Applying Rough Set Theory to Establish Artificial Neural Networks Model for Short Term Incidence Rate Forecasting

Abstract:

Choosing input variable and networks architecture are key processes for modeling short term incidence rate forecast by artificial neural networks, in this paper a method based on rough set theory is proposed to deal with them. In the proposed approach, the key factors that affect the incidence rate forecasting are firstly identified by rough set theory and then the input variables of forecast model can be determined. On the basis of the process mentioned above a set of influence rules can been obtained through reductive mining process of attributes and attribute values, then a neural networks of incidence rate forecast model is established on the rule set and BP-algorithm is adopt to optimize the networks. The method indicates that incidence rate forecast model can be established according some theoretical principles and avoiding blindness. A practical application is given at last to demonstrate the usefulness of the novel method.

• Periodical: Applied Mechanics and Materials (Volumes 347-350)
• Pages: 2937-2941
• DOI: https://doi.org/10.4028/www.scientific.net/AMM.347-350.2937
• Online since: August 2013
• Authors: Xiang Yu Zhao, Liang Liang Ma
• Keywords: Incidence Rate Forecasting, Neural Network (NN), Rough Set (RS)

References

[1] Tamimi M and Egbert R. Sneddon, Short term electric load forecasting via fuzzy neural collaboration, Electric Power Systems Research, vol. 56, p.243–248, April (2000).

DOI: 10.1016/s0378-7796(00)00123-1

[2] Mastorocostas P A, Theocharis J B, and Bakirtizis A G, Fuzzy modeling for short term load forecasting using the orthogonal least squares method, IEEE Transaction on Power Systems, vol. 14, p.29–36, January (1999).

DOI: 10.1109/59.744480

[3] Xie Hong, Chen Zhiye, and Niu Dongxiao, The research of daily load forecasting model based on wavelet decomposing and climate influencing, Proceeding of the CSEE, vol. 21, p.5–10, May (2001).

[4] Wang Feng, Yu Erkang, and Yan Chengshan, Study of short term load forecasting based on influencing factors, Proceeding of the CSEE, vol. 19, p.54–57, Auguest (1999).

[5] Xie Hong, Cheng Haozhong, Zhang Guoli, Niu Dongxiao, and Yang Jingfei, Applying rough set theory to establish artificial neural networks for short term load forecasting, Proceeding of the CSEE, vol. 23, p.1–4, November (2003).

[6] Wang Guoying, Rough set theory and knowledge acquisition. China, Xi'an: Xi'an Jiaotong University Press, (2001).

[7] Fen Chunshan, Wu Jiachun, Jiang Fu. Combined Prediction of Oil Prices. Journal of the University of Petroleum, China (Edition of Social Sciences), vol. 1, pp.12-14, January (2004).

[8] Li Xiguo, Tan Dingshan, Shao Jinhua. Research of Precipitation in Yantai Based on ARIMA Model. Journal of Shandong water conservancy, vol. 2, pp.37-39, September (2006).

[9] Sheng Yanbo. Forecast of Domestic Product Per Capita in Zhejiang Province Based on Combined Model of BP Neural Network and ARIMA Model. Journal of Business research, vol. 23. pp.49-50, April (2006).

[10] Wang Ping. Forecasting of Tourism Demand Theoretical and Empirical Study Based on Artificial Neural Network-Case of Qingdao City. Lanzhou: Northwest Normal University, vol. 3, pp.37-39, October (2004).

[11] Ma Liangliang, Tian Fupeng. Research of Nephritis Morbidity Situation in Haixizhou Region Based on Season Model. Journal of Beijing Union University(Natural Sciences), vol. 23, pp.68-69, March (2003).

[12] Ma Liangliang, Tian Fupeng. Research of cerebral hemorrhage morbidity situation in Haixizhou region based on PDL Model. Journal of Hunan University of Arts and Science (Natural Science Edition), vol. 21, pp.17-19, March (2009).

[13] Ma Liangliang, Tian Fupeng. Research of Hypertension Morbidity Situation in Haixizhou Region Based on ADL Model. Journal of Zhejiang Wanli University, vol. 22, pp.6-9, May (2009).