{"id":"W3167113330","doi":"10.1109/syscon48628.2021.9447076","title":"Enhancing The Performance of Network Traffic Classification Methods Using Efficient Feature Selection Models","year":2021,"lang":"en","type":"article","venue":"","topic":"Internet Traffic Analysis and Secure E-voting","field":"Computer Science","cited_by":9,"is_retracted":false,"has_abstract":true,"ca_institutions":"Toronto Metropolitan University","funders":"","keywords":"Autoencoder; Artificial intelligence; Computer science; Feature selection; Support vector machine; Machine learning; Traffic classification; Pattern recognition (psychology); Dimensionality reduction; Principal component analysis; Network packet; Binary classification; Precision and recall; k-nearest neighbors algorithm; Classifier (UML); Data mining; Feature (linguistics); Artificial neural network","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":[0.00115006,0.0001117205,0.000180838,0.0000452003,0.0002330976,0.0001019252,0.0003491761,0.00007145376,0.00001196212],"category_scores_gemma":[0.00002139273,0.00007676186,0.00012111,0.0009712134,0.00002432361,0.0001726076,0.00008827612,0.0001993533,0.000001695821],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005532872,"about_ca_system_score_gemma":0.0001056258,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000003224613,"about_ca_topic_score_gemma":0.00003153796,"domain_scores_codex":[0.9986375,0.000263966,0.0003071086,0.000314698,0.0002406463,0.0002360829],"domain_scores_gemma":[0.9991801,0.0001336219,0.0001695087,0.0002205843,0.0002660379,0.0000301465],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000001840237,0.00002054943,0.000007503105,0.000009346355,0.00002386696,2.847812e-7,0.000640441,0.9240851,0.005294665,0.06089465,0.00004343964,0.008978315],"study_design_scores_gemma":[0.00005508024,0.00001738786,0.00008288776,0.00003780636,0.00002488304,0.00001873368,0.0001428433,0.9842839,0.01517845,0.000007958579,0.00006086306,0.00008926208],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3584444,0.0001597027,0.6408254,0.0001124592,0.0001678432,0.00004311897,5.772969e-8,0.00004067874,0.0002063648],"genre_scores_gemma":[0.7670953,0.000008293236,0.232547,0.00007118069,0.00008720993,0.000002029915,0.000001087004,0.000005029737,0.0001828844],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.4086509,"threshold_uncertainty_score":0.3130258,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03122738801619786,"score_gpt":0.292252393020669,"score_spread":0.2610250050044712,"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."}}