Mobile Internet Application Classification Based on Machine Learning

  • Yangqun LiEmail author
Conference paper
Part of the Advances in Intelligent Systems and Computing book series (AISC, volume 905)


Service classification technology helps service suppliers understand how to use network services that offer personalized services to users. In this study, machine learning technology is used to classify such services, called mobile Internet applications (APPs). Firstly traffic of different application is collected and is used to build model by using C4.5 and SVM algorithm. Secondly, the model is used to classify the application type from the mobile internet traffic. Then traffic of applications is merged as major class by application type such as web browsing, e-commerce and the above two algorithms are applied to classify the major class that different applications belong to. Finally the Precision and Recall ration of two algorithms are compared and analyzed. Mobile stream video/audio is better recognized than Mobile app using http by using machine learning method. In order to improve the mobile application classification result, the only machine learning algorithm is not enough.


Service classification Machine learning C4.5 SVM Mobile app 


  1. 1.
  2. 2.
    Jiang, W.L.: Research and design of P2P traffic monitoring system based on DPI. BeiJiing University of Posts and Telecommunications (2013). (in Chinese)Google Scholar
  3. 3.
    Zhang, H.: Design of a P2P traffic detection based on DPI. BeiJiing University of Posts and Telecommunications (2013). (in Chinese)Google Scholar
  4. 4.
    Zhu, Y.N.: Identification and control of P2P business based on DPI. Shanghai Jiao Tong University (2008). (in Chinese)Google Scholar
  5. 5.
    Han, Y.M.: Design and implementation of a VoIP traffic detection system based on DPI. BeiJiing University of Posts and Telecommunications (2010). (in Chinese)Google Scholar
  6. 6.
    Hurley, J., Garcia-Palacios, E., Sezer, S.: Classification of P2P and HTTP using specific protocol characteristics. In: Oliver, M., Sallent, S. (eds.) Proceedings of the 15th Open European Summer School and IFIP TC6.6 Workshop on the Internet of the Future (EUNICE 2009), pp. 31–40, Springer, Heidelberg (2009)CrossRefGoogle Scholar
  7. 7.
    Michalski, R.S., Carbonell, J.G., Mitchell, T.M., et al.: Machine Learning: An Artificial Intelligence Approach. Springer, Berlin (1983)CrossRefGoogle Scholar
  8. 8.
    Li, W., Moore, A.W.: A machine learning approach for efficient traffic classification. In: Proceedings of the 15th International Symposium on Modeling, Analysis, and Simulation of Computer and Telecommunication Systems (MASCOTS 2007), Washington, DC, USA, pp. 310–317 (2007)Google Scholar
  9. 9.
    Zander, S., Nguyen, T., Armitage, G.: Automated traffic classification and application identification using machine learning. In: Proceedings of IEEE Conference on Local Computer Networks, Sidney, Australia (2005)Google Scholar
  10. 10.
    Singh, K., Agrawal, S., Sohi, B.S.: A near real-time IP traffic classification using machine learning. Intell. Syst. Appl. 3, 83–93 (2013)Google Scholar
  11. 11.
    Zhang, H.L., Lu, G.: Machine learning algorithms for classifying the imbalanced protocol flows: Evaluation and comparison. J. Softw. 23(6), 1500–1516 (2012). (in Chinese)CrossRefGoogle Scholar

Copyright information

© Springer Nature Switzerland AG 2020

Authors and Affiliations

  1. 1.College of Internet of ThingsNanjing University of Posts and TelecommunicationsNanjingChina

Personalised recommendations