基于稀疏分解和模糊理论的心电信号波形检测及识别  

The Detection and Recognition of Electrocardiogram's Waveform Based on Sparse Decomposition and Fuzzy Theory

作　　者：王春光[1] 刘金江[2] 孙即祥[1] 

机构地区：[1]国防科技大学电子科学与工程学院,湖南长沙410073 [2]南阳师范学院计算机系,河南南阳473061

出　　处：《信号处理》2009年第7期1057-1061,共5页Journal of Signal Processing

摘　　要：心电图是现代医学的一个重要诊断依据。用计算机检测识别心电信号波形,能缓解越来越庞大的心电数据给医务人员带来的工作压力,减少因疲劳、疏忽以及主观偏差产生的误差。利用改进的Gabor字典和粒子群优化算法,对心电信号做稀疏分解,并根据所得系数及对应的原子特性,建立模糊规则检测QRS波群。再在QRS波群前后,通过稀疏分解找到最有可能对应着P波、T波的原子,然后用模糊系统完成P波、T波的检测识别。实验表明,算法QRS波群检测正确率高,P波、T波波形识别符合专家的主观判断,算法切实可行。Electrocardiogram （ECG） is an important method of diagnosis. Using computer to detect and recognize all kinds of wave of ECG can release doctor＇ s tension coming from more and more ECG data, and decrease error because of tiredness, negligence, and subjective warp. Based on Gabor dictionary modified and the particle swarm optimization, ECG data are decomposed by the theory of sparse decomposition. Then, to detect QRS-complex, the fuzzy rules are instituted in term of coefficients and atoms. Beside QRS-complex, atoms which represent P-wave or T-wave with the most probability can be found through sparse decomposition, and then the detections and reorganizations of P-waves and T-waves can be completed with the help of fuzzy system. The experiments have proved the algorithm proposed could get a high ratio of QRS-complex＇ s detection, and recognitions of P-waves and T-waves were accord with expert＇ s judgments.

关 键 词：稀疏分解 模糊理论 粒子群优化 心电信号 波形检测识别 

分 类 号：TN911.72[电子电信—通信与信息系统]