{"id":"W2061068783","doi":"10.1109/ccece.2012.6335034","title":"Early internet traffic recognition based on machine learning methods","year":2012,"lang":"en","type":"article","venue":"","topic":"Internet Traffic Analysis and Secure E-voting","field":"Computer Science","cited_by":11,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"","keywords":"Computer science; The Internet; Payload (computing); Deep packet inspection; Network packet; Internet traffic; Internet traffic engineering; Traffic classification; Field (mathematics); Artificial intelligence; Machine learning; Port (circuit theory); Traffic flow (computer networking); Real-time computing; Data mining; Computer network; Engineering; World Wide Web","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":[0.001293645,0.0007843344,0.001009589,0.002804185,0.0002931497,0.001082922,0.0007523682,0.0009830545,0.001383109],"category_scores_gemma":[0.003467748,0.0003435677,0.0006162837,0.001791304,0.0005503013,0.001668789,0.000369266,0.001071503,0.001283632],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00063426,"about_ca_system_score_gemma":0.0004828396,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00162421,"about_ca_topic_score_gemma":0.001263977,"domain_scores_codex":[0.998974,0.0002783926,0.00008258989,0.0001984241,0.0003970289,0.00006949667],"domain_scores_gemma":[0.9982407,0.0008474834,0.0001073787,0.0001442691,0.0006322898,0.00002790022],"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":[0.0001765534,0.0002315236,0.00524516,0.0003164947,0.00008327776,0.0001370052,0.0001177282,0.06018784,0.0205262,0.01251316,0.002798965,0.8976661],"study_design_scores_gemma":[0.00001818827,0.0001443645,0.004036601,0.00008080596,0.00003749672,0.0002880268,0.00004738709,0.9347466,0.03826836,0.00885285,0.01341056,0.00006868163],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.03755448,0.002276004,0.9520867,0.0002232536,0.0002319554,0.0001693325,0.000148185,0.001959474,0.005350568],"genre_scores_gemma":[0.4868798,0.003287531,0.4994819,0.0002089651,0.0003962833,0.0002479092,0.0006367865,0.0001606098,0.008700221],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.002804185,"threshold_uncertainty_score":0.00684154,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03263489212259707,"score_gpt":0.2894015370766884,"score_spread":0.2567666449540913,"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."}}