摘要
本文提出了一种基于频域特征的心电信号身份识别的方法,利用傅立叶变换对心电信号进行频域分析,得到心电信号的幅频特性图谱,提取包括信号频域斜率、谐波数、幅度差值等特征参数,以及根据傅里叶变换,得到心电信号的能量谱中的低频能量、高频能量占总能量的比率构成代表心电波形的特征向量.分别利用相关分析和神经网络分类器进行识别,其中基于神经网络的身份识别准确率达到96.4%.
The paper proposed a human identification strategy based on ECG (electrocardiogram) frequency domain features. Fourier transform was used on ECG signal to get frequency domain features. The features contained frequency-domain signal slope, harmonic number, the magnitude gap, ratio of different frequency energy to total energy. Classifiers of correlation analysis and neural network were used in identification, and the accuracy of neural network reached 96.4%.
出处
《天津理工大学学报》
2015年第6期34-39,共6页
Journal of Tianjin University of Technology
基金
天津市自然科学基金项目(15JCYBJC15800)
天津市科技支撑计划重点项目(10ZCKFSF00800)
关键词
幅频特征
能量谱
神经网络
amplitude frequency characteristics
energy spectrum
the neural network