Journal of Advanced Navigation Technology (한국항행학회논문지)

The Korean Navigation Institute (한국항행학회)
권호 표지
DOI QR코드

DOI QR Code

Three Stage Neural Networks for Direction of Arrival Estimation

도래각 추정을 위한 3단계 인공신경망 알고리듬

  • Park, Sun-bae (Department of Electronic and Electrical Engineering, Hongik University) ;
  • Yoo, Do-sik (Department of Electronic and Electrical Engineering, Hongik University)
  • 박선배 (홍익대학교 전자전기공학과) ;
  • 유도식 (홍익대학교 전자전기공학과)
  • Received : 2020.02.03
  • Accepted : 2020.02.25
  • Published : 2020.02.28
Download PDF
⟨ Previous Next ⟩

Abstract

Direction of arrival (DoA) estimation is a scheme of estimating the directions of targets by analyzing signals generated or reflected from the targets and is used in various fields. Artificial neural networks (ANN) is a field of machine learning that mimics the neural network of living organisms. They show good performance in pattern recognition. Although researches has been using ANNs to estimate the DoAs, there are limitationsin dealing with variations of the signal-to-noise ratio (SNR) of the target signals. In this paper, we propose a three-stage ANN algorithm for DoA estimation. The proposed algorithm can minimize the performance reduction by applying the model trained in a single SNR environment to various environments through a 'noise reduction process'. Furthermore, the scheme reduces the difficulty in learning and maintains efficiency in estimation, by employing a process of DoA shift. We compare the performance of the proposed algorithm with Cramer-Rao bound (CRB) and the performances of existing subspace-based algorithms and show that the proposed scheme exhibits better performance than other schemes in some severe environments such as low SNR environments or situations in which targets are located very close to each other.

도래각추정은 표적으로부터 생성, 혹은 반사된 신호를 분석하여 표적의 방향을 추정하는 것으로 다양한 분야에 활용되고 있다. 인공신경망은 생물의 신경망을 모방한 기계학습의 한 분야로 패턴인식에서 좋은 성능을 보인다. 이러한 인공신경망을 도래각 추정에 활용하는 연구가 진행되어왔으나, 다양한 신호대잡음비 환경에 대응하는데에 제한이 있는 상황이다. 본 논문에서는 도래각 추정을 위한 3단계 인공신경망 알고리듬을 제안한다. 제안하는 알고리듬은 잡음제거과정을 통해 단일 신호대잡음비 환경에서 학습한 모델을 다양한 환경에 적용해도 성능감소를 최소화할 수 있다. 또한 도래각 시프트 과정을 통해 학습 난이도를 낮출 수 있고 효율적인 추정이 가능하다. 우리는, 제안하는 알고리듬과 다른 부공간 기법, Cramer-Rao bound (CRB)와의 성능 비교를 통해 제안하는 알고리듬이 낮은 신호대잡음비 환경, 표적들의 도래각이 가까운 환경 등 특정한 열악한 관측환경에서 타 기법에 비해 좋은 성능을 보이는 것을 확인하였다.

Keywords

References

  1. P. Stoica, and R. L. Moses, Spectral Analysis of Signals, Upper Saddle River, NJ: Prentice-Hall, ch. 6, pp. 263-273, 2005.
  2. R. Schmidt, “Multiple emitter location and signal parameter estimation,” IEEE Transactions on Antennas and Propagation, Vol. 34, No. 3, pp. 276-280, Mar. 1986. https://doi.org/10.1109/TAP.1986.1143830
  3. R. Roy, and T. Kailath, "ESPRIT-estimation of signal parameters via rotational invariance techniques," IEEE Transactions on Acoustics, Speech, and Signal Processing, Vol. 37, No. 7, pp. 984.995, Jul. 1989. https://doi.org/10.1109/29.32276
  4. J. Xin, and A. Sano, “Computationally efficient subspace-based method for direction-of-arrival estimation without eigendecomposition,” IEEE Transactions on Signal Processing, Vol. 52, No. 4, pp. 876-893, Apr. 2004. https://doi.org/10.1109/TSP.2004.823469
  5. B. G. Byun, and D. S. Yoo, “Improved direction of arrival estimation based on coprime array and propagator method by noise power spectral density estimation,” The Journal of Korea Navigation Institute, Vol. 20, No. 4, pp. 367-373, Aug, 2017.
  6. D. S. Yoo, "A low complexity subspace-Based DOA estimation algorithm with uniform linear array correlation matrix subsampling," International Journal of Antennas and Propagation, Vol. 2015, Article ID. 323545, pp. 1-10, Nov, 2015. https://doi.org/10.1155/2015/323545
  7. L. Deng, “A tutorial survey of architectures algorithms and applications for deep learning,” APSIPA Transactions on Signal and Information Processing, Vol. 3, No. 2, pp. 1-29, Jan. 2014. https://doi.org/10.1017/ATSIP.2013.8
  8. S. Mishra, R. Yadav, and R. Singh, "A survey on applications of multi layer perceptron neural networks in DOA estimation for smart antennas,", International Journal of Computer Applications, Vol. 83, No. 17, pp. 22-28, Dec. 2013. https://doi.org/10.5120/14670-2998
  9. M. K. Cho, D. H. Lee, S. Y. Baek, "Performance evaluation and system implementation of a radio-wave direction finding system based on neural networks,", The Journal of Korean Institute of Communication and Information Science, Vol. 42, No. 10, pp. 1896-1903, Oct. 2017. https://doi.org/10.7840/kics.2017.42.10.1896
  10. P. Stoica, and A. Nehorai, "Performance study of conditional and unconditional direction-of-arrival estimation," IEEE Transactions on Acoustics, Speech, and Signal Processing, Vol. 38, No. 10, pp. 1783-1795, Oct. 1990. https://doi.org/10.1109/29.60109
  11. M. Abadi, A. Agarwal, B. Paul, et al. (2016, Mar). Tensorflow: large-scale machine learning on heterogeneous distributed systems. Available: https://arxiv.org/abs/1603.04467.