전기전자학회논문지 (Journal of IKEEE)

  • 제23권4호
  • /
  • Pages.1400-1407
  • /
  • 2019
  • /
  • 1226-7244(pISSN)
  • /
  • 2288-243X(eISSN)
한국전기전자학회 (Institute of Korean Electrical and Electronics Engineers)
권호 표지
DOI QR코드

DOI QR Code

자가학습 가능한 SVM 기반 가스 분류기의 설계

Design of SVM-Based Gas Classifier with Self-Learning Capability

  • Jeong, Woojae (Dept. of Electronics and Information Engineering, Korea Aerospace University) ;
  • Jung, Yunho (Dept. of Electronics and Information Engineering, Korea Aerospace University)
  • 투고 : 2019.12.12
  • 심사 : 2019.12.30
  • 발행 : 2019.12.31
PDF 다운로드
⟨ 이전 논문 다음 논문 ⟩

초록

본 논문은 실시간 자가학습과 분류 기능을 모두 지원하는 support vector machine (SVM) 기반 가스 분류기의 하드웨어 구조 설계 및 구현 결과를 제시한다. 제안된 가스 분류기는 학습 알고리즘으로 modified sequential minimal optimization(MSMO)을 사용하였고, 학습과 분류 기능을 공유구조를 사용하여 설계함으로써 기존 논문 대비 하드웨어 면적을 35% 감소시켰다. 설계된 가스 분류기는 Xilinx Zynq UltraScale+ FPGA를 사용하여 구현 및 검증되었고, 108MHz의 동작 주파수에서 3,337개의 CLB LUTs로 구현 가능함을 확인하였다.

In this paper, we propose a support vector machine (SVM) based gas classifier that can support real-time self-learning. The modified sequential minimal optimization (MSMO) algorithm is employed to train the proposed SVM. By using a shared structure for learning and classification, the proposed SVM reduced the hardware area by 35% compared to the existing architecture. Our system was implemented with 3,337 CLB (configurable logic block) LUTs (look-up table) with Xilinx Zynq UltraScale+ FPGA (field programmable gate array) and verified that it can operate at the clock frequency of 108MHz.

키워드

참고문헌

  1. Muhammad Hassan, Muhammad Umar, and Amine Bermak, "Computationally efficient weighted binary decision codes for gas identification with array of gas sensors," IEEE Sensors Journal, vol.17, no.2, pp.487-497, 2017. DOI: 10.1109/JSEN.2016.2631476
  2. Woojae Jeong, Minwoo Kim, Jaechan Cho, Yunho Jung, "Design of gas classifier based on artificial neural network," Journal of IKEEE, vol.22, no.3, pp.700-705, 2018. DOI: 10.7471/ikeee.2018.22.3.700
  3. Jingli Yang, Zhen Sun, and Yinsheng Chen, "Fault detection using the clustering-kNN rule for gas sensor arrays," Sensors, vol.16, pp.1-21, 2016. DOI: 10.3390/s16122069
  4. Muhammad Hassan, Amine Bermak, "Gas classification using binary decision tree classifier," IEEE International Symposium on Circuits and System (ISCAS), pp.2579-2582, 2014. DOI: 10.1109/ISCAS.2014.6865700
  5. Xiaojun Zhai, Amine Ait Si Ali, Abbes Amira, and Faycal Bensaali, "MLP neural network based gas classification system on zynq soc," IEEE Access, vol.4, pp.8138-8146, 2016. DOI: 10.1109/ACCESS.2016.2619181
  6. Kun Wang, Wenbin Ye, Xiaojin Zhao, and Xiaofang Pan, "A support vector machine-based genetic algorithm method for gas classification," International Conference on Frontiers of Sensors Technologies (ICFST), pp.363-366, 2017.
  7. Bernhard E, Boser, Isabelle M. Guyon, and Vladimir N. Vapnik, "A training algorithm for optimal margin classifiers," in Proc. 5th Annu. Workshop Computational Learning Theory, Pittsburgh, Pennsylvania, USA, pp.144-152, 1992. DOI: 10.1145/130385.130401
  8. Edgar Elias Osuna, Robert M. Freund, Federico Girosi, "An improved training algorithm for support vector machines," in Proc. IEEE Signal Processing Society Workshop, pp.276-285, 1997. DOI: 10.1109/NNSP.1997.622408
  9. T. Joachims, "Making large-scale SVM learning practical," in Advances in Kernel Methods, B. Scholkopf, C. J. C. Burges, and A. J. Smola, Eds. Cambridge, MA, USA, MIT Press, 1998. DOI: 10.1.1.62.2274
  10. D. DeCoste and B. Scholkopf, "Training invariant support vector machines," Machine Learn, vol.46, no.1, pp.161-190, 2002. DOI: 10.1023/A:1012454411458
  11. S. Keerthi, S. K. Shevade, C. Bhattacharyya, and K. Murthy, "A fast iterative nearest point algorithm for support vector machine classifier design," IEEE Trans. Neural Network, vol.11, no.1, pp.124-136, 2000. DOI: 10.1109/72.822516
  12. J. C. Platt, "Fast training of support vector machines using sequential minimal optimization," B. Scholkopf, C. J. C. Burges, and A. J. Smola, editors, Advances in Kernel Methods-Support Vector Learning, Cambridge, MA, USA, pp.185- 208, 1999. DOI: 10.5555/299094.299105
  13. S. S. Keerthi, C. Bhattacharyya, K. R. K. Murthy, "Improvements to Platt's SMO algorithm for SVM classifier design," Neural Computation, vol.13, no.3, pp.637-649, 2001. DOI: 10.1162/089976601300014493
  14. Jia-Ching Wang, Li-Xun Lian, Yan-Yu Lin, and Jia-Hao Zhao, "VLSI design for SVM-based speaker verification system," IEEE Trans. on Very Large Scale Integration (VLSI), vol.23, no.7, pp. 1355-1359, 2015. DOI: 10.1109/TVLSI.2014.2335112
  15. Zehra Camlica, H. R. Tizhoosh, and Farzad Khalvati, "Medical image classification via SVM using LBP features from saliency-based folded data," International Conf. on Machine Learning and Applications, pp.128-132, 2015. DOI: 10.1109/ICMLA.2015.131
  16. Lichen Feng, Zunchao Li, and Yuan Wang, "VLSI design of SVM-based seizure detection system with on-chip learning capability," IEEE Trans. on Biomedical Circuits and Systems, vol.12, no.1, pp.171-181, 2018. DOI: 10.1109/TBCAS.2017.2762721
  17. Alexander Vergara, Shankar Vembu, Tuba Ayhan, Margaret A. Ryan, Margie L. Homer, and Ramon Huerta, "Chemical gas sensor drift compensation using classifier ensembles," Sensors and Actuators B: Chemical, vol.166-167, no.20, pp.320-329, 2012. DOI: 10.1016/j.snb.2012.01.074
  18. Alexander Vergara, "UCI machine learning Repository," https://archive.ics.uci.edu/ml/datasets/gas+sensor+array+drift+dataset.