{"id":"W1987785235","doi":"10.1109/lgrs.2015.2487226","title":"Feature Extraction for Hyperspectral Imagery via Ensemble Localized Manifold Learning","year":2015,"lang":"en","type":"article","venue":"IEEE Geoscience and Remote Sensing Letters","topic":"Remote-Sensing Image Classification","field":"Engineering","cited_by":14,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"Canadian Space Agency; Natural Sciences and Engineering Research Council of Canada; Canada Research Chairs","keywords":"Hyperspectral imaging; Feature extraction; Pattern recognition (psychology); Nonlinear dimensionality reduction; Artificial intelligence; Manifold (fluid mechanics); Computer science; Manifold alignment; Classifier (UML); Feature vector; Feature (linguistics); Dimensionality reduction","routes":{"ca_aff":true,"ca_fund":true,"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":[0.0003955971,0.0002059937,0.0001925297,0.0001542859,0.0002146633,0.0001851073,0.00007753143,0.0001112149,2.786034e-7],"category_scores_gemma":[0.0001062972,0.0002037332,0.00006418689,0.0002505967,0.0001320594,0.0003456103,0.00001030588,0.0003016847,0.00001382244],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001553083,"about_ca_system_score_gemma":0.00002499831,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00007010183,"about_ca_topic_score_gemma":0.00001086699,"domain_scores_codex":[0.9987351,0.00004288364,0.0001600729,0.0003745176,0.0002443579,0.0004430893],"domain_scores_gemma":[0.9994024,0.00008129205,0.00006593611,0.0002087771,0.00008895272,0.0001526167],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00001612647,0.000002438122,0.000004395792,0.00002463642,0.000007217842,0.00002624971,0.0002939789,0.004890145,0.8756494,0.00000151783,0.003650178,0.1154337],"study_design_scores_gemma":[0.0003994167,0.00003347059,0.0001667885,0.00005885973,0.00002628795,0.0004155747,0.0002198869,0.9233073,0.06619041,0.00009452714,0.008787777,0.0002997209],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3206121,0.00008877564,0.675055,0.002344427,0.001196941,0.0001604732,6.217853e-7,0.0002916805,0.0002499642],"genre_scores_gemma":[0.6998963,0.00005337574,0.2978027,0.0007668022,0.000532936,1.756775e-7,0.0000100527,0.00007026387,0.0008673977],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9184172,"threshold_uncertainty_score":0.8307998,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02030931379477991,"score_gpt":0.2438496339788738,"score_spread":0.2235403201840939,"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."}}