Cognitive Informatics

The 2005 IEEE International Conference on Cognitive Informatics (ICCI’05) was held during August 8th to 10th 2005 on the campus of University of California, Irvine. This was the fourth conference of ICCI [Kinsner et al. 05]. The previous conferences were held at Calgary, Canada (ICCI’02) [Wang et al. 02], London, UK (ICCI’03) [Patel et al. 03], and Victoria, Canada (ICCI’04) [Chan et al. 04], respectively. ICCI’05 was organized by General Co-Chairs of Jeffrey Tsai (University of Illinois) and Yingxu Wang (University of Calgary), Program Co-Chairs of Du Zhang (California State University) and Witold Kinsner (University of Manitoba), and Organization Co- Chairs of Philip Sheu (University of California), Taehyung Wang (California State University, Northridge), and Shangping Ren (Illinois Institute of Technology).

Development of an Ontology for an Industrial Domain

This chapter presents a method for ontology construction and its application in developing ontology in the domain of natural gas pipeline operations. Both the method as well as the application ontology developed, contribute to the infrastructure of Semantic Web that provides semantic foundation for supporting information processing by autonomous software agents. This chapter presents the processes of knowledge acquisition and ontology construction for developing a knowledge-based decision support system for monitoring and control of natural gas pipeline operations. Knowledge on the problem domain was acquired and analyzed using the Inferential Modeling Technique, then the analyzed knowledge was organized into an application ontology and represented in the Knowledge Modeling System. Since ontology is an explicit specification of a conceptualization that provides a comprehensive foundation specification of knowledge in a domain, it provides semantic clarifications for autonomous software agents that process information on the Internet.

Towards Cognitive Machines

Numerous attempts are being made to develop machines that could act not only autonomously, but also in an increasingly intelligent and cognitive manner. Such cognitive machines ought to be aware of their environments which include not only other machines, but also human beings. Such machines ought to understand the meaning of information in more human-like ways by grounding knowledge in the physical world and in the machines’ own goals. The motivation for developing such machines ranges from self-evidenced practical reasons, such as the expense of computer maintenance, to wearable computing in health care, and gaining a better understanding of the cognitive capabilities of the human brain. To achieve such an ambitious goal requires solutions to many problems, ranging from human perception, attention, concept creation, cognition, consciousness, executive processes guided by emotions and value, and symbiotic conversational human-machine interactions. An important component of this cognitive machine research includes multiscale measures and analysis. This chapter presents definitions of cognitive machines, representations of processes, as well as their measurements, measures and analysis. It provides examples from current research, including cognitive radio, cognitive radar, and cognitive monitors.

Theoretical Foundations of Autonomic Computing

Autonomic computing (AC) is an intelligent computing approach that autonomously carries out robotic and interactive applications based on goal- and inference-driven mechanisms. This chapter attempts to explore the theoretical foundations and technical paradigms of AC. It reviews the historical development that leads to the transition from imperative computing to AC. It surveys transdisciplinary theoretical foundations for AC such as those of behaviorism, cognitive informatics, denotational mathematics, and intelligent science. On the basis of this work, a coherent framework towards AC may be established for both interdisciplinary theories and application paradigms, which will result in the development of new generation computing architectures and novel information processing systems.

A Commonsense Approach to Representing Spatial Knowledge Between Extended Objects

This chapter proposes a commonsense understanding of distance and orientation knowledge between extended objects, and presents a formal representation of spatial knowledge. The connection relation is taken as primitive. A new axiom is introduced to govern the connection relation. Notions of ‘near extension’ regions and the ‘nearer’ predicate are coined. Distance relations between extended objects are understood as degrees of the near extension from one object to the other. Orientation relations are understood as distance comparison from one object to the sides of the other object. Therefore, distance and orientation relations are internally related through the connection relation. The ‘fiat projection’ mechanism is proposed to model the mental formation of the deictic orientation reference framework. This chapter shows diagrammatically the integration of topological relations, distance relations, and orientation relations in the RCC frameworks.

