【摘要】 针对无线传感器网络中通信数据的高维、高冗余现象,基于高维空间往往可以由其低维来本质表示这一特性,提出一种基于广义逆非负矩阵分解的无线传感器网络节能通信(giNMF)算法。首先,采用奇异值分解方法对原始通信数据矩阵进行初始化操作,求出其对应的特征空间;然后,采用非负矩阵分解方法对奇异值分解后的矩阵进行降维操作,利用乘法更新法快速求解出最终降维结果。仿真实验结果表明:giNMF算法能够对通信数据进行有效压缩,从而降低通信能耗,延长网络生命周期,达到节能的目的。更多还原

【Abstract】 In order to solve the dilemma of the high-dimensional and high-redundant communication data in wireless sensor networks(WSNs),based on the fact that low-dimensional manifold of plausible space embedded in the high-dimensional space,novel algorithm(giNMF) using generalized inverse nonnegative matrix factorization was proposed for energy-efficient communication in WSNs.Firstly,a singular value decomposition(SVD) method was employed to initialize the original communication data matrix,and the corresponding feature space was found.Then,the nonnegative matrix factorization(NMF) approach was adopted to reduce dimensions of the matrix decomposed by SVD into lower dimensions,and the multiplication update law was used quickly to acquire the final dimension reduction results.The numerical results show that giNMF has its effectiveness in compressing the communication data,so as to reduce the communication energy consumption and prolong the network lifetime,and finally to achieve the goal of energy saving.更多还原