Spectrum Prediction Based on LMBP Neural Network

摘要：

Spectrum sensing detects the availability of the radio frequency spectrum, which is essential and vital to cognitive radio. However, traditional techniques for spectrum sensing fail to take the latency between spectrum sensing data. Prediction can be utilized to solve the previous problem. In spectrum prediction, cognitive radio devices are intelligent enough and can learn the usage pattern from the sensing spectrum data. In this paper, we propose a spectrum usage behavior prediction method using back propagation neural network and then use Levenberg-Marquardt algorithm to train back propagation neural network. We compare the performance of the aforementioned method with other prediction methods by adopting measured spectrum as our experimental data. The experimental result proves that our proposed method has a better performance in spectrum prediction.

关键词： cognitive radio spectrum prediction LMBP neural network

作者: Binhua Chen Wenbin Guo Xing Zhang Wenbo Wang

作者单位: Wireless Signal Processing and Network Lab Key Lab of Universal Wireless Communications Ministry of Education Beijing University of Posts and Telecommunications (BUPT) Beijing 100876 China

会议类型: 国际会议

会议名称: 2010 4th International Conference on Intelligent Information Techonlogy Application(第四届智能信息技术应用国际学术研讨会 IITA 2010)

会议地点: 秦皇岛

会议语种:英文

页码: 246-249

在线出版日期: 2010-11-05（万方平台首次上网日期，不代表论文的发表时间）