• The Transactions of the Korean Institute of Electrical Engineers
• /
• v.45 no.4
• /
• pp.602-611
• /
• 1996

In this paper, radial basis function networks with two hidden layers, which employ the K-means clustering method and the hierarchical training, are proposed for improving the short-term predictability of chaotic time series. Furthermore the recursive training method of radial basis function network using the recursive modified Gram-Schmidt algorithm is proposed for the purpose. In addition, the radial basis function networks trained by the proposed training methods are compared with the X.D. He A Lapedes's model and the radial basis function network by nonrecursive training method. Through this comparison, an improved radial basis function network for predicting chaotic time series is presented. (author). 17 refs., 8 figs., 3 tabs.

• Journal of the Korean Institute of Navigation
• /
• v.24 no.3
• /
• pp.147-155
• /
• 2000

In this paper, we propose the Chaos Fuzzy controller to analyze the chaotic character of time series obtained from the specific plant and to predict the short-term for power consumption of the plant using the Fuzzy controller. We compared the predicted data with the active ones and checked the error generated by them after we time series of supplied power to the proposed controller. As a result of the simulation, we obtained a admirable consequence that the proposed controller can be advanced through various and accurate data acquisition, and continuous analysis of the resident and industrial environment.

• The Research Journal of the Costume Culture
• /
• v.18 no.6
• /
• pp.1274-1290
• /
• 2010

This study analyzed the design elements and fashion images of women's knitwear in collections of Paris, Milan, London and New York between 2003 and 2008, and examined knitwear trends in an effort to verify whether knitwear trends are repeated in certain cycles, whether they show complicated patterns in cycles and yet occur in quasi cycles, or whether they occur non-periodically in complicated forms of chaotic cycles. Trend cycle analysis results are deemed to identify the time series attribute of knit fashions. It also sought to categorize the attribute of various factors influencing knitwear trends with a view to determining relevancy between design elements, and to present the direction of predicting knitwear fashion trends and the progression of short-term knitwear trends. This study reached the following conclusion. According to design elements or fashion images, knitwear fashion trends occur in cycles, quasi cycles, non-periodical cycles. These cyclic characteristics can be used as scientific data for planning knitwear products. The study confirmed close relevancy between fashion images and fashion elements. It identified close relevancy between designs with similar fashion elements and images through coordinates by year and season, and it is possible to make short-term prediction of trend direction through the flow of coordinates. Time series data were insufficient, thereby making it difficult to perfectly verify chaos indices and giving limitations to this study. A study with more time series data will produce a more effective method of predicting and using knitwear fashion trends.

• Water for future
• /
• v.27 no.3
• /
• pp.45-54
• /
• 1994

Basic theory of fractal dimension is introduced and performed for the generated time series using the water balance model. The water balance equation over a large area is analyzed at seasonal time scales. In the generation and modification of mesoscale circulation local recycling of precipitation and dynamic effects of soil moisture are explicitly included. Time delay is incorporated in the analysis. Depending on the parameter values, the system showed different senarios in the evolution such as fixed point, limit cycle, and chaotic types of behavior. The stochastic behavior of the generated time series is due to deterministic chaos which arises from a nonlinear dynamic system with a limited number of equations whose trajectories are highly sensitive to initial conditions. The presence of noise arose from the characterization of the incoming precipitation, destroys the organized structure of the attractor. The existence of the attractor although noise is present is very important to the short-term prediction of the evolution. The implications of this nonlinear dynamics are important for the interpretation and modeling of hydrologic records and phenomena.