{"id":"W3212628164","doi":"10.1016/j.bios.2021.113782","title":"Machine learning-based feature combination analysis for odor-dependent hemodynamic responses of rat olfactory bulb","year":2021,"lang":"en","type":"article","venue":"Biosensors and Bioelectronics","topic":"Advanced Chemical Sensor Technologies","field":"Engineering","cited_by":6,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Toronto; Ontario Brain Institute; Sunnybrook Health Science Centre","funders":"National Research Foundation of Korea; Hansung University","keywords":"Odor; Brain–computer interface; Artificial intelligence; Computer science; Feature (linguistics); Pattern recognition (psychology); Random forest; Olfactory bulb; Kurtosis; Support vector machine; Sniffing; Olfactometer; Psychology; Mathematics; Neuroscience; Statistics; Host (biology); Electroencephalography; Biology","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":[0.00005124697,0.000167172,0.0002849449,0.0001572319,0.0000557131,0.00001616559,0.00007877669,0.0001958104,0.000006460217],"category_scores_gemma":[0.0001630108,0.0001568357,0.0001226337,0.0004397988,0.00006206446,0.00003064618,0.00002068395,0.0002390026,4.323268e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001125519,"about_ca_system_score_gemma":0.00001459303,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000003092017,"about_ca_topic_score_gemma":0.00004957389,"domain_scores_codex":[0.9992071,0.00002190972,0.0001660166,0.0002244813,0.0001200407,0.0002604286],"domain_scores_gemma":[0.9994713,0.0001568171,0.0000599336,0.0001833189,0.00009339417,0.00003520761],"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":[0.00009184178,0.00004413956,0.001615108,0.0001029316,0.0002197503,0.000003921928,0.00001254723,0.0272724,0.9683617,0.0003487932,0.00004063426,0.001886212],"study_design_scores_gemma":[0.0005597262,0.0001439002,0.0003647936,0.000008182365,0.0001408764,0.00000335871,0.00003939187,0.1465966,0.8491593,0.0002737331,0.002528193,0.0001819896],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9874319,0.005366677,0.006352358,0.0003086129,0.0000487271,0.0001210852,0.00005957198,0.0002904616,0.00002061714],"genre_scores_gemma":[0.997319,0.0009008697,0.001195095,0.00001558884,0.000008436034,0.000006452508,0.0001404461,0.00002431946,0.0003898104],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.1193242,"threshold_uncertainty_score":0.6395575,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01108371550395143,"score_gpt":0.2208760159216698,"score_spread":0.2097923004177183,"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."}}