{"id":"W3186410859","doi":"10.3390/rs13152927","title":"A Building Roof Identification CNN Based on Interior-Edge-Adjacency Features Using Hyperspectral Imagery","year":2021,"lang":"en","type":"article","venue":"Remote Sensing","topic":"Remote-Sensing Image Classification","field":"Engineering","cited_by":4,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"National Natural Science Foundation of China","keywords":"Hyperspectral imaging; Adjacency list; Computer science; Convolutional neural network; Roof; Artificial intelligence; Pattern recognition (psychology); Remote sensing; Enhanced Data Rates for GSM Evolution; Identification (biology); Computer vision; Geology; Algorithm; Geography","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":[0.0001921181,0.0007125608,0.0003047237,0.0004710682,0.0002475836,0.0003491612,0.0008468932,0.0004229388,0.001793561],"category_scores_gemma":[0.0003109115,0.0003319071,0.0004857354,0.0004595739,0.0002245761,0.0008900643,0.0005805076,0.0005527723,0.0006340511],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006249591,"about_ca_system_score_gemma":0.0006441355,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01935379,"about_ca_topic_score_gemma":0.03529811,"domain_scores_codex":[0.9998763,0.000006594627,0.000003426743,0.00004511284,0.00003461829,0.00003399837],"domain_scores_gemma":[0.9999094,0.0000105008,0.00001198927,0.00001832468,0.00004119712,0.000008523815],"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":[0.0002177289,0.000223996,0.01011903,0.0001613581,0.000242535,0.0003116129,0.00008013692,0.2732196,0.1327996,0.002609567,0.01238128,0.5676336],"study_design_scores_gemma":[0.000005024526,0.00003539393,0.003198582,0.00001098225,0.00003259871,0.00006560198,0.00002028868,0.9698676,0.02469227,0.0003788747,0.001680205,0.00001254002],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.269085,0.0008144273,0.7107903,0.0003984623,0.0002523488,0.0001850277,0.001349578,0.006259644,0.01086526],"genre_scores_gemma":[0.8319132,0.0004518301,0.1536091,0.0002571778,0.00004617823,0.000109647,0.003051275,0.0001114745,0.01045001],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.01935379,"threshold_uncertainty_score":0.03848231,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01978793797607799,"score_gpt":0.2592753569630338,"score_spread":0.2394874189869558,"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."}}