Neural Computing and Applications

, Volume 18, Issue 5, pp 407–408 | Cite as

Editorial to special issue: computational intelligence for optimization, modeling and control

Editorial

The Fifth International Symposium on Neural Networks (ISNN’08) was held in Beijing, China, between September 24 and 28, 2008.

The ISNN’08 was a great success and covered broad topics of neural network research and applications in diverse fields. As a continuation of this successful conference, we organized this special issue of Neural Computing and Applications on “computational intelligence for optimization and control”, with 12 selected quality papers from ISNN’08. The theme of this special issue is to present the state-of-the-art developments in recent research focusing on neural networks for optimization, modeling and control. Over the past decades, many important theoretical and application researches were developed in the area of neural networks and learning systems. Although the understanding of natural intelligence behavior and design brain-like intelligent machines still remain a challenging topic, neural networks have been proven successful in many real-world applications. To this end, the selected 12 papers in this special issue can be categorized into four major sections under this theme.

The first section is focused on intelligent algorithms and optimization. For instance, Hong Zhang and Masumi Ishikawa presented particle swarm optimization with diversive curiosity (PSO/DC). The obtained experimental results basically accord with the findings in psychology, i.e., diversive curiosity being prone to exploration and anxiety. Traffic congestion identification is a popular research topic of intelligent transport systems (ITS). Identification rate of existing methods usually cannot meet the practical requirements. To improve the identification rate and reduce the computation cost, Zhanquan Sun et al. proposed a novel intelligent identification method. The paper by Michael M. Li et al. investigated two different intelligent techniques—the neural network method and the simulated annealing algorithm for solving the inverse problem of Rutherford backscattering with noisy data. The paper by André Cyr et al. presented a software simulator designed to explore the computational power of pulsed coding at the level of small cognitive systems.

The second section is focused on information fusion. For instance, Yongwei Li et al. discussed a structure of fault information fusion system, in which BP neural network was used as a classifier to distinguish different fault types. Fiber Bragg grating sensing technique was applied to monitor the high-voltage electric equipment in order to overcome the harsh monitoring environment. The paper by Ning Chen et al. presented a novel neural network approach which combines modified probabilistic neural network and D–S evidence theory (PNN–DS) for target classification problems. This scheme was based on the supervised learning, where the posterior probabilities are achieved and a primary classification decision is made by a PNN structure.

The third section is focused on neural modeling. For instance, Vishy Karri and Tien Ho investigated the use of artificial intelligent models as virtual sensors to predict relevant emissions such as carbon dioxide, carbon monoxide, unburnt hydrocarbons and oxides of nitrogen for a hydrogen powered car. The virtual sensors were developed by means of application of various artificial intelligent models, namely AI software built at the University of Tasmania, back propagation neural networks with Levenberg–Marquardt algorithm, and adaptive neuro-fuzzy inference systems. Radial basis function neural network was widely used in nonlinear function approximation. One of the key issues in RBFNN modeling is to improve the approximation ability with samples as few as possible, so as to limit the network’s complexity. To solve this problem, Wen Yao et al. presented a gradient-based sequential RBFNN modeling method, which can utilize the gradient information of the present model to expand the sample set and refine the model sequentially, so as to improve the approximation accuracy effectively. Dirk Gorissen et al. presented the results of an extensive study on the performance of neural networks as compared to other modeling techniques in the context of active learning. They investigated the scalability and accuracy in function of the number design variables and number of datapoints.

We also selected three papers to show the recent developments on applications and analysis of dynamic behavior of neural networks. For instance, Hongbo Wang et al. presented a fast self-localization method based on wireless sensor network and an obstacle avoidance algorithm based on ultrasonic sensors for a mobile robot. Zhaowan Sun et al. proposed a novel video watermarking scheme based on motion location. In the proposed scheme, independent component analysis (ICA) was used to extract a dynamic frame from two successive frames of original video, and the motion was located by using the variance of 8 × 8 block in the extracted dynamic frame. Fengli Ren and Jinde Cao studied the anti-synchronization of a class of stochastic perturbed chaotic delayed neural networks. By employing the Lyapunov functional method combined with the stochastic analysis as well as the feedback control technique, several sufficient conditions were established that guarantee the mean-square exponential anti-synchronization of two identical delayed networks with stochastic disturbances.

In summary, all these selected 12 papers presented recent developments of neural network related research with a focus on computational intelligence for optimization, modeling and control. These papers provided a coherent way to present the latest research. In this editorial, we categorize them into the above four sections to help readers to understand the organization of this special issue. In closing this editorial, we would like to express our deepest gratitude to many reviewers who helped us in several rounds of the review process for this special issue. Their knowledge and professional comments guaranteed the high qualify of the selected papers. In addition, we would also like to thank Dr. John MacIntyre, Editor-In-Chief of the Neural Computing and Applications, Prof. Bo Zhang, General Chair of the ISNN’08 and Dr. Jianwei Zhang, General Co-Chair of the ISNN’08, for their great help and suggestions in this process.

We hope you will enjoy reading this Special Issue.

Copyright information

© Springer-Verlag London Limited 2009

Authors and Affiliations

  1. 1.Key Laboratory of Complex Systems and Intelligence Science, Institute of AutomationThe Chinese Academy of SciencesBeijingChina
  2. 2.Department of Control Science and EngineeringHuazhong University of Science and TechnologyWuhanChina
  3. 3.School of AutomationSoutheast UniversityNanjingChina

Personalised recommendations