{"id":"W3199896426","doi":"10.1007/s12652-021-03470-9","title":"Interpretability of artificial intelligence models that use data fusion to predict yield in aeroponics","year":2021,"lang":"en","type":"article","venue":"Journal of Ambient Intelligence and Humanized Computing","topic":"Advanced Chemical Sensor Technologies","field":"Engineering","cited_by":17,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Saskatchewan","funders":"","keywords":"Interpretability; Computer science; Artificial intelligence; Computational intelligence; Feature selection; Yield (engineering); Automation; Machine learning; Data mining; Pattern recognition (psychology); Engineering","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002274395,0.0006031561,0.0004718218,0.0008314766,0.0003443972,0.001883124,0.0004949463,0.0008221102,0.001172208],"category_scores_gemma":[0.01296084,0.0002544437,0.0006300026,0.0004114347,0.0005745462,0.001684512,0.0007052022,0.0009267596,0.0001682748],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0007677027,"about_ca_system_score_gemma":0.000450278,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.005182436,"about_ca_topic_score_gemma":0.002355035,"domain_scores_codex":[0.99936,0.0002530936,0.00006020692,0.0001280575,0.0001409925,0.00005776872],"domain_scores_gemma":[0.9951947,0.003447336,0.0003954337,0.0003524565,0.0005443367,0.00006578123],"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":[0.0007334136,0.0003119292,0.03409675,0.0000876358,0.0002373992,0.0003751305,0.0005077844,0.8712366,0.01231429,0.01148935,0.000988495,0.06762133],"study_design_scores_gemma":[0.000006560449,0.00003358108,0.002982962,0.000006566583,0.00001727428,0.00001574837,0.00003603474,0.9916358,0.001377119,0.003807058,0.00007554218,0.000005728513],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8447052,0.0002278225,0.1495292,0.0008321779,0.0000932172,0.00004287081,0.0002697746,0.0005722643,0.003727612],"genre_scores_gemma":[0.9963248,0.00002531168,0.003351476,0.00002038426,0.000009243466,0.000006484336,0.00008580128,0.00001226848,0.0001641199],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.005182436,"threshold_uncertainty_score":0.01202828,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1404529023590546,"score_gpt":0.3022720410406889,"score_spread":0.1618191386816343,"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."}}