{"id":"W3199713575","doi":"10.1051/e3sconf/202129701043","title":"Comparing Single and Hybrid methods of Deep Learning for Remaining Useful Life Prediction of Lithium-ion Batteries","year":2021,"lang":"en","type":"article","venue":"E3S Web of Conferences","topic":"Advanced Battery Technologies Research","field":"Engineering","cited_by":12,"is_retracted":false,"has_abstract":true,"ca_institutions":"Carleton University","funders":"","keywords":"Benchmark (surveying); Battery (electricity); Computer science; Reliability (semiconductor); Reliability engineering; Convolutional neural network; Lithium (medication); Lithium-ion battery; Artificial neural network; Mean squared error; Mean squared prediction error; Artificial intelligence; Machine learning; Statistics; Engineering; Power (physics); Mathematics","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":[0.0003262228,0.0001052264,0.0003764207,0.0001418041,0.00003802646,0.00001716673,0.0001258073,0.00006246055,0.00003025804],"category_scores_gemma":[0.0009041585,0.0001083076,0.00004006951,0.0001514634,0.0001906145,0.0001503475,0.000104694,0.0001652334,1.490192e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001470491,"about_ca_system_score_gemma":0.00006969002,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000004880061,"about_ca_topic_score_gemma":0.000008283238,"domain_scores_codex":[0.999079,0.00006964336,0.000374345,0.0001571778,0.0001484147,0.0001713443],"domain_scores_gemma":[0.9989515,0.0005328017,0.0001233627,0.000153505,0.0002074425,0.00003139046],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.00004982679,0.00003296041,0.1039254,0.001175677,0.0001351313,0.000001608257,0.0005470706,0.01508195,0.8034616,0.001033701,0.00002890224,0.07452622],"study_design_scores_gemma":[0.0002967579,0.0002035788,0.01008984,0.0002272707,0.00001808722,0.000004432887,0.002092825,0.1191298,0.8652588,0.0007509011,0.001833033,0.00009462765],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7569755,0.0009397595,0.2399355,0.00003923922,0.0001059342,0.00009432872,0.000008628172,0.0001061118,0.001794902],"genre_scores_gemma":[0.9600847,0.0002218032,0.03961579,0.000002044978,0.0000193567,0.0000126792,0.0000114417,0.00001361946,0.00001858485],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.2031091,"threshold_uncertainty_score":0.4416654,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.06874132486302334,"score_gpt":0.314267895269951,"score_spread":0.2455265704069277,"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."}}