자가학습 가능한 SVM 기반 가스 분류기의 설계
Design of SVM-Based Gas Classifier with Self-Learning Capability
0
조회
0
다운로드
0
인용
0
참고문헌
키워드
초록
본 논문은 실시간 자가학습과 분류 기능을 모두 지원하는 support vector machine (SVM) 기반 가스 분류기의 하드웨어구조 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 주파수에서3,337개의 CLB LUTs로 구현 가능함을 확인하였다.
Abstract
In this paper, we propose a support vector machine (SVM) based gas classifier that can support real-timeself-learning. The modified sequential minimal optimization (MSMO) algorithm is employed to train the proposedSVM. By using a shared structure for learning and classification, the proposed SVM reduced the hardware area by35% 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 canoperate at the clock frequency of 108MHz.
참고문헌 (18)
- Muhammad Hassan, "Computationally Efficient Weighted Binary Decision Codes for Gas Identification With Array of Gas Sensors", IEEE Sensors Journal, 17(2), pp.487~497 (2017), Institute of Electrical and Electronics Engineers (IEEE)[DOI]
- 정우재, "인공신경망 기반 가스 분류기의 설계", 전기전자학회논문지, 22(3), pp.700~705 (2018), 한국전기전자학회[DOI]
- Jingli Yang, "Fault Detection Using the Clustering-kNN Rule for Gas Sensor Arrays", Sensors, 16(12), pp.2069~ (2016), MDPI AG[DOI]
- Muhammad Hassan, "Gas classification using binary decision tree classifier", IEEE International Symposium on Circuits and System (ISCAS), pp.2579~2582 (2014)
- Xiaojun Zhai, "MLP Neural Network Based Gas Classification System on Zynq SoC", IEEE Access, 4, pp.8138~8146 (2016), Institute of Electrical and Electronics Engineers (IEEE)[DOI]
- Kun Wang, "A support vector machine-based genetic algorithm method for gas classification", International Conference on Frontiers of Sensors Technologies (ICFST), pp.363~366 (2017)
- Bernhard E, Boser, "A training algorithm for optimal margin classifiers", Proc. 5th Annu. Workshop Computational Learning Theory, pp.144~152 (1992)
- Edgar Elias Osuna, "An improved training algorithm for support vector machines", Proc. IEEE Signal Processing Society Workshop, pp.276~285 (1997)
- T. Joachims, "Advances in Kernel Methods" (1998), MIT Press
- Dennis Decoste, "Training invariant support vector machines", Machine Learning, 46(1, pp.3) (2002), 161~190[DOI]
- S.S. Keerthi, "A fast iterative nearest point algorithm for support vector machine classifier design", IEEE Transactions on Neural Networks, 11(1), pp.124~136 (2000), Institute of Electrical and Electronics Engineers (IEEE)[DOI]
- J. C. Platt, "Advances in Kernel Methods–Support Vector Learning", pp.185~208 (1999)
- S. S. Keerthi, "Improvements to Platt's SMO Algorithm for SVM Classifier Design", Neural Computation, 13(3), pp.637~649 (2001), MIT Press - Journals[DOI]
- Jia-Ching Wang, "VLSI Design for SVM-Based Speaker Verification System", IEEE Transactions on Very Large Scale Integration (VLSI) Systems, 23(7), pp.1355~1359 (2015), Institute of Electrical and Electronics Engineers (IEEE)[DOI]
- Zehra Camlica, "Medical image classification via SVM using LBP features from saliency-based folded data", International Conf. on Machine Learning and Applications, pp, 128(132), pp.2015~ (2015)[DOI]
- Lichen Feng, "VLSI design of SVM-based seizure detection system with on-chip learning capability", IEEE Trans. on Biomedical Circuits and Systems, 12(1), pp.171~181 (2018)[DOI]
- Alexander Vergara, "Chemical gas sensor drift compensation using classifier ensembles", Sensors and Actuators B: Chemical, 166-167, pp.320~329 (2012), Elsevier BV[DOI]
- "UCI machine learning Repository"[URL]