{"id":"W2023331163","doi":"10.1109/icassp.2013.6637805","title":"Independent component analysis on Lie groups for multi-object analysis of first episode depression","year":2013,"lang":"en","type":"article","venue":"","topic":"Blind Source Separation Techniques","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"Queen's University; University of British Columbia","funders":"","keywords":"Lie group; Pattern recognition (psychology); Similarity (geometry); Artificial intelligence; Orientation (vector space); Mathematics; Psychology; Surface (topology); Object (grammar); Component analysis; Tangent space; Independent component analysis; Component (thermodynamics); Computer vision; Computer science; Pure mathematics; Geometry; Image (mathematics); Physics","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":[],"consensus_categories":[],"category_scores_codex":[0.0004544715,0.0001680442,0.0004826285,0.001331645,0.0001124496,0.0001324901,0.0007523617,0.0001060931,0.0001279092],"category_scores_gemma":[0.00004403128,0.000132429,0.0005173613,0.002170329,0.0000268079,0.0003470271,0.0002048899,0.00009789288,0.00001847931],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005108677,"about_ca_system_score_gemma":0.00001095108,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001293207,"about_ca_topic_score_gemma":0.002070048,"domain_scores_codex":[0.9983037,0.00009889557,0.0004645794,0.0005024269,0.0004143433,0.0002160931],"domain_scores_gemma":[0.9982677,0.0002705366,0.0002549632,0.0008814331,0.0002269494,0.00009840055],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00009289698,0.004173108,0.733409,0.00009716191,0.01752476,0.000004807011,0.005739727,0.113454,0.005854755,0.07970886,0.006633435,0.03330746],"study_design_scores_gemma":[0.0002443607,0.00007658322,0.1841036,0.000005669447,0.0005035921,1.660088e-7,0.00002551946,0.7985148,0.01594578,0.0003010762,0.0001296864,0.0001491433],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1451351,0.00001675455,0.8534181,0.0003248906,0.00002931021,0.000431077,0.000006000153,0.0002001668,0.0004386641],"genre_scores_gemma":[0.8570932,0.00000753919,0.142237,0.0002836627,0.000007513418,0.0001501073,0.00003069652,0.00000672894,0.0001836024],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.7119581,"threshold_uncertainty_score":0.5400296,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02950561426749218,"score_gpt":0.2941300034968121,"score_spread":0.2646243892293199,"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."}}