한국정보전자통신기술학회논문지 (The Journal of Korea Institute of Information, Electronics, and Communication Technology)

  • 제10권4호
  • /
  • Pages.257-267
  • /
  • 2017
  • /
  • 2005-081X(pISSN)
  • /
  • 2288-9302(eISSN)
한국정보전자통신기술학회 (Korea Information Electronic Communication Technology)
권호 표지
DOI QR코드

DOI QR Code

딥러닝 기술을 활용한 압축센싱 신호 복원방법 분석

Analysis of Signal Recovery for Compressed Sensing using Deep Learning Technique

  • Seong, Jin-Taek (Department of Information and Communication Engineering, Honam University)
  • 투고 : 2017.06.20
  • 심사 : 2017.07.04
  • 발행 : 2017.08.30
PDF 다운로드
⟨ 이전 논문 다음 논문 ⟩

초록

압축센싱(Compressed Sensing)은 선형 역문제(inverse problem)를 다루고 있으며, 그 이론적 연구결과는 관련 분야에 많은 영향을 주어 놀랄 만한 연구성과를 발표하였다. 그러나 압축센싱을 실제 환경에 적용하기 위해서는 두 가지 중요한 문제가 남아 있다. 하나는 실시간에 가까운 복원 성능이 보장되어야 하며, 다른 하나는 신호가 희소성을 갖도록 전처리가 가능해야 한다는 점이다. 이에 대한 문제들을 해결하고자 딥러닝(deep learning) 기술을 활용한 압축센싱 신호 복원방법이 최근에 등장하였다. 본 논문에서는 딥러닝 기반의 압축센싱 신호 복원방법을 고찰하고 최신 연구결과를 비교 분석하고자 한다. 관련 연구결과에서는 실시간에 가까운 복원 시간에 도달하였으며, 기존 복원방법 대비 더 우수한 복원 성능을 보여 주었다. 최근 연구에서 보여준 딥러닝을 활용한 압축센싱 신호 복원방법은 압축센싱의 활용가치를 더욱 높일 뿐만 아니라 신호처리와 통신분야에서 크게 활용될 수 있을 것으로 기대된다.

Compressed Sensing(CS) deals with linear inverse problems. The theoretical results of CS have had an impact on inference problems and presented amazing research achievements in the related fields including signal processing and information theory. However, in order for CS to be applied in practical environments, there are two significant challenges to be solved. One is to guarantee in real time recovery of CS signals, and the other is that the signals have to be sparse. To this end, the latest researches using deep learning technology have emerged. In this paper, we consider CS problems based on deep learning and discuss the latest research results. And the approaches for CS signal reconstruction using deep learning show superior results in terms of recovery time and performance. It is expected that the approaches for CS reconstruction using deep learning shown in recent studies can not only raise the possibility of utilization of CS, but also be highly exploited in the fields of signal processing and communication areas.

