在无线传感器网络(WSNs)的研究与应用中,利用数据融合来提高网络中能量利用率是其中一个重要的研究方向。文章利用BP(Back Propagation)神经网络能够对曲线进行无限逼近的特性来对无线传感器的监测数据进行数据拟合,然后传输拟合好的权值与阈值,同时通过将上一次拟合的权值与阈值赋予下一次拟合来减少神经网络的训练步数:模拟实验表明利用该方案能够有效减少数据的传输量,从而达到高效利用传感器能量的目的。
In the research and application of Wireless Sensor Networks (WSNs), the use of data fusion to improve energy efficiency is an important direction. Due to the fact that BP Neural Network can he used to approximate a curve unlimitedly, we use it for data fusion in WSNs, and then send the weight and thresho]d rather than the raw data monitored from sensors to the sink, at the same time, using the weight and threshold in the last fitting as the input of the new fitting, the number of Neural Network training steps can be reduced greatly. Simulation experiments show that the proposed scheme can be effectively reduce data transmissions, so as to achieve energy efficiency in WSNs.