Taiji Satoh

Artificial life system for optimization of nonconvex functions

This paper presents a distributed algorithm for optimization of nonconvex multimodal functions. In recent years, new distributed algorithms based on artificial life (ALife) system has been studied and its potential power has been demonstrated. In this paper, the frame work of ALife system is employed into a function minimization. We also propose a hybrid algorithm in which ALife system is incorporated with the local search method for finding good start points for the local search. Since the proposed method utilizes no gradient information it can be applied to very wide class of optimization problems. The effectiveness of the proposed method is demonstrated through some numerical tests.

A new framework of neural network for nonlinear system modeling

In this paper, a new modeling framework of neural network for nonlinear system is proposed. We point out problems in modeling systems with traditional neural networks, that is, difficulty for analyzing internal representation, no reproducibility in system modeling (approximation), and no assumption about system property. Based on these considerations, we suggest three main improvements. The first is design of a nonlinear output function. The second is a deterministic scheme for weight initialization. The third is an updating rule for weight parameter. Simulation results show beneficial characteristics of our proposed method.

On the study about an communication system by opening and shutting of an eyelid-application to the support system of medical care

Bedridden persons who have the inconvenient hands, legs and mouth can tell his/her will to a nurse by only opening and shutting his/her eyelids. Hence a medical care support system for such persons to become to be able to communicate to other people has been desired. In this paper, a system to automatically estimate opening and shutting of an eyelid from a sequence of real images which are taken by CCD camera has been developed.

Continuation Method for Dynamic Economic Load Dispatch with Emission Constraints

Abstract This paper presents a method for solving a dynamic economic load dispatch problem of electric power systems. Since the expected system load varies over a given time horizon, the sum of generator outputs must follows the system load subject to power-rate limits on generators. In order to solve the dynamic ELD problem, the continuation method is employed in this paper. It is shown that each generator output is expressed as a piecewise-linear function of a continuation parameter, and this fact enables us to obtain the optimal solution efficiently. Numerical tests for a model system indicate the validity and effectiveness of the proposed method.