{"id":"W3185246004","doi":"10.2196/24402","title":"Upper-Limb Motion Recognition Based on Hybrid Feature Selection: Algorithm Development and Validation","year":2021,"lang":"en","type":"article","venue":"JMIR mhealth and uhealth","topic":"Context-Aware Activity Recognition Systems","field":"Computer Science","cited_by":10,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Artificial intelligence; Computer science; Feature selection; Feature (linguistics); Pattern recognition (psychology); Naive Bayes classifier; Inertial measurement unit; Feature extraction; Filter (signal processing); Computer vision; Support vector machine","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":true,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006112071,0.0001944832,0.0002454385,0.0002206287,0.0005088032,0.000207968,0.00008481133,0.0001072241,0.00001688081],"category_scores_gemma":[0.00004459399,0.0002027948,0.00003442471,0.0004319265,0.00002001572,0.0004482389,0.00004605555,0.0002897036,0.00003176139],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002212766,"about_ca_system_score_gemma":0.0006654097,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002639804,"about_ca_topic_score_gemma":0.00002968681,"domain_scores_codex":[0.9979439,0.0003482164,0.0003272833,0.0006600056,0.0003580771,0.0003624971],"domain_scores_gemma":[0.9988056,0.0001624464,0.000206318,0.0002175759,0.0002681562,0.0003398361],"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":[0.00001999873,0.0001194694,0.0007910714,0.0002638732,0.000005547996,0.00000814199,0.0002816671,0.000002031426,0.00002159494,0.00004750797,0.0007006368,0.9977385],"study_design_scores_gemma":[0.01072011,0.003167276,0.410232,0.001828775,0.000125461,0.002811722,0.0008665047,0.3775259,0.06434071,0.003403113,0.1220047,0.002973733],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.4209706,0.0004757441,0.5649275,0.0108547,0.0008906985,0.0008914322,0.00003782644,0.0003889202,0.0005626441],"genre_scores_gemma":[0.9477364,0.0001217686,0.04829878,0.002961667,0.0002613885,0.0001400404,0.0002584998,0.00001906629,0.0002023378],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9947647,"threshold_uncertainty_score":0.8269733,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05454604702258784,"score_gpt":0.3185812222010956,"score_spread":0.2640351751785078,"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."}}