{"id":"W4401919341","doi":"10.54254/2755-2721/71/20241635","title":"Evaluating the efficacy of machine learning in calibrating low-cost sensors","year":2024,"lang":"en","type":"article","venue":"Applied and Computational Engineering","topic":"Air Quality Monitoring and Forecasting","field":"Environmental Science","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"Concordia University","funders":"","keywords":"Random forest; Computer science; Machine learning; Calibration; Reliability (semiconductor); Support vector machine; Artificial neural network; Mean squared error; Sensitivity (control systems); Artificial intelligence; Data mining; Engineering; Statistics","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":[0.009990132,0.001322206,0.0007216281,0.001176589,0.0005101631,0.001363427,0.001284008,0.001599821,0.001012354],"category_scores_gemma":[0.03652798,0.0003874869,0.0006595609,0.00135496,0.0007383185,0.002155571,0.0008485884,0.001015609,0.0005503847],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0007401698,"about_ca_system_score_gemma":0.0006945189,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003009993,"about_ca_topic_score_gemma":0.00216509,"domain_scores_codex":[0.993758,0.002531419,0.0003408376,0.0007870952,0.002373659,0.0002090493],"domain_scores_gemma":[0.9832619,0.0115567,0.0009251634,0.001796323,0.002373209,0.00008660175],"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":[0.0007680456,0.000497892,0.0322584,0.00166633,0.0005670368,0.0001182578,0.0001541649,0.5856063,0.02512754,0.006551099,0.002366859,0.3443181],"study_design_scores_gemma":[0.00005288818,0.0009162356,0.01537348,0.0002998566,0.0001556805,0.0001491704,0.0001233662,0.9166855,0.05331068,0.006217314,0.006633942,0.0000819545],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2882003,0.008309468,0.6892071,0.000952582,0.0005009625,0.000423153,0.0007667384,0.001678577,0.009961238],"genre_scores_gemma":[0.7942973,0.002428626,0.2007559,0.000206386,0.00009832422,0.0002818889,0.0007414626,0.0001993883,0.0009908188],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.009990132,"threshold_uncertainty_score":0.05283344,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02099999469523883,"score_gpt":0.2721360570079214,"score_spread":0.2511360623126825,"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."}}