{"id":"W4223505452","doi":"10.1101/2022.04.11.487925","title":"Stair Recognition for Robotic Exoskeleton Control using Computer Vision and Deep Learning","year":2022,"lang":"en","type":"preprint","venue":"bioRxiv (Cold Spring Harbor Laboratory)","topic":"Prosthetics and Rehabilitation Robotics","field":"Engineering","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"Toronto Rehabilitation Institute; University of Toronto; University of Waterloo","funders":"University of Waterloo; AGE-WELL","keywords":"Exoskeleton; Artificial intelligence; Convolutional neural network; Computer science; Software deployment; Wearable computer; Deep learning; Inference; Feature (linguistics); Computer vision; Human–computer interaction; Simulation; 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":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0005014378,0.0004168162,0.0004890933,0.0002519983,0.000278116,0.0001970521,0.0001772082,0.0003137888,0.00002252278],"category_scores_gemma":[0.00007338359,0.0004717481,0.0001376231,0.0001839361,0.00006518555,0.0001131611,0.0001977258,0.0007149707,0.000004560061],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002701134,"about_ca_system_score_gemma":0.00007834364,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000005461779,"about_ca_topic_score_gemma":5.367844e-7,"domain_scores_codex":[0.9982216,0.0001140024,0.0004614919,0.0005658535,0.0002305867,0.0004064646],"domain_scores_gemma":[0.9988204,0.0001953909,0.0001799359,0.0003766954,0.0002689085,0.000158723],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00002488919,0.0000511389,0.0007364067,0.001478273,0.0001309654,0.000007896861,0.00002386648,0.920883,0.07645334,0.000099094,0.00002200086,0.00008913343],"study_design_scores_gemma":[0.0008835971,0.0001906903,0.007073793,0.000318307,0.000155855,3.676839e-8,0.000006337681,0.9875743,0.002029723,0.00001522266,0.001062047,0.0006900516],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.4641064,0.001363723,0.5311637,0.00005399529,0.00158992,0.001124127,0.00007526565,0.000520968,0.00000190297],"genre_scores_gemma":[0.9399145,0.0002283621,0.05919056,0.00005114626,0.0002764216,0.0001624877,0.000002316609,0.0001731431,0.000001113303],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.475808,"threshold_uncertainty_score":0.9997734,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01102078271112999,"score_gpt":0.2160853413638127,"score_spread":0.2050645586526827,"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."}}