{"id":"W4395056482","doi":"10.1109/tevc.2024.3392749","title":"Superpixel Segmentation-Based Evolutionary Multitasking Algorithm for Feature Selection of Hyperspectral Images","year":2024,"lang":"en","type":"article","venue":"IEEE Transactions on Evolutionary Computation","topic":"Remote-Sensing Image Classification","field":"Engineering","cited_by":12,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of British Columbia","funders":"National Natural Science Foundation of China","keywords":"Hyperspectral imaging; Human multitasking; Computer science; Feature selection; Artificial intelligence; Pattern recognition (psychology); Segmentation; Image segmentation; Evolutionary algorithm; Feature (linguistics); Selection (genetic algorithm); Genetic algorithm; Algorithm; Computer vision; Machine learning; Biology","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":[0.0006491449,0.0007852823,0.0008973642,0.000666438,0.0004585257,0.0004301616,0.000958643,0.0007330889,0.00130243],"category_scores_gemma":[0.00109219,0.0003551549,0.0006771901,0.0006839383,0.0004089769,0.0005971455,0.000656693,0.0005677947,0.0001937489],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006127158,"about_ca_system_score_gemma":0.0008241679,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004113673,"about_ca_topic_score_gemma":0.004201691,"domain_scores_codex":[0.9996847,0.00005889544,0.00001638665,0.0000836883,0.0001087812,0.00004748802],"domain_scores_gemma":[0.9996897,0.0001381611,0.00004019728,0.00002565643,0.00008077015,0.00002557098],"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":[0.00009135849,0.00007701914,0.001326699,0.00006421892,0.00006170363,0.0001219695,0.0001544845,0.7825927,0.01622107,0.004612719,0.00157406,0.1931021],"study_design_scores_gemma":[0.000005182823,0.0000147242,0.0001404498,0.000001820064,0.000004322889,0.00001204864,0.0000053125,0.9981732,0.0007406771,0.0006522744,0.0002472211,0.000002684066],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.02738044,0.0001751696,0.970735,0.00007477002,0.00002491603,0.00004151355,0.00001877288,0.0003118078,0.001237731],"genre_scores_gemma":[0.5338388,0.0001650384,0.4623268,0.0001396624,0.00003584133,0.0002772445,0.0001725992,0.000102478,0.002941484],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.004113673,"threshold_uncertainty_score":0.008179486,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01171468054613622,"score_gpt":0.2489950395692011,"score_spread":0.2372803590230649,"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."}}