{"id":"W4367725259","doi":"10.2139/ssrn.4435617","title":"Machine Learning Algorithm for Wheelchair Control Through Pof-Based Pressure Sensors and Neck Movements","year":2023,"lang":"en","type":"preprint","venue":"SSRN Electronic Journal","topic":"Gaze Tracking and Assistive Technology","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"ca_institutions":"Toronto Metropolitan University","funders":"","keywords":"Wheelchair; Computer science; Control (management); Pressure sensor; Algorithm; Artificial intelligence; Engineering; Mechanical engineering","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":[0.0006689742,0.0005554248,0.0009647722,0.0004983016,0.0005067142,0.0007082705,0.0008388043,0.001277042,0.003140155],"category_scores_gemma":[0.002267104,0.0002974512,0.0004852192,0.0005447091,0.0002957557,0.0005468164,0.0005505355,0.0009512016,0.0008836127],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004572567,"about_ca_system_score_gemma":0.001116281,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.009640989,"about_ca_topic_score_gemma":0.004987674,"domain_scores_codex":[0.9997118,0.00004515707,0.0000233541,0.0001069457,0.00006510907,0.00004764563],"domain_scores_gemma":[0.9994842,0.0002426728,0.00003466043,0.00003220955,0.0001899114,0.00001636203],"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":[0.0002163042,0.0001079842,0.00123494,0.00008934871,0.00005981365,0.0000772617,0.00007014472,0.3377541,0.005678218,0.002907321,0.001907754,0.6498969],"study_design_scores_gemma":[0.0000103646,0.00002515648,0.0003374803,0.000006219597,0.000006018842,0.0000174309,0.000005157835,0.9978917,0.0007957467,0.0006377373,0.0002632461,0.00000373422],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01299597,0.0002745991,0.9846756,0.0001078752,0.00006002215,0.00005429468,0.00004708435,0.0007060447,0.001078477],"genre_scores_gemma":[0.6612808,0.000319551,0.3312845,0.0001641268,0.0001088536,0.0004346902,0.0002594404,0.00007582495,0.006072074],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.009640989,"threshold_uncertainty_score":0.01916975,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01401387689087528,"score_gpt":0.257198521235995,"score_spread":0.2431846443451197,"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."}}