{"id":"W4387870872","doi":"10.1109/icc45041.2023.10279746","title":"Improving Freezing of Gait Detection and Prediction Using ML and Transformers","year":2023,"lang":"en","type":"article","venue":"","topic":"Gait Recognition and Analysis","field":"Engineering","cited_by":4,"is_retracted":false,"has_abstract":true,"ca_institutions":"Université de Moncton","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Accelerometer; Linear discriminant analysis; Artificial intelligence; Gradient boosting; Machine learning; Wearable computer; Boosting (machine learning); Gait; Transformer; Feature extraction; Wearable technology; Gait analysis; Pattern recognition (psychology); Data mining; Random forest; Voltage; Engineering","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":[0.0008866612,0.001181415,0.00102157,0.001685149,0.0002030017,0.0007640706,0.0006623073,0.0005517161,0.0008506922],"category_scores_gemma":[0.002973983,0.0002685515,0.0008336536,0.0007769849,0.0002544161,0.0008192207,0.0008438246,0.0006583049,0.0007462256],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002931439,"about_ca_system_score_gemma":0.0004071304,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003761498,"about_ca_topic_score_gemma":0.004623558,"domain_scores_codex":[0.9995667,0.00007761903,0.0000402384,0.0001312041,0.0001098332,0.00007433193],"domain_scores_gemma":[0.9993747,0.0002668882,0.00007533968,0.00007121028,0.0001670107,0.00004487588],"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":[0.001030775,0.0004919624,0.04835704,0.0002753967,0.0002662789,0.000336131,0.00008589027,0.1826769,0.01812384,0.001042833,0.009932897,0.73738],"study_design_scores_gemma":[0.00002637161,0.0001601358,0.01025768,0.0000325764,0.00005253918,0.0001940235,0.00003350375,0.9811972,0.005761131,0.00117472,0.001088574,0.00002156401],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3434867,0.002533365,0.6413642,0.0004702144,0.0004049945,0.0001369307,0.002149086,0.006841697,0.002612743],"genre_scores_gemma":[0.9291063,0.0006013392,0.06561578,0.0001524945,0.000100854,0.00006069929,0.002892934,0.00009674452,0.001372691],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.003761498,"threshold_uncertainty_score":0.007479191,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01101383609272479,"score_gpt":0.1930191495991688,"score_spread":0.182005313506444,"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."}}