Search

This paper proposes a novel self-constructing least-Wilcoxon generalized Radial Basis Function Neural-Fuzzy System (LW-GRBFNFS) and its applications to non-linear function approximation and chaos time sequence prediction. In general, the hidden layer parameters of the antecedent part of most traditional RBFNFS are decided in advance and the output weights of the consequent part are evaluated by least square estimation. The hidden layer structure of the RBFNFS is lack of flexibility because the structure is fixed and cannot be adjusted effectively according to the dynamic behavior of the system. Furthermore, the resultant performance of using least square estimation for output weights is often weakened by the noise and outliers. This paper creates a self-constructing scenario for generating antecedent part of RBFNFS with particle swarm optimizer (PSO). For training the consequent part of RBFNFS, instead of traditional least square (LS) estimation, least-Wilcoxon (LW) norm is employed in the proposed approach to do the estimation. As is well known in statistics, the resulting linear function by using the rank-based LW norm approximation to linear function problems is usually robust against (or insensitive to) noises and outliers and therefore increases the accuracy of the output weights of RBFNFS. Several nonlinear functions approximation and chaotic time series prediction problems are used to verify the efficiency of self-constructing LW-GRBFNIS proposed in this paper. The experimental results show that the proposed method not only creates optimal hidden nodes but also effectively mitigates the noise and outliers problems.

This paper proposes an intelligent flight task algorithm for unmanned aerial vehicles (UAV) to effectively determine and search the best flight routes in three-dimensional and complicated topographies, where the topography data includes the height of the object on the earth and the aerial imagery map of the earth is obtained by the Satellite. The proposed method is composed mainly of the particle swarm optimizer (PSO), skeletonization, and B-spline curve. Skeletonization is regarded as a pre-processing procedure for topography data to reduce complexity of the searching space and inhibit aimless searches of solutions. B-spline curve method is adopted to provide a smooth flight route for UAV. The best control points of a B-spline curve are determined by PSO. In this paper, the initial population of PSO is acquired through skeletonization to improve the efficiency of the search for the best flight route. The results of the simulation demonstrate the abilities of the proposed method to provide the best flight routes efficiently for UAV.

Noise reduction without any prior knowledge of noise or signals is addressed in this study. Compared with conventional filters, wavelet shrinkage can respect this requirement to reduce noise from received signal in wavelet coefficients. However, wavelet threshold depends on an estimate of noise deviation and a weight relating signal's length cannot be applied in every case. This paper uses particle swarm optimization (PSO) to explore a suitable threshold in a complete solution space, named PSOShrink. A general-purpose objective function which is derived from blind signal separation (BSS) theory is further proposed. In simulation, four benchmarks signals and three degrading degrees are testing; meanwhile, three existing algorithm with state-of-the-art are performed for comparison. PSOShrink can not only recovers source signals from a heavy blurred signal but also remains details of a source signal from a light blurred signal; moreover, it performs outstanding denoising in every simulation case.

This paper proposes an improved multi-objective particle swarm optimizer with proportional distribution and jump improved operation, named PDJI-MOPSO, for dealing with multi-objective problems. PDJI-MOPSO maintains diversity of new found non-dominated solutions via proportional distribution, and combines advantages of wide-ranged exploration and extensive exploitations of PSO in the external repository with the jump improved operation to enhance the solution searching abilities of particles. Introduction of cluster and disturbance allows the proposed method to sift through representative non-dominated solutions from the external repository and prevent solutions from falling into local optimum. Experiments were conducted on eight common multi-objective benchmark problems. The results showed that the proposed method operates better in five performance metrics when solving these benchmark problems compared to three other related works.

In this paper, a sharing evolution genetic algorithms (SEGA) is proposed to solve various global numerical optimization problems. The SEGA employs a proposed population manager to preserve chromosomes which are superior and to eliminate those which are worse. The population manager also incorporates additional potential chromosomes to assist the solution exploration, controlled by the current solution searching status. The SEGA also uses the proposed sharing concepts for cross-over and mutation to prevent populations from falling into the local minimal, and allows GA to easier find or approach the global optimal solution. All the three parts in SEGA, including population manager, sharing cross-over and sharing mutation, can effective increase new born offspring's solution searching ability. Experiments were conducted on CEC-05 benchmark problems which included unimodal, multi-modal, expanded, and hybrid composition functions. The results showed that the SEGA displayed better performance when solving these benchmark problems compared to recent variants of the genetic algorithms.

A difficult blind source separation (BSS) issue dealing with an unknown and dynamic number of sources is tackled in this study. In the past, the majority of BSS algorithms familiarize themselves with situations where the numbers of sources are given, because the settings for the dimensions of the algorithm are dependent on this information. However, such an assumption could not be held in many advanced applications. Thus, this paper proposes the adaptive neural algorithm (ANA) which designs and associates several auto-adjust mechanisms to challenge these advanced BSS problems. The first implementation is the on-line estimator of source numbers improved from the cross-validation technique. The second is the adaptive structure neural network that combines feed-forward architecture and the self-organized criterion. The last is the learning rate adjustment in order to enhance efficiency of learning. The validity and performance of the proposed algorithm are demonstrated by computer simulations, and are compared to algorithms with state of the art. From the simulation results, these have been confirmed that the proposed ANA performed better separation than others in static BSS cases and is feasible for dynamic BSS cases.

This paper focuses on blind source separation with an unknown number of sources, which is the case generally assumed in most practical applications. Several over-determined neural algorithms (more sensors m than sources n) have been proposed to solve the problems associated with these cases, but separating performance is often sacrificed in order to prevent divergence. The general natural gradient descent can be validly applied to determined algorithms (m=n) only. Therefore, to better solve the problems, an algorithm associating the feed-forward neural network and an auto-trimming technique is proposed. The learning process starts with an over-determined architecture, followed by two steps used in every iteration. First, the number of sources is estimated by using the stability discriminant function, next, the neural network gradually trims redundant nodes according to an instant estimation. Validity and performance of the proposed approaches are demonstrated with computer simulations on artificially synthesized signals and compared with the well-known algorithm proposed by Ye et al.