{"id":"W2009175682","doi":"10.5589/m06-029","title":"Noise reduction and best band selection techniques for improving classification results using hyperspectral data: application to lithological mapping in Canada's Arctic","year":2006,"lang":"en","type":"article","venue":"Canadian Journal of Remote Sensing","topic":"Geochemistry and Geologic Mapping","field":"Computer Science","cited_by":21,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Hyperspectral imaging; Redundancy (engineering); Arctic; Noise reduction; Remote sensing; Field (mathematics); Computer science; Noise (video); Principal component analysis; Data mining; Pattern recognition (psychology); Artificial intelligence; Selection (genetic algorithm); Geography; Mathematics; Geology; Image (mathematics)","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":true,"about_ca":true,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006398241,0.00009823837,0.0001467881,0.0002287792,0.0001878872,0.0001059794,0.0002046765,0.00006903287,1.633705e-7],"category_scores_gemma":[0.0003221559,0.0001035842,0.0000175927,0.0003680763,0.00002616909,0.0002652962,0.00002098454,0.0001802947,6.542275e-8],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0009256429,"about_ca_system_score_gemma":0.001310669,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_topic_score_codex":0.7915704,"about_ca_topic_score_gemma":0.7745546,"domain_scores_codex":[0.9988914,0.0000421027,0.0003850705,0.000311027,0.0001006236,0.0002697795],"domain_scores_gemma":[0.999025,0.00004043988,0.0002618649,0.0002177494,0.0002906224,0.0001642906],"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":[0.00003325032,0.000008976591,0.001106495,0.00007902426,0.000008285427,0.00006458009,0.0003747838,0.002719346,0.3300128,0.0001680213,0.0002306524,0.6651938],"study_design_scores_gemma":[0.0004110748,0.00009247033,0.01022746,0.0002894622,0.00002281825,0.003087512,0.0007993242,0.950828,0.02497308,0.002386589,0.00654984,0.0003324412],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3156384,0.00005284965,0.6804618,0.003386371,0.0001210076,0.000190809,0.000004599514,0.000009259962,0.0001348934],"genre_scores_gemma":[0.6745247,0.000001514588,0.3252528,0.00002876796,0.000172872,8.284876e-8,0.000005489051,0.000002367379,0.00001138897],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9481086,"threshold_uncertainty_score":0.4224042,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03232509128987228,"score_gpt":0.2416253705024396,"score_spread":0.2093002792125673,"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."}}