{"id":"W2588217599","doi":"10.5194/isprsarchives-xl-1-w5-37-2015","title":"A COMPARISON STUDY OF DIFFERENT MARKER SELECTION METHODS FOR SPECTRAL-SPATIAL CLASSIFICATION OF HYPERSPECTRAL IMAGES","year":2015,"lang":"en","type":"article","venue":"˜The œinternational archives of the photogrammetry, remote sensing and spatial information sciences/International archives of the photogrammetry, remote sensing and spatial information sciences","topic":"Remote-Sensing Image Classification","field":"Engineering","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Ottawa","funders":"Purdue University","keywords":"Pattern recognition (psychology); Hyperspectral imaging; Artificial intelligence; Support vector machine; Computer science; Segmentation; Benchmark (surveying); Image segmentation; Pixel; Cluster analysis; Scale-space segmentation; Selection (genetic algorithm); Geography; Cartography","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":[0.002722024,0.00074535,0.0007901468,0.002684631,0.000378441,0.0007641081,0.0006354116,0.0006303804,0.0005441954],"category_scores_gemma":[0.003916073,0.0001457643,0.0005895363,0.001599146,0.0002461317,0.00100952,0.0003466414,0.0003566116,0.0002857595],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003459989,"about_ca_system_score_gemma":0.0003991084,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002242324,"about_ca_topic_score_gemma":0.002858541,"domain_scores_codex":[0.9986336,0.0004519588,0.0000960151,0.0002468305,0.0004759817,0.00009558533],"domain_scores_gemma":[0.9975082,0.001181194,0.0002068036,0.0001726612,0.0008493643,0.00008174955],"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":[0.001581814,0.0005077776,0.02037939,0.0004484262,0.0004506524,0.0000921133,0.0001791112,0.03769317,0.03241166,0.0009488394,0.002462066,0.902845],"study_design_scores_gemma":[0.00007127973,0.0007370322,0.03840074,0.00006054465,0.0002795776,0.0002579783,0.0002945972,0.9099967,0.04656603,0.0008318538,0.002460351,0.00004323359],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.6868439,0.004869258,0.3022125,0.0002509832,0.0001423567,0.0001970354,0.0003709347,0.002154348,0.002958651],"genre_scores_gemma":[0.8390399,0.0006836731,0.1584428,0.00005186911,0.00003990658,0.00006544002,0.000816734,0.000111699,0.0007479229],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.002722024,"threshold_uncertainty_score":0.01439559,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0423487683217518,"score_gpt":0.3227572754962461,"score_spread":0.2804085071744943,"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."}}