本文選題：心電圖　切入點(diǎn)：集成學(xué)習(xí)　出處：《生物醫(yī)學(xué)工程學(xué)雜志》2016年05期 　論文類型：期刊論文

【摘要】：隨著心電圖數(shù)據(jù)量快速增長(zhǎng),計(jì)算機(jī)輔助心電圖分析也有著越來(lái)越廣闊的應(yīng)用需求。本文在基于導(dǎo)聯(lián)卷積神經(jīng)網(wǎng)絡(luò)的臨床心電圖分類算法上提出多種策略,進(jìn)一步提升其在實(shí)際應(yīng)用中的性能。首先用不同的預(yù)處理方法和訓(xùn)練方法獲得兩個(gè)不同的分類器,接著用多重輸出預(yù)測(cè)法來(lái)增強(qiáng)每個(gè)分類器的性能,最后用貝葉斯方法進(jìn)行融合。測(cè)試了超過15萬(wàn)條心電圖記錄,所提方法的準(zhǔn)確率和受試者工作特征曲線下面積(AUC)分別為85.04%和0.918 5,明顯優(yōu)于基于特征提取的傳統(tǒng)方法。
[Abstract]:With the rapid growth of ECG data, computer-aided ECG analysis has more and more extensive application needs. This paper proposes a variety of strategies on clinical ECG classification algorithm based on lead convolution neural network. Firstly, two different classifiers are obtained by using different preprocessing methods and training methods, and then the performance of each classifier is enhanced by using multiple output prediction method. Finally, more than 150,000 ECG records were tested by Bayesian method. The accuracy of the proposed method and the area under the operating characteristic curve were 85.04% and 0.918 5, respectively, which were obviously superior to the traditional method based on feature extraction.
【作者單位】： 中國(guó)科學(xué)院蘇州納米技術(shù)與納米仿生研究所;中國(guó)科學(xué)院大學(xué);
【分類號(hào)】：R540.41;TP391.4
，

本文編號(hào)：1613140