The basic role of network management is to provide quality of service suitable for users. Accurate application traffic classification is essential to provide adequate quality of service and to ensure a secure network environment. The existing traffic classification methods are port-based classification methods, payload-based classification methods and statistic information-based classification methods. However, due to the emergence of applications that generate packets with dynamic ports or encrypted payloads, the limitations of existing traffic classification techniques are occurred. In this paper, in order to address these limitations, we propose an application traffic classification model applying the convolution neural network algorithm which is one of the machine learning algorithms for 10 kinds of web application traffic(Baidu, Bing, Daum, Google, Kakaotalk, Nate, Naver, Yahoo, Youtube, Zum). The proposed model achieves 100% train classification accuracy and 99.4% validation classification accuracy.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.