Yang Licai, Shen Jun, Bao Shudi, Wei Shoushui
School of Control Science and Engineering, Shandong University, Jinan 250061, China.
Shenzhen Institutes of Advanced Technology, Chinese Academy of Sciences, Shenzhen 518055, China.
Sheng Wu Yi Xue Gong Cheng Xue Za Zhi. 2013 Oct;30(5):976-81.
To treat the problem of identification performance and the complexity of the algorithm, we proposed a piecewise linear representation and dynamic time warping (PLR-DTW) method for ECG biometric identification. Firstly we detected R peaks to get the heartbeats after denoising preprocessing. Then we used the PLR method to keep important information of an ECG signal segment while reducing the data dimension at the same time. The improved DTW method was used for similarity measurements between the test data and the templates. The performance evaluation was carried out on the two ECG databases: PTB and MIT-BIH. The analystic results showed that compared to the discrete wavelet transform method, the proposed PLR-DTW method achieved a higher accuracy rate which is nearly 8% of rising, and saved about 30% operation time, and this demonstrated that the proposed method could provide a better performance.
为了解决识别性能和算法复杂度的问题，我们提出了一种用于心电图生物特征识别的分段线性表示和动态时间规整（PLR-DTW）方法。首先，我们在去噪预处理后检测R波峰以获取心跳。然后，我们使用PLR方法在降低数据维度的同时保留心电图信号段的重要信息。改进的DTW方法用于测试数据与模板之间的相似度测量。在两个心电图数据库PTB和MIT-BIH上进行了性能评估。分析结果表明，与离散小波变换方法相比，所提出的PLR-DTW方法实现了更高的准确率，提高了近8%，并节省了约30%的运算时间，这表明所提出的方法可以提供更好的性能。
