基于隐马尔科夫模型的J波自动识别检测

发布时间：2018-08-09 18:51

【摘要】：J波检测在临床上可以作为判定某些心脏病的一种非创性的标记手段。主要定义了5个精确反映J波特性的特征向量,包括3个时域特征向量和两个基于小波的特征向量,并使用主成分分析减少特征向量的维数,作为分类器的输入。利用这些特征向量训练隐马尔可夫模型作为分类器,输出最终的判定结果。结果表明,提出的方法提供了93.8%的平均准确度、94.2%的平均敏感性、93.3%的平均特异性和93.4%的平均阳性预测值,揭示了很高的评价标准,表明该方法有能力准确地检测识别J波,并且可以利用该方法检测心电图中的其他病变波形。
[Abstract]:J-wave detection can be used as a non-invasive marker for the diagnosis of some heart diseases. Five Eigenvectors which accurately reflect the characteristics of J wave are defined, including three time domain Eigenvectors and two wavelet based Eigenvectors, and the principal component analysis (PCA) is used to reduce the dimension of the Eigenvectors as the input of the classifier. These Eigenvectors are used to train hidden Markov models as classifiers to output the final decision results. The results show that the proposed method provides an average accuracy of 93.8%, an average sensitivity of 94.2%, an average specificity of 93.3% and an average positive predictive value of 93.4%. It reveals a high evaluation standard and shows that the method has the ability to accurately detect and identify J waves. And this method can be used to detect other pathological waveforms in electrocardiogram.
【作者单位】： 太原理工大学信息工程学院;
【基金】：国家自然科学基金面上项目(61371062) 山西省国际科技合作项目(2014081029-1) 山西省留学回国人员科研资助项目(2013-032)
【分类号】：R540.41
，

本文编号：2174984