{"id":"W4394685122","doi":"10.4271/2024-01-2426","title":"Sequence Training and Data Shuffling to Enhance the Accuracy of Recurrent Neural Network Based Battery Voltage Models","year":2024,"lang":"en","type":"article","venue":"SAE technical papers on CD-ROM/SAE technical paper series","topic":"Advanced Battery Technologies Research","field":"Engineering","cited_by":43,"is_retracted":false,"has_abstract":true,"ca_institutions":"McMaster University","funders":"","keywords":"Computer science; Battery (electricity); Voltage; Artificial neural network; Shuffling; Sequence (biology); Recurrent neural network; State of charge; Power (physics); Artificial intelligence; Electrical engineering; Engineering","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":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0010742,0.0006926995,0.0007866802,0.0002402595,0.0002672252,0.0001982735,0.002719625,0.0004788533,0.00009107947],"category_scores_gemma":[0.001431666,0.0005337832,0.0001771953,0.001416864,0.001030669,0.001028383,0.00158464,0.002234224,0.0000219216],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002363512,"about_ca_system_score_gemma":0.0000970362,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001200668,"about_ca_topic_score_gemma":0.005251959,"domain_scores_codex":[0.9954501,0.0001026385,0.001002225,0.001382039,0.0008515719,0.001211418],"domain_scores_gemma":[0.9945869,0.002290208,0.00009245273,0.002701448,0.0000694476,0.0002595247],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"observational","study_design_scores_codex":[0.00007413944,0.00003798333,0.00001405261,0.0002241394,0.00004281214,0.00006275003,0.00005117137,0.0299844,0.8472227,0.001972476,0.002847805,0.1174655],"study_design_scores_gemma":[0.002248168,0.00771798,0.5464335,0.01618249,0.0007256418,0.0008758413,0.002092025,0.0207698,0.008846745,0.05385955,0.3299682,0.01028004],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9103122,0.01385064,0.003361398,0.02884275,0.001926249,0.005940123,0.00122289,0.02259849,0.01194528],"genre_scores_gemma":[0.9883336,0.0009448166,0.009085841,0.0008909943,0.0001596717,0.0003282579,0.00005904075,0.0001596278,0.00003815513],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.838376,"threshold_uncertainty_score":0.9997114,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.06375871568971372,"score_gpt":0.3376063173138554,"score_spread":0.2738476016241417,"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."}}