本文選題：心律失常分類 + 循環(huán)譜�。� 參考：《計(jì)算機(jī)科學(xué)與探索》2017年11期

【摘要】：心電信號(hào)心律失常分類性能主要取決于有效的特征提取和分類器設(shè)計(jì)。針對(duì)傳統(tǒng)心律失常分類研究中,多數(shù)研究直接利用時(shí)域或者頻域特征實(shí)現(xiàn)心律失常分類,對(duì)于多類別的分類性能仍有待提高。鑒于此,選用循環(huán)譜分析方法實(shí)現(xiàn)心律失常多分類任務(wù)。假設(shè)信號(hào)處于非平穩(wěn)狀態(tài),建立更符合心電信號(hào)實(shí)際狀態(tài)的模型去捕捉心電信號(hào)中的隱含周期實(shí)現(xiàn)心律失常分類。在提取形態(tài)特征和時(shí)頻域小波系數(shù)特征之外,利用循環(huán)譜技術(shù)提取了譜相關(guān)系數(shù)特征用于后續(xù)多分類任務(wù)。除此之外,比較了人工神經(jīng)網(wǎng)絡(luò)、傳統(tǒng)支持向量機(jī)和超限學(xué)習(xí)機(jī)分類器在該實(shí)驗(yàn)環(huán)境下的分類性能,通過多組對(duì)比實(shí)驗(yàn),結(jié)果表明,利用循環(huán)譜技術(shù)結(jié)合超限學(xué)習(xí)機(jī)分類器進(jìn)行心律失常分類,可以區(qū)分10類心律失常并在MIT-BIH心律失常數(shù)據(jù)庫上實(shí)現(xiàn)了98.13%的平均分類準(zhǔn)確率。
[Abstract]:The performance of ECG arrhythmia classification mainly depends on the effective feature extraction and classifier design. In the traditional classification of arrhythmia, most of the studies directly use the time-domain or frequency-domain features to achieve the classification of arrhythmias, but the classification performance of multi-category still needs to be improved. In view of this, circulatory spectrum analysis was used to achieve multi-classification task of arrhythmia. Assuming that the signal is in a non-stationary state, a model which is more consistent with the actual state of the ECG signal is established to capture the hidden period in the ECG signal to realize the classification of arrhythmia. In addition to morphological features and wavelet coefficients in time-frequency domain, spectral correlation coefficients are extracted by cyclic spectrum technique for subsequent multi-classification tasks. In addition, the classification performance of artificial neural network, traditional support vector machine and over-limit learning machine classifier in this experimental environment is compared. Using circulatory spectrum technology and learning machine classifier to classify arrhythmias, 10 kinds of arrhythmias can be distinguished and the average classification accuracy is 98.13% on MIT-BIH arrhythmia database.
【作者單位】： 天津大學(xué)電子信息工程學(xué)院;
【基金】：國家自然科學(xué)基金,No.61271069~~
【分類號(hào)】：R541.7;TP18

【相似文獻(xiàn)】

相關(guān)碩士學(xué)位論文 前1條

1 王曉娜;面向可穿戴式心電監(jiān)護(hù)設(shè)備的信號(hào)處理與分類方法研究[D];天津大學(xué);2016年

，

本文編號(hào)：1942406