Fault Prediction Based on the Kernel Function for Ribbon Wireless Sensor Networks |
| |
Authors: | Yinggao Yue Jianqing Li Hehong Fan Qin Qin Le Gu Li Du |
| |
Affiliation: | 1.Artificial Intelligence Key Laboratory of Sichuan Province,Sichuan University of Science and Engineering,Zigong,People’s Republic of China;2.School of Instrument Science and Engineering,Southeast University,Nanjing,People’s Republic of China |
| |
Abstract: | There exist several applications of wireless sensor networks in which the reliable operation can be crucial. Fault prediction is a critical problem in reliability theory for ribbon wireless sensor networks (RWSNs). Accurate fault prediction can effectively improve the availability of the WSNs system. In this paper, we evaluated the network performance for RWSNs, studied the basic theory of kernel functions, proposed a new failure prediction method based on kernel function, and selected the radial basis function as kernel function failure prediction models from two aspects of node hardware failures and network failures for fault prediction. Theoretical evidence and experimental results have shown that the proposed algorithmic prediction method has higher accuracy of 12 and 15% than that of GRNN and PNN respectively. Finally, we provided extensive numerical results to demonstrate the usage and efficiency of the proposed algorithms and complement our theoretical analysis. |
| |
Keywords: | |
本文献已被 SpringerLink 等数据库收录! |
|