{"id":"W2966886210","doi":"10.3390/s19163491","title":"Practical Considerations for Accuracy Evaluation in Sensor-Based Machine Learning and Deep Learning","year":2019,"lang":"en","type":"article","venue":"Sensors","topic":"Fault Detection and Control Systems","field":"Engineering","cited_by":21,"is_retracted":false,"has_abstract":true,"ca_institutions":"Dalhousie University","funders":"Natural Sciences and Engineering Research Council of Canada; Killam Trusts","keywords":"Deep learning; Artificial intelligence; Machine learning; Computer science","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":[],"consensus_categories":[],"category_scores_codex":[0.0004550853,0.00009917035,0.0001452681,0.0001064608,0.00007249794,0.00005324006,0.0000098974,0.00007388504,0.0001171142],"category_scores_gemma":[0.00150682,0.0001035086,0.00003213671,0.00007885641,0.000009872096,0.00007953103,0.000003822394,0.0002510758,0.00004498912],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005732881,"about_ca_system_score_gemma":0.00001867976,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003039665,"about_ca_topic_score_gemma":0.00009063658,"domain_scores_codex":[0.9992,0.0001646113,0.000192467,0.0001492995,0.0001349089,0.0001586641],"domain_scores_gemma":[0.9987758,0.001018346,0.00003867209,0.00006641495,0.00005963297,0.00004113288],"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":[0.00003032913,0.000009386279,0.006218076,0.00005796178,0.00002025556,0.00000340325,0.0002961931,0.9809297,0.00868452,0.0001191172,0.00002263424,0.003608371],"study_design_scores_gemma":[0.001400777,0.00005206451,0.0009570481,0.00001736889,0.00001556919,0.00002124712,0.0005637259,0.9897906,0.0005210509,0.00003432626,0.006504671,0.0001215213],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9951596,0.0001656059,0.001887108,0.0003830914,0.0002488405,0.0007516549,0.00000192684,0.0002041829,0.001197948],"genre_scores_gemma":[0.9984514,0.0000111218,0.001214235,0.00003397056,0.0000402838,0.00004762231,0.000009782445,0.00002374371,0.0001678709],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.008860876,"threshold_uncertainty_score":0.4220958,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02472887090716955,"score_gpt":0.29930160709551,"score_spread":0.2745727361883404,"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."}}