키워드

참고문헌

  1. D. L. Donoho, "Compressed Sensing," IEEE Tran. on Inf. Theory, vol. 52, no. 4, pp. 1289-1306, Apr. 2006. https://doi.org/10.1109/TIT.2006.871582
  2. C. A. Metzler, A. Maleki, and R. G. Baraniuk, "From Denoising to Compressed Sensing," IEEE Tran. on Inf. Theory, vol. 62, no. 9, pp. 5117-5144, Sep. 2016. https://doi.org/10.1109/TIT.2016.2556683
  3. Y. LeCun, Y. Bengio, and G. Hinton, "Deep Learning," Nature 521, pp. 436-444, 2015. https://doi.org/10.1038/nature14539
  4. A. Mousavi, A. B. Patel, R. G. Baraniuk, "A deep learning approach to structured signal recovery," 53rd Annual Allerton Conference on Communication, Control, and Computing, pp. 1226-1343, 2015.
  5. K. Kulkarni, S. Lohit, P. Turaga, R. Kerviche, A. Ashok, "ReconNet: Non-Iterative Reconstruction of Images from Compressively Sensed Measurements," IEEE Conference on Computer Vision and Pattern Recognition, pp. 449-458, 2016.
  6. A. Mousavi and R. G. Baraniuk, "Learning to invert: Signal recovery via deep convolutional networks," arXiv preprint arXiv:1701.03891, 2017.
  7. C. A. Metzler, A. Mousavi, R. G. Baraniuk, "Learned D-AMP: Principled Neural-Network- based Compressive Image Recovery," arXiv preprint arXiv:1704.06625, 2017.
  8. M. Borgerding, P. Schniter, and S. Rangan, "AMP-Inspired Deep Networks for Sparse Linear Inverse Problems," IEEE Trans. Sig. Processing, early access, May 2017.
  9. H. Palangi, R. Ward, and L. Deng, "Distributed Compressive Sensing: A Deep Learning Approach," IEEE Trans. Sig. Processing, vol. 64, no. 17, pp. 4504-4518, Sep. 2016. https://doi.org/10.1109/TSP.2016.2557301
  10. D. E. Rumelhart, G. Hinton and R. J. Williams, "Learning presentations by back-propagation errors," Nature 323, pp. 533-536, 1986. https://doi.org/10.1038/323533a0
  11. G. Hinton, S. Osinder, and Y. W. The, "A fast learning algorithm for deep belif nets," Neural computation, vol. 18, no. 7, pp. 1527-1554, Jul. 2006. https://doi.org/10.1162/neco.2006.18.7.1527
  12. A. Krizhevsky, I. Sutskever, and G. Hinton, "Imagenet classification with Deep Convolutional Neural Networks," Advances in Neural Information Processing Systems, pp. 1097-1105, Dec. 2012.
  13. N. Srivastava, G Hinton, A. Krizhevsky, "Dropout: A simple way to prevent neural networks from overfitting," The Journal of Machine Learning Research 15.1, pp. 1928-1958, 2014.
  14. C. Szegedy et al, "Going deeper with convolutions," CoRR, abs/1409.4842, 2014.
  15. K. He, X. Zhang, S. Ren, and J. Sun, "Deep Residual Learning for Image Recognition," IEEE International Conference on Computer Vision and Pattern Recognition, Nevada, USA, pp. 770-778, Nov. 2016.
  16. Y. Lecun, L. Bottou, Y. Bengio, P. Haffner, "Gradient-based learning applied to document recognition," Proceedings of the IEEE, vol. 86, no. 11, pp. 2278-2324, Nov. 1998. https://doi.org/10.1109/5.726791
  17. I. Goodfellow, Y. Bengio, and A. Courville, Deep Learning, The MIT Press, 2016.
  18. G. Dahl, T. Sainath, and G. Hinton, "Improving deep neural networks for LVCSR using rectified linear units and dropout," IEEE International Conference on Acoustics, Speech and Signal Processing(ICASSP), BC, Canada, pp. 8609-8613, 2013.
  19. D. L. Donoho and Y. Tsaig, "Fast Solution of L1-norm Minimization Problems When the Solutioni May Be Sparse," IEEE Trans. Info. Theory, vol. 54, no. 11, pp. 4789-4812, Nov. 2008. https://doi.org/10.1109/TIT.2008.929958
  20. A. Chambolle, R. A. DeVore, N. Lee, and B. J. Lucier, "Nonlinear wavelet image processing: Variational problems, compression, and noise removal through wavelet shrinkage," IEEE Trans. Image Process., vol. 7, no. 3, pp. 319-335, Mar. 1998. https://doi.org/10.1109/83.661182
  21. D. L. Donoho, A. Maleki, and A. Montanari, "Message passing algorithms for compressed sensing," Proc. Nat. Acad. Sci., vol. 106, pp. 18914-18919, Nov. 2009. https://doi.org/10.1073/pnas.0909892106
  22. Christopher A. Metzler, A. Maleki, and R. G. Baraniuk, "From Denoising to Compressed Sensing," IEEE Trans. Info. Theory, vol. 62, no. 9, pp. 5117-5144, Sep. 2016. https://doi.org/10.1109/TIT.2016.2556683
  23. C. Li, W. Yin, and Y. Zhang, "User's guide for tval3: TV minimization by augmented lagrangian and alternating direction algorithms," CAAM report, vol. 20, pp. 46-47, 2009.
  24. W. Dong et al, "Compressive Sensing via Nonloca Low-Rank Regularizatioin," IEEE Trans. Image Processing, vol. 23, no. 8, pp. 3618-3632, Aug. 2014. https://doi.org/10.1109/TIP.2014.2329449
  25. P. Schniter, S. Rangan, and A. Fletcher, "Vector approximate message passing for the generalized linear model," 2016 50th Asilomar Conference on Signals, Systems and Computers, CA, USA, Nov. 2016.
  26. E. J. Candes, J. Romberg, and T. Tao, "Robust uncertainty principles: Exact signal reconstruction from highly incomplete frequency information," IEEE Trans. Info. Theory, vol. 52, no. 2, pp. 489-509, Feb. 2006. https://doi.org/10.1109/TIT.2005.862083
  27. A. Mousavi, A. Maleki, R. G. Baraniuk, "Consistent parameter estimation for LASSO and approximate message passing," Annals of Statistics, 2017.

피인용 문헌

  1. 주성분 분석법을 이용한 회귀다항식 기반 모델 및 패턴 분류기 설계 vol.10, pp.6, 2017, https://doi.org/10.17661/jkiiect.2017.10.6.594
  2. 무인기 탑재 다중 센서 기반 국지 산불 감시 및 상황 대응 플랫폼 설계 및 구현 vol.10, pp.6, 2017, https://doi.org/10.17661/jkiiect.2017.10.6.626
  3. 로그 분석 처리율 향상을 위한 맵리듀스 기반 분할 빅데이터 분석 기법 vol.11, pp.5, 2017, https://doi.org/10.17661/jkiiect.2018.11.5.593