year":2025,"lang":"en","type":"article","venue":"Scientific Reports","topic":"Advanced Neural Network Applications","field":"Computer Science","cited_by":18,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Regina","funders":"Ministry of Science and ICT, South Korea; National Research Foundation of Korea; King Khalid University; Soonchunhyang University; National Research Foundation","keywords":"Computer science; Quantization (signal processing); Algorithm","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000520964,0.0006243393,0.0003485943,0.0001758235,0.000231117,0.000566896,0.0007396956,0.0005886063,0.00146122],"category_scores_gemma":[0.002150199,0.0001822183,0.0001979489,0.0002548725,0.0004919858,0.001336839,0.0005023978,0.0007324946,0.0002593234],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0009580859,"about_ca_system_score_gemma":0.0008659567,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.005353207,"about_ca_topic_score_gemma":0.01046586,"domain_scores_codex":[0.9998208,0.00003671052,0.000007829437,0.0000403062,0.00005207918,0.00004234314],"domain_scores_gemma":[0.9995993,0.0002294786,0.00003733548,0.00003971492,0.00007484545,0.00001940441],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.00007271121,0.0000440687,0.0007568724,0.00008889872,0.00002167978,0.0001206195,0.00004128237,0.9030265,0.01262112,0.00714981,0.00229638,0.07376001],"study_design_scores_gemma":[0.000002914708,0.00001926291,0.00008827562,0.000006688831,0.000003465645,0.00002035304,0.00001220233,0.9948835,0.002148099,0.002432958,0.0003792563,0.000003031959],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1407988,0.000912912,0.8454728,0.0007605836,0.0001090598,0.0000549062,0.000128687,0.00126652,0.01049566],"genre_scores_gemma":[0.8910667,0.0002150379,0.1064604,0.0001925473,0.00001720761,0.00003832203,0.0001020579,0.00008282675,0.001824768],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.005353207,"threshold_uncertainty_score":0.01064408,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02944142329957647,"score_gpt":0.2850476369391056,"score_spread":0.2556062136395291,"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."}}