论文部分内容阅读
数据融合是无线传感器网络中减少节点能量消耗的一个基本方法.在基于预测的时域数据融合中,通过对传感器节点采集的时间序列数据进行分析,建立能够反映时间序列中所包含的动态依存关系的数学模型,从而减少节点间冗余数据的传输.本文引入流行学习中局部线性重构的思想,结合改进的极限学习机(Extreme Learning Machine),提出KNN-PSOELM数据预测模型.首先运用K近邻的方法对输入样本点进行局部线性重构,然后采用粒子群优化算法(Particle Swarm Optimization)改进极限学习机回归方法产生最优的初始参数.优化之后的模型不仅使得原始非线性传感器数据具有线性的特征,而且避免由异常数据样本引起的病态隐层输出矩阵,提高了模型的预测精度和泛化能力.实验结果表明了算法的有效性.
Data fusion is a basic method to reduce node energy consumption in WSN.Based on the prediction of time-domain data fusion, the time series data collected by sensor nodes are analyzed to establish the model that can reflect the dynamic dependencies contained in the time series , Which can reduce the redundant data transmission between nodes.This paper introduces the idea of local linear reconstruction in popular learning and puts forward the KNN-PSOELM data prediction model combined with the improved extreme learning machine.First, , The local linear reconstruction of the input sample points is carried out, and then the Particle Swarm Optimization (PSO) regression method is used to improve the optimal initial parameters. The optimized model not only makes the original nonlinear sensor data linear Feature, but also avoids the output layer of pathological hidden layer caused by abnormal data samples and improves the prediction accuracy and generalization ability of the model.The experimental results show the effectiveness of the algorithm.