基于流形学习的多源传感器体域网数据融合模型  

Multi-source Sensor Body Area Network Data Fusion Model Based on Manifold Learning

作　　者：张俊 王杨 李坤豪 李昌 赵传信 ZHANG Jun;WANG Yang;LI Kun-hao;LI Chang;ZHAO Chuan-xin(School of Computer and Information,Anhui Normal University,Wuhu,Anhui 241003,China)

机构地区：[1]安徽师范大学计算机与信息学院,安徽芜湖241003

出　　处：《计算机科学》2020年第8期323-328,共6页Computer Science

基　　金：国家自然科学基金(61871412);安徽省自然科学基金重点项目(KJ2019A0938);安徽省社科规划项目(AHSKY2017D42);安徽省高校优秀青年人才支持计划一般项目(gxyq2017140);安徽省质量工程重大项目(2018jyxm0342);安徽省教育厅项目(gxyqZD2016593)。

摘　　要：无线体域网多传感器由于采集的数据量大、数据类型冗杂,难以有效进行多维度数据的融合。虽然传统流形及分解类型的数据融合方法(Isomap,MDS,PCA等)具备使距离较小点产生合理排斥梯度的能力和受异常影响较小的优点,但是针对无线多传感器体域网的数据降维效果并不理想。对此,提出了一种基于流形学习的T分布式随机邻域嵌入(T-SNE)算法对多传感器体域网数据进行融合。T-SNE算法首先将高维数据点与其对应的低维数据点间的欧氏距离转换为条件概率矩阵,然后对处理好的低维概率集合进行有限次迭代,最后更新低维概率矩阵,使距离较小点间产生合理的排斥梯度,从而构建了多维度体域网数据融合模型。实验结果表明,在特定的体域网数据集下,T-SNE算法的精度为Isomap的1.11倍,MDS的1.33倍,PCA的1.21倍,具有较好的数据降维效果。Due to the problem of large amount of data collected by multi-sensors in wireless body area networks and redundant data types,it is difficult to effectively perform multi-dimensional data fusion.Although traditional manifold and decomposition data fusion methods(Isomap,MDS,PCA,etc.)have the ability to generate a reasonable rejection gradient at a small distance and are less affected by anomalies,the data dimension reduction effect for wireless multi-sensor volume domain networks is not ideal.Therefore,this paper proposed the T-SNE algorithm based on manifold learning to fuse multi-sensor body area network data.The T-SNE algorithm first converts the Euclidean distance between a high-dimensional data point and its corresponding low-dimensional data point into a conditional probability matrix,then iterates the processed low-dimensional probability set a finite number of times,and finally updates the low-dimensional probability matrix to make the distance more reasonable exclusion gradient be generated between the small points,and a multi-dimensional body area network data fusion model is constructed.Experimental results show that compared with the traditional manifold reduction algorithm and traditional decomposition dimensionality reduction algorithm under a specific body area network data set,the T-SNE algorithm has a precision of 1.11 times that of Isomap,1.33 times that of MDS,and 1.21 times that of PCA,achieves a better data dimensionality reduction effect.

关 键 词：流形学习 数据融合 传感器 体域网 

分 类 号：TP393[自动化与计算机技术—计算机应用技术]