{"id":"W2962879438","doi":"10.1109/tnsre.2019.2896269","title":"Deep Learning for Electromyographic Hand Gesture Signal Classification Using Transfer Learning","year":2019,"lang":"en","type":"article","venue":"IEEE Transactions on Neural Systems and Rehabilitation Engineering","topic":"Muscle activation and electromyography studies","field":"Engineering","cited_by":723,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Natural Sciences and Engineering Research Council of Canada; Fondation Choquette-Legault; Norges Forskningsråd; Institut de Recherche Robert-Sauvé en Santé et en Sécurité du Travail","keywords":"Computer science; Gesture; Transfer of learning; Artificial intelligence; Deep learning; Spectrogram; Linear discriminant analysis; Machine learning; Gesture recognition; Pattern recognition (psychology); Raw data; SIGNAL (programming language); Modalities; Modality (human–computer interaction); Speech recognition","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007515617,0.0009475072,0.0006550346,0.0005760457,0.0001965607,0.0004499003,0.0009172505,0.00066374,0.002130596],"category_scores_gemma":[0.001577279,0.0002473272,0.0006423824,0.0007254235,0.0003807723,0.0008208843,0.0009277186,0.001203965,0.0009100427],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005551552,"about_ca_system_score_gemma":0.0005863578,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004051495,"about_ca_topic_score_gemma":0.003957863,"domain_scores_codex":[0.9996603,0.00006732169,0.0000221528,0.0001021332,0.0000918031,0.00005636091],"domain_scores_gemma":[0.9997069,0.0001229052,0.00003212499,0.00004564885,0.00007457775,0.00001776313],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0002598737,0.0002662243,0.002720583,0.0001421429,0.0001207939,0.0002128131,0.00008609306,0.2029646,0.02174089,0.002168848,0.003863866,0.7654532],"study_design_scores_gemma":[0.000007082968,0.00008395001,0.001245913,0.00001530892,0.00001168013,0.0000386448,0.00002201679,0.9894259,0.005994667,0.002313001,0.0008318438,0.0000098946],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1132937,0.001969755,0.8771584,0.0004111203,0.0001198155,0.000119543,0.0003741009,0.003404855,0.003148688],"genre_scores_gemma":[0.8758776,0.0007393518,0.1148376,0.0002192179,0.00007154582,0.0002155354,0.00104682,0.00008314845,0.006909187],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.004051495,"threshold_uncertainty_score":0.008055866,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.008887433270310033,"score_gpt":0.2041281633244585,"score_spread":0.1952407300541485,"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."}}