Abstract: We propose a systematic ECG quality classification method based on a kernel support vector machine (KSVM) and genetic algorithm (GA) to determine whether ECGs collected via mobile phone are acceptable or not. This method includes mainly three modules, i.e., lead-fall detection, feature extraction, and intelligent classification. First, lead-fall detection is executed to make the initial classification. Then the power spectrum, baseline drifts, amplitude difference, and other time-domain features for ECGs are analyzed and quantified to form the feature matrix. Finally, the feature matrix is assessed using KSVM and GA to determine the ECG quality classification results. A Gaussian radial basis function (GRBF) is employed as the kernel function of KSVM and its performance is compared with that of the Mexican hat wavelet function (MHWF). GA is used to determine the optimal parameters of the KSVM classifier and its performance is compared with that of the grid search (GS) method. The performance of the proposed method was tested on a database from PhysioNet/Computing in Cardiology Challenge 2011, which includes 1500 12-lead ECG recordings. True positive (TP), false positive (FP), and classification accuracy were used as the assessment indices. For training database set A (1000 recordings), the optimal results were obtained using the combination of lead-fall, GA, and GRBF methods, and the corresponding results were: TP 92.89%, FP 5.68%, and classification accuracy 94.00%. For test database set B (500 recordings), the optimal results were also obtained using the combination of lead-fall, GA, and GRBF methods, and the classification accuracy was 91.80%.

基于非线性支持向量机和遗传算法的移动ECG质量评估

[1]Ataman, E., Aatre, V., Wong, K., 1980. A fast method for real-time median filtering. IEEE Trans. Acoust. Speech Signal Process., 28(4):415-421.

[2]Biswal, B., Biswal, M.K., Dash, P.K., et al., 2013. Power quality event characterization using support vector machine and optimization using advanced immune algorithm. Neurocomputing, 103:75-86.

[3]Chen, Y., Yang, H., 2012. Self-organized neural network for the quality control of 12-lead ECG signals. Physiol. Meas., 33(9):1399-1418.

[4]Clifford, G.D., Moody, G.B., 2012. Signal quality in cardiorespiratory monitoring. Physiol. Meas., 33(9):E01.

[5]Clifford, G.D., Behar, J., Li, Q., et al., 2012. Signal quality indices and data fusion for determining clinical acceptability of electrocardiograms. Physiol. Meas., 33(9):1419-1433.

[6]Han, L., Kendall, G., 2003. Guided operators for a hyperheuristic genetic algorithm. LNCS, 2903:807-820.

[7]Hayn, D., Jammerbund, B., Schreier, G., 2012. QRS detection based ECG quality assessment. Physiol. Meas., 33(9):1449-1462.

[8]Johannesen, L., Galeotti, L., 2012. Automatic ECG quality scoring methodology: mimicking human annotators. Physiol. Meas., 33(9):1479-1489.

[9]Kasturiwale, H.P., Deshmukh, C.N., 2009. Quality assessment of ICA for ECG signal analysis. 2nd Int. Conf. on Emerging Trends in Engineering and Technology, p.73-75.

[10]Khazaee, A., Ebrahimzadeh, A., 2010. Classification of electrocardiogram signals with support vector machines and genetic algorithms using power spectral features. Biomed. Signal Process. Contr., 5(4):252-263.

[11]Kligfield, P., Gettes, L.S., Bailey, J.J., et al., 2007. Recommendations for the standardization and interpretation of the electrocardiogram. Part I: the electrocardiogram and its technology. A scientific statement from the American Heart Association Electrocardiography and Arrhythmias Committee, Council on Clinical Cardiology; the American College of Cardiology Foundation; and the Heart Rhythm Society endorsed by the International Society for Computerized Electrocardiology. J. Am. Coll. Cardiol., 49(10):1109-1127.

[12]Langley, P., di Marco, L.Y., King, S., et al., 2011. An algorithm for assessment of quality of ECGs acquired via mobile telephones. IEEE 38th Annual Scientific Conf. of Computing in Cardiology, p.281-284.

[13]Li, Q., Clifford, G.D., 2012. Signal quality and data fusion for false alarm reduction in the intensive care unit. J. Electrocardiol., 45(6):596-603.

[14]Liu, C.Y., Li, P., Zhao, L.N., et al., 2011. Real-time signal quality assessment for ECGs collected using mobile phones. IEEE 38th Annual Scientific Conf. of Computing in Cardiology, p.357-360.

[15]Moody, G.B., 2011. Physionet/Computing in Cardiology Challenge 2011. Available from http://physionet.org/challenge/2011/.

[16]Ramakrishnan, A.G., Saha, S., 1997. ECG coding by wavelet-based linear prediction. IEEE Trans. Biomed. Eng., 44(12):1253-1261.

[17]Redmond, S.J., Xie, Y., Chang, D., et al., 2012. Electrocardiogram signal quality measures for unsupervised telehealth environments. Physiol. Meas., 33(9):1517-1534.

[18]Suh, S.C., Gurupur, V.P., Tanik, M.M., 2011. Biomedical Engineering: Health Care Systems, Technology and Techniques. Springer, New York, USA, p.211-227.

[19]Thakor, N.V., Webster, J.G., Tompkins, W.J., 1984. Estimation of QRS complex power spectra for design of a QRS filter. IEEE Trans. Biomed. Eng., 31(11):702-706.

[20]Wang, X., Yang, C., Qin, B., et al., 2005. Parameter selection of support vector regression based on hybrid optimization algorithm and its application. J. Contr. Theory Appl., 3(4):371-376.

[21]Zaunseder, S., Huhle, R., Malberg, H., 2011. Assessing the usability of ECG by ensemble decision trees. IEEE 38th Annual Scientific Conf. of Computing in Cardiology, p.277-280.

[22]Zhang, J.H., 2012. Optimization of kernel function parameters