A new automatic target recognition system based on wavelet extreme learning machine

Abstract

In this paper, an automatic system is presented for target recognition using target echo signals of High Resolution Range (HRR) radars. This paper especially deals with combination of the feature extraction and classification from measured real target echo signal waveforms by using X-band pulse radar. The past studies in the field of radar target recognition have shown that the learning speed of feedforward neural networks is in general much slower than required and it has been a major disadvantage. There are two key reasons forth is status of feedforward neural networks: (1) the slow gradient-based learning algorithms are extensively used to train neural networks, and (2) all the parameters of the networks are tuned iteratively by using such learning algorithms (Feng, Huang, Lin, & Gay, 2009; Huang & Siew, 2004, 2005; Huang & Chen, 2007, 2008; Huang, Chen, & Slew, 2006; Huang, Ding, & Zhou, 2010; Huang, Zhu, & Slew, 2004; Huang, Liang, Rong, Saratchandran, & Sundararajan, 2005; Huang, Zhou, Ding, & Zhang, in press; Huang, Li, Chen, & Siew, 2008; Huang, Wang, & Lan, 2011; Huang et al., 2006; Huang, Zhu, & Siew, 2006a, 20066; Lan, Soh, & Huang, 2009; Li, Huang, Saratchandran, & Sundararajan, 2005; Liang, Huang, Saratchandran, & Sundararajan, 2006; Liang, Saratchandran, Huang, & Sundararajan, 2006; Rong, Huang, Saratchandran, & Sundararajan, 2009; Wang & Huang, 2005; Wang, Cao, & Yuan, 2011; Yeu, Lim, Huang, Agarwal, & Ong, 2006; Zhang, Huang, Sundararajan, & Saratchandran, 2007; Zhu, Qin, Suganthan, & Huang, 2005). To resolve these disadvantages of feedforward neural networks for automatic target recognition area in this paper suggested a new learning algorithm called extreme learning machine (ELM) for single-hidden layer feedforward neural networks (SLFNs) (Feng, Huang, Lin, & Gay, 2009; Huang & Siew, 2004, 2005; Huang & Chen, 2007, 2008; Huang, Chen, & Slew, 2006; Huang, Ding, & Zhou, 2010; Huang, Zhu, & Siew, 2004: Huang, Liang, Rong, Saratchandran, & Sundararajan, 2005; Huang, Zhou, Ding, & Zhang, in press; Huang, Li, Chen, & Slew, 2008; Huang, Wang, & Lan, 2011; Huang et al., 2006; Huang, Zhu, & Siew, 2006a, 2006b; Lan, Soh, & Huang, 2009; Li, Huang, Saratchandran, & Sundararajan, 2005; Liang, Huang, Saratchandran, & Sundararajan, 2006; Liang, Saratchandran, Huang, & Sundararajan, 2006; Rong, Huang, Saratchandran, & Sundararajan, 2009; Wang & Huang, 2005; Wang, Cao, & Yuan, 2011; Yeu, Lim, Huang, Agarwal, & Ong, 2006; Zhang, Huang, Sundararajan, & Saratchandran, 2007; Zhu, Qin, Suganthan, & Huang, 2005) which randomly choose hidden nodes and analytically determines the output weights of SLFNs. In theory, this algorithm tends to provide good generalization performance at extremely fast learning speed. Moreover, the Discrete Wavelet Transform (DWT) and wavelet entropy is used for adaptive feature extraction in the time-frequency domain in feature extraction stage to strengthen the premium features of the ELM in this study. The correct recognition performance of this new system is compared with feedforward neural networks. The experimental results show that the new algorithm can produce good generalization performance in most cases and can learn thousands of times faster than conventional popular learning algorithms for feedforward neural networks. (C) 2012 Elsevier Ltd. All rights reserved.