Parameterizable Decision Tree Classifier on NetFPGA
Machine learning approaches based on decision trees (DTs) have been proposed for classifying networking traffic. Although this technique has been proven to have the ability to classify encrypted and unknown traffic, the software implementation of DT cannot cope with the current speed of packet traffic. In this paper, hardware architecture of decision tree is proposed on NetFPGA platform. The proposed architecture is fully parameterizable to cover wide range of applications. Several optimizations have been done on the DT structure to improve the tree search performance and to lower the hardware cost. The optimizations proposed are: a) node merging to reduce the computation latency, b) limit the number of nodes in the same level to control the memory usage, and c) support variable throughput to reduce the hardware cost of the tree.
KeywordsData Mining Machine Learning Search Tree
Unable to display preview. Download preview PDF.
- 3.Eklund, P., Kirkby, S.: Machine learning classifier performance as an indicator for data acquisition regimes in geographical field surveys. In: Proceedings of the Third Australian and New Zealand Conference on Intelligent Information Systems, pp. 264–269 (1995)Google Scholar
- 6.Lockwood, J.W., McKeown, N., Watson, G., Gibb, G., Hartke, P., Naous, J., Raghuraman, R., Luo, J.: NetFPGA–An Open Platform for Gigabit-Rate Network Switching and Routing. In: Proceedings of 2007 IEEE International Conference on Microelectronic Systems Education (2007)Google Scholar
- 7.Lopez-Estrada, S., Cumplido, R.: Decision Tree Based FPGA-Architecture for Texture Sea State Classification. In: IEEE International Conference on Reconfigurable Computing and FPGA’s (2006)Google Scholar
- 9.NetFPGA (2012), http://www.netfpga.org/
- 10.Nguyen, T., Armitage, G.: Training on multiple sub-flows to optimise the use of machine learning classifiers in real-world IP networks. In: Proceedings of IEEE 31st Conference on Local Computer Networks, pp. 369–376 (2006)Google Scholar
- 12.Qi, Y., Fong, J., Jiang, W., Xu, B., Li, J., Prasanna, V.: Multi-dimensional packet classification on FPGA: 100 Gbps and beyond. In: International Conference on Field-Programmable Technology, FPT, pp. 241–248 (2010)Google Scholar
- 14.Wang, Y., Yu, S.Z.: Machine Learned Real-time Traffic Classifiers. In: Second International Symposium on Intelligent Information Technology Application, vol. 3, pp. 449–454 (2008)Google Scholar
- 15.Williams, N., Zander, S., Armitage, G.: A preliminary performance comparison of five machine learning algorithms for practical IP traffic flow classification. Special Interest Group on Data Communication (SIGCOMM) 36(5), 5–16 (2006)Google Scholar