The Journal of Korean Institute of Information Technology (한국정보기술학회논문지)

Korean Institute of Information Technology (한국정보기술학회)
권호 표지
DOI QR코드

DOI QR Code

The Estimation of the Target Position and Size Using Multi-layer Neural Network in Electrical Impedance Tomography

전기 임피던스 단층촬영법에서 다층 신경회로망을 이용한 표적의 위치와 크기 추정

  • 김지훈 (경북대학교 IT대학 전자공학부) ;
  • 김찬용 (경북대학교 IT대학 전자공학부) ;
  • 조태현 (경북대학교, 대학원 전자공학과) ;
  • 이인수 (경북대학교 IT대학 전자공학부)
  • Received : 2018.09.05
  • Accepted : 2018.10.14
  • Published : 2018.11.30
⟨ Previous Next ⟩

Abstract

Electrical impedance tomography (EIT) is a kind of nondestructive testing technique that obtains the internal resistivity distribution from the voltages measured at the electrodes located outside the area of interest. However, an image reconstruction problem in EIT has innate non-linearity and ill-posedness, so that it is difficult to obtain satisfactory reconstructed results. In general, a neural network can efficiently model the input and output relationships of a non-linear system. This paper proposes a method for estimating the position and size of a circular target using a multi-layer neural network. To verify the performance of the proposed method, neural network was trained and various computer simulations were performed and satisfactory performance was verified.

전기 임피던스 단층촬영법 (EIT, electrical impedance tomography)은 비파괴검사의 일종으로 관심영역 외부에 설치된 전극에서 측정된 전압으로부터 내부의 저항률분포를 얻는 기술이다. 그러나 EIT에서 영상복원은 타고난 비선형성 (non-linearity)과 부정치성 (ill-posedness) 때문에 만족할만한 복원결과를 얻기 어렵다. 일반적으로 신경회로망은 비선형 시스템의 입력 및 출력 관계를 효율적으로 모델링 할 수 있다. 이 논문은 다층 신경회로망을 이용하여 원형인 표적의 위치(중심좌표)와 크기(반지름)를 추정하는 방법을 제안한다. 제안한 방법의 성능을 알아보기 위해, 신경회로망을 학습시키고 다양한 컴퓨터 모의실험을 수행하였고 결과로부터 제안한 방법의 만족할만한 추정성능을 확인할 수 있었다.

Keywords

References

  1. D. S. Holder, "Electrical Impedance Tomography: Methods", History and Applications. London, U.K.: Institute of Physics Publishing, 2005.
  2. J. G. Webster, "Electrical Impedance Tomography", Bristol, U.K. Adam Hilger, 1990.
  3. J. H. Kim, B. S. Kim, C. Y. Kim, K. Y. Kim, and I. S. Lee, "Dynamic Directional Algebraic Reconstruction Technique for Time-Varying Imaging in Electrical Impedance Tomography", J. KIIT, Vol. 13, No. 10, pp. 1-8, Oct. 2015.
  4. J. Johnson and P. Picton, "Concepts in artificial intelligence", Butterworth-Heinemann LTD, Ch(4): pp. 95-96, 1995.
  5. M. J. Willis, G. A. Montague, C. D. Massimo, M. T. Tham, and A. J. Morris, "Artificial neural networks in process estimation and control", Automatica, Vol. 28, No. 6, pp. 1181-1187, Nov. 1992. https://doi.org/10.1016/0005-1098(92)90059-O
  6. S. Bhama and H. Singh, "Single layer neural networks for linear system identification using gradient descent technique", IEEE Trans. Neural Networks, Vol. 4, No. 5, pp. 884-888, Sep. 1993. https://doi.org/10.1109/72.248467
  7. S. C, Lim and G. W. Jin, "Alternative tactile sensor for measuring rehabilitation study using to neural network", Journal of IIBC, Vol. 12, No. 4, pp. 23-29, Aug. 2012.
  8. J. Schurmann, "Pattern classification : a unified view of statistical and neural approaches", John Wiley and Sons, New York, 1996.
  9. T. Kohonen, "Self-Organizing Maps", Springer, Berlin, 1997.
  10. L. Fausett, "Fundamentals of neural networks : architectures, algorithms, and applications", Prentice Hall, 1994.
  11. C. C. Yang, S. O. Prasher, R. Lacroix, S. Sreekanth, N. K. Patni, and L. Masse, "Artificial neural network model for subsurface-drained farmlands", J. Irrig. Drain Eng., Vol. 123, No. 4, pp. 285-292, Jul. 1997. https://doi.org/10.1061/(ASCE)0733-9437(1997)123:4(285)
  12. C. C. Yang, S. O. Prasher, and G. R. Mehuys, "An artificial neural network to estimate soil temperature", Can. J. Soil Sci., Vol. 77, No. 3, pp. 421-429, Aug. 1997. https://doi.org/10.4141/S96-062
  13. A. Adler and R. Guardo, "A neural network image reconstruction technique for electrical impedance tomography", IEEE Trans. Med. Imag., Vol. 13, No. 4, pp. 594-600, Dec. 1994. https://doi.org/10.1109/42.363109
  14. V. Kolehmainen, A. Voutilainen, and J. P. Kaipio, "Estimation of non-stationary region boundaries in EIT-state estimation approach", Inv. Prob., Vol. 17, No. 6, pp. 1937-1956, Nov. 2001. https://doi.org/10.1088/0266-5611/17/6/324
  15. E. Somersalo, M. Cheney, and D. Isaacson, "Existence and uniqueness for electrode models for electric current computed tomography", SIAM J. Appl. Math., Vol. 52, No. 4, pp. 1023-1040, Aug. 1992. https://doi.org/10.1137/0152060
  16. T. F. Schuessler and J. H. Bates, "Current patterns and electrode types for single-source electrical impedance tomography of the thorax", Ann. Biomed. Eng., Vol. 26, No. 2, pp. 253-259, Mar. 1998. https://doi.org/10.1114/1.116
  17. D. E. Rumelhart and J. L. McClelland, "Parallel distributed processing: explorations in the microstructure of cognition. Vol. 1: Foundations", MIT Press, Cambridge, MA, 1986.
  18. M. F. Moller, "A Scaled Conjugate Gradient Algorithm for Fast Supervised Learning", Neural Netw., Vol. 6, No. 4, pp. 525-533, May 1993. https://doi.org/10.1016/S0893-6080(05)80056-5
  19. C. B. Khadse, M. A. Chaudhari, and V. B. Borghate, "Electromagnetic compatibility estimator using scaled conjugate gradient backpropagation based artificial neural network", IEEE Trans. Ind. Informat., Vol. 13, No. 3, pp. 1036-1045, Jun. 2017. https://doi.org/10.1109/TII.2016.2605623
  20. T. J. Yorkey, J. G. Webster, and W. J. Tompkins, "Comparing reconstruction algorithms for electrical impedance tomography", IEEE Trans. Biomed. Eng., Vol. BME-34, No. 11, pp. 843-852, Nov. 1987. https://doi.org/10.1109/TBME.1987.326032