Multiple neural networks for a long term time series forecast

The artificial neural network (ANN) methodology has been used in various time series prediction applications. However, the accuracy of a neural network model may be seriously compromised when it is used recursively for making long-term multi-step predictions. This study presents a method using multiple ANNs to make a long term time series prediction. A multiple neural network (MNN) model is a group of neural networks that work together to solve a problem. In the proposed MNN approach, each component neural network makes forecasts at a different length of time ahead. The MNN method was applied to the problem of forecasting an hourly customer demand for gas at a compression station in Saskatchewan, Canada. The results showed that a MNN model performed better than a single ANN model for long term prediction.

Service level negotiation andcops-sls protocol

The Internet is a set of interconnected domains in which different QoS technologies can be deployed. The dynamic provision of end-to-end QoS over heterogeneousip networks assumes the negotiation of mutually acceptablesla. This paper presents the concept of intra-, inter- and multiple-domain service level negotiation using thecops-sls protocol. The negotiation process gives different parties in the negotiation the ability to agree upon the service level that a data stream can obtain, along with the permissible pricing of the service.     

Use of the CT images for BNCT calculation: development of BNCT treatment planning system and its applications to dose calculation for voxel phantoms

A BNCT (Boron Neutron Capture Therapy) treatment planning system (BTPS) was developed for BNCT study and treatment planning. Three kinds of CT images, VHP, PINNACLE and DICOM images, were employed to make voxel phantoms for BNCT patient treatment using the BTPS. The thermal neutron, fast neutron, gamma and boron doses are calculated and background, tissue, and tumour doses for idealised standard reactor neutron field (ISRNF) neutron beam were calculated by using BTPS and MCNP code. It was noted that the total computing times needed for BNCT analysis could be greatly reduced since the BTPS system provides a dose analysis tool and a lengthy MCNP input in a short time. It is, thus, expected that the BTPS can significantly contribute the BNCT study for the treatment of patients.     

Research on advanced soft computing and its applications

The main objective for the research presented in this special issue is to advance theoretical basis in soft computing, for the purpose of improving applications. Why is this theoretical research needed? Because soft computing in general (and intelligent control and decision making in particular) are, in many aspects, still an art. To make this methodology easier to apply, we must use the experience of successful applications of fuzzy control, decision making or classification and extract formal rules that would capture this experience. To be able to do that efficiently, we must understand why some versions of soft computing methodology turned out to be more successful in some practical situations and less successful in others. In other words, to advance the practical success of soft computing methodology, we need further theoretical analysis of soft computing – analysis targeted at enhancing its application abilities.     

Study on a new and effective fuzzy PID ship autopilot

Ship autopilots are usually designed based on Proportional Differential (PD) and Proportional Integrate Differential (PID) controllers because of their simplicity, reliability, and ease of construction. However, their performance in various environmental conditions is not as good as desired. This disadvantage can be overcome by adjusting works or constructing adaptive controllers, although these methods are complex and not easy. This article presents a new method for constructing a ship autopilot based on the combination of fuzzy logic control (FLC) and linear control theory (PID control). The new ship autopilot has the advantages of both the PID and FLC control methodologies: ease of construction, and optimal control laws can be established based on ship master knowledge. Therefore, the new ship autopilot can be well adapted with parameter variations and strong environment effects. Simulation using MATLAB software for a ship with real parameters showed high effectiveness of the fuzzy PID autopilot in course-keeping and course-changing maneuvers in comparison with the ordinary PID ship autopilots.This work was presented, in part, at the 8th International Symposium on Artificial Life and Robotics, Oita, Japan, January 24–26, 2003     

On the elastic plastic initial-boundary value problem and its numerical integration

An interative approach is proposed for the numerical analysis of elastic–plastic continua. This approach gives after convergence an implicit scheme of integration of the evolution problem, and is concerned with elastic-perfectly plastic materials and with hardening standard materials. Under a generalized assumption of positive hardening, the proof of convergence of the iterative solutions is given. Some numerical examples by the finite element method are also discussed.     

Computing the behaviour of asynchronous processes

We describe a variation of Brock-Ackerman's (1981) model of nondeterministic asynchronous process, and devise a computational method for characterizing asynchronous processes defined by networks. This method is shown to be equivalent to a method of combining traces related to that of Brock and Ackerman. Recursively defined networks are also considered.     

Field near the interface of a jungle dielectric slab

The transmitted far field of a short vertical dipole located in a jungle dielectric medium is evaluated by the steepest-descent technique. At near-grazing angles of transmission, the technique is modified to account for the influence of the branch point. The influence is found significant only in the field amplitude and is confined within a short distance from the jungle-air interface, within which the difference between the path of the geometric-optical wave and that of the lateral wave is less than a wavelength.     

Global controllability of linear autonomous systems: A geometric consideration

The global controllability in finite time of a linear autonomous system with restrained controls is investigated. Necessary and sufficient conditions are obtained by an approach based on the consideration of geometric properties of the system.     

脉冲等离子弧焊接焊透质量的闭环控制

本文根据脉冲等离子弧焊接的特点,研制了一种反馈控制系统,用以控制焊缝的焊透质量。放置在焊缝背面的光电管接收并监控来自等离子弧尾焰的光线。接收到的光信号被光电管转换成光—电脉冲信号。在把光—电脉冲信号放大、积分并把它与给定电压比较后,反馈系统可输出电信号对焊接电流的脉冲宽度进行自动调整,使小孔存在时间增加或减小,实现了对焊缝焊透质量的闭环控制。