{"id":"W2198521890","doi":"10.1016/j.jelekin.2015.12.001","title":"An approach for improving repeatability and reliability of non-negative matrix factorization for muscle synergy analysis","year":2015,"lang":"en","type":"article","venue":"Journal of Electromyography and Kinesiology","topic":"Muscle activation and electromyography studies","field":"Engineering","cited_by":60,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Ottawa","funders":"University of Waterloo; Canadian Institutes of Health Research; Sharif University of Technology; Natural Sciences and Engineering Research Council of Canada; Amirkabir University of Technology; Canada Foundation for Innovation","keywords":"Repeatability; Non-negative matrix factorization; Matrix decomposition; Reliability (semiconductor); Pattern recognition (psychology); Computer science; Artificial intelligence; Matching (statistics); Rank (graph theory); Rank correlation; Mathematics; Statistics; Physics","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":[0.01690838,0.001869514,0.001609137,0.002033038,0.001696899,0.001577996,0.002007089,0.00199756,0.001675648],"category_scores_gemma":[0.0777318,0.0009557998,0.001547453,0.001722084,0.001051722,0.002458346,0.002685966,0.002343294,0.001176494],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000475994,"about_ca_system_score_gemma":0.002262635,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00454878,"about_ca_topic_score_gemma":0.008761247,"domain_scores_codex":[0.9860663,0.005730367,0.001185411,0.003682594,0.002880235,0.0004551004],"domain_scores_gemma":[0.948642,0.0247202,0.002220005,0.008714315,0.015243,0.0004604287],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0008187105,0.0005444392,0.01409,0.0005264091,0.0009260137,0.0002154726,0.000904799,0.03470892,0.1271928,0.008474252,0.004338579,0.8072597],"study_design_scores_gemma":[0.0001912522,0.0009783121,0.02427123,0.0001131947,0.0005043795,0.001017503,0.0003010872,0.8732672,0.07482672,0.01583622,0.008428247,0.0002646117],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.009640861,0.0001594943,0.9889939,0.00006195661,0.00005269017,0.00009397294,0.00005314092,0.0006981922,0.0002458156],"genre_scores_gemma":[0.08624493,0.00008224987,0.9124311,0.00007722926,0.00005678449,0.000187681,0.0002070868,0.0002428105,0.0004700527],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.01690838,"threshold_uncertainty_score":0.08942109,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01065653407541159,"score_gpt":0.2523226931544144,"score_spread":0.2416661590790028,"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."}}