A Neural Network-Assisted Denoiser for Sparse Signals With Low Rank Property of Transformed Hankel Matrices

被引：0
作者：
Cho, Wanjei [1 ,2 ]
Kim, Seong-Cheol [1 ,2 ]
Lee, Woong-Hee [3 ]
机构：
[1] Seoul Natl Univ, Dept Elect & Comp Engn, Seoul 08826, South Korea
[2] Seoul Natl Univ, INMC, Seoul 08826, South Korea
[3] Dongguk Univ Seoul, Div Elect & Elect Engn, Seoul 04620, South Korea
来源：
IEEE ACCESS | 2024年 / 12卷
基金：
新加坡国家研究基金会;
关键词：
Noise reduction; Sparse matrices; Signal to noise ratio; Noise measurement; Vectors; Training; Signal denoising; Radar; Estimation; Artificial neural networks; sparse signals; neural networks; JOINT RANGE; DECOMPOSITION; SVD;
D O I：
10.1109/ACCESS.2024.3519580
中图分类号：
TP [自动化技术、计算机技术];
学科分类号：
0812 ;
摘要：
Designing a denoising framework for high-mobility environments is challenging due to the limited size of collected data and low latency requirements. In this paper, we introduce a neural network (NN)-assisted denoiser for sparse signals in the frequency domain, referred to as dssNET, based on the low-rank property of the transformed Hankel matrices constructed from sparse signals. The proposed method is based on optimizing the NN model by inputting singular values of the noisy transformed Hankel matrices and outputting the ground truth singular values. Furthermore, we additionally propose the advanced version of dssNET, referred to as selective dssNET (sdssNET), which can be operated more adaptively with the current signal-to-noise ratio (SNR). Notably, the proposed schemes show excellent denoising performance while requiring an extremely small training dataset compared to conventional schemes. Finally, we provide an application of joint-range-and-velocity estimation in automotive radar systems to validate the benefit of our proposed method in practical scenarios.
引用
收藏
页码：192990 / 193000
页数：11
相关论文
共 33 条
  • [21] Lu X., Tsao Y., Matsuda S., Hori C., Speech enhancement based on deep denoising autoencoder, Proc. Interspeech, pp. 436-440, (2013)
  • [22] Lee W.-H., Ozger M., Challita U., Sung K.W., Noise learningbased denoising autoencoder, IEEE Commun. Lett, 25, 9, pp. 2983-2987, (2021)
  • [23] Chatterjee S., Thakur R.S., Yadav R.N., Gupta L., Sparsitybased modified wavelet de-noising autoencoder for ECG signals, Signal Process, 198, (2022)
  • [24] Banerjee R., Mukherjee A., Ghose A., Noise cleaning of ECG on edge device using convolutional sparse contractive autoencoder, Proc. IEEE Int. Conf. Pervasive Comput. Commun. Workshops other Affiliated Events (PerCom Workshops), pp. 491-496, (2022)
  • [25] Oruc H., Phillips G.M., Explicit factorization of the Vandermonde matrix, Linear Algebra Appl, 315, 1-3, pp. 113-123, (2000)
  • [26] Hansen P.C., The truncated SVD as a method for regularization, BIT Numer. Math, 27, 4, pp. 534-553, (1987)
  • [27] Jokela M., Pyykonen P., Kutila M., Kauvo K., LiDAR performance review in Arctic conditions, Proc. IEEE 15th Int. Conf. Intell. Comput. Commun. Process. (ICCP), pp. 27-31, (2019)
  • [28] Zhao Z., Wang Z., Sun Y., Joint angle, range and velocity estimation for bi-static FDA-MIMO radar, Proc. IEEE 2nd Adv. Inf. Technol., Electron. Autom. Control Conf. (IAEAC), pp. 818-824, (2017)
  • [29] Zhang F., Zhang Z., Yu W., Truong T.-K., Joint range and velocity estimation with intrapulse and intersubcarrier Doppler effects for OFDM-based RadCom systems, IEEE Trans. Signal Process, 68, pp. 662-675, (2020)
  • [30] Xiong K., Cui G., Yu X., Wang S., Kong L., Joint estimation of target range and velocity for radar system via complex-valued kernel quasi- Newton method, IEEE Trans. Instrum. Meas, 71, pp. 1-13, (2022)
1234