{"id":"W2038304857","doi":"10.1016/j.laa.2012.04.033","title":"Sparse nonnegative matrix underapproximation and its application to hyperspectral image analysis","year":2012,"lang":"en","type":"article","venue":"Linear Algebra and its Applications","topic":"Remote-Sensing Image Classification","field":"Engineering","cited_by":51,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Hyperspectral imaging; Non-negative matrix factorization; Interpretability; Principal component analysis; Dimensionality reduction; Pattern recognition (psychology); Matrix decomposition; Constraint (computer-aided design); Artificial intelligence; Matrix (chemical analysis); Mathematics; Sparse matrix; Image (mathematics); Curse of dimensionality; Sparse PCA; Computer science; Feature extraction; Nonnegative matrix; Symmetric matrix; Eigenvalues and eigenvectors","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":[0.0001469246,0.0001796353,0.0001963675,0.0002474996,0.0001571921,0.00006155692,0.00008549828,0.00008993509,0.0000137278],"category_scores_gemma":[0.00003181686,0.0001903377,0.00004561475,0.0009224757,0.00002875964,0.0003789181,0.00002913982,0.0001232992,0.0001971929],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006216647,"about_ca_system_score_gemma":0.000008334026,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00000486618,"about_ca_topic_score_gemma":0.000005336276,"domain_scores_codex":[0.9990472,0.00002324612,0.00025467,0.0002834611,0.0001319414,0.0002594652],"domain_scores_gemma":[0.9992704,0.00006688821,0.00005944071,0.0002739955,0.0001169987,0.0002123192],"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":[0.00001858801,0.0002078524,0.0006982918,0.0002223884,0.0005224706,3.800624e-7,0.003402996,0.004697083,0.8693795,0.09790371,0.0003598643,0.02258694],"study_design_scores_gemma":[0.0002928251,0.00002259139,0.02088247,0.00001029479,0.0004937437,0.00001167096,0.0003681477,0.9062333,0.06543916,0.0008287875,0.004919787,0.0004972272],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.4008681,0.001038476,0.5946023,0.0007681891,0.00003409496,0.001156202,0.00004153505,0.0003398737,0.001151315],"genre_scores_gemma":[0.9760533,0.0001861645,0.02303148,0.00005339216,0.0002014252,0.000185458,0.0001137229,0.00003583235,0.00013922],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9015362,"threshold_uncertainty_score":0.7761745,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01359840595848155,"score_gpt":0.2617552126817133,"score_spread":0.2481568067232318,"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."}}