{"id":"W4401415607","doi":"10.1109/access.2024.3440314","title":"Improving EKF-Based IMU/GNSS Fusion Using Machine Learning for IMU Denoising","year":2024,"lang":"en","type":"article","venue":"IEEE Access","topic":"Inertial Sensor and Navigation","field":"Engineering","cited_by":19,"is_retracted":false,"has_abstract":true,"ca_institutions":"Carleton University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Inertial measurement unit; GNSS applications; Computer science; Artificial intelligence; Extended Kalman filter; Sensor fusion; Inertial navigation system; Units of measurement; Kalman filter; Global Positioning System; Computer vision; Gyroscope; Engineering; Inertial frame of reference; Telecommunications","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":[0.001207821,0.001037148,0.001285114,0.0009094052,0.0004286114,0.0007314996,0.0008819313,0.00103358,0.0007734362],"category_scores_gemma":[0.003009595,0.000426166,0.001035077,0.0007782532,0.0004415664,0.001246513,0.001060894,0.001141166,0.0007932853],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003769477,"about_ca_system_score_gemma":0.000740338,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003815248,"about_ca_topic_score_gemma":0.003307679,"domain_scores_codex":[0.9994879,0.00007788979,0.00003621921,0.0001218712,0.0002058454,0.00007027005],"domain_scores_gemma":[0.9994186,0.000170024,0.00006430221,0.00007744177,0.0002469043,0.0000227911],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0001873632,0.0001320034,0.003304229,0.000124919,0.0001212695,0.0001411462,0.0001522034,0.6391771,0.02351877,0.002648528,0.001798771,0.3286937],"study_design_scores_gemma":[0.000003625575,0.00001778761,0.0005283876,0.000006149051,0.000008965453,0.00001603898,0.000008010809,0.9957381,0.002642217,0.0005420434,0.0004819204,0.000006764305],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.02477507,0.0003372852,0.9728545,0.00009201792,0.000100415,0.00002336793,0.00004023517,0.0008168523,0.0009601915],"genre_scores_gemma":[0.65218,0.0003557399,0.3443221,0.0001973647,0.0001104143,0.00008572138,0.0004198301,0.0001750748,0.002153722],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.003815248,"threshold_uncertainty_score":0.007586062,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02611936370660171,"score_gpt":0.2945299191379525,"score_spread":0.2684105554313507,"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."}}