{"id":"W2315625626","doi":"10.1016/j.neucom.2015.08.111","title":"L2,p-norm and sample constraint based feature selection and classification for AD diagnosis","year":2016,"lang":"lv","type":"article","venue":"Neurocomputing","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":17,"is_retracted":false,"has_abstract":false,"ca_institutions":"","funders":"National Institute of Biomedical Imaging and Bioengineering; Canadian Institutes of Health Research; National Institutes of Health; Genentech; National Natural Science Foundation of China; Northern California Institute for Research and Education; Alzheimer's Disease Neuroimaging Initiative; GE Healthcare; Pfizer; BioClinica; Biogen; Novartis Pharmaceuticals Corporation; U.S. Department of Defense; Eli Lilly and Company; Bristol-Myers Squibb; F. Hoffmann-La Roche; Merck; Alzheimer's Drug Discovery Foundation; Meso Scale Diagnostics; Takeda Pharmaceutical Company; AbbVie; National Institute on Aging; Fujirebio Europe; Alzheimer's Association","keywords":"Norm (philosophy); Feature selection; Computer science; Artificial intelligence; Adaptability; Feature (linguistics); Algorithm; Pattern recognition (psychology); Flexibility (engineering); Machine learning; Mathematics; Data mining; Statistics","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow","sts","scholarly_communication","research_integrity","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.002248857,0.001022091,0.0003759015,0.0005498135,0.002276977,0.00167704,0.001675545,0.003013606,0.1408415],"category_scores_gemma":[0.003507318,0.001924581,0.001443478,0.0009846529,0.001515187,0.0006098634,0.001862431,0.001810056,0.000474645],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001905041,"about_ca_system_score_gemma":0.001519939,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0008222032,"about_ca_topic_score_gemma":0.0008953236,"domain_scores_codex":[0.9908745,0.0005971787,0.001996106,0.002136481,0.001828446,0.002567304],"domain_scores_gemma":[0.9915749,0.002448102,0.002676603,0.001886607,0.0002821262,0.001131618],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.00333066,0.000620973,0.0002872794,0.004255455,0.002672767,0.0007174699,0.002677458,0.004699231,0.03695315,0.2228568,0.6924384,0.02849043],"study_design_scores_gemma":[0.002882262,0.00254143,0.0003896822,0.001226951,0.001246495,0.001756253,0.0009071135,0.08023004,0.8966954,0.000143361,0.01021361,0.001767373],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7316598,0.001428011,0.009979307,0.001951437,0.002869289,0.0001242111,0.0007135171,0.0003398078,0.2509347],"genre_scores_gemma":[0.980246,0.001460202,0.00993057,0.002518532,0.002207892,0.001059376,0.001642065,0.0007772276,0.0001581417],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.8597423,"threshold_uncertainty_score":0.9993593,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01412911428053626,"score_gpt":0.2362020652980386,"score_spread":0.2220729510175023,"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."}}