{"id":"W4411640001","doi":"10.1109/tmrb.2025.3583144","title":"Genetic Algorithm-Optimized Feature Selection for sEMG-IMU Fusion Improves Intention Detection in AI-Driven Robotic Walking System","year":2025,"lang":"en","type":"article","venue":"IEEE Transactions on Medical Robotics and Bionics","topic":"Electric and Hybrid Vehicle Technologies","field":"Engineering","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Carleton University","funders":"","keywords":"Inertial measurement unit; Artificial intelligence; Computer science; Feature selection; Genetic algorithm; Selection (genetic algorithm); Pattern recognition (psychology); Feature (linguistics); Computer vision; Sensor fusion; Machine learning","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":[0.000187474,0.0001968259,0.0002654059,0.0003922659,0.0001988599,0.0000512416,0.0001096312,0.0004302555,0.000002107349],"category_scores_gemma":[0.00002342963,0.0001835441,0.000091432,0.0005802747,0.00005086681,0.00007086124,0.000003033242,0.0006401312,0.000001440213],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002612617,"about_ca_system_score_gemma":0.00004925857,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002685411,"about_ca_topic_score_gemma":0.000173772,"domain_scores_codex":[0.9988812,0.00003149245,0.0003104968,0.0002757707,0.0002029488,0.0002980796],"domain_scores_gemma":[0.9995801,0.0001133602,0.00003600625,0.0001217497,0.00007519134,0.0000735702],"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":[0.00005005078,0.00007900749,0.00002367602,0.0003386367,0.00007789205,0.000003899264,0.00002189177,0.3401206,0.00609525,0.0001639848,0.00004918574,0.6529759],"study_design_scores_gemma":[0.0009640969,0.0001785271,0.0002720223,0.0003100136,0.00009450482,0.00002575378,0.00007912018,0.9897232,0.007902843,0.0002201276,0.00005861669,0.0001711609],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01545505,0.0004361395,0.9817669,0.0005006741,0.0008782912,0.0004442,0.000003441792,0.0005009813,0.00001428453],"genre_scores_gemma":[0.9682428,0.00171095,0.02974801,0.00005984772,0.00003787745,0.00007997963,0.000003560257,0.00002472358,0.00009224144],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9527878,"threshold_uncertainty_score":0.748471,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.00508161103951405,"score_gpt":0.2180868572380747,"score_spread":0.2130052461985606,"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."}}