{"id":"W3178681001","doi":"10.3390/s21144713","title":"Physical Activity Recognition Based on a Parallel Approach for an Ensemble of Machine Learning and Deep Learning Classifiers","year":2021,"lang":"en","type":"article","venue":"Sensors","topic":"Context-Aware Activity Recognition Systems","field":"Computer Science","cited_by":11,"is_retracted":false,"has_abstract":true,"ca_institutions":"École de Technologie Supérieure; Centre Hospitalier de l’Université de Montréal; Institut National de la Recherche Scientifique; Université TÉLUQ","funders":"Canada Research Chairs","keywords":"Activity recognition; Wearable computer; Computer science; Artificial intelligence; Machine learning; Feature engineering; Accelerometer; Classifier (UML); Wearable technology; Feature (linguistics); Deep learning; Embedded system","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":[0.001047596,0.0008005385,0.001001685,0.0007368455,0.000516072,0.0009317638,0.001205258,0.0007281927,0.002229198],"category_scores_gemma":[0.001855749,0.0005240044,0.0007533568,0.0008980297,0.0002775899,0.00135251,0.0007663428,0.00149063,0.001058231],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0007418925,"about_ca_system_score_gemma":0.001308894,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.008680999,"about_ca_topic_score_gemma":0.0137162,"domain_scores_codex":[0.9994851,0.00007013061,0.0000367998,0.0001869133,0.0001512843,0.0000697147],"domain_scores_gemma":[0.9992123,0.0001848294,0.00005113112,0.0001301719,0.0003781542,0.00004336248],"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":[0.0002935349,0.0005110576,0.004365596,0.00006254,0.0002097095,0.00009522088,0.00007902645,0.1786672,0.01698964,0.002887382,0.002519231,0.7933199],"study_design_scores_gemma":[0.000007790081,0.00005723576,0.0006455951,0.0000036824,0.0000231444,0.00002873574,0.000009145651,0.9946471,0.002834723,0.001070342,0.0006657335,0.000006727842],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.03732451,0.0002693952,0.9583147,0.0001881706,0.0001526866,0.000133425,0.0000987649,0.001763153,0.001755088],"genre_scores_gemma":[0.5363932,0.0002784611,0.4552607,0.0001844852,0.0001733904,0.0003529658,0.0004725149,0.000105935,0.00677821],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.008680999,"threshold_uncertainty_score":0.01726097,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0546264820847625,"score_gpt":0.2832454706733922,"score_spread":0.2286189885886297,"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."}}