Radar HRRP Target Recognition Based on Stacked Autoencoder and Extreme Learning Machine.

Feixiang Zhao,Zhongshuai Zhang,Shuanghui Zhang,Kai Huo,Yongxiang Liu

doi:10.3390/s18010173

Feixiang Zhao, Zhongshuai Zhang + Show 3 more

Open Access

https://doi.org/10.3390/s18010173

Copy DOI

Abstract

A novel radar high-resolution range profile (HRRP) target recognition method based on a stacked autoencoder (SAE) and extreme learning machine (ELM) is presented in this paper. As a key component of deep structure, the SAE does not only learn features by making use of data, it also obtains feature expressions at different levels of data. However, with the deep structure, it is hard to achieve good generalization performance with a fast learning speed. ELM, as a new learning algorithm for single hidden layer feedforward neural networks (SLFNs), has attracted great interest from various fields for its fast learning speed and good generalization performance. However, ELM needs more hidden nodes than conventional tuning-based learning algorithms due to the random set of input weights and hidden biases. In addition, the existing ELM methods cannot utilize the class information of targets well. To solve this problem, a regularized ELM method based on the class information of the target is proposed. In this paper, SAE and the regularized ELM are combined to make full use of their advantages and make up for each of their shortcomings. The effectiveness of the proposed method is demonstrated by experiments with measured radar HRRP data. The experimental results show that the proposed method can achieve good performance in the two aspects of real-time and accuracy, especially when only a few training samples are available.

Highlights

Radar target recognition based on high-resolution range profile (HRRP) has become a research hotspot due to the acquisition and processing of HRRP data being relatively easy [1,2,3,4,5,6,7]
(b) This paper proposes a combination of stacked autoencoder (SAE) and regularized extreme learning machine (ELM), which can improve the recognition performance by making full use of the advantages of SAE and ELM
Required to be fine-tuned, the proposed algorithm is faster than the other deep learning models (b) This paper proposes a combination of SAE and regularized ELM, which can improve the recognition performance by making full use of the advantages of SAE and ELM

Summary

Introduction

Radar target recognition based on high-resolution range profile (HRRP) has become a research hotspot due to the acquisition and processing of HRRP data being relatively easy [1,2,3,4,5,6,7]. In the non-cooperative situation, such as at the battle with time, the amount of data under the test is usually huge but the training data is limited. HRRP in each range cell [3], which represents the projection of the complex returns target returnedHRRP echoes the target ontosummations the radar ofline-of-sight (LOS). The canfrom be regarded as the scattering amplitude ofcenters the coherent the complex time returns from target scatters each range cella [3], which represents the in projection of Since the complex illustration of an HRRPinsample from plane target is shown Figure 1.

Results

Discussion

Conclusion