{"id":"W2541546981","doi":"10.1016/j.microc.2016.10.024","title":"Projection pursuit and PCA associated with near and middle infrared hyperspectral images to investigate forensic cases of fraudulent documents","year":2016,"lang":"en","type":"article","venue":"Microchemical Journal","topic":"Spectroscopy and Chemometric Analyses","field":"Chemistry","cited_by":47,"is_retracted":false,"has_abstract":false,"ca_institutions":"Dalhousie University","funders":"Fundação de Amparo à Ciência e Tecnologia do Estado de Pernambuco; Conselho Nacional de Desenvolvimento Científico e Tecnológico; Natural Sciences and Engineering Research Council of Canada; Coordenação de Aperfeiçoamento de Pessoal de Nível Superior; Fundação de Amparo à Pesquisa do Estado de São Paulo","keywords":"Principal component analysis; Hyperspectral imaging; Pattern recognition (psychology); Artificial intelligence; Projection (relational algebra); Projection pursuit; Computer science; White (mutation); Chemistry","routes":{"ca_aff":true,"ca_fund":true,"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":[],"consensus_categories":[],"category_scores_codex":[0.00009665587,0.0001800337,0.0002856542,0.0001017881,0.0001157158,0.0001011945,0.0001186987,0.0001081427,0.0001965633],"category_scores_gemma":[0.0003704577,0.0001175154,0.00005177872,0.0002455807,0.0002766268,0.0001503497,0.0000691232,0.000203369,0.000001817903],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001426292,"about_ca_system_score_gemma":0.00006476969,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002688064,"about_ca_topic_score_gemma":0.000004559094,"domain_scores_codex":[0.9989352,0.00001417071,0.0002701629,0.0002419573,0.00023845,0.0003000834],"domain_scores_gemma":[0.9992073,0.0001125414,0.0001873878,0.0001059694,0.0001357646,0.0002510323],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0001338457,0.00006492577,0.01941234,0.00003079295,0.0001841892,0.00002441784,0.0001860068,2.158461e-7,0.9781584,0.000003124269,0.001226001,0.0005757455],"study_design_scores_gemma":[0.001168082,0.0001648201,0.001809598,0.000285308,0.0001744849,0.0005409029,0.0003073062,0.000003291062,0.9948946,0.0003320096,0.0001387258,0.0001808888],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9983438,0.0006661054,0.00009226803,0.0004013774,0.00001404257,0.00004809229,0.00002772197,0.00002269256,0.0003839588],"genre_scores_gemma":[0.9961987,0.0001566982,0.002559622,0.00009332748,0.00007034358,0.00000445343,0.000004540563,0.00001876575,0.0008935721],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.01760274,"threshold_uncertainty_score":0.4792139,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01588536113740452,"score_gpt":0.2437494256184472,"score_spread":0.2278640644810427,"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."}}