An effective ensemble should consist of a set of networks that are both accurate and diverse. We propose a novel clustering-based selective algorithm for constructing neural network ensemble, where clustering technology is used to classify trained networks according to similarity and optimally select the most accurate individual network from each cluster to make up the ensemble. Empirical studies on regression of four typical datasets showed that this approach yields significantly smaller ensemble achieving better performance than other traditional ones such as Bagging and Boosting. The bias variance decomposition of the predictive error shows that the success of the proposed approach may lie in its properly tuning the bias/variance trade-off to reduce the prediction error (the sum of bias² and variance).

A multi-objective particle swarm optimization (MOPSO) approach for multi-objective economic load dispatch problem in power system is presented in this paper. The economic load dispatch problem is a non-linear constrained multi-objective optimization problem. The proposed MOPSO approach handles the problem as a multi-objective problem with competing and non-commensurable fuel cost, emission and system loss objectives and has a diversity-preserving mechanism using an external memory (call 鈥渞epository鈥? and a geographically-based approach to find widely different Pareto-optimal solutions. In addition, fuzzy set theory is employed to extract the best compromise solution. Several optimization runs of the proposed MOPSO approach were carried out on the standard IEEE 30-bus test system. The results revealed the capabilities of the proposed MOPSO approach to generate well-distributed Pareto-optimal non-dominated solutions of multi-objective economic load dispatch. Comparison with Multi-objective Evolutionary Algorithm (MOEA) showed the superiority of the proposed MOPSO approach and confirmed its potential for solving multi-objective economic load dispatch.

An information model is defined to support sharing scientific information on Web for archaeological pottery. Apart from non-shape information, such as age, material, etc., the model also consists of shape information and shape feature information. Shape information is collected by Lasers Scanner and geometric modelling techniques. Feature information is generated from shape information via feature extracting techniques. The model is used in an integrated storage, archival, and sketch-based query and retrieval system for 3D objects, native American ceramic vessels. A novel aspect of the information model is that it is totally implemented with XML, and is designed for Web-based visual query and storage application.

This paper presents an automatic non-photorealistic rendering approach to generating technical illustration from 3D models. It first decomposes the 3D object into a set of CSG primitives, and then performs the hidden surface removal based on the prioritized list, in which the rendition order of CSG primitives is sorted out by depth. Then, each primitive is illustrated by the pre-defined empirical lighting model, and the system mimics the stroke-drawing by user-specified style. In order to artistically and flexibly modulate the illumination, the empirical lighting model is defined by three major components: parameters of multi-level lighting intensities, parametric spatial occupations for each lighting level, and an interpolation method to calculate the lighting distribution over primitives. The stylized illustration is simulated by a grid-based method, in which we ‘fill’ the desirable pictorial units into the spatial occupation of CSG primitives, instead of “pixel-by-pixel” painting. This region-by-region shading facilitates the simulation of illustration styles.

Based on the framework of evidence theory, data fusion aims at obtaining a single Basic Probability Assignment (BPA) function by combining several belief functions from distinct information sources. Dempster’s rule of combination is the most popular rule of combinations, but it is a poor solution for the management of the conflict between various information sources at the normalization step. Even when it faces high conflict information, the classical Dempster-Shafer’s (D-S) evidence theory can involve counter-intuitive results. This paper presents a modified averaging method to combine conflicting evidence based on the distance of evidences; and also gives the weighted average of the evidence in the system. Numerical examples showed that the proposed method can realize the modification ideas and also will provide reasonable results with good convergence efficiency.