生物医学工程学杂志

生物医学工程学杂志

基于递归最小二乘法的回声状态网络算法用于心电信号降噪

查看全文

远程医疗的复杂环境中,心电信号极易被噪声淹没,从而影响心血管疾病的智能诊断。基于此,本文提出了一种基于递归最小二乘法的回声状态网络心电信号降噪算法。该算法通过递归最小二乘法对该网络进行训练,可自动学习得到含噪心电数据中非线性的且具有区分度的深层次特征,并利用这些特征自动分离心电信号与噪声。实验中,采用信噪比和均方根误差为指标,将本文方法与基于子带自适应阈值的小波变换法和 S 变换法进行比较。实验结果表明,本方法降噪精度更优,同时信号的低频成分也得到了很好的保持。本文方法可做到消除心电信号中的复杂噪声并完整保留心电信号的形态,为心电图的特征检测和心血管疾病的智能诊断奠定了基础。

Electrocardiogram (ECG) is easily submerged in noise of the complex environment during remote medical treatment, and this affects the intelligent diagnosis of cardiovascular diseases. Considering this situation, this paper proposes an echo state network (ESN) denoising algorithm based on recursive least square (RLS) for ECG signals. The algorithm trains the ESN through the RLS method, and can automatically learn the deep nonlinear and differentiated characteristics in the noisy ECG data, and then the network can use these characteristic to separate out clear ECG signals automatically. In the experiment, the proposed method is compared with the wavelet transform with subband dependent threshold and the S-transform method by evaluating the signal-to-noise ratio and root mean square error. Experimental results show that the denoising accuracy is better and the low frequency component of the signal is well preserved. This method can effectively filter out complex noise and effectively preserve the effective information of ECG signals, which lays a foundation for the recognition of ECG signal feature waveform and the intelligent diagnosis of cardiovascular disease.

关键词: 心电信号; 降噪; 回声状态网络; 递归最小二乘法

Key words: electrocardiogram signal; denoising; echo state network; recursive least square

引用本文: 张杰烁, 刘明, 李鑫, 熊鹏, 刘秀玲. 基于递归最小二乘法的回声状态网络算法用于心电信号降噪. 生物医学工程学杂志, 2018, 35(4): 539-549. doi: 10.7507/1001-5515.201710072 复制

登录后 ,请手动点击刷新查看全文内容。 没有账号,
登录后 ,请手动点击刷新查看图表内容。 没有账号,
1. 陈伟伟, 高润霖, 刘力生, 等. 《中国心血管病报告 2017》概要. 中国循环杂志, 2018, 33(1): 1-8.
2. 刘胜洋, 张根选, 曹阳. 心电信号中的工频干扰滤除方法. 生物医学工程学杂志, 2014, (3): 577-582.
3. Kaergaard K, Jensen S H, Puthusserypady S. A comprehensive performance analysis of EEMD-BLMS and DWT-NN hybrid algorithms for ECG denoising. Biomed Signal Process Control, 2016, 25: 178-187.
4. Jebaraj J, Arumugam R. Ensemble empirical mode decomposition-based optimised power line interference removal algorithm for electrocardiogram signal. IET Signal Processing, 2016, 10(6): 583-591.
5. Alickovic E, Subasi A. Effect of multiscale PCA de-noising in ECG beat classification for diagnosis of cardiovascular diseases. Circuits Systems and Signal Processing, 2015, 34(2): 513-533.
6. Barhatte A S, Ghongade R, Tekale S V. Noise analysis of ECG signal using fast ICA// Advances in Signal Processing. Pune, 2016: 118-122.
7. Sadhukhan D, Mitra M. ECG noise reduction using Fourier coefficient suppression// International Conference on Control, Instrumentation, Energy and Communication. Calcutta, 2014: 142-146.
8. Ari S, Das M K, Chacko A. ECG signal enhancement using S-Transform. Comput Biol Med, 2013, 43(6): 649-660.
9. 刘秀玲, 乔磊, 杨建利, 等. 改进小波阈值法用于心电信号去噪. 生物医学工程学杂志, 2014, (3): 511-515.
10. Singh O, Sunkaria R K. ECG signal denoising via empirical wavelet transform. Australasian Physical & Engineering Sciences in Medicine, 2017, 40(1): 219-229.
11. Alyasseri Z A, Khader A T, Al-Betar M A, et al. Hybridizing beta-hill climbing with wavelet transform for denoising ECG signals. Inf Sci (Ny), 2018, 429: 229-246.
12. Goldberger A L, Amaral L A, Glass L, et al. PhysioBank, PhysioToolkit, and PhysioNet: components of a new research resource for complex physiologic signals. Circulation, 2000, 101(23): E215-E220.
13. Jaeger H. The " echo state” approach to analysing and training recurrent neural networks, überwachtes lernen, 2001:1-47.
14. 韩敏, 孙磊磊, 洪晓军. 基于回声状态网络的脑电信号特征提取. 生物医学工程学杂志, 2012, 29(2): 206-211.
15. Jaeger H, Haas H. Harnessing nonlinearity:predicting chaotic systems and saving energy in wireless telecommunication. Science, 2004, 304(5667): 78-80.
16. 敖露. LMS和RLS算法在自适应逆控制中的应用. 工业控制计算机, 2012, 25(5): 75-77.
17. Zhang Bo, Zhao Jiasheng, Chen Xiao, et al. ECG data compression using a neural network model based on multi-objective optimization. PLoS One, 2017, 12(10): e0182500.
18. Petrėnas A, Sörnmo L, Lukoševičius A, et al. Detection of occult paroxysmal atrial fibrillation. Med Biol Eng Comput, 2015, 53(4): 287-297.
19. 彭宇, 王建民, 彭喜元. 基于回声状态网络的时间序列预测方法研究. 电子学报, 2010, 38(S1): 148-154.
20. Park B G, Kim R Y, Hyun D S. Fault diagnosis using recursive least square algorithm for permanent magnet synchronous motor drives// IEEE International Conference on Power Electronics and Ecce Asia. Jeju, South Korea: 2011: 2506-2510.