Journal of the Korea Institute of Information and Communication Engineering (한국정보통신학회논문지)

The Korea Institute of Information and Commucation Engineering (한국정보통신학회)
권호 표지
DOI QR코드

DOI QR Code

Multiaspect-based Active Sonar Target Classification Using Deep Belief Network

DBN을 이용한 다중 방위 데이터 기반 능동소나 표적 식별

  • Kim, Dong-wook (School of Electronics Engineering, Kyungpook National University) ;
  • Bae, Keun-sung (School of Electronics Engineering, Kyungpook National University) ;
  • Seok, Jong-won (Department of Information and Communication, Changwon National University)
  • Received : 2018.01.08
  • Accepted : 2018.02.19
  • Published : 2018.03.28
Download PDF
⟨ Previous Next ⟩

Abstract

Detection and classification of underwater targets is an important issue for both military and non-military purposes. Recently, many performance improvements are being reported in the field of pattern recognition with the development of deep learning technology. Among the results, DBN showed good performance when used for pre-training of DNN. In this paper, DBN was used for the classification of underwater targets using active sonar, and the results are compared with that of the conventional BPNN. We synthesized active sonar target signals using 3-dimensional highlight model. Then, features were extracted based on FrFT. In the single aspect based experiment, the classification result using DBN was improved about 3.83% compared with the BPNN. In the case of multi-aspect based experiment, a performance of 95% or more is obtained when the number of observation sequence exceeds three.

수중 표적 탐지 및 식별은 군사 및 비군사적으로 중요한 문제이다. 최근 패턴인식 분야에서 딥러닝 기술이 발전되면서 많은 성능개선 결과가 발표되고 있다. 그중 DBN(Deep Belief Network)기법은 DNN(Deep Neural Network)을 사전 훈련하는데 사용되어 좋은 성능을 보여주고 있다. 본 논문에서는 능동 소나를 이용한 수중 표적의 식별 문제에 DBN을 사용하여 실험을 진행하고, 그 결과를 비교하였다. 표적신호는 3차원 하이라이트 모델을 사용하여 합성된 능동 소나 신호를 사용하였고, 특징추출 방법으로는 FrFT(Fractional Fourier Transform) 기반의 특징추출을 사용하였다. 단일 센서, 즉, 단일 방위 데이터 기반의 실험에서 DBN을 이용한 식별 결과는 기존의 BPNN(Back Propagation Neural Network)에 비해 약 3.83 % 향상되었다. 또한, 다중 방위 기반의 식별 실험에서는 관측열의 개수가 3을 초과하면 95% 이상의 성능을 얻을 수 있었다.

Keywords

References

  1. P. R. Runkle, P. K. Bharadwaj, L. Couchman, and L. Carin, "Hidden Markov models for multiaspect target classification," IEEE Transactions on Signal Processing, vol.47, no. 7, pp. 2035-2040, Jul. 1999. https://doi.org/10.1109/78.771050
  2. R. H. Huan, Y Pan. "Target recognition for multi-aspect SAR images with fusion strategies," Progress In Electromagnetics Research, vol. 134, pp. 267-288, Jan. 2013. https://doi.org/10.2528/PIER12100304
  3. D. P. Williams, E. Fakiris, "Exploiting environmental information for improved underwater target classification in sonar imagery," IEEE Transactions on Geoscience and Remote Sensing, vol. 52, no. 10, pp. 6284-6297, Oct. 2014. https://doi.org/10.1109/TGRS.2013.2295843
  4. J. Seok and K. Bae, "Target Classification Using Features Based on Fractional Fourier Transform," IEICE Transactions on Information and Systems, vol. E97.D, no. 9, pp. 2518-2521, Sep. 2014. https://doi.org/10.1587/transinf.2014EDL8003
  5. G. E. Hinton, S. Osindero, and Y.-W. Teh, "A fast learning algorithm for deep belief nets," Neural computation, vol. 18, no. 7, pp. 1527-1554, Jul. 2006. https://doi.org/10.1162/neco.2006.18.7.1527
  6. J. Baek, J. Seok, K. Bae, "Active sonar target detection using fractional fourier trasform," Journal of the Korea Institute of Information and Communication Engineering, vol. 20, no. 1, pp. 22-29, Jan. 2016. https://doi.org/10.6109/jkiice.2016.20.1.22
  7. D. MJ. Cowell, Steven Freear. "Separation of overlapping linear frequency modulated(LFM) signals using the fractional Fourier transform," IEEE Ttransactions on Ultrasonics, Ferroelectrics, and Frequency Control, vol.57, no.10, pp. 2324-2333, Sep. 2010. https://doi.org/10.1109/TUFFC.2010.1693
  8. H. Ozaktas, O. Arikan, M. Kutay, and G. Bozdagt, "Digital computation of the fractional Fourier transform," IEEE Trans. Signal Process, vol. 44, no. 9, pp. 2141-2150, Sep. 1996. https://doi.org/10.1109/78.536672
  9. LeCun, Yann, Yoshua Bengio, and Geoffrey Hinton. "Deep learning." Nature, vol. 521, no. 7553, pp. 436-444, May. 2015. https://doi.org/10.1038/nature14539
  10. J. Schmidhuber. "Deep learning in neural networks: An overview," Neural networks, vol. 61, pp. 85-117, Jan. 2015. https://doi.org/10.1016/j.neunet.2014.09.003
  11. J. Kim, K. Bhatele, "Recognition using Cyber bullying in view of Semantic-Enhanced Minimized Auto-Encoder", Asia-pacific Journal of Convergent Research Interchange, vol. 2, no. 4, pp. 7-14, Dec. 2016.