Recognition of specified wave patterns in one-dimensional signals is an important task in many application areas such as computer science, medical science, and geophysics. Many researchers have tried to automate this task with various techniques, recently the soft computing algorithms. This paper proposes a new neuro-fuzzy recognition system for detecting one-dimensional wave patterns using wavelet coefficients as features of the signals and evolution strategy as the training algorithm of the system. The neuro-fuzzy recognition system first trains the wavelet coefficients of the training wave patterns and then evaluates the degree of matching between test wave patterns and the training wave patterns. This system was applied to picking first arrival events in seismic data. Experimental results with three seismic data showed that the system was very successful in terms of learning speed and performances.

A processor allocation scheme for mesh computers greatly affects their system utilization. The performance of an allocation scheme is largely dependent on its ability to detect available submeshes. We propose a new type of submesh, called a link-disjoint submesh, for processor allocation in mesh computers. This type of submesh increases the submesh recognition capability of an allocation scheme. A link-disjoint submesh is not a contiguous submesh as in the previous scheme, but this submesh still has no common communication link with any other submesh. When wormhole routing or circuit switching is used, the communication delay caused by non-contiguous processor allocation is minor. Through simulation, the performance of our scheme is measured and compared to the previous schemes in terms of such parameters as finish time and system utilization. It is shown through simulation that the link-disjoint submesh increases the performance of an allocation scheme.

PID-type controllers have been well-known and widely used in many industries. Their regulation property of those was more improved through the addition of Bang-Bang-action. In spite of the potentials of these PID-plus Bang-Bang controllers, their regulation property is still limited by the fixed window limit value that determines the control action, i. e., PID or Bang-Bang. Thus, this paper presents an approach for improving the regulation property by dynamically changing the window limit value according to the plant dynamics with Neural Network predictive model. The improved regulation property is illustrated through simulation studies for position control of DC servo-motor system in the sense of classical figures of merit such as overshoot and rise time.

This paper proposes novel methods to provide intelligence for characters in fighting action games by using neural networks. First, how a character learns basic game rules and matches against randomly acting opponents is considered. Since each action takes more than one time unit in general fighting action games, the results of a character's action are exposed not immediately but several time units later. We evaluate the fitness of a decision by using the relative score change caused by the decision. Whenever the scores of fighting characters are changed, the decision causing the score change is identified, and then the neural network is trained by using the score difference and the previous input and output values which induced the decision. Second, how to cope more properly with opponents that act with predefined action patterns is addressed. The opponents' past actions are utilized to find out the optimal counter-actions for the patterns. Lastly, a method in order to learn moving actions is proposed. To evaluate the performance of the proposed algorithm, we implement a simple fighting action game. Then the proposed intelligent character (IC) fights with the opponent characters (OCs) which act randomly or with predefined action patterns. The results show that the IC understands the game rules and finds out the optimal counter-actions for the opponents' action patterns by itself.