Journal of the Korea Institute of Military Science and Technology (한국군사과학기술학회지)

The Korea Institute of Military Science and Technology (한국군사과학기술학회)
권호 표지
DOI QR코드

DOI QR Code

Analysis of the Applicability of Blind Beamforming Techniques using Deep Neural Network to Defense Systems

심층신경망을 이용한 블라인드 빔포밍 기법의 방위산업 체계 적용가능성 분석

  • Jaehyuk Lim (Missile Research Institute, Agency for Defense Development) ;
  • Hogeun Yoo (Department of Computer Science and Engineering, Korea University) ;
  • Euihyuk Lee (Missile Research Institute, Agency for Defense Development) ;
  • Sunjin Oh (Missile Research Institute, Agency for Defense Development) ;
  • Sungkwon Kim (Missile Research Institute, Agency for Defense Development) ;
  • Daekyo Jeong (Missile Research Institute, Agency for Defense Development) ;
  • Jaehoon Lee (Department of Computer Science and Engineering, Korea University)
  • 임재혁 (국방과학연구소 미사일연구원) ;
  • 유호근 (고려대학교 컴퓨터학과) ;
  • 이의혁 (국방과학연구소 미사일연구원) ;
  • 오선진 (국방과학연구소 미사일연구원) ;
  • 김성권 (국방과학연구소 미사일연구원) ;
  • 정대교 (국방과학연구소 미사일연구원) ;
  • 이재훈 (고려대학교 컴퓨터학과)
  • Received : 2024.08.05
  • Accepted : 2024.11.29
  • Published : 2025.02.05
Download PDF
⟨ Previous Next ⟩

Abstract

This paper compares the performance of deep neural networks(DNN) applied to antenna arrays with different element counts(8, 16, 32). The DNNs were designed using fully connected(FC) layers, comprising input, hidden, and output layers. Each hidden layer includes a single FC layer and a rectified linear unit(ReLU) activation function. Results indicate that blind beamforming with DNNs performs well with fewer elements but degrades as the number of elements increases due to increased nonlinearity, complicating training. State-of-the-art defense radar systems require many array elements, making current research insufficient. To effectively apply DNN-based blind beamforming to these large arrays, further research is needed to address the signal-to-interference noise ratio(SINR) performance degradation associated with larger array elements.

Keywords

References

  1. Van Trees, Harry L., "Optimum array processing: Part IV of detection, estimation, and modulation theory," John Wiley & Sons, 2002.
  2. Ramezanpour, P., Rezaei, M. J., Mosavi, M. R., "Deep‐learning‐based beamforming for rejecting interferences," IET Signal Processing, Vol. 14, No. 7, pp. 467-473, 2020. https://doi.org/10.1049/iet-spr.2019.0495
  3. Ramezanpour, P., Mosavi, M. R., "Two-stage beamforming for rejecting interferences using deep neural networks," IEEE Systems Journal, Vol. 15, No. 3, pp. 4439-4447, 2020. https://doi.org/10.1109/JSYST.2020.3034957
  4. Kingma, D. P., Ba, J., "Adam: a method for stochastic optimization," Proc. of the 3rd Int. Conf. on Learning Representations(ICLR), San Diego, CA, USA, 2015.
  5. Sarevska, M., Salem, A. B. M., "Antenna array beamforming using neural network," World Academy of Science, Engineering and Technology, Vol. 24, pp. 115-119, 2006.
  6. Mallioras, I., Zaharis, Z. D., Lazaridis, P. I., Pantelopoulos, S., "A novel realistic approach of adaptive beamforming based on deep neural networks," IEEE Transactions on Antennas and Propagation, Vol. 70, No. 10, pp. 8833-8848, 2022. https://doi.org/10.1109/TAP.2022.3168708