Browsing by Author "Duh, FB"

Now showing 1 - 5 of 5

A neural fuzzy network for word information processing
(2002-04-01)
Lin, CT
;
Duh, FB
;
Liu, DJ
;
電控工程研究所
;
Institute of Electrical and Control Engineering
A neural fuzzy system learning with fuzzy training data is proposed in this study. The system is able to process and learn numerical information as well as word information. At first, we propose a basic structure of five-layered neural network for the connectionist realization of a fuzzy inference system. The connectionist structure can house fuzzy logic rules and membership functions for fuzzy inference. The inputs, outputs, and weights of the proposed network can be fuzzy numbers of any shape. Also they can be hybrid of fuzzy numbers and numerical numbers through the use of fuzzy singletons. Based on interval arithmetics, a fuzzy supervised learning algorithm is developed for the proposed system. It extends the normal supervised learning techniques to the learning problems where only word teaching signals are available. The fuzzy supervised learning scheme can train the proposed system with desired fuzzy input-output pairs. An experimental system is constructed to illustrate the performance and applicability of the proposed scheme. (C) 2002 Elsevier Science B.V. All rights reserved.
Application of neural fuzzy network to pulse compression with binary phase code
(2003)
Duh, FB
;
Juang, CF
;
Lin, CT
;
電控工程研究所
;
Institute of Electrical and Control Engineering
To solve the existing dilemma between making good range resolution and maintaining the low average transmitted power, it is necessary for the pulse compression processing to give low range sidelobes in the modern high-resolution radar systems. The traditional pulse compression algorithms based on 13-element Barker code such as direct autocorrelation filter (ACF), least squares (LS) inverse filter, and linear programming (LP) filter have been developed, and the neural network algorithms were issued recently. However, the traditional algorithms cannot achieve the requirement of high signal-to-sidelobe ratio, and the normal neural network such as backpropagation (BP) network usually produces the extra problems of low convergence speed and sensitive to the Doppler frequency shift. To overcome these defects, a new approach using a neural fuzzy network with binary phase code to deal with pulse compression in a radar system is presented in this paper. The 13-element Barker code used as the binary phase signal code is carried out by six-layer self-constructing neural fuzzy network (SONFIN) with supervised learning algorithm. Simulation results show that this neural fuzzy network pulse compression (NFNPC) algorithm has the significant advantages in noise rejection performance, range resolution ability and Doppler tolerance, which are superior to the traditional and BP algorithms, and has faster convergence speed than BP algorithm.
Radar tracking for a maneuvering target using neural fuzzy based Kalman filter
(2002)
Duh, FB
;
Lin, CT
;
電控工程研究所
;
Institute of Electrical and Control Engineering
A fast target maneuver detecting and highly accurate tracking technique using a neural fuzzy network based on Kalman filter is proposed in this paper. In the automatic target tracking system, there exists an important and difficult problem: how to detect the target maneuvers and fast response to avoid miss-tracking ? To solve this problem, neural network and fuzzy algorithms have been issued recently. However, the normal neural networks such as backpropagation networks usually produce the extra problems of low convergence speed and/or large network size, and the fuzzy algorithms are not easy to partition the parameters. To overcome these defects and to make use of neural learning ability, a developed standard Kalman filter with a self-constructing neural fuzzy inference network (KF-SONFIN) algorithm for target tracking is presented in this paper. Without having to change the structure of Kalman filter nor modeling the maneuvering target, SONFIN algorithm, can always find itself an economic network size with a fast learning process. Simulation results show that the KF-SONFIN is superior to the traditional IE and VDF methods in estimation accuracy.
Tracking a maneuvering target using neural fuzzy network
(2004-02-01)
Duh, FB
;
Lin, CT
;
電控工程研究所
;
Institute of Electrical and Control Engineering
A fast target maneuver detecting and highly accurate tracking technique using a neural fuzzy network based on Kalman filter is proposed in this paper. In the automatic target tracking system, there exists an important and difficult problem: how to detect the target maneuvers and fast response to avoid misstracking? The traditional maneuver detection algorithms, such as variable dimension filter (VDF) and input estimation (IE) etc., are computation intensive and difficult to implement in real time. To solve this problem, neural network algorithms have been issued recently. However, the normal neural networks such as backpropagation networks usually produce the extra problems of low convergence speed and/or large network size. Furthermore, the way to decide the network structure is heuristic. To overcome these defects and to make use of neural learning ability, a developed standard Kalman filter with a self-constructing neural fuzzy inference network (KF-SONFIN) algorithm for target tracking is presented in this paper. By generating possible target trajectories including maneuver information to train the SONFIN, the trained SONFIN can detect when the maneuver occurred, the magnitude of maneuver values and when the maneuver disappeared. Without having to change the structure of Kalman filter nor modeling the maneuvering target, this new algorithm, SONFIN, can always find itself an economic network size with a fast learning process. Simulation results show that the KF-SONFIN is superior to the traditional IE and VDF methods in estimation accuracy.
Tracking a maneuvering target using neural fuzzy network
(2001)
Duh, FB
;
Lin, CT
;
電控工程研究所
;
Institute of Electrical and Control Engineering
A fast target maneuver detecting and highly accurate tracking technique using a neural fuzzy network based on Kalman filter is proposed in this paper. In the automatic target tracking system, there exists an important and difficult problem: how to detect the target maneuvers and fast response to avoid miss-tracking ? To solve this problem, neural network and fuzzy algorithms have been issued recently. However, the normal neural networks such as backpropagation networks usually produce the extra problems of low convergence speed and/or large network size, and the fuzzy algorithms are not easy to partition the parameters. To overcome these defects and to make use of neural learning ability, a developed standard Kalman filter with a self-constructing neural fuzzy inference network (KF-SONFIN) algorithm for target tracking is presented in this paper. Without having to change the structure of Kalman filter nor modeling the maneuvering target, SONFIN algorithm, can always find itself an economic network size with a fast learning process. Simulation results show that the KF-SONFIN is superior to the traditional IE and VDF methods in estimation accuracy.