{"id":"W2216719796","doi":"10.1109/iros.2015.7354082","title":"Automatically characterizing driving activities onboard smart wheelchairs from accelerometer data","year":2015,"lang":"en","type":"article","venue":"","topic":"Gaze Tracking and Assistive Technology","field":"Computer Science","cited_by":5,"is_retracted":false,"has_abstract":true,"ca_institutions":"McGill University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Wheelchair; Accelerometer; Computer science; Classifier (UML); Random forest; Machine learning; Artificial intelligence; Human–computer interaction; World Wide Web","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":[0.0001662008,0.0005819172,0.0003020537,0.001104163,0.000162167,0.0004013018,0.0002490306,0.0003645525,0.0006306584],"category_scores_gemma":[0.001191995,0.0001185293,0.0002160363,0.0006049506,0.00008538932,0.0004349159,0.0003063976,0.000211223,0.0005559675],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001270791,"about_ca_system_score_gemma":0.0002508316,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003369928,"about_ca_topic_score_gemma":0.009345325,"domain_scores_codex":[0.9998434,0.00003172201,0.00001538632,0.00004451314,0.00003891773,0.00002597437],"domain_scores_gemma":[0.999613,0.0001198778,0.00007623779,0.00003996593,0.0001215024,0.0000294067],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0005268632,0.0003700292,0.1867424,0.0003779659,0.0001768152,0.0006388052,0.00102645,0.01754696,0.1260341,0.000636617,0.00563351,0.6602895],"study_design_scores_gemma":[0.00004070601,0.0003979007,0.4083329,0.0001079295,0.0001415963,0.0007102807,0.001806715,0.5257552,0.05191468,0.002897605,0.007835175,0.00005928946],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8667474,0.0005550359,0.1251386,0.0001934684,0.00005212865,0.0001354737,0.002767861,0.002191015,0.002219013],"genre_scores_gemma":[0.9579555,0.000301264,0.03812664,0.00003275601,0.00002981968,0.00006129481,0.00218613,0.00003827324,0.001268236],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.003369928,"threshold_uncertainty_score":0.006700635,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.09207690936223566,"score_gpt":0.2856834849862595,"score_spread":0.1936065756240238,"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."}}