{"id":"W4406900260","doi":"10.1016/j.eswa.2025.126656","title":"DeepUKF-VIN: Adaptively-tuned Deep Unscented Kalman Filter for 3D Visual-Inertial Navigation based on IMU-Vision-Net","year":2025,"lang":"en","type":"article","venue":"Expert Systems with Applications","topic":"Robotics and Sensor-Based Localization","field":"Engineering","cited_by":6,"is_retracted":false,"has_abstract":true,"ca_institutions":"Carleton University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Inertial measurement unit; Kalman filter; Computer vision; Computer science; Artificial intelligence; Inertial frame of reference; Extended Kalman filter; 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":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0001094066,0.0002771924,0.0002718862,0.000208329,0.000259992,0.00009474935,0.0001633046,0.0001515104,0.00001307412],"category_scores_gemma":[0.00001506028,0.0002480648,0.00007135791,0.0005097507,0.00003981797,0.00009075331,0.00001106483,0.0001103651,0.00002940812],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000189524,"about_ca_system_score_gemma":0.00004812529,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00005771288,"about_ca_topic_score_gemma":0.00002016748,"domain_scores_codex":[0.9985918,0.00004479252,0.0004372899,0.0003928154,0.0002395649,0.000293714],"domain_scores_gemma":[0.998957,0.0001703272,0.00008495921,0.0004568909,0.0002264634,0.0001043779],"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":[0.0001293668,0.0001998921,0.00009615189,0.0002408971,0.00008292844,0.000001166662,0.0001669724,0.9749895,0.009781175,0.006147461,0.004983502,0.00318095],"study_design_scores_gemma":[0.001028598,0.000126467,0.0001204937,0.0002736279,0.00002734001,0.000001278995,0.00012052,0.9475445,0.003758813,0.00001898129,0.04670816,0.0002712596],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.001306423,0.0002550133,0.9940891,0.0002441736,0.0002706385,0.002239335,0.00004003049,0.000413214,0.001142102],"genre_scores_gemma":[0.982678,0.00001147648,0.01179614,0.0002681667,0.0002612427,0.003600493,0.0009789377,0.00008368622,0.0003218579],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.982293,"threshold_uncertainty_score":0.9999971,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.007168347885564663,"score_gpt":0.2542914169666275,"score_spread":0.2471230690810629,"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."}}