{"id":"W4251080734","doi":"10.32920/ryerson.14661300","title":"A Comparative Study of the Impact of Data Augmentation in Machine Learning Based Classification Accuracy","year":2021,"lang":"en","type":"preprint","venue":"","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Toronto Metropolitan University","funders":"","keywords":"Gramian matrix; Computer science; Pattern recognition (psychology); Artificial intelligence; Discriminant; SIGNAL (programming language); Linear discriminant analysis; Machine learning; Field (mathematics); Series (stratigraphy); Data mining; Mathematics; Eigenvalues and eigenvectors","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":[0.01058009,0.001343047,0.001470579,0.002075659,0.0006272559,0.002366652,0.0009229058,0.001278022,0.001321477],"category_scores_gemma":[0.03156081,0.000264284,0.001107444,0.002046257,0.0006872343,0.002538109,0.001008639,0.001329711,0.0008945619],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0007644749,"about_ca_system_score_gemma":0.0007743266,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003294847,"about_ca_topic_score_gemma":0.002165976,"domain_scores_codex":[0.9932827,0.002335073,0.0008867166,0.001144918,0.001970551,0.0003800316],"domain_scores_gemma":[0.9641106,0.02566695,0.001231828,0.004009474,0.004555,0.000426135],"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":[0.005033228,0.001185067,0.0833716,0.0008470968,0.0007890089,0.0002465366,0.0004393167,0.08995053,0.009495973,0.0009354057,0.008535424,0.7991708],"study_design_scores_gemma":[0.0001540763,0.004460069,0.09710402,0.0003247803,0.0006569352,0.0006266278,0.0008323781,0.847006,0.03703187,0.002618346,0.009013184,0.0001717474],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9253223,0.01096082,0.04715229,0.001321921,0.001150727,0.0001964105,0.00274321,0.003153802,0.007998603],"genre_scores_gemma":[0.9622878,0.00100164,0.03002241,0.0001181843,0.0001686041,0.00007576384,0.004537422,0.0001303135,0.00165793],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.01058009,"threshold_uncertainty_score":0.05595356,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.6646261969874546,"score_gpt":0.6398211815144802,"score_spread":0.02480501547297442,"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."}}