Differentiated analysis for music traffic in software defined networks: A method of deep learning

Abstract

With the rapid development of software defined network, people have more and better choices for huge music network resources. However, they cannot find music traffic and services that meet their needs quickly and accurately. Deep learning technology has achieved various successes in speech signal processing and other fields. To meet the demand for music traffic, we propose an improved Apriori method for deep learning and implement it systematically. We then study differentiated analysis for music traffic systems and analyze the effectiveness of music traffic analysis by comparing the improved Apriori method with other methods. The experimental results indicate that the differentiated analysis for music traffic system using the improved Apriori method has a faster response speed and higher accuracy of differentiated user traffic; additionally, it has better practicability for differentiated analysis for music traffic.