FPGA Implementation of Classification Based on SVM For Smart Grid Application

Authors

  • Ms. T. Tamileselvi  Associate Professor, Department of ECE, Jerusalem College of Engineering, Pallikaranai, Tamil Nadu, Chennai, India
  • K. Kanagaraj  UG Scholar, Department of ECE, Jerusalem College of Engineering, Pallikaranai, Tamil Nadu, Chennai, India
  • M. Korkaimaran  
  • M. Surya Rao  

Keywords:

FPGA devices , support vector machine and smart grid.

Abstract

In order to increase predictive accuracy, Support Vector Machines (SVMs), a common classification and regression prediction tool, employ supervised machine learning theory. The field programmable gate array (FPGA) implementation of a classification system using a support vector machine is the main emphasis of this study. The FPGA-based two-class SVM classifier can rapidly classify data due to the powerful parallel computation capability it offers. Depending on the classification's dimensions, the system operates in either a linear or non-linear fashion. The system would help in the classification system which is efficient at quickly classify data and is a promising method for enhancing communication security in the Smart Grid.

References

  1. Markos Papadonikolakis, Christos-Savvas Bouganis, “Novel Cascade FPGA Accelerator for Support Vector Machines Classification,” IEEE Transactions on Neural
  2. Networks and Learning Systems, Vol. 23, No. 7, July 2012
  3. M. Papadonikolakis and C.-S. Bouganis, “A scalable FPGA architecture for non-linear SVM training,” in Proc. Int. Conf. FPT Technol., Dec. 2008, pp. 337–340.
  4. S. Cadambi, I. Durdanovic, V. Jakkula, M. Sankaradass, E. Cosatto, S.Chakradhar, and H. Graf, “A massively parallel FPGA-based coprocessor for support vector machines,” in Proc. 17th IEEE Symp. Field Programm. Custom Comput. Mach., Apr. 2009,
  5. D. Anguita, A. Boni, and S. Ridella, “A digital architecture for support vector machines: Theory, algorithm, and FPGA implementation,” IEEE Trans. Neural Network., vol. 14, no. 5, pp. 993–1009, Sep. 2003
  6. F. Khan, M. Arnold, and W. Pottenger, “Hardware-based support vector machine classification in logarithmic number systems,” in Proc. IEEE Int. Symp. Circuits System., vol. 5. May 2005, pp. 5154–5157.
  7. K. Irick, M. DeBole, V. Narayanan, and A. Gayasen, “A hardware efficient support vector machine architecture for FPGA,” in Proc. Annu. IEEE Symp. Field-Programm. Custom Comput. Mach., Apr. 2008
  8. B. Catanzaro, N. Sundaram, and K. Keutzer, “Fast support vector machine training and classification on graphics processors,” in Proc. 25th Int. Conf. Mach. Learn., 2008, pp. 104–111.
  9. A. Carpenter. (2009). CUSVM: A Cuda Implementation of Support Vector Classification and Regression [Online]. Available: http://patternsonascreen.net/cuSVM.html
  10. NVidia. (2008). NVIDIA CUDA Compute Unified Device Architecture, Programming Guide, Santa Clara, CA [Online]. Available: http://www.nvidia.co.uk/cuda.
  11. M. Papadonikolakis, C.-S. Bouganis, and G. Constantinides, “Performance comparison of GPU and FPGA architectures for the SVM training problem,” in Proc. Int. Conf. Field-Programm. Technol., 2009
  12. T.Tamilselvi, Dr.V.Rajendran, “Comparative Study of SVM and KNN Machine Learning Algorithm for Spectrum Sensing in Cognitive Radio”, 2022, in  Intelligent Communication Technologies and Virtual Mobile Networks, Lecture Notes on Data Engineering and Communications Technologies 131, https://doi.org/10.1007/978-981-19-1844-5_41

Downloads

Published

2023-02-28

Issue

Section

Research Articles

How to Cite

[1]
Ms. T. Tamileselvi, K. Kanagaraj, M. Korkaimaran, M. Surya Rao, " FPGA Implementation of Classification Based on SVM For Smart Grid Application" International Journal of Scientific Research in Computer Science, Engineering and Information Technology(IJSRCSEIT), ISSN : 2456-3307, Volume 9, Issue 1, pp.72-79, January-February-2023.