{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.003895139,0.001665411,0.001958013,0.003819644,0.0008887143,0.0009503587,0.00197068,0.001643594,0.001259963],"category_scores_gemma":[0.005846667,0.000392187,0.001592283,0.002852163,0.000378434,0.001698428,0.0008451661,0.001480195,0.00123738],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0007505085,"about_ca_system_score_gemma":0.001666475,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.008343712,"about_ca_topic_score_gemma":0.009458485,"domain_scores_codex":[0.9981344,0.0003495004,0.0001861322,0.0005372713,0.0005478442,0.0002449382],"domain_scores_gemma":[0.9979932,0.0007820603,0.0001363758,0.0002003281,0.0008162727,0.00007181491],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0005098424,0.0005684379,0.01097033,0.0002072933,0.0002418653,0.0002156471,0.00008400715,0.1061387,0.008291505,0.001667137,0.01678161,0.8543236],"study_design_scores_gemma":[0.0000605095,0.0001552044,0.001968884,0.00002878163,0.00006779755,0.0001339314,0.0000360677,0.9900113,0.003469309,0.002061066,0.00198021,0.00002686886],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.08169467,0.001417337,0.9074435,0.0004323859,0.0002903167,0.0005793409,0.00144201,0.00509488,0.001605597],"genre_scores_gemma":[0.4366576,0.0006281867,0.5512947,0.0003721666,0.0003020261,0.0009100557,0.006782854,0.0002436939,0.002808805],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.008343712,"threshold_uncertainty_score":0.02059966,"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."}}