Elpida S. Tzafestas

Computational Intelligence Techniques for Short-Term Electric Load Forecasting

Electric load forecasting has received an increasing attention over the years by academic and industrial researchers and practitioners due to its major role for the effective and economic operation of power utilities. The aim of this paper is to provide a collective unified survey study on the application of computational intelligence (CI) model-free techniques to the short-term load forecasting of electric power plants. All four classes of CI methodologies, namely neural networks (NNs), fuzzy logic (FL), genetic algorithms (GAs) and chaos are addressed. The paper starts with some background material on model-based and knowledge-based forecasting methodologies revealing a number of key issues. Then, the pure NN-based and FL-based forecasting methodologies are presented in some detail. Next, the hybrid neurofuzzy forecasting methodology (ANFIS, GARIC and Fuzzy ART variations), and three other hybrid CI methodologies (KB-NN, Chaos-FL, Neurofuzzy-GA) are reviewed. The paper ends with eight representative case studies, which show the relative merits and performance that can be achieved by the various forecasting methodologies under a large repertory of geographic, weather and other peculiar conditions. An overall evaluation of the state-of-art of the field is provided in the conclusions.

Performance evaluation and dynamic node generation criteria for “principal component analysis” neural networks

This paper is concerned with the solution of the principal component analysis (PCA) problem with the aid of neural networks (NNs). After an overview of the basic NN-based PCA concepts and a listing of the available algorithms, two criteria for evaluating PCA NN algorithms are proposed. Then, a new criterion for the generation of improved PCA NN structures with reduced size is presented. Using this criterion, one can start with a small network and dynamically add new nodes at the hidden layer(s) during training, one at a time, until the desired performance is achieved. A simulation example is provided that shows the applicability and effectiveness of the methodology.

Integrating drawing tools with behavioral modeling in digital painting

Our goal is to integrate traditional artistic media that demand hand dexterity (such as drawing) with intelligent systems techniques that may both constrain and nourish this dexterity. To this end we are experimenting with special brush tools that on top of traditional drawing provide possibilities that involve information processing and behavioral modeling. In this work, we are introducing a behavioral model as a color processing feature of our brush. More precisely, we use a regulation mechanism, that has been shown elsewhere to solve a typical problem in artificial ant societies, to distribute color on the drawing canvas. Our drawing tool, called “AntBrush”, manages to create controlled color variety during drawing by regulating its own quantity of color through picking and depositing color on the canvas. Different color effects are possible by controlling the brushs parameters on line.

Human–Machine Interaction in Intelligent Robotic Systems: A Unifying Consideration with Implementation Examples

The goal of this paper is to provide a general unified discussion of the human machine interaction issues as applied to robotics. First, the general structure of intelligent Human Machine Interfaces (HMIs) is presented. Then the class of natural language interfaces (NLIs) is reviewed. Next the class of graphical HMIs (GHMIs) is investigated including the combination of GHMIs with Virtual Reality (VR) system facilities. Finally, the category of force sensing/tactile-based HMIs is considered, where joysticks, force-reflecting devices, exoskeleton haptic devices and dextrous arm masters are included. The paper ends with a short presentation of five implementation examples of HMIs in various robotic systems and applications.

The Blackboard Architecture in Knowledge-Based Robotic Systems

Integrated knowledge-based robotic systems that employ multi-sensor feedback information require the effective treatment of a large volume of complex knowledge. To this end, several methods of knowledge organisation and exploitation have been developed. One of them is the so-called blackboard architecture, which belongs to the class of distributed problem solving architectures, and employs more than one problem solving agents. The three basic elements of the blackboard architecture are: the blackboard, the knowledge sources and the control mechanism. The blackboard plays the role of a central working memory within the system and the controller stands for the conflict resolution mechanism. The knowledge about the system (problem) is split in a number of comparatively small knowledge bases called knowledge sources and controlled through the blackboard control (scheduling) mechanism which is usually a meta-knowledge control mechanism. This mechanism is not committed to any reasoning technique (e.g. forward or backward inference chaining), but has a rather opportunistic nature (i.e., the control action is determined by the optimal decision taken at each cycle of operation). The purpose of this paper is to provide an account of the main concepts and issues of the blackboard architecture and their use in designing integrated knowledge-based intelligent robotic systems. Some particular applications of this approach will also be discussed, one of which has been designed and tested by the authors. The paper is complemented by general design issues of intelligent robotic and flexible manufacturing systems.

On Modeling Proto-Imitation in a Pre-associative Babel

In this paper we present a model of generative proto-imitation that replicates external signals without associating with objects, as in higher-level imitation. A mixed population of adults, that have fixed associations objects-signals, and infants, that do not have associations but imitate unconditionally, endowed with a kinship and interaction structure, allows infants to develop signal affinity with their kin in a variety of conditions and within an initial random world, i.e. in a Babel. Our results indicate that the communicative value of imitation can be discovered after the basic apparatus is in place, rather than that communication is the end to which imitation is the means.

Cultural diversity dynamics

In this work, we are exploring mechanisms that may contribute to cultural dynamics and cultural diversity. To this end, we are experimenting with an extended Axelrod model that uses a Moore neighborhood and heterogeneous sets of cultural features per agent. We are gradually introducing a number of psychologically realistic, basic and more advanced, conceptual models of cultural affinity perception and imitation and show that in many cases the population stabilizes to multi-cultural configurations. We also demonstrate the transitive advantage of two other mechanisms, attraction and spatial migration. In sum, our results show that a mix of initially differentially evolved or developed agents will not converge to monoculture, and that this is due to intrinsic psychological factors that are key players in behavioral change.

REGULATION PROBLEMS IN EXPLORER AGENTS

ABSTRACT In the present study, we investigate and analyze the behavior of explorer agents. We perform a number of experiments with single and multiple agents and we obtain a number of corresponding results. First, we decouple the agents functional/motivational system from its cognitive/representational system and show that intricate regulation is necessary to achieve effective and efficient behavior. In the multiple agents case, we extend the single agent behavioral model with a form of sociality selected from a progression of alternatives designed and evaluated. We also show how the general regulation perspective allows for design and analysis of explorer systems. We do not miss to provide variations of the problem and potential applications all along the way.

Intelligent forecasting, fault diagnosis, scheduling and control

The special issue of Mathematics and Computers in Simulation involves 22 timely contributions in the combined field of intelligent forecasting, fault diagnosis, scheduling and control. These papers have been selected among the papers presented in the two parallel workshops IFDICON’2001 and SERVICEROB’2001 held in the island of Santorini, Greece (23–27 June, 2001). The papers have been organized in the following four groups:

MULTI-AGENT ROBOT ARCHITECTURES: THE DECOMPOSITION ISSUE AND A CASE STUDY

In this paper, some fundamental issues of modern multi-agent robot architectures are discussed. It is argued that the multi-agent approach provides the necessary flexibility and adaptivity for such architectures, and that the primary issue in designing a multi-agent robot architecture is the selection of the granularity level, i.e., the decision on decomposing the overall desired functionality physically or across tasks. It is explained why at the various system levels different decomposition grains are needed; physical components, tasks or hybrid. This granularity decision is made on the basis of specific criteria of control localization, knowledge decoupling and interaction minimization so as to identify the decision points of the overall functionality. The above criteria lead to a dual composition-decomposition relation, which provides a good basis for system scaling. The paper specializes the discussion to a proposed neuro-fuzzy multi-agent architecture, which is then applied to design the local path planning system of an indoor mobile robot.