Advances in Knowledge Discovery and Data Analysis for Artificial Intelligence

The Sixth International Symposium on Neural Networks (ISNN’09) was held on 26–29 May 2009 in Wuhan, China. The ISNN 2009 was a great success and provided a high-level international forum for scientists, engineers and educators to present the latest research in neural networks and related fields. To highlight the success of this conference, we edited this special issue for the Journal of Experimental & Theoretical Artificial Intelligence (JETAI). We chose nine papers from over a thousand submissions to ISNN’09, as these papers clearly reflect the high quality of the presentations at the conference while capturing the spirit of our theme, ‘Advances in Knowledge Discovery and Data Analysis for Artificial Intelligence’, for this special issue. Our goal for this special issue is to present the state-of-the-art development in knowledge discovery and data analysis in artificial intelligence (AI) research. Over the past decades, we have witnessed tremendous efforts and developments from all spheres of AI research, including theoretical foundations, architectures, models and algorithms, as well as a wide range of applications across different domains. Recently, new advances in cognitive science, psychology, neuroscience, computer science, biomedical research, nanotechnology, among others, have provided exciting opportunities and new insights as well as significant challenges for the research community towards the long-term goal of developing truly brain-like intelligent systems. In this special issue we focus on the recent developments in knowledge discovery and data analysis that are clearly geared towards this long-term goal. With the continuous expansion of data availability in many of today’s large-scale, complex and networked systems, it becomes critical for us to develop natural intelligent systems that can capitalise on the efficient use of such large-scale raw data. These systems will support human-like decision-making processes and lead to fundamental understanding of knowledge discovery and analysis. The selected papers can be organised into the following four coherent sections. First, robotics and automation has been a major topic within the AI community for a very long time. In this special issue, we have selected two related papers to highlight some of the recent developments in this area. The paper by P. Li et al. propose an approach for the efficient smooth path planning for the mobile robots in unknown dynamic environments. This approach considers the multi-agent system with cooperative control, and uses the information fusion technique to build the map of the dynamic environment. Simulation analysis and experimental results illustrates the effectiveness of this method. In the other paper, H. Qiao et al. propose a manifold learning method named Intrinsic Variable Preserving Manifold Learning (IVPML) approach. The key idea of this approach is to transfer the manifold learning framework to real-time tracking to preserve the continuity of intrinsic variables. Therefore, the feature extracted by this approach can be directly used for the system control. The authors test this approach on a dynamic robotic system to track a non-cooperative person with free motion in complex environment.