{"id":"W4408592929","doi":"10.1016/j.iot.2025.101561","title":"Intelligent multi-sensor fusion and anomaly detection in vehicles via deep learning","year":2025,"lang":"en","type":"article","venue":"Internet of Things","topic":"Anomaly Detection Techniques and Applications","field":"Computer Science","cited_by":7,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Ottawa","funders":"Natural Sciences and Engineering Research Council of Canada; Ontario Centre of Innovation","keywords":"Anomaly detection; Deep learning; Artificial intelligence; Computer science; Sensor fusion; Fusion; Anomaly (physics); Computer vision; Physics","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":[0.0001772448,0.00007613136,0.0001058834,0.0002131025,0.0000411859,0.00004475259,0.0002505529,0.00006368568,0.000004103737],"category_scores_gemma":[0.0000304637,0.0000755023,0.00003566553,0.0002598089,0.00003577009,0.0001966152,0.0002356262,0.0001707178,0.000004454826],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004003662,"about_ca_system_score_gemma":0.000005772273,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0007760512,"about_ca_topic_score_gemma":0.00006804818,"domain_scores_codex":[0.9993449,0.00003292664,0.0002284802,0.0002288976,0.00006779015,0.00009704117],"domain_scores_gemma":[0.9996456,0.00004574833,0.000090659,0.0001497566,0.00004583113,0.00002241886],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00001372644,0.00007022399,0.005788294,0.00003188687,0.000009983441,0.000001830152,0.001688833,0.00004860058,0.08745238,0.003074345,0.000009941043,0.9018099],"study_design_scores_gemma":[0.0001354624,0.00009146075,0.01203748,0.00007232274,0.000003557983,0.000007650997,0.00008834311,0.5778232,0.4061655,0.001451481,0.002032821,0.00009070372],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3050239,0.00008717603,0.6943017,0.0001233269,0.00004460879,0.00008537005,4.360046e-8,0.00009384422,0.0002400583],"genre_scores_gemma":[0.9650788,0.00003932193,0.03409977,0.000103169,0.000004645188,0.00001760074,2.540953e-7,0.000003772444,0.0006526556],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9017193,"threshold_uncertainty_score":0.3078894,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01023616674970234,"score_gpt":0.254420061811178,"score_spread":0.2441838950614757,"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."}}