{"id":"W2971762798","doi":"10.1016/j.gaitpost.2019.09.005","title":"Machine learning algorithms can classify outdoor terrain types during running using accelerometry data","year":2019,"lang":"en","type":"article","venue":"Gait & Posture","topic":"Lower Extremity Biomechanics and Pathologies","field":"Engineering","cited_by":40,"is_retracted":false,"has_abstract":false,"ca_institutions":"Carré Technologies (Canada)","funders":"","keywords":"Accelerometer; Artificial intelligence; Computer science; Machine learning; Algorithm; Wearable computer; Convolutional neural network; Gradient boosting; Simulation; Random forest; Embedded system","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":[0.0007001077,0.001142811,0.0007013364,0.002077958,0.0003274035,0.0009757919,0.0005741193,0.001148434,0.001963736],"category_scores_gemma":[0.002637492,0.000286466,0.0007512874,0.001310111,0.0001740753,0.0007456089,0.0004367172,0.0007554808,0.001897139],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002405766,"about_ca_system_score_gemma":0.0003863027,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003894264,"about_ca_topic_score_gemma":0.004937662,"domain_scores_codex":[0.9997026,0.00003915149,0.00003756271,0.0001142487,0.00006411289,0.00004223361],"domain_scores_gemma":[0.9992146,0.0003751774,0.00009022219,0.00007505241,0.0002133911,0.00003159263],"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":[0.0003222645,0.000636921,0.07008531,0.0001380515,0.0002692659,0.0001851173,0.00008546582,0.1031939,0.01488762,0.0006661775,0.005090669,0.8044392],"study_design_scores_gemma":[0.00003078291,0.0001545405,0.04465326,0.00006017714,0.00007937097,0.0001467298,0.0001241251,0.9455573,0.00465036,0.002168727,0.002348174,0.00002639375],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.4278507,0.001340567,0.5533762,0.0007398995,0.0005452326,0.0003215666,0.00305939,0.004433693,0.008332752],"genre_scores_gemma":[0.8451511,0.0005944494,0.1443891,0.0002414486,0.0002366311,0.0002127694,0.004333076,0.0001476502,0.00469377],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.003894264,"threshold_uncertainty_score":0.00774318,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03064762593888954,"score_gpt":0.2482902551780722,"score_spread":0.2176426292391827,"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."}}