Abstract

The High Resolution Range Profile (HRRP) recognition has attracted great concern in the field of Radar Automatic Target Recognition (RATR). However, traditional HRRP recognition methods failed to model high dimensional sequential data efficiently and have a poor anti-noise ability. To deal with these problems, a novel stochastic neural network model named Attention-based Recurrent Temporal Restricted Boltzmann Machine (ARTRBM) is proposed in this paper. RTRBM is utilized to extract discriminative features and the attention mechanism is adopted to select major features. RTRBM is efficient to model high dimensional HRRP sequences because it can extract the information of temporal and spatial correlation between adjacent HRRPs. The attention mechanism is used in sequential data recognition tasks including machine translation and relation classification, which makes the model pay more attention to the major features of recognition. Therefore, the combination of RTRBM and the attention mechanism makes our model effective for extracting more internal related features and choose the important parts of the extracted features. Additionally, the model performs well with the noise corrupted HRRP data. Experimental results on the Moving and Stationary Target Acquisition and Recognition (MSTAR) dataset show that our proposed model outperforms other traditional methods, which indicates that ARTRBM extracts, selects, and utilizes the correlation information between adjacent HRRPs effectively and is suitable for high dimensional data or noise corrupted data.

Highlights

  • A high-resolution range profile (HRRP) is the amplitude of the coherent summations of the complex time returns from target scatters in each range cell, which represents the projection of the complex returned echoes from the target scattering centers on to the radar line-of-sight (LOS) [1].The HRRP recognition has been studied for decades in the field of Radar Automatic Target Recognition (RATR) because it contains important structural information such as the target size and the distribution of scattering points [1,2,3,4]

  • Experimental results on the Moving and Stationary Target Acquisition and Recognition (MSTAR) dataset show that our proposed model outperforms other traditional methods, which indicates that Attention-based Recurrent Temporal Restricted Boltzmann Machine (ARTRBM) extracts, selects, and utilizes the correlation information between adjacent HRRPs effectively and is suitable for high dimensional data or noise corrupted data

  • Restricted Boltzmann Machine (RTRBM) model with contrast models on different hidden layer sizes while the second is to investigate whether the attention mechanism really works and how much effect it has on performance

Read more

Summary

Introduction

A high-resolution range profile (HRRP) is the amplitude of the coherent summations of the complex time returns from target scatters in each range cell, which represents the projection of the complex returned echoes from the target scattering centers on to the radar line-of-sight (LOS) [1]. Machine (RBM) learning, the Recurrent Temporal Restricted Boltzmann Machine (RTRBM) has been proposed as a generative model for high dimensional sequences [19,20,21,22,23,24]. In order to solve the problems which have been put forward, a new method that combines the RTRBM model with the attention mechanism [29] for sequential radar HRRP recognition is proposed in this paper. The attention mechanism was first proposed in the field of the visual image in Reference [30] and has shown good performance on a range of tasks including machine translation, machine comprehension, and Relation classification [31,32,33,34,35,36] It is theoretically possible for HRRP sequence recognition when utilizing the attention mechanism. Briefly and give preliminaries about Recurrent Temporal Restricted Boltzmann Machine (RTRBM), which is a temporal extension of RBMs

Restricted
Recurrent
The Proposed Model
Learning the Parameters of the Model
Experiments
The Sensors
The composition thesequential sequential
Experiment 1
Methods
Experiment 2
10. Testing different
Findings
Conclusions

Talk to us

Join us for a 30 min session where you can share your feedback and ask us any queries you have

Schedule a call

Disclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.