Based on Cluster Cover Algorithm in Coal Mine Gas Forecast Application
Compares with the traditional forward neural network, the cover algorithm has the running rate to be quick, precision high characteristic, but the cover algorithms initial domain center is the stochastic selection. The experiment indicated that the network performance and the study order have the close relationship. Proposed one kind of new improvement overlapping cover algorithm in the forward neural network overlapping cover algorithm foundation-based on the cluster overlapping cover algorithm. And utilizes this algorithm in the coal mine gas predict that the experimental result indicated that this algorithm suits compared to the original cover algorithm in the coal mine gas forecast.
gas density cluster analysis cover algorithm time series
Zhang Yueqin Duan Xiaopeng
Computer and Software Institute, Taiyuan University of Technology, Taiyuan, Shanxi, China
国际会议
长沙
英文
854-857
2010-05-11（万方平台首次上网日期，不代表论文的发表时间）