{"id":"W3185006080","doi":"10.1007/s00521-021-06292-0","title":"Improving sEMG-based motion intention recognition for upper-limb amputees using transfer learning","year":2021,"lang":"en","type":"article","venue":"Neural Computing and Applications","topic":"Muscle activation and electromyography studies","field":"Engineering","cited_by":42,"is_retracted":false,"has_abstract":false,"ca_institutions":"Lakehead University","funders":"National Natural Science Foundation of China","keywords":"Computer science; Gesture; Electromyography; Transfer of learning; Amputation; Forearm; Feature (linguistics); Artificial intelligence; Motion (physics); SIGNAL (programming language); Speech recognition; Pattern recognition (psychology); Physical medicine and rehabilitation; Psychology; Medicine","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":[0.0003611346,0.0004915347,0.0004170042,0.0003760844,0.0001186361,0.0003129653,0.0003679821,0.0005099314,0.002101094],"category_scores_gemma":[0.001195255,0.0001405426,0.0003512301,0.0003115723,0.0001215353,0.000398675,0.0004047266,0.0004410225,0.0008858028],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00009867988,"about_ca_system_score_gemma":0.0002147777,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001364626,"about_ca_topic_score_gemma":0.001914341,"domain_scores_codex":[0.9998524,0.00002736704,0.000009719727,0.00003995484,0.00004638349,0.00002403864],"domain_scores_gemma":[0.9995908,0.0001653739,0.00003012565,0.00004112261,0.0001547967,0.00001772525],"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":[0.0003355416,0.0002969963,0.003132743,0.0001892232,0.00008819221,0.0001240704,0.0000685831,0.02355572,0.1024739,0.0002285081,0.001424316,0.8680822],"study_design_scores_gemma":[0.00003575774,0.0005379827,0.02174194,0.00003237817,0.00007448639,0.0003377465,0.00006193279,0.9218972,0.05330467,0.0009698434,0.0009714407,0.00003466794],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2258461,0.0006785985,0.7672992,0.000157467,0.0001416301,0.000127409,0.0002725443,0.002708327,0.002768737],"genre_scores_gemma":[0.9158901,0.0002407084,0.07894656,0.0001171811,0.0000421289,0.0001001154,0.0003297999,0.00009490184,0.004238461],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.002101094,"threshold_uncertainty_score":0.007028878,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02296978150151563,"score_gpt":0.2436115834690701,"score_spread":0.2206418019675545,"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."}}