{"id":"W4376865759","doi":"10.1016/j.sna.2023.114429","title":"Optimization of MEMS-based Energy Scavengers and output prediction with machine learning and synthetic data approach","year":2023,"lang":"en","type":"article","venue":"Sensors and Actuators A Physical","topic":"Innovative Energy Harvesting Technologies","field":"Engineering","cited_by":25,"is_retracted":false,"has_abstract":false,"ca_institutions":"","funders":"Natural Sciences and Engineering Research Council of Canada; Indian Institute of Technology Delhi; University of Alberta","keywords":"Power (physics); Context (archaeology); Computer science; Microelectromechanical systems; Energy (signal processing); Mechanical energy; Preprocessor; Data pre-processing; Efficient energy use; Artificial intelligence; Engineering; Materials science; Mathematics; Nanotechnology; Electrical engineering; Physics","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00008888511,0.0001268542,0.0001670935,0.000124847,0.00006272758,0.00002458154,0.00005756796,0.00004993993,4.456529e-7],"category_scores_gemma":[0.0000753423,0.0001033069,0.000007681102,0.0003017859,0.0001666941,0.000118189,0.00007392355,0.0001228789,1.067728e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000007730862,"about_ca_system_score_gemma":0.00000558051,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001776752,"about_ca_topic_score_gemma":8.717977e-7,"domain_scores_codex":[0.9994394,0.00001915367,0.00009589364,0.0002198425,0.0001000643,0.0001256964],"domain_scores_gemma":[0.9996726,0.00008471884,0.00003599494,0.0001558298,0.00002384106,0.00002704082],"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":[0.00003667162,0.0000486197,0.002764389,0.0002174676,0.0001045999,0.000004949208,0.0003674972,0.9563691,0.003037347,0.001733208,0.00008956686,0.0352266],"study_design_scores_gemma":[0.0002135247,0.00006836376,0.0005190727,0.00003949682,0.00002203225,0.000003687784,0.0001468979,0.9955626,0.003131917,0.00006170549,0.0001258348,0.0001048482],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9632653,0.00004997204,0.03589384,0.00003336334,0.00001746193,0.000050221,0.00003496313,0.0005036775,0.0001512297],"genre_scores_gemma":[0.9948392,0.00007513001,0.004900326,0.00000242056,0.00002363636,0.00000486585,0.0001109584,0.00002759122,0.00001589422],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.03919354,"threshold_uncertainty_score":0.4212732,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01544109918879528,"score_gpt":0.210374439517534,"score_spread":0.1949333403287387,"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."}}