Format

Send to

Choose Destination
Sensors (Basel). 2018 May 16;18(5). pii: E1585. doi: 10.3390/s18051585.

Attention-Based Recurrent Temporal Restricted Boltzmann Machine for Radar High Resolution Range Profile Sequence Recognition.

Author information

1
College of Electronic Science, National University of Defense Technology, Changsha 410073, China. zhangyifan16@nudt.edu.cn.
2
College of Electronic Science, National University of Defense Technology, Changsha 410073, China. gaoxunzhang@nudt.edu.cn.
3
College of Electronic Science, National University of Defense Technology, Changsha 410073, China. pengxuan@nudt.edu.cn.
4
College of Electronic Science, National University of Defense Technology, Changsha 410073, China. 18390906478@163.com.
5
College of Electronic Science, National University of Defense Technology, Changsha 410073, China. lixiang01@vip.sina.com.

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.

KEYWORDS:

HRRP; RATR; RTRBM; attention mechanism

Supplemental Content

Full text links

Icon for Multidisciplinary Digital Publishing Institute (MDPI) Icon for PubMed Central
Loading ...
Support Center