{"id":"W1516724916","doi":"10.1109/lgrs.2015.2438227","title":"Semisupervised Hyperspectral Image Classification via Neighborhood Graph Learning","year":2015,"lang":"en","type":"article","venue":"IEEE Geoscience and Remote Sensing Letters","topic":"Remote-Sensing Image Classification","field":"Engineering","cited_by":21,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Guelph","funders":"","keywords":"Hyperspectral imaging; Artificial intelligence; Computer science; Pattern recognition (psychology); Exploit; Pixel; Graph; Labeled data; Binary classification; Contextual image classification; Image (mathematics); Machine learning; Support vector machine; Theoretical computer science","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":[0.001093695,0.0007408836,0.001070094,0.001337087,0.0005160307,0.0007349527,0.001544218,0.001104633,0.0009763053],"category_scores_gemma":[0.004111384,0.0003451589,0.0007099948,0.001150145,0.001080535,0.0020055,0.001279861,0.0009928098,0.0004462205],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006845676,"about_ca_system_score_gemma":0.0006513541,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002294178,"about_ca_topic_score_gemma":0.004620071,"domain_scores_codex":[0.9988801,0.000484059,0.0000385631,0.0002968924,0.0002471231,0.00005324855],"domain_scores_gemma":[0.9973437,0.00119524,0.0004663477,0.0005246439,0.0003838787,0.00008623793],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0002541758,0.0003198292,0.004108214,0.0002407214,0.000178057,0.0002159493,0.0002741628,0.5303573,0.01385958,0.04275753,0.0106389,0.3967956],"study_design_scores_gemma":[0.000004318102,0.00001296414,0.0001884377,0.000003683717,0.000004015436,0.00002471286,0.00001267322,0.9862564,0.0009197159,0.01211874,0.0004496185,0.000004735231],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.02878581,0.0002046359,0.9683939,0.0002344614,0.00001952603,0.00006790628,0.0001140553,0.000829324,0.001350431],"genre_scores_gemma":[0.5477535,0.0003125727,0.446785,0.0003187088,0.0001169949,0.0002558649,0.001316241,0.0002287452,0.002912459],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.002294178,"threshold_uncertainty_score":0.005784094,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02144790727728335,"score_gpt":0.2257903075405959,"score_spread":0.2043424002633125,"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."}}