{"id":"W4411879513","doi":"10.3390/mi16070753","title":"Using Adaptive Surrogate Models to Accelerate Multi-Objective Design Optimization of MEMS","year":2025,"lang":"en","type":"article","venue":"Micromachines","topic":"Advanced Multi-Objective Optimization Algorithms","field":"Computer Science","cited_by":5,"is_retracted":false,"has_abstract":true,"ca_institutions":"National Institute for Nanotechnology; National Research Council Canada; University of Manitoba","funders":"National Research Council Canada","keywords":"Robustness (evolution); Actuator; Finite element method; Flexibility (engineering); Computer science; Microelectromechanical systems; Engineering optimization; Mathematical optimization; Surrogate model; Optimization problem; Multi-objective optimization; Control engineering; Engineering; Artificial intelligence; Algorithm; Machine learning; Mathematics","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":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0002748364,0.0002919971,0.0003683241,0.0004994852,0.0002063118,0.00009349867,0.0006854227,0.00008867747,0.000005817719],"category_scores_gemma":[0.00009053995,0.0002879094,0.00008300809,0.001582063,0.00006562945,0.001025379,0.0003989419,0.0001305591,0.000004524778],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001776965,"about_ca_system_score_gemma":0.0001782101,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000197491,"about_ca_topic_score_gemma":0.00001770487,"domain_scores_codex":[0.9982517,0.0001891425,0.0004172394,0.0006426855,0.000183204,0.0003160486],"domain_scores_gemma":[0.9983621,0.0001614931,0.0002142118,0.0004697879,0.0007056267,0.000086737],"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":[0.00004398902,0.0001097748,0.0000325662,0.000008665786,0.00005210669,0.000003369489,0.001102611,0.9698559,0.02493402,0.001216626,0.00001915686,0.002621191],"study_design_scores_gemma":[0.0007757351,0.00005786292,0.0001012043,0.00006357097,0.00001552664,0.000004520874,0.00006964678,0.9318858,0.06566542,0.001113702,0.00000583102,0.0002411743],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.001472737,0.000162499,0.9966846,0.00008259475,0.000345113,0.0007808852,0.00001759696,0.0001794051,0.0002746066],"genre_scores_gemma":[0.1091837,0.00001578267,0.8903015,0.0002003131,0.00001540117,0.00003182029,0.000004258486,0.00002324376,0.0002240339],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.107711,"threshold_uncertainty_score":0.9999573,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.08309343457273025,"score_gpt":0.3209810037232397,"score_spread":0.2378875691505095,"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."}}