{"id":"W3198999105","doi":"10.1080/13658816.2021.1977814","title":"A random forest classifier with cost-sensitive learning to extract urban landmarks from an imbalanced dataset","year":2021,"lang":"en","type":"article","venue":"International Journal of Geographical Information Systems","topic":"Automated Road and Building Extraction","field":"Engineering","cited_by":24,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"National Key Research and Development Program of China; Ministry of Natural Resources","keywords":"Landmark; Random forest; Artificial intelligence; Computer science; Decision tree; Classifier (UML); Pattern recognition (psychology); Sample (material); Feature extraction; Data mining; Machine learning","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002548273,0.0001303653,0.000227608,0.0003155154,0.00005200555,0.0003532338,0.0001709794,0.0001016174,0.00002290554],"category_scores_gemma":[0.00008378293,0.0001036386,0.00006968929,0.0002077497,0.00001896726,0.001635962,0.00001890288,0.0003892775,0.00002141252],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006917999,"about_ca_system_score_gemma":0.00003935725,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00006235588,"about_ca_topic_score_gemma":0.0000335732,"domain_scores_codex":[0.9985451,0.0000680984,0.0005967881,0.00007853248,0.0005710335,0.0001404489],"domain_scores_gemma":[0.998637,0.0001212102,0.0002709155,0.0001003853,0.0007144173,0.0001560835],"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":[0.001327125,0.0001045162,0.02972532,0.0000397716,0.001152396,0.0002818637,0.001843589,0.9355808,0.004123838,0.0002270572,0.01155118,0.01404251],"study_design_scores_gemma":[0.006461146,0.0003374852,0.1024814,0.0009188809,0.00009637469,0.001836048,0.004063784,0.4461226,0.001516985,0.00002891027,0.4355418,0.0005946275],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8296717,0.0001151174,0.1657145,0.0003301394,0.002294807,0.0002272286,0.0006526465,0.0001429124,0.0008508312],"genre_scores_gemma":[0.9972394,0.00005474411,0.0004723595,0.0001362602,0.0003970101,0.000008141393,0.001672227,0.00001132521,0.00000853072],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.4894582,"threshold_uncertainty_score":0.4226261,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.007506347576063224,"score_gpt":0.2478299455851892,"score_spread":0.2403235980091259,"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."}}