Improving performance in pulse radar detection using neural networks

Rao, K. Deergha; Sridhar, G.

doi:10.1109/7.395219

Cited by 28 publications

(10 citation statements)

References 4 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…This property was first exploited in [5], and subsequently by several researchers [6]- [10]. The objective in these papers is to make the ANN approximate an ideal autocorrelation sequence; i.e., peak when the autocorrelation lag is zero, and zero elsewhere.…”

Section: Introductionmentioning

confidence: 99%

A Novel Application of Support Vector Machines to Detect Targets

Padaki¹,

George

2010

2010 Second International Conference on Computational Intelligence, Modelling and Simulation

View full text Add to dashboard Cite

In this paper we develop a novel pulse radar detection scheme using Support Vector Machines (SVMs). SVMs are a powerful tool for pattern classification. Exploiting this, we design a SVM for pulse radar detection of targets embedded in noise. An adaptive pre-processing stage is included when the echoes are very weak. It is observed that the signal-to-sidelobe ratio obtained is much higher compared to neural network based pulse radar detection schemes. We further examine the noise tolerance, range resolution ability and Doppler tolerance of the new algorithm for pulse compression, and compare it with the ones available in literature.

show abstract

Section: Introductionmentioning

confidence: 99%

A Novel Application of Support Vector Machines to Detect Targets

Padaki¹,

George

2010

2010 Second International Conference on Computational Intelligence, Modelling and Simulation

View full text Add to dashboard Cite

show abstract

“…Kwan and Lee [15] have employed a backpropagation (BP) algorithm to realize pulse compression with a phase-coded waveform, and obtained a good result. But the convergence speed of the BP algorithm is inherently low [16] and sensitive to the Doppler frequency shift. To cope with the drawbacks, a novel solution to the problem of pulse compression has been proposed in this work.…”

Section: Introductionmentioning

confidence: 99%

“…Hua et al [13] tried to combine the advantages of Rihaczek's matched filter [14] and Zoraster's linear programming methods to obtain a new Barker code sidelobe suppression algorithm. Recently, neural networks applied to pulse compression were proposed with their learning capabilities [15], [16]. Kwan and Lee [15] have employed a backpropagation (BP) algorithm to realize pulse compression with a phase-coded waveform, and obtained a good result.…”

Section: Introductionmentioning

confidence: 99%

A Neural Fuzzy Network Approach to Radar Pulse Compression

Duh

Juang²,

Lin³

2004

IEEE Geosci. Remote Sensing Lett.

View full text Add to dashboard Cite

To make good range resolution and accuracy compatible with a high detection capability while maintaining the low average transmitted power, pulse compression processing giving low-range sidelobes is necessary. The traditional algorithms such as the direct autocorrelation filter (ACF), least squares (LS) inverse filter, and linear programming (LP) filter based on three-element Barker code (B13 code) have been developed. Recently, the neural network algorithms were issued. However, the traditional algorithms cannot achieve the requirements of high signal-to-sidelobe ratio and low integrated sidelobe level (ISL), and the normal neural networks such as the backpropagation (BP) network usually produce the extra problems of low convergence speed and are sensitive to the Doppler frequency shift. To overcome these defects, a new approach using a neural fuzzy network to deal with pulse compression in a radar system is presented. Two different Barker codes are carried out by a six-layer self-constructing neural fuzzy network (SONFIN). Simulation results show that this neural fuzzy network pulse compression (NFNPC) algorithm has significant advantages in noise rejection performance, range resolution ability, and Doppler tolerance, which are superior to the traditional and BP algorithms

show abstract

“…There have been some methods [6], [7], [8], [9], [10], [11] proposed to choose SWs for data communication systems. It can be classified as: (1) Adopting specific kinds of codes as SW, for example M-sequence codes, Barker codes, etc.…”

Section: Introductionmentioning

confidence: 99%

“…It can be classified as: (1) Adopting specific kinds of codes as SW, for example M-sequence codes, Barker codes, etc. [6], [7].…”

Section: Introductionmentioning

confidence: 99%

Fast Selecting Optimal Sync Word Based on Filtering and Backtracking for Burst Synchronization

Liang

Ding

et al. 2006

2006 8th International Conference on Signal Processing

View full text Add to dashboard Cite

The frame sync word (SW) is very important for burst data communication systems. Commonly used SWs such as Msequences are not optimized for specific system environments in terms of misdetection (including false alarm and detection failure) probability. In this paper, both upper boundary and lower boundary of misdetection probability of frame synchronization are derived for given length and pattern of the preamble, length of SW and BER of channel. Based on the proposed boundaries, filtering out the SWs impossible to be optimal. And then, a backtracking full searching algorithm is used on the resulting SWs to select the optimal ones. Numerical results show that the Filtering and Backtracking Full Search Algorithm (FBFSA) is very efficient and flexible.

show abstract

Improving performance in pulse radar detection using neural networks

Cited by 28 publications

References 4 publications

A Novel Application of Support Vector Machines to Detect Targets

A Novel Application of Support Vector Machines to Detect Targets

A Neural Fuzzy Network Approach to Radar Pulse Compression

Fast Selecting Optimal Sync Word Based on Filtering and Backtracking for Burst Synchronization

Contact Info

Product

Resources

About