{"id":"W3009784468","doi":"10.3389/fbioe.2020.00158","title":"Interpreting Deep Learning Features for Myoelectric Control: A Comparison With Handcrafted Features","year":2020,"lang":"en","type":"article","venue":"Frontiers in Bioengineering and Biotechnology","topic":"Muscle activation and electromyography studies","field":"Engineering","cited_by":119,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of New Brunswick; Université Laval","funders":"Natural Sciences and Engineering Research Council of Canada; Institut de Recherche Robert-Sauvé en Santé et en Sécurité du Travail","keywords":"Discriminative model; Deep learning; Convolutional neural network; Feature engineering; ENCODE; Feature (linguistics); Focus (optics); Feature learning; Task (project management); Pattern recognition (psychology)","routes":{"ca_aff":true,"ca_fund":true,"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":[0.001410588,0.0009187699,0.0005041728,0.0009272379,0.0001658639,0.001175138,0.0005829,0.0006683337,0.002447619],"category_scores_gemma":[0.005946383,0.0001895794,0.0004017818,0.0007121839,0.0005675617,0.001789871,0.0008510067,0.0009238265,0.000425941],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004083052,"about_ca_system_score_gemma":0.00034651,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001145821,"about_ca_topic_score_gemma":0.001268525,"domain_scores_codex":[0.99934,0.0001731126,0.00004560769,0.0001829292,0.000204928,0.00005345806],"domain_scores_gemma":[0.9978501,0.001225272,0.0002050198,0.0003499969,0.0003080473,0.00006157943],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"observational","study_design_scores_codex":[0.001063888,0.0001864421,0.01127307,0.0005027778,0.0002062362,0.0002509106,0.0002079529,0.1763328,0.02602156,0.007475484,0.002716686,0.7737622],"study_design_scores_gemma":[0.00004824182,0.0003748153,0.0129146,0.00009787624,0.00006722658,0.0002174578,0.0001041943,0.9529982,0.01558845,0.01348482,0.004065268,0.00003895677],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2480364,0.004889962,0.7382289,0.0008657226,0.0003427359,0.0001396764,0.0008754151,0.001536067,0.005085248],"genre_scores_gemma":[0.9184763,0.0009767831,0.07782478,0.0001248184,0.0001142336,0.00005572689,0.0006903161,0.0001619603,0.001575135],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.002447619,"threshold_uncertainty_score":0.008188069,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.003890511625040076,"score_gpt":0.1852945550464202,"score_spread":0.1814040434213801,"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."}}