基于递推最小二乘和改进支持度的WSN数据融合算法

Data Fusion Method Based on Recursive Least Square and Improved Support for WSN

中文关键词:  WSN  数据融合  递推最小二乘  支持度函数  分批融合

英文关键词:WSN  data fusion  recursive least square  support function  batch fusion

中文摘要:

      无线传感器网络(WSN)在空间和时间上均存在数据冗余问题。为了在保证精度的前提下减少冗余量，提出了基于递推最小二乘和改进支持度的WSN数据融合方法。针对单个传感器节点，采用递推最小二乘法进行数据融合。针对节点之间的冗余问题，应用分批融合思想对系统降维，将灰色接近度理论与自支持度结合改进支持度函数，对各子系统分别采用基于改进支持度函数的加权算法进行融合。采用一个包含7个传感器节点的无线传感器网络对该算法进行了检验。结果表明，该融合算法能够显著减少数据计算量与传输量。融合后的数据均方误差为0.1597，能够满足实际应用对精度的要求。

英文摘要:

      Wireless sensor networks (WSN) have data redundancy in both space and time.To ensure accuracy while reducing the amount of redundancy,a data fusion method based on recursive least square and improved support for WSN is proposed.For a single sensor node,recursive least square method was used for data fusion within the node.To solve the problem of data redundancy among nodes,the idea of batch fusion was used to reduce the dimensionality of the system,the theory of gray proximity and self-support were combined to improve the support function,then subsystems were respectively weighted based on the improved support function.The algorithm was tested by using WSN with seven sensor nodes.The results show that the amount of data calculation and transmission can be significantly reduced.The data mean square error is 0.1597 after fusion,which meets the precision requirements of practical applications.