{"id":"W3217472497","doi":"10.1109/lsp.2021.3130504","title":"Uncertainty Estimation via Monte Carlo Dropout in CNN-Based mmWave MIMO Localization","year":2021,"lang":"en","type":"article","venue":"IEEE Signal Processing Letters","topic":"Indoor and Outdoor Localization Technologies","field":"Engineering","cited_by":19,"is_retracted":false,"has_abstract":true,"ca_institutions":"McGill University","funders":"Canadian Network for Research and Innovation in Machining Technology, Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Monte Carlo method; MIMO; Convolutional neural network; Expectation propagation; Algorithm; Bayesian inference; Inference; Bayesian probability; Artificial intelligence; Beamforming; Mathematics; Telecommunications; Statistics","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":[0.0001159684,0.0002066103,0.0002012333,0.0002139364,0.0001038663,0.000106004,0.0001302253,0.0001469108,0.00002682779],"category_scores_gemma":[0.00003470422,0.0002254192,0.00005120484,0.0006774438,0.00007779766,0.0002300812,0.00001033144,0.0002211895,0.00001595482],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002375984,"about_ca_system_score_gemma":0.00006891143,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00004578188,"about_ca_topic_score_gemma":0.00004932949,"domain_scores_codex":[0.9988059,0.0000385737,0.0003357156,0.0002625889,0.0002480621,0.0003091255],"domain_scores_gemma":[0.9996035,0.00003768617,0.00005867628,0.0001585913,0.0001014971,0.00004006378],"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":[0.000007383481,0.00001563792,0.0006269297,0.0001923063,0.000007396789,0.00004672533,0.0002249683,0.9390352,0.02198089,0.000006278678,0.0005202785,0.03733598],"study_design_scores_gemma":[0.0003687264,0.000009098877,0.00008840695,0.0001638857,0.00001275105,0.000004496259,0.00008292661,0.89548,0.1032513,0.0001226375,0.0001770571,0.000238658],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1012578,0.0002306631,0.8969066,0.0005219198,0.0001923341,0.0001162811,0.00000370087,0.0006424644,0.0001282663],"genre_scores_gemma":[0.9964642,0.000004622948,0.002253754,0.001107111,0.00005323234,0.00002500439,0.00003484752,0.0000435617,0.00001368475],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8952063,"threshold_uncertainty_score":0.9192329,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.00826032944837046,"score_gpt":0.2124626585426561,"score_spread":0.2042023290942857,"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."}}