Classification of Internet video traffic using multi-fractals

Video traffic is booming in the Internet, and the types of video traffic are numerous. So it is necessary and imminent to effectively classify video traffic. The existing methods of classifying video traffic depend heavily on extracted features, which are statistically accessed from given samples, and thus may not be effective for other types of video applications. Therefore, in this paper, we propose a novel classification method based on the theory of multi-fractals, and it relies on fractal characteristics obtained by physical calculations to classify video traffic, which is quite different from statistical features obtained by a long-term statistical analysis. A number of experiments are performed to demonstrate the feasibility of the proposed method and its adaptability to new environments. The results show that video traffic classification with multi-fractals, can effectively mitigate some of the defects of statistical features, and achieve a superior performance.

[1]  Bir Bhanu,et al.  Latent Fingerprint Image Segmentation Using Fractal Dimension Features and Weighted Extreme Learning Machine Ensemble , 2016, 2016 IEEE Conference on Computer Vision and Pattern Recognition Workshops (CVPRW).

[2]  Shengnan Hao,et al.  Improved SVM method for internet traffic classification based on feature weight learning , 2015, 2015 International Conference on Control, Automation and Information Sciences (ICCAIS).

[3]  George Varghese,et al.  Graption: A graph-based P2P traffic classification framework for the internet backbone , 2011, Comput. Networks.

[4]  Maria G. Martini,et al.  Hysteresis based rate adaptation for scalable video traffic over an LTE downlink , 2015, 2015 IEEE International Conference on Communication Workshop (ICCW).

[5]  Terrence P. Fries.  Fuzzy clustering of network traffic features for security , 2015, 2015 IEEE 5th Symposium on Large Data Analysis and Visualization (LDAV).

[6]  Jun Zhang,et al.  Internet Traffic Classification by Aggregating Correlated Naive Bayes Predictions , 2023, IEEE Transactions on Information Forensics and Security.

[7]  Domenec Puig,et al.  A practical approach for detection and classification of traffic signs using Convolutional Neural Networks , 2016, Robotics Auton. Syst..

[8]  LiTing Hu,et al.  Real-time internet traffic identification based on decision tree , 2012, World Automation Congress 2012.

[9]  Hong-di He,et al.  Fractal behavior of traffic volume on urban expressway through adaptive fractal analysis , 2016 .

[10]  Jesús E. Díaz-Verdejo,et al.  Network traffic application identification based on message size analysis , 2015, J. Netw. Comput. Appl..

[11]  Trianggoro Wiradinata,et al.  Clustering and Principal Feature Selection Impact for Internet Traffic Classification Using K-NN , 2016 .

[12]  Jinsoo Hwang,et al.  High-Performance Internet Traffic Classification Using a Markov Model and Kullback-Leibler Divergence , 2016, Mob. Inf. Syst..

[13]  Riyad Alshammari,et al.  Identification of VoIP encrypted traffic using a machine learning approach , 2015, J. King Saud Univ. Comput. Inf. Sci..

[14]  Walter Willinger,et al.  On the self-similar nature of Ethernet traffic , 1993, SIGCOMM '93.

[15]  Shengda Zeng,et al.  Local Fractional Laplace Variational Iteration Method for Fractal Vehicular Traffic Flow , 2014 .

[16]  Abuagla Babiker Mohd,et al.  Towards a Flow-based Internet Traffic Classification for Bandwidth Optimization , 2009 .