基于过完备字典的体域网压缩感知心电重构

ECG Reconstruction of Body Sensor Network Using Compressed Sensing Based on Overcomplete Dictionary

针对体域网远程监护中心对重构的心电信号（Electrocardiogram，ECG）精度要求高和体域网（Bodysensornet—work，BSN）低功耗问题，提出基于过完备字典的体域网压缩感知心电重构方法．该方法利用压缩感知理论，在传感节点端利用随机二进制矩阵对心电信号进行观测，观测值被传送至远程监护中心后，再利用基于K—SVD算法训练得到的过完备字典和块稀疏贝叶斯学习重构算法对心电信号进行重构．仿真结果表明，当心电信号压缩率在70％-95％时，基于K—SVD过完备字典比基于离散余弦变换基的压缩感知心电重构信噪比高出5—22dB．该方法具有信号重构精度高、功耗低和易于硬件实现的优点．

Regarding to tackle the problem of demanding high accuracy reconstruction electrocardiogram （ECG） signal in a remote monitoring center of the body sensor network （BSN） and the low power problem of the body sensor network, this paper proposes a method of ECG reconstruction of body sensor network using compressed sensing based on overcomplete dictionary. The proposed method uses the compressed sensing theory and random binary matrices as the sensing matrix to measure the ECG signal on the sensor nodes. After the measured value is transmitted to the remote monitoring center, the overcomplete dictionary based on K-SVD algorithm training and the block sparse Bayesian learning reconstruction algorithm are used to reconstruct the ECG signal. Simulation results show that the SNR of the compressed sensing reconstruction ECG based on K-SVD overcomplete dictionary method is 5 - 22 dB higher than that of the method using discrete cosine transform when the ECG signal compression rate is at 70 % - 95 %. The method has the advantages of high accuracy of signal reconstruction, low power, and easy hardware implementation.