{"id":"W2523265165","doi":"10.3846/20296991.2016.1226388","title":"USING PIXEL-BASED AND OBJECT-BASED METHODS TO CLASSIFY URBAN HYPERSPECTRAL FEATURES","year":2016,"lang":"en","type":"article","venue":"Geodesy and Cartography","topic":"Remote-Sensing Image Classification","field":"Engineering","cited_by":6,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Ottawa","funders":"Università degli Studi di Pavia","keywords":"Hyperspectral imaging; Pattern recognition (psychology); Pixel; Artificial intelligence; Support vector machine; Computer science; Segmentation; Feature (linguistics); Feature extraction","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":[0.0002181184,0.000211258,0.0002002807,0.0003248151,0.0001116809,0.00008452845,0.00006834765,0.0001191205,0.000005410661],"category_scores_gemma":[0.00004529042,0.0001695152,0.00008834834,0.0003613826,0.0001422294,0.00009333713,0.00001215172,0.0001153911,0.00000228593],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003897074,"about_ca_system_score_gemma":0.00002242346,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001836576,"about_ca_topic_score_gemma":0.0000140055,"domain_scores_codex":[0.9990098,0.00008565388,0.0001538464,0.0003109881,0.0001200091,0.0003196568],"domain_scores_gemma":[0.9993191,0.0001435667,0.000027029,0.0002818177,0.00004849489,0.0001800218],"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":[0.00003019868,0.00001146096,0.002826797,0.00004622842,0.00003499904,0.000003307463,0.0001543194,0.0005756497,0.9475814,0.0002062673,0.000664114,0.04786529],"study_design_scores_gemma":[0.003425495,0.000349066,0.1581672,0.0005433341,0.000350248,0.00006589479,0.0003830514,0.1093969,0.6853148,0.0008913621,0.03908821,0.0020244],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.5522417,0.001022108,0.4446796,0.0004744356,0.0002438043,0.0002121059,0.00001442091,0.0003303452,0.0007814749],"genre_scores_gemma":[0.8439398,0.00001968891,0.1557249,0.0001759876,0.00007307944,0.000005171379,0.000002993235,0.00003647665,0.00002192336],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.2916982,"threshold_uncertainty_score":0.6912627,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02237846050484841,"score_gpt":0.2823605784573717,"score_spread":0.2599821179525232,"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."}}