Presentation 2008-01-31
The Correlation between Centralities of Node and Prediction Accuracy in Complex Network Systems
Shinichi IKEDA, Tomoya SUZUKI,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) Some real systems compose networks where each element interacts with each other. We can obtain their behavior as time series data, and can use them for understanding mechanisms of systems and predicting future behavior. For example, in economic systems, each company corresponds to a node of a network and interacts with each company. Thus, stock markets show us complex movements. In the case of predicting such movements, it is possible that the difficulty of prediction and the optimum model of prediction are different according to properties of each node, such as large company or medium company. In this study, we prepared some coupled chaos systems with the WS model, which generates the small-world network, as numerical models to model real systems. Then, we predicted time series generated by coupled chaos systems by nonlinear prediction method. In addition, we examined the correlations between prediction accuracies of each node and centralities of each node:degree centrality, betweenness centrality and closeness centrality, and then we discuss the predictability of complex real system like economic systems.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) Small-world networks / Coupled chaos system / Centralities of node / Nonlinear prediction
Paper # NLP2007-132
Date of Issue

Conference Information
Committee NLP
Conference Date 2008/1/24(1days)
Place (in Japanese) (See Japanese page)
Place (in English)
Topics (in Japanese) (See Japanese page)
Topics (in English)
Chair
Vice Chair
Secretary
Assistant

Paper Information
Registration To Nonlinear Problems (NLP)
Language JPN
Title (in Japanese) (See Japanese page)
Sub Title (in Japanese) (See Japanese page)
Title (in English) The Correlation between Centralities of Node and Prediction Accuracy in Complex Network Systems
Sub Title (in English)
Keyword(1) Small-world networks
Keyword(2) Coupled chaos system
Keyword(3) Centralities of node
Keyword(4) Nonlinear prediction
1st Author's Name Shinichi IKEDA
1st Author's Affiliation Department of Information System Design, Faculty of Engineering, Doshisha University()
2nd Author's Name Tomoya SUZUKI
2nd Author's Affiliation Department of Information System Design, Faculty of Engineering, Doshisha University
Date 2008-01-31
Paper # NLP2007-132
Volume (vol) vol.107
Number (no) 477
Page pp.pp.-
#Pages 6
Date of Issue