Radar Target Recognition Based on Kernel Projection Vector Space Using High-resolution Range Profile

Abstract

In this paper, a novel approach, namely kernel projection vector space (KPVS), is proposed for radar target recognition using high-resolution range profile (HRRP). First, the HRRP samples are mapped into a high-dimensional feature space using nonlinear mapping. Second, the kernel projection vectors, are obtained by kernel discriminant analysis. Then, for each class, the kernel projection vector space is formed using all the training kernel projection vectors of class. Finally, the minimum hyperplane distance classifier (MHDC) is used for classification. The aim of KPVS method is to represent the feature area of target using kernel projection vector space, and effectively measure the distance between the test HRRP and feature area via minimum hyperplane distance (MHD) metric. The experimental results of measured data show that the proposed method has better performance of recognition than KPCA and KFDA.

Fault Diagnosis of Variable Load Bearing Based on Quantum Chaotic Fruit Fly VMD and Variational RVM

“…In addition, the use of the probit model can also easily extend the binary classification to multiple classifications [43]. Compared with the multivariate logistic model [44], the multivariate probit model can also avoid complex approximate calculations, has more simple and practical characteristics, and can be well approximated to the logistic model. e experimental platform is shown in Figure 7; it uses bearing type 6203-2RS JEM SKF deep groove rolling bearing.…”

Space Precession Target Classification Based on Radar High-Resolution Range Profiles

“…There is no doubt that the importance of space target classification is becoming more and more significant. A number of researchers have carried out a lot of exploration on this problem [3][4][5][6][7][8], but it is still a quite difficult and challenging task. Various classification methods based on different features have been proposed under specific application scenarios and detection measures.…”

“…Various classification methods based on different features have been proposed under specific application scenarios and detection measures. The main features used by classification methods that have been widely studied and applied for space targets include radar high-resolution range profiles (HRRPs) [4,7,8], micromotion features [9,10], ISAR images [6], RCS features [11], and polarization features [12]. Space targets usually possess several complex micromotion forms such as spinning, rotation, tumbling, and precession, whereas discriminations generally exist in the micromotion parameters of different targets.…”

Multi‐scale feature‐based fuzzy‐support vector machine classification using radar range profiles

“…One focus on the research of the classification method, which evolves from the early template matching methods [3, 4] to the contemporary pattern recognition techniques such as machine learning [5, 6] and kernel theory [7, 8]. The second one puts efforts on the optimisation of range profiles’ imaging algorithm [9, 10], which aims at further enhancing range profiles’ quality and robustness in attitude and noise interference. The third research direction concentrates on the feature extraction of the range profile.…”