{"id":"W4386829988","doi":"10.1016/j.mechatronics.2023.103060","title":"Uncertainty-aware safe adaptable motion planning of lower-limb exoskeletons using random forest regression","year":2023,"lang":"en","type":"article","venue":"Mechatronics","topic":"Prosthetics and Rehabilitation Robotics","field":"Engineering","cited_by":9,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Random forest; Exoskeleton; Robot; Mahalanobis distance; Artificial intelligence; Leverage (statistics); Computer science; Machine learning; Deep learning; Engineering; Human–robot interaction; Simulation","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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002852659,0.000150929,0.0002311746,0.0001637686,0.0001076906,0.00001833002,0.0001219277,0.0001240713,0.00001830505],"category_scores_gemma":[0.00005048526,0.0001359055,0.0001086756,0.0003585966,0.0000300178,0.00008571086,0.00005066858,0.0001651696,0.00001775622],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001142385,"about_ca_system_score_gemma":0.00003987901,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001426573,"about_ca_topic_score_gemma":0.00001025881,"domain_scores_codex":[0.998988,0.00002880324,0.0003029381,0.0001518166,0.000214352,0.0003140302],"domain_scores_gemma":[0.9994338,0.0001113225,0.00006611168,0.0002559746,0.00007096226,0.00006178925],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00003232858,0.00001427757,0.0001589059,0.0001229506,0.0000186084,0.000003295982,0.0001663245,0.9913295,0.005611992,0.001199404,0.0002469336,0.001095486],"study_design_scores_gemma":[0.0006774545,0.0000943005,0.0001123079,0.0001966791,0.00002231048,0.000002343415,0.0003523378,0.994123,0.001196286,0.001589323,0.001480947,0.0001526696],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.6662218,0.0006459965,0.3310286,0.0001001466,0.001042619,0.0003163024,0.00003573864,0.0003688078,0.0002400059],"genre_scores_gemma":[0.9963727,0.0001214662,0.00323492,0.000005343834,0.00004855463,0.0000091626,0.00005417925,0.00004477906,0.0001089094],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.3301509,"threshold_uncertainty_score":0.5542066,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02229257830887851,"score_gpt":0.2603094481978528,"score_spread":0.2380168698889743,"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."}}