{"id":"W4312251372","doi":"10.1109/iscas48785.2022.9937940","title":"Optimizing a Multispectral-Images-Based DL Model, Through Feature Selection, Pruning and Quantization","year":2022,"lang":"en","type":"article","venue":"2022 IEEE International Symposium on Circuits and Systems (ISCAS)","topic":"Smart Agriculture and AI","field":"Agricultural and Biological Sciences","cited_by":7,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Saskatchewan","funders":"","keywords":"Multispectral image; Computer science; Pruning; Quantization (signal processing); Feature selection; Artificial intelligence; Software deployment; Inference; Machine learning; Population; Pattern recognition (psychology); Data mining; Computer vision","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":[0.0005106854,0.0007514199,0.0007620092,0.0003406004,0.0002322234,0.0008632553,0.001222495,0.0009478949,0.001513069],"category_scores_gemma":[0.001623611,0.0003780423,0.0005888678,0.0003807763,0.0004273547,0.001030309,0.0005925414,0.001448009,0.0005039227],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0008737202,"about_ca_system_score_gemma":0.001062174,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01008748,"about_ca_topic_score_gemma":0.01208873,"domain_scores_codex":[0.999806,0.00003535047,0.00001409398,0.00006257436,0.00004961936,0.00003250847],"domain_scores_gemma":[0.9995424,0.0002274786,0.00004301774,0.00005485737,0.0001135082,0.00001871487],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00008050651,0.00007753171,0.001109739,0.00005600165,0.00003871046,0.00007425723,0.00002661978,0.8790097,0.006832933,0.002204888,0.001126439,0.1093626],"study_design_scores_gemma":[0.000003474335,0.000009220274,0.00008408935,0.00000240814,0.000003984196,0.000007045772,0.000002353729,0.9984345,0.0007164991,0.0005920968,0.0001427906,0.000001620906],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.04739206,0.0004276541,0.948382,0.0004248717,0.00004879855,0.00004684589,0.0001804473,0.001438564,0.001658812],"genre_scores_gemma":[0.7350844,0.0003470718,0.2590619,0.0004350601,0.00006042141,0.0001605657,0.000685365,0.0001444359,0.004020691],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.01008748,"threshold_uncertainty_score":0.02005756,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0258733469313551,"score_gpt":0.2415366400573778,"score_spread":0.2156632931260227,"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."}}