Search

This paper proposes unconstrained functional networks as a new classifier to deal with the pattern recognition problems. Both methodology and learning algorithm for this kind of computational intelligence classifier using the iterative least squares optimization criterion are derived. The performance of this new intelligent systems scheme is demonstrated and examined using real-world applications. A comparative study with the most common classification algorithms in both machine learning and statistics communities is carried out. The study was achieved with only sets of second-order linearly independent polynomial functions to approximate the neuron functions. The results show that this new framework classifier is reliable, flexible, stable, and achieves a high-quality performance. Index Terms--Functional networks, minimum description length, statistical pattern recognition.

The industrial network, often referred to as fieldbus, becomes an indispensable component for intelligent manufacturing systems. Thus, in order to satisfy the real-time requirements of field devices such as sensros, actuators, and controllers, numerous fieldbus protocols have been developed. But, the application of fieldbus has been limited due to the high cost of hardware and the difficulty in interfacing with multivendor products. As an alternative to fieldbus, the Ethernet (IEEE 802.3) technology is being adapted to the industrial environment. However, the crucial technical obstacle of Ethernet is its nondeterministic behavior that cannot satisfy the real-time requirements. Recently, the switched Ethernet becomes a very promising alternative for real-time industrial application due to the elimination of uncertainties in Ethernet. This paper focuses on the application of the switched Ethernet with multiple levels (that is, cascade structure with multiple switching hubs) for real-time industrial networking. More specifically, this paper presents an analytical performance evaluation of the switched Ethernet with multiple levels from timing diagram analysis, and experimental evaluation from an experimental testbed of networked control system. Index Terms--Fieldbus, industrial network, network delay, networked control system (NCS), real-time requirements, switched Ethernet.

This paper reports on the use of multi-agent system technology to automate the management and analysis of SCADA and digital fault recorder (DFR) data. The multi-agent system, entitled Protection Engineering Diagnostic Agents (PEDA), integrates legacy intelligent systems that analyze SCADA and DFR data to provide data management and online diagnostic information to protection engineers. Since November 2004, PEDA agents have been intelligently interpreting and managing data online at a transmission system operator in the U.K. As the results presented in this paper demonstrate, PEDA supports protection engineers by providing access to interpreted power systems data via the corporate intranet within minutes of the data being received. In this paper, the authors discuss their experience of developing a multi-agent system that is robust enough for continual online use within the power industry. The use of existing agent development toolsets and standards is also discussed. Index Terms--Cooperative systems, decision support systems, fault diagnosis, intelligent systems, knowledge-based systems, power transmission protection.

Some major issues of human-friendly man-machine interaction/interfaces in an intelligent residential system are dealt with to cope with increasing needs of the elderly and the handicapped for a higher level of living conditions. Specifically, the existing systems in this area are first examined and the inadequacy of some current remote-control interfaces for the elderly/handicapped is pointed out. Then, some intention-reading techniques are introduced for the elderly and/or the physically handicapped, for easier and more convenient use of machines and engineering systems. Index Terms--Human-friendly interface, intelligent residential system, intention reading.

Different partial discharge (PD) detection and measurement procedures suitable for use on cables, capacitors, transformers and rotating machines are examined and compared. Both narrow and wide bandwidth PD detectors are considered; particular attention is given in regard to their suitability to different types of electrical apparatus and cable specimens under test as well as their applicability to discharge site location and their capability to detect different forms of PD. A rather substantial portion of the discussion is devoted to the use of intelligent machines as applied to ED pattern recognition in terms of either ED pulse-height/discharge epoch (phase) distributions or discharge pulse shape attributes.

This paper focuses on automotive applications and discusses the development of a suite of integrated radar and IR sensors that can be used to surround a vehicle (car, truck, boat, etc.). The primary function is to provide information to the vehicle systems and operator as enhancements to passenger and vehicle safety. It may also provide vehicle information (speed, location, destination, etc.) and integrate information (weather, road/traffic conditions, service/rest-area location, route details, etc.) from an intelligent vehicle highway system. Index Terms--Airplane, automotive, boat, car, GPS, highway, intelligent vehicle highway system, IR, radar, sensors, truck, vehicle.

The range of experiments that a typical undergraduate energy conversion laboratory facility can support does not adequately prepare power engineering students for the digital-computer oriented power system industry. Traditional approach to experimentation involves manually reading several meters, logging data, performing necessary calculations and plotting results. In order to correct this problem, an Intelligent Data-Acquisition and Control (IDAC) system is implemented for the energy conversion laboratory at Penn State University-Harrisburg. Using the IDAC system, data gathering and analysis becomes automated. Students are therefore able to devote the bulk of their time to the intellectual aspects of the project.

Support vector machines (SVMs) provide a significant algorithm for machine learning that can lead to high performances in a wide range of practical applications. SVMs are better than other machine learning algorithms because they can be analyzed theoretically using simple ideas from computational learning theory. Examples of real problems that can be addressed by SVMs include text categorization and face detection. The algorithm can be implemented efficiently using sequential minimal optimization.

Knowledge management faces challenges as it tries to be an integral part to an organization's culture and infrastructure. These include finding and eliciting knowledge, mentoring, and cost concerns.

Human beings are constantly interacting with systems surrounding them. These include personal computers, automobiles, and smart appliances, among many others. It is expected that in the near future there will be interactions with service robots in homes and offices. A great deal of efforts have been made into advancing this interaction using science and technology. The main goal is to make human interactions with systems not only effective and safe, but also enjoyable and entertaining. The objective of this paper is to provide a survey of the current research on such interactions, based on a taxonomy framework. The work presented in this paper embodies human-computer interactions, human-machine interactions, and human-robot interactions. The research undertakings are classified based on five criteria of: application, research approach, system autonomy, interaction distance, and interaction media. Multiple categories are provided in each classification and a large number of research efforts are presented in each category. Additionally, more than 150 cited references are listed in summary tables with respect to each classification category. This provides an easy reference guide for related works with certain characteristics. The advanced interactions discussed in this paper cover a wide range, including: tele-robots, virtual reality, user interfaces, bio-feedback, mobile robots, intelligent user interfaces, sport machines, medical technology, human-machine interfaces, entertainment, intelligent systems, computer input/output devices, human-computer interfaces, and multimedia. [C] 2000 Elsevier Science Ltd. All rights reserved. Keywords: Advanced human-system interactions; Human-computer interaction; Human-machine interaction; Human-robot interaction; Intelligent user interfaces; Research taxonomy; Multimedia

Automatic meter reading (AMR) is the remote collection of consumption data from customers' utility meters over telecommunication, radio, power-line and other links. Electric utilities are exploring the usage of AMR data for outage management for distribution systems. Signals from automated meters can provide additional information in the outage detection and determination processes as well as restoration phases of outage management. However due to its low quality, AMR outage data cannot be fed directly into outage management systems. This paper details the development of an intelligent information filter for automated metering systems. The filter prevents false outage notifications in addition to improving the quality of outage data. The nature of wireless communication in the AMR system introduces uncertainty issues in the query process. This uncertainty has been modeled using probabilistic and fuzzy engineering techniques. The filter has also been tested using historical outage data. Index Terms--Automated meter reading (AMR) systems, fault location, fuzzy logic, intelligent systems, outage management system, power system restoration, probability.