DOI QR코드

DOI QR Code

인지 무선 시스템에서 웨이블릿 패킷 분해를 이용한 서포트 벡터 머신 기반 스펙트럼 센싱

Spectrum Sensing based on Support Vector Machine using Wavelet Packet Decomposition in Cognitive Radio Systems

  • 투고 : 2018.02.14
  • 심사 : 2018.04.06
  • 발행 : 2018.04.30

초록

부사용자가 주사용자의 주파수 사용 상태를 판별하기 위해 인지 무선 시스템의 핵심 기술인 스펙트럼 센싱을 사용한다. 스펙트럼 센싱 기법 중 에너지 검출법은 할당 된 채널 신호의 강도에 따라서 주사용자의 주파수 사용 유무를 판별한다. 이 기법은 단순히 신호의 크기를 이용해 스펙트럼 센싱하기 때문에 SNR 대역이 낮아질수록 주사용자의 신호를 검출하기 어렵다는 단점이 있다. 본 논문은 낮은 SNR 대역에서의 성능 열화를 극복하기 위해 웨이블릿 패킷 분해를 사용한 서포트 벡터 머신을 스펙트럼 센싱과 융합하는 방식을 제안하였다. 이 방식은 센싱 신호를 웨이블릿 패킷 분해를 기반으로 특징 추출하여 Support Vector Machine의 훈련과 실험용 데이터로 사용한다. 제안한 방식의 실험 결과를 SNR대역에 대해 정확도와 ROC 커브 그래프의 AUC를 이용하여 에너지 검출법과 비교하였다. 실험 결과, 제안한 시스템은 낮은 SNR대역에서 에너지 검출법 보다 더 향상된 판별 성능을 보였다.

Spectrum sensing, the key technology of the cognitive radio networks, is used by a secondary user to determine the frequency state of a primary user. The energy detection in the spectrum sensing determines the presence or absence of a primary user according to the intensity of the allocated channel signal. Since this technique simply uses the strength of the signal for spectrum sensing, it is difficult to detect the signal of a primary user in the low SNR band. In this paper, we propose a way to combine spectrum sensing and support vector machine using wavelet packet decomposition to overcome performance degradation in low SNR band. In our proposed scheme, the sensing signals were extracted by wavelet packet decomposition and then used as training data and test data for support vector machine. The simulation results of the proposed scheme are compared with the energy detection using the AUC of the ROC curve and the accuracy according to the SNR band. With simulation results, we demonstrate that the proposed scheme show better determining performance than one of energy detection in the low SNR band.

키워드

참고문헌

  1. Oh-Soon Shin and Yo-An Shin, "An Improved Combining of Hard Decisions for Cooperative Spectrum Sensing in Cognitive Radio Systems", The Journal of The Korean Institute of Communication Sciences, Vol. 34, No. 2, pp. 132-138, Feb 2009.
  2. So-Young Lee and Jin-Young Kim, "Optimal Soft Decision for Cooperative Spectrum Sensing in Cognitive Radio Systems", The Journal of Korean Institute of Electromagnetic Engineering and Science, Vol. 22, No. 4, pp. 423-429, Apr 2011. DOI: http://dx.doi.org/10.5515/KJKIEES.2011.22.4.423
  3. Jun-Ho Baek, Jong-Hwan Lee, Hyeong-Joo Oh and Seung-Hoon Hwang, "Performance Improvements of Energy Detector for Spectrum Sensing in Cognitive Radio Environments: Verification using Time delay", The Institute of Electronics Engineers of Korea, Vol. 45, No. 1, pp. 72-77, Jan 2008. DOI: http://www.dbpia.co.kr/Journal/ArticleDetail/ NODE00941783
  4. Zhang dandan and Zhai Xuping, "SVM-based spectrum sensing in cognitive radio", 7th International Conference on Wireless Communications Networking and Mobile Computing (WiCOM'11), pp. 1-4, Sept 2011. DOI: http://dx.doi.org/10.1109/wicom.2011.6040028
  5. Yuqing Huang, Hong Jiang, Hong Hu and Yuancheng Yao, "Design of Learning Engine Based on Support Vector Machine in Cognitive Radio", International Conference on Computational Intelligence and Software Engineering (CiSE'09), pp. 1-4, Dec 2009. DOI: http://dx.doi.org/10.1109/CISE.2009.5363127
  6. Karaputugala Madushan Thilina, Kae Won Choi, Nazmus Saquib and Ekram Hossain, "Machine Learning Techniques for Cooperative Spectrum Sensing in Cognitive Radio Networks", IEEE JOURNAL ON SELECTED AREAS IN COMMUNICATIONS, Vol. 31, No. 11, pp. 2209 - 2221, Nov 2013 DOI: http://dx.doi.org/10.1109/JSAC.2013.131120
  7. Md.Sipon-Miah and In-Soo Koo, "A Cooperative Spectrum Sensing Method based on Eigenvalue and Superposition for Cognitive Radio Networks", The Journal of The Institute of Internet, Broadcasting and Communication, Vol. 13, No.4, pp 39-46, Aug 2013. DOI: http://dx.doi.org/10.7236/JIIBC.2013.13.4.39
  8. Thomas W. Rauber, Francisco de Assis Boldt and Flavio Miguel Varejao, "Heterogeneous Feature Models and Feature Selection Applied to Bearing Fault Diagnosis," IEEE Transaction on Industrial Electronics, Vol. 62, No. 1, pp. 637-646, Jan 2015. DOI: http://dx.doi.org/10.1109/TIE.2014.2327589
  9. Zi-Long Jiang, Qin-Yu Zhang, Ye Wang and Xue-Quan Shang, "Wavelet packet entropy based spectrum sensing in cognitive radio", Communication Software and Networks (ICCSN), pp. 293-298, 2011. DOI: http://dx.doi.org/10.1109/ICCSN.2011.6014054
  10. Yang-Seok Kim, Do-Hwan Lee and Seong-Kook Kim, "Fault Classification for Rotating Machinery Using Support Vector Machines with Optimal Features Corresponding to Each Fault Type", Transactions of the Korean Society of Mechanical Engineers A, Vol. 34 ,No. 11, pp.1681-1689, 2010. DOI: http://dx.doi.org/10.3795/KSME-A.2010.34.11. 1681
  11. Yang-Seok Kim, Do-Hwan Lee and Dae-Woong Kim, "Fault Severity Diagnosis of Ball Bearing by Support Vector Machine", Trans. Korean Soc. Mech. Eng. B, Vol. 37, No. 6, pp. 551-558, 2013 DOI: http://dx.doi.org/10.3795/KSME-B.2013.37.6.551
  12. Hyun-Suk Kang and Young-Seok Lee, "Support Vector Machines-based classification of video file fragments", Journal of the Korea Academia-Industrial cooperation Society, Vol. 15, No. 1, pp.652-657, 2015 DOI: https://doi.org/10.5762/KAIS.2015.16.1.652
  13. Jun Ma and Ye Li, "Soft Combination and Detection for Cooperative Spectrum Sensing in Cognitive Radio Networks", IEEE Transactions on Wireless Communications, Vol. 7, No. 11 ,pp. 4502-4507, Nov 2008. DOI: http://dx.doi.org/10.1109/T-WC.2008.070941