{"id":"W4362720253","doi":"10.1007/s12652-023-04596-8","title":"Data filtering and deep learning for enhanced human activity recognition from UWB radars","year":2023,"lang":"en","type":"article","venue":"Journal of Ambient Intelligence and Humanized Computing","topic":"Advanced SAR Imaging Techniques","field":"Engineering","cited_by":11,"is_retracted":false,"has_abstract":false,"ca_institutions":"Université du Québec à Chicoutimi","funders":"","keywords":"Computer science; Convolutional neural network; Deep learning; Artificial intelligence; Filter (signal processing); Chebyshev filter; Population; Artificial neural network; Radar; Computational intelligence; Pattern recognition (psychology); Ultra-wideband; Machine learning; Telecommunications; Computer vision","routes":{"ca_aff":true,"ca_fund":false,"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":[0.0004882763,0.0001371492,0.000253508,0.0001696322,0.0002322435,0.0001074276,0.0002206017,0.00004230584,0.000006798422],"category_scores_gemma":[0.0001711269,0.0001449482,0.00003761202,0.0001097589,0.00003967882,0.0004059137,0.0001866569,0.0003199581,0.00000166542],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003745638,"about_ca_system_score_gemma":0.000006532134,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000009147907,"about_ca_topic_score_gemma":0.000008271622,"domain_scores_codex":[0.9990824,0.00002811606,0.0003612206,0.0001931063,0.0001267475,0.000208368],"domain_scores_gemma":[0.9992286,0.0002764672,0.0001951629,0.0001444366,0.00008584341,0.00006947128],"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":[0.00003337264,0.00001414282,0.00008618095,0.00009426023,0.00006751006,0.00001142863,0.001487289,0.00669456,0.2742155,0.00002573929,0.00009894602,0.7171711],"study_design_scores_gemma":[0.0004574627,0.0002726645,0.0009366213,0.0008367031,0.00007278461,0.00003927507,0.001023509,0.6425706,0.3380283,0.0138187,0.001506321,0.0004370948],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.4977509,0.0001761278,0.5017088,0.00001217159,0.0001137059,0.00006998925,0.000004985627,0.0001455655,0.0000177015],"genre_scores_gemma":[0.9483494,0.000521429,0.05085887,0.00001506002,0.0001918172,0.000001365169,0.00002704885,0.00002951289,0.00000554723],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.716734,"threshold_uncertainty_score":0.5910817,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.09115158472796475,"score_gpt":0.3321709965435814,"score_spread":0.2410194118156166,"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."}}