Design of Neural Network Based on Rough Set

Abstract:

After years of development, the neural network classification, clustering and forecasting applications have a lot of development, but the neural network has the inevitable defects, if you enter the attribute set, the classification boundaries are not clear, convergence low efficiency and accuracy, there may even be the state does not converge, using rough set theory, the right value to modify the function to be modified, and joined the contradictions sample test module, after the use of EEG to verify reached the deletion of number of features and the purpose to improve the classification accuracy.

• Periodical: Applied Mechanics and Materials (Volumes 263-266)
• Pages: 3378-3381
• DOI: https://doi.org/10.4028/www.scientific.net/AMM.263-266.3378
• Online since: December 2012
• Authors: Xue Min Zhang, Zhen Dong Mu
• Keywords: Algorithm Design, Neural Network (NN), Rough Set (RS)

References

[1] Yang ye, Based on rough sets and support vector machine centrifugal pump cavitation fault diagnosis, Ruan Jian Dao Kan, vol 10, No 11, pp.43-44, 2011.

[2] Ming Li-te, Jiang Yun, Wang Yong,Gene expression profiles classification method based on neighborhood rough set and probabilistic neural networks ensemble, Application Research of Computers,vol 28, No 12，pp.4440-4444, 2011.

[3] Wang Li-zhen, Neural network and self－structuring fuzzy control algorithm and its application, Mechancal Research and Application, pp.10-12, 2011.

[4] Sang lin, Gong Yue, Chen si,, Discretization of continuous attributes based on rough set algorithm and its application, Gao Shi Li Ke Xue Kan,vol 28,No 2,pp.1-4, (2011)