【摘要】：J波檢測在臨床上可以作為判定某些心臟病的一種非創(chuàng)性的標(biāo)記手段。主要定義了5個精確反映J波特性的特征向量,包括3個時域特征向量和兩個基于小波的特征向量,并使用主成分分析減少特征向量的維數(shù),作為分類器的輸入。利用這些特征向量訓(xùn)練隱馬爾可夫模型作為分類器,輸出最終的判定結(jié)果。結(jié)果表明,提出的方法提供了93.8%的平均準(zhǔn)確度、94.2%的平均敏感性、93.3%的平均特異性和93.4%的平均陽性預(yù)測值,揭示了很高的評價標(biāo)準(zhǔn),表明該方法有能力準(zhǔn)確地檢測識別J波,并且可以利用該方法檢測心電圖中的其他病變波形。
[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.
【作者單位】： 太原理工大學(xué)信息工程學(xué)院;
【基金】：國家自然科學(xué)基金面上項目(61371062) 山西省國際科技合作項目(2014081029-1) 山西省留學(xué)回國人員科研資助項目(2013-032)
【分類號】：R540.41
，

本文編號：2174984