{"id":"W4415209400","doi":"10.3390/s25206318","title":"Augmenting a ResNet + BiLSTM Deep Learning Model with Clinical Mobility Data Helps Outperform a Heuristic Frequency-Based Model for Walking Bout Segmentation","year":2025,"lang":"en","type":"article","venue":"Sensors","topic":"Traffic Prediction and Management Techniques","field":"Engineering","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"St. Joseph’s Healthcare Hamilton; McMaster University","funders":"Natural Sciences and Engineering Research Council of Canada; Canadian Frailty Network; Arthritis Society","keywords":"Generalizability theory; Deep learning; Gait; Heuristic; Segmentation; Recall; Wearable computer; Data modeling","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":[],"consensus_categories":[],"category_scores_codex":[0.0008515259,0.0001990794,0.0002348544,0.0001609021,0.0001681131,0.00006742121,0.0002599985,0.0001041022,0.000002615466],"category_scores_gemma":[0.0001588965,0.0001933541,0.00006414819,0.0001747649,0.00005043538,0.000188748,0.00007707139,0.0002942433,0.000001735689],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001167611,"about_ca_system_score_gemma":0.0000520823,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001086644,"about_ca_topic_score_gemma":0.0001106711,"domain_scores_codex":[0.9985787,0.00004513859,0.0004354114,0.0004501399,0.0001787678,0.0003118626],"domain_scores_gemma":[0.9991304,0.0001348927,0.00007551369,0.0005387339,0.00005925502,0.00006122996],"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":[0.00005424381,0.00004739775,0.00110548,0.0002681056,0.0000776169,0.000001425157,0.0001682853,0.9819111,0.0002107071,0.0002596743,0.001228817,0.01466712],"study_design_scores_gemma":[0.0007605768,0.0000469881,0.0001894338,0.0001160437,0.0001150736,3.919911e-7,0.0002073378,0.9977111,0.0002050411,0.0002611817,0.0001966719,0.0001901893],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1251007,0.00004555687,0.8703001,0.00007364258,0.0001223903,0.0006796387,0.00004378356,0.002686424,0.0009477273],"genre_scores_gemma":[0.8961019,0.00003977062,0.1031146,0.0001110733,0.00003051618,0.000102962,0.0002481906,0.00003578414,0.0002152098],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.7710012,"threshold_uncertainty_score":0.7884753,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04003641784500939,"score_gpt":0.3142268302532134,"score_spread":0.274190412408204,"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."}}