[in Japanese]

View full abstract

[in Japanese]

View full abstract

[in Japanese]

View full abstract

There have been several applications of Evolutionary Computation (EC) to the financial problems, such as portfolio optimization, bankruptcy prediction, financial forecasting, fraud detection and scheduling. This paper presents the application of Genetic Programming (GP) to the prediction of the price data in Japanese stock market. The goal of this task is to choose the best stocks when making an investment and to decide when and how many stocks to sell or buy. We describe how successfully GP and its variant, i.e., STROGANOFF, are employed to predicting the stock data so as to gain the high profit. The comparative experiments are conducted with neural networks to show the effectiveness of the GP-based approach.

View full abstract

In this paper, we propose nonlinear wind prediction methods for predictive control of wind power generation, based on techniques of nonlinear time series analysis. The proposed methods provide prediction of wind at an observational equipment in contiguity with a windmill, and achieve local wind prediction suitable for the time-space scale of windmill by the reconstruction of a local wind dynamical system only from observed time series data. We demonstrates that the methods have predictability of real wind time series data.

View full abstract

[in Japanese]

View full abstract

This paper proposes the simple risk assessment method about human errors, which influences the occurrence of accidents. This method is relative evolution on hierarchy structure of task. We showed the validity by presenting two sorts research examples in railway. In one research on one mission to stop trains when a meteorological disaster was carried out, we evaluated the frequency of task failure by human errors. In second research on several missions of train drivers or instruction members, we evaluated the risk of task failure. On both cases, we construct the hierarchical structure model of working conditions and mission situations.

View full abstract