{"id":"W3039091317","doi":"10.1109/jsen.2020.3007431","title":"Improving the Detection of Explosives in a MOX Chemical Sensors Array With LSTM Networks","year":2020,"lang":"en","type":"article","venue":"IEEE Sensors Journal","topic":"Advanced Chemical Sensor Technologies","field":"Engineering","cited_by":30,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Saskatchewan","funders":"Universidad de las Fuerzas Armadas ESPE; Secretaría de Educación Superior, Ciencia, Tecnología e Innovación","keywords":"Electronic nose; Explosive material; Computer science; Artificial intelligence; Deep learning; Machine learning; Feature extraction; Sensor array; Explosive detection; Pattern recognition (psychology)","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":[0.00005518069,0.0002047244,0.0002692064,0.00006681788,0.00004879608,0.00002662934,0.000228115,0.0001485791,0.000005944617],"category_scores_gemma":[0.0001503771,0.0001417187,0.00007679225,0.0003980862,0.0001411022,0.0001416117,0.00001622328,0.001120324,0.000002587157],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00008950222,"about_ca_system_score_gemma":0.000004564694,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000003192948,"about_ca_topic_score_gemma":0.000002915294,"domain_scores_codex":[0.9988716,0.00002849995,0.0003622341,0.0001680223,0.000212883,0.0003568059],"domain_scores_gemma":[0.9994344,0.0001258158,0.0001252653,0.0001631102,0.00005346435,0.00009792539],"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":[0.00004344752,0.000005345951,0.00006508253,0.00001525552,0.00002027137,0.00002330198,0.0002316118,0.3357909,0.6615331,0.000001221634,0.00001421238,0.002256226],"study_design_scores_gemma":[0.0003484157,0.00005663372,0.00004212397,0.00004754156,0.00001528303,0.0001782601,0.0008300716,0.09274014,0.9054515,0.00005198167,0.00007165264,0.0001663372],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9655167,0.0002521453,0.0334651,0.0002324241,0.0001190387,0.0001117492,0.000001410218,0.0002343459,0.0000671259],"genre_scores_gemma":[0.9979348,0.0001434117,0.001571139,0.00003549893,0.0002607034,0.000004518839,2.549421e-7,0.00004624759,0.000003393222],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.2439185,"threshold_uncertainty_score":0.5779122,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.009708685852415208,"score_gpt":0.1889852350039404,"score_spread":0.1792765491515252,"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."}}