{"id":"W3005522532","doi":"10.3390/s20030874","title":"Improved Deep CNN with Parameter Initialization for Data Analysis of Near-Infrared Spectroscopy Sensors","year":2020,"lang":"en","type":"article","venue":"Sensors","topic":"Advanced Chemical Sensor Technologies","field":"Engineering","cited_by":41,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Guelph","funders":"China Scholarship Council; Natural Sciences and Engineering Research Council of Canada; National Natural Science Foundation of China; U.S. Department of Veterans Affairs","keywords":"Overfitting; Computer science; Convolutional neural network; Artificial intelligence; Normalization (sociology); Initialization; Pattern recognition (psychology); Deep learning; Dropout (neural networks); Kernel (algebra); Artificial neural network; 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":[],"consensus_categories":[],"category_scores_codex":[0.00002542859,0.0002005234,0.0004211192,0.00009510007,0.00003300096,0.00002567948,0.0003151138,0.000124318,0.00002622692],"category_scores_gemma":[0.0004389702,0.0001816102,0.00007868663,0.000972209,0.0001156431,0.0001201605,0.000061566,0.0001356027,0.000003089254],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003533668,"about_ca_system_score_gemma":0.00000445986,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000006813068,"about_ca_topic_score_gemma":0.00001194957,"domain_scores_codex":[0.9989137,0.00001087133,0.0002972399,0.0003631224,0.0001352352,0.0002798535],"domain_scores_gemma":[0.9989531,0.0001730864,0.00008761488,0.000648806,0.00006465678,0.00007274023],"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":[0.0001935492,0.00002084481,0.0006064583,0.0001622377,0.00135713,0.000007574888,0.0004339845,0.6103535,0.3852007,0.00008172586,0.0002882633,0.00129396],"study_design_scores_gemma":[0.0002436429,0.00006188173,0.00005475851,0.000004911808,0.0003420254,4.919556e-7,0.0001393126,0.6502799,0.3480462,0.00008922894,0.0005810649,0.0001565286],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8598192,0.00005129916,0.1384643,0.0001341102,0.00003455079,0.0003164997,0.0002077849,0.0007364794,0.0002358167],"genre_scores_gemma":[0.8850213,0.00003318884,0.1144245,0.00005584711,0.00003297248,0.0000101575,0.0003519049,0.00005500493,0.00001512485],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.03992639,"threshold_uncertainty_score":0.7405851,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02585304342045356,"score_gpt":0.2569353230166354,"score_spread":0.2310822795961819,"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."}}