A Novel Radar HRRP Recognition Method with Accelerated T-Distributed Stochastic Neighbor Embedding and Density-Based Clustering
High-resolution range profile (HRRP) has attracted intensive attention from radar community because it is easy to acquire and analyze. However, most of the conventional algorithms require the prior information of targets, and they cannot process a large number of samples in real time. In this paper,...
Main Authors: | , , |
---|---|
Format: | Article |
Language: | English |
Published: |
MDPI AG
2019-11-01
|
Series: | Sensors |
Subjects: | |
Online Access: | https://www.mdpi.com/1424-8220/19/23/5112 |
_version_ | 1811212935297499136 |
---|---|
author | Hao Wu Dahai Dai Xuesong Wang |
author_facet | Hao Wu Dahai Dai Xuesong Wang |
author_sort | Hao Wu |
collection | DOAJ |
description | High-resolution range profile (HRRP) has attracted intensive attention from radar community because it is easy to acquire and analyze. However, most of the conventional algorithms require the prior information of targets, and they cannot process a large number of samples in real time. In this paper, a novel HRRP recognition method is proposed to classify unlabeled samples automatically where the number of categories is unknown. Firstly, with the preprocessing of HRRPs, we adopt principal component analysis (PCA) for dimensionality reduction of data. Afterwards, t-distributed stochastic neighbor embedding (t-SNE) with Barnes−Hut approximation is conducted for the visualization of high-dimensional data. It proves to reduce the dimensionality, which has significantly improved the computation speed. Finally, it is exhibited that the recognition performance with density-based clustering is superior to conventional algorithms under the condition of large azimuth angle ranges and low signal-to-noise ratio (SNR). |
first_indexed | 2024-04-12T05:37:53Z |
format | Article |
id | doaj.art-9ae7eba8a2f2489fb4561ea0bceea8ef |
institution | Directory Open Access Journal |
issn | 1424-8220 |
language | English |
last_indexed | 2024-04-12T05:37:53Z |
publishDate | 2019-11-01 |
publisher | MDPI AG |
record_format | Article |
series | Sensors |
spelling | doaj.art-9ae7eba8a2f2489fb4561ea0bceea8ef2022-12-22T03:45:46ZengMDPI AGSensors1424-82202019-11-011923511210.3390/s19235112s19235112A Novel Radar HRRP Recognition Method with Accelerated T-Distributed Stochastic Neighbor Embedding and Density-Based ClusteringHao Wu0Dahai Dai1Xuesong Wang2State Key Laboratory of Complex Electromagnetic Environment Effects on Electronics and Information System, National University of Defense Technology, Changsha 410073, ChinaState Key Laboratory of Complex Electromagnetic Environment Effects on Electronics and Information System, National University of Defense Technology, Changsha 410073, ChinaState Key Laboratory of Complex Electromagnetic Environment Effects on Electronics and Information System, National University of Defense Technology, Changsha 410073, ChinaHigh-resolution range profile (HRRP) has attracted intensive attention from radar community because it is easy to acquire and analyze. However, most of the conventional algorithms require the prior information of targets, and they cannot process a large number of samples in real time. In this paper, a novel HRRP recognition method is proposed to classify unlabeled samples automatically where the number of categories is unknown. Firstly, with the preprocessing of HRRPs, we adopt principal component analysis (PCA) for dimensionality reduction of data. Afterwards, t-distributed stochastic neighbor embedding (t-SNE) with Barnes−Hut approximation is conducted for the visualization of high-dimensional data. It proves to reduce the dimensionality, which has significantly improved the computation speed. Finally, it is exhibited that the recognition performance with density-based clustering is superior to conventional algorithms under the condition of large azimuth angle ranges and low signal-to-noise ratio (SNR).https://www.mdpi.com/1424-8220/19/23/5112radarhigh-resolution range profileprincipal component analysist-distributed stochastic neighbor embeddingdensity-based clustering |
spellingShingle | Hao Wu Dahai Dai Xuesong Wang A Novel Radar HRRP Recognition Method with Accelerated T-Distributed Stochastic Neighbor Embedding and Density-Based Clustering Sensors radar high-resolution range profile principal component analysis t-distributed stochastic neighbor embedding density-based clustering |
title | A Novel Radar HRRP Recognition Method with Accelerated T-Distributed Stochastic Neighbor Embedding and Density-Based Clustering |
title_full | A Novel Radar HRRP Recognition Method with Accelerated T-Distributed Stochastic Neighbor Embedding and Density-Based Clustering |
title_fullStr | A Novel Radar HRRP Recognition Method with Accelerated T-Distributed Stochastic Neighbor Embedding and Density-Based Clustering |
title_full_unstemmed | A Novel Radar HRRP Recognition Method with Accelerated T-Distributed Stochastic Neighbor Embedding and Density-Based Clustering |
title_short | A Novel Radar HRRP Recognition Method with Accelerated T-Distributed Stochastic Neighbor Embedding and Density-Based Clustering |
title_sort | novel radar hrrp recognition method with accelerated t distributed stochastic neighbor embedding and density based clustering |
topic | radar high-resolution range profile principal component analysis t-distributed stochastic neighbor embedding density-based clustering |
url | https://www.mdpi.com/1424-8220/19/23/5112 |
work_keys_str_mv | AT haowu anovelradarhrrprecognitionmethodwithacceleratedtdistributedstochasticneighborembeddinganddensitybasedclustering AT dahaidai anovelradarhrrprecognitionmethodwithacceleratedtdistributedstochasticneighborembeddinganddensitybasedclustering AT xuesongwang anovelradarhrrprecognitionmethodwithacceleratedtdistributedstochasticneighborembeddinganddensitybasedclustering AT haowu novelradarhrrprecognitionmethodwithacceleratedtdistributedstochasticneighborembeddinganddensitybasedclustering AT dahaidai novelradarhrrprecognitionmethodwithacceleratedtdistributedstochasticneighborembeddinganddensitybasedclustering AT xuesongwang novelradarhrrprecognitionmethodwithacceleratedtdistributedstochasticneighborembeddinganddensitybasedclustering |