{"id":"W3146730906","doi":"10.1002/smr.2343","title":"On the value of filter feature selection techniques in homogeneous ensembles effort estimation","year":2021,"lang":"en","type":"article","venue":"Journal of Software Evolution and Process","topic":"Software Engineering Research","field":"Computer Science","cited_by":20,"is_retracted":false,"has_abstract":true,"ca_institutions":"École de Technologie Supérieure","funders":"","keywords":"Computer science; Feature selection; Preprocessor; Artificial intelligence; Data mining; Software; Filter (signal processing); Support vector machine; Feature (linguistics); Pattern recognition (psychology); Multilayer perceptron; Machine learning; Subspace topology; Random forest; k-nearest neighbors algorithm; Dimensionality reduction; Process (computing); Curse of dimensionality; Homogeneous; Artificial neural network; Mathematics","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":[0.000512088,0.00007840437,0.000133127,0.0001970567,0.00005839932,0.00005117786,0.0002150165,0.00007362034,0.000004562319],"category_scores_gemma":[0.00131913,0.00005613657,0.00003985823,0.0005888667,0.00002487257,0.0002598112,0.00003851524,0.0002824707,5.630856e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00008259076,"about_ca_system_score_gemma":0.0002088226,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00000421975,"about_ca_topic_score_gemma":0.000003271028,"domain_scores_codex":[0.9991366,0.00005457186,0.0002126921,0.0001171954,0.000361148,0.0001178169],"domain_scores_gemma":[0.9987968,0.0004631286,0.0001416365,0.0001148955,0.0004453725,0.00003818132],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.0005518386,0.001299271,0.3954095,0.002678297,0.0003202452,0.0004703164,0.007975607,0.1766181,0.01521058,0.04254228,0.01631168,0.3406123],"study_design_scores_gemma":[0.001388851,0.001626203,0.4810652,0.00286415,0.00004622852,0.0043272,0.0002057915,0.1308857,0.2976574,0.07839013,0.0008712984,0.0006718407],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3616025,0.0006747366,0.6368955,0.0006035034,0.0001037887,0.00007041722,8.74868e-7,0.00003919709,0.000009560419],"genre_scores_gemma":[0.9573464,0.00004762787,0.04246036,0.00005202931,0.00004365523,0.000005058214,5.520808e-7,0.000005928409,0.00003833209],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.595744,"threshold_uncertainty_score":0.2289183,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.008875852151698763,"score_gpt":0.2611015249772128,"score_spread":0.2522256728255141,"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."}}