Title :
Based on Cluster Cover Algorithm in Coal Mine Gas Forecast Application
Author :
Yueqin, Zhang ; Xiaopeng, Duan
Author_Institution :
Comput. & Software Inst., Taiyuan Univ. of Technol., Taiyuan, China
Abstract :
Compares with the traditional forward neural network, the cover algorithm has the running rate to be quick, precision high characteristic, but the cover algorithm´s 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.
Keywords :
coal; minerals; mining; mining industry; neural nets; stochastic processes; cluster cover algorithm; coal mine gas forecast application; forward neural network overlapping cover algorithm; stochastic selection; Clustering algorithms; Computer networks; Density measurement; Explosions; Neural networks; Product safety; Production; Software algorithms; Stochastic processes; Tin; cluster analysis; cover algorithm; gas density; time series;
Conference_Titel :
Intelligent Computation Technology and Automation (ICICTA), 2010 International Conference on
Conference_Location :
Changsha
Print_ISBN :
978-1-4244-7279-6
Electronic_ISBN :
978-1-4244-7280-2
DOI :
10.1109/ICICTA.2010.172
