{"id":"W4416956834","doi":"10.1016/j.mlwa.2025.100811","title":"Enhancing skin cancer diagnosis using late discrete wavelet transform and new swarm-based optimizers","year":2025,"lang":"en","type":"article","venue":"Machine Learning with Applications","topic":"Cutaneous Melanoma Detection and Management","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Xerox (Canada)","funders":"","keywords":"Pattern recognition (psychology); Convolutional neural network; Hyperparameter; Discrete wavelet transform; Skin cancer; Feature (linguistics); Wavelet transform","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":[0.00008561461,0.0001531524,0.0002074402,0.0001761835,0.0002734321,0.00004057753,0.00004999397,0.00004579594,0.0001403592],"category_scores_gemma":[0.00001464265,0.0001286793,0.00004680017,0.0003897035,0.00004411817,0.00003190896,0.00002002593,0.0002638747,0.000004467544],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001032746,"about_ca_system_score_gemma":0.0001174913,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001841109,"about_ca_topic_score_gemma":0.0006652192,"domain_scores_codex":[0.999194,0.00002085602,0.0001803866,0.0002933602,0.0001211972,0.000190251],"domain_scores_gemma":[0.9995316,0.0000646531,0.00006501563,0.0001797196,0.0000341116,0.0001249445],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.001342229,0.0003815932,0.08914366,0.001332178,0.001057639,0.00005299885,0.00148752,0.2135057,0.01006688,0.00136923,0.001003269,0.679257],"study_design_scores_gemma":[0.006510566,0.0003972853,0.008969376,0.000782112,0.001475057,0.00005824854,0.000352838,0.4467559,0.02470303,0.0001470884,0.5092148,0.0006337284],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1020337,0.0006437309,0.8816295,0.0105665,0.00004611841,0.001510135,0.00001208042,0.0002651933,0.00329302],"genre_scores_gemma":[0.9584114,0.0002521033,0.03075763,0.001114358,0.00007562291,0.0009578062,0.00004873444,0.00003865148,0.008343728],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8563777,"threshold_uncertainty_score":0.524739,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01024682742314963,"score_gpt":0.2781564507920706,"score_spread":0.267909623368921,"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."}}