A Selective Sparse Coding Model with Embedded Attention Mechanism

Sparse coding theory demonstrates that the neurons in the primary visual cortex form a sparse representation of natural scenes in the viewpoint of statistics, but a typical scene contains many different patterns (corresponding to neurons in cortex) competing for neural representation because of the limited processing capacity of the visual system. We propose an attention-guided sparse coding model. This model includes two modules: the non-uniform sampling module simulating the process of retina and a data-driven attention module based on the response saliency. Our experiment results show that the model notably decreases the number of coefficients which may be activated, and retains the main vision information at the same time. It provides a way to improve the coding efficiency for sparse coding model and to achieve good performance in both population sparseness and lifetime sparseness.

A Unified Approach to Fractal Dimensions

Many scientific chapters treat the diversity of fractal dimensions as mere variations on either the same theme or a single definition. There is a need for a unified approach to fractal dimensions for there are fundamental differences between their definitions. This chapter presents a new description of three essential classes of fractal dimensions based on: (a) morphology, (b) entropy, and (c) transforms, all unified through the generalized-entropy-based Rényi fractal dimension spectrum. It discusses practical algorithms for computing 15 different fractal dimensions representing the classes. Although the individual dimensions have already been described in the literature, the unified approach presented in this chapter is unique in terms of its progressive development of the fractal dimension concept, similarity in the definitions and expressions, analysis of the relation between the dimensions, and their taxonomy. As a result, a number of new observations have been made, and new applications discovered. Of particular interest are behavioral processes (such as dishabituation), irreversible and birth-death growth phenomena (e.g., diffusion-limited aggregates, DLAs, dielectric discharges, and cellular automata), as well as dynamical nonstationary transient processes (such as speech and transients in radio transmitters), multifractal optimization of image compression using learned vector quantization with Kohonen’s self-organizing feature maps (SOFMs), and multifractal-based signal denoising.

Constructivist Learning During Software Development

This article explores the non-monotonic nature of the programmer learning that takes place during incremental program development. It uses a constructivist learning model that consists of four fundamental cognitive activities: absorption that adds new facts to the knowledge, denial that rejects facts that do not fit in, reorganization that reorganizes the knowledge, and expulsion that rejects obsolete knowledge. A case study of an incremental program development illustrates the application of the model and demonstrates that it can explain the learning process with episodes of both increase and decrease in the knowledge. Implications for the documentation systems are discussed in the conclusions.

A Cognitive Computational Knowledge Representation Theory

Encouraging results of last years in the field of knowledge representation within virtual learning environments confirms that artificial intelligence research in this topic find it very beneficial to integrate the knowledge psychological research have accumulated on understanding the cognitive mechanism of human learning and all the positive results obtained in computational modelling theories. This chapter introduces a novel cognitive and computational knowledge representation approach inspired by cognitive theories which explain the human cognitive activity in terms of memory subsystems and their processes, and whose aim is to suggest formal computational models of knowledge that offer efficient and expressive representation structures for virtual learning. Practical studies both contribute to validate the novel approach and permit to draw general conclusions.

Towards Autonomic Computing

Cognitive approach through the neural network (NN) paradigm is a critical discipline that will help bring about autonomic computing (AC). NN-related research, some involving new ways to apply control theory and control laws, can provide insight into how to run complex systems that optimize to their environments. NN is one kind of AC systems that can embody human cognitive powers and can adapt, learn, and take over certain functions previously performed by humans. In recent years, artificial neural networks have received a great deal of attention for their ability to perform nonlinear mappings. In trajectory control of robotic devices, neural networks provide a fast method of autonomously learning the relation between a set of output states and a set of input states. In this chapter, we apply the cognitive approach to solve position controller problems using an inverse geometrical model. In order to control a robot manipulator in the accomplishment of a task, trajectory planning is required in advance or in real time. The desired trajectory is usually described in Cartesian coordinates and needs to be converted to joint space for the purpose of analyzing and controlling the system behavior. In this chapter, we use a memory neural network (MNN) to solve the optimization problem concerning the inverse of the direct geometrical model of the redundant manipulator when subject to constraints. Our approach offers substantially better accuracy, avoids the computation of the inverse or pseudoinverse Jacobian matrix, and does not produce problems such as singularity, redundancy, and considerably increased computational complexity.