{"id":"W2028469338","doi":"10.1109/jstars.2015.2414816","title":"Hyperspectral Image Classification With Limited Labeled Training Samples Using Enhanced Ensemble Learning and Conditional Random Fields","year":2015,"lang":"en","type":"article","venue":"IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing","topic":"Remote-Sensing Image Classification","field":"Engineering","cited_by":61,"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; Artificial intelligence; Pattern recognition (psychology); Overfitting; AdaBoost; Computer science; Random forest; Contextual image classification; Ensemble learning; Conditional random field; Context (archaeology); Curse of dimensionality; Support vector machine; Machine learning; Image (mathematics); Artificial neural network","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":[0.0003589384,0.0001641722,0.0002990603,0.0002497904,0.0001268206,0.000111401,0.0000399342,0.0001265201,8.743722e-7],"category_scores_gemma":[0.0002039318,0.0001562631,0.00002226915,0.0004903239,0.00008507515,0.0001932811,0.000006031971,0.0005076804,2.353205e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00009738433,"about_ca_system_score_gemma":0.0001506543,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001522993,"about_ca_topic_score_gemma":0.00007641859,"domain_scores_codex":[0.9988657,0.00006179786,0.0004473655,0.000160583,0.0002474924,0.0002170381],"domain_scores_gemma":[0.9989225,0.0001593849,0.0002058068,0.00008370817,0.0005268444,0.0001017375],"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":[0.0001007167,0.000009720343,0.00009869658,0.00003142268,0.00005285,0.0000120653,0.001797171,0.03247545,0.9240605,0.00009822603,0.00001281114,0.04125037],"study_design_scores_gemma":[0.002939769,0.00008611144,0.008867892,0.0002129653,0.0000673658,0.0003418795,0.00167194,0.9337475,0.05054555,0.0009800859,0.0002551206,0.0002838731],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.6675262,0.00007396088,0.3317433,0.0001403321,0.00007755404,0.0001040115,8.792273e-7,0.00003926081,0.0002945005],"genre_scores_gemma":[0.7336475,0.0001026447,0.2660276,0.00001952326,0.0001547445,6.715818e-8,0.000009869805,0.00002112868,0.00001693549],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.901272,"threshold_uncertainty_score":0.6372224,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.06267270060563282,"score_gpt":0.2538046624579312,"score_spread":0.1911319618522984,"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."}}