Flow classification method and device based on deep ensemble learning

• Main Authors: DENG QIUXIA, LIAO NIANDONG
• Format: Patent
• Language: Chinese; English
• Published: 01.07.2022
• Subjects: CALCULATING; COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS; COMPUTING; COUNTING; ELECTRIC COMMUNICATION TECHNIQUE; ELECTRICITY; HANDLING RECORD CARRIERS; PHYSICS; PRESENTATION OF DATA; RECOGNITION OF DATA; RECORD CARRIERS; TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHICCOMMUNICATION

The invention relates to a traffic classification method and device based on deep ensemble learning, and the method comprises the steps: carrying out the preprocessing of an original data set, and obtaining a processed data set; and performing feature filtering on the processed data set to obtain a feature-filtered data set. And screening the data set after feature filtering based on a plurality of feature selection methods to obtain a sample sub-data set corresponding to each feature selection method. And performing learning classification on each sample sub-data set based on a preset ensemble learning model, wherein the ensemble learning model at least comprises two classifiers. And performing voting integration on the output of each classifier in the integrated learning model to obtain a final classification category of the original data set. According to the method, the confidence coefficient of the selected features can be improved through integration of multiple feature selection methods; moreover, the