{"id":"W2123930659","doi":"10.5194/isprsarchives-xl-2-w3-35-2014","title":"AN EFFICIENT INITIALIZATION METHOD FOR K-MEANS CLUSTERING OF HYPERSPECTRAL DATA","year":2014,"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":6,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Ottawa","funders":"Università degli Studi di Pavia","keywords":"Hyperspectral imaging; Initialization; Cluster analysis; Computer science; Endmember; Thresholding; Pattern recognition (psychology); Confusion matrix; Artificial intelligence; Simplex; Image (mathematics); Mathematics","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":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.002153518,0.0003891916,0.0004473628,0.0008527719,0.0008315322,0.0005687165,0.001981185,0.00009930364,0.000003178911],"category_scores_gemma":[0.001018002,0.0002693968,0.0002595537,0.0007864155,0.001863554,0.0005504882,0.0006205451,0.0003161818,0.000001168661],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005098572,"about_ca_system_score_gemma":0.0001462256,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_topic_score_codex":0.3931939,"about_ca_topic_score_gemma":0.08252391,"domain_scores_codex":[0.9959072,0.0003255711,0.001490057,0.000422293,0.001398155,0.0004566879],"domain_scores_gemma":[0.9961922,0.001207555,0.001282317,0.000810513,0.0003708013,0.0001366826],"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":[0.00009573015,0.00001722771,0.00003989844,0.0000764207,0.00006775624,6.223527e-8,0.002415695,0.1022227,0.01066091,0.00001486076,0.00002315148,0.8843656],"study_design_scores_gemma":[0.000704509,0.0001391698,0.001163842,0.0002903756,0.00006195629,0.00007332942,0.001289566,0.9758373,0.01548989,0.002372521,0.002286631,0.0002908563],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.005467899,0.00001846617,0.9865832,0.001329696,0.001829678,0.0007255143,0.0001799919,0.0000775196,0.003788082],"genre_scores_gemma":[0.9524575,0.00007091797,0.04678375,0.0003555374,0.0001722587,3.227493e-7,0.0001230435,0.00001913877,0.00001755614],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9469896,"threshold_uncertainty_score":0.9999758,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02868060640415367,"score_gpt":0.2889958834230084,"score_spread":0.2603152770188548,"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."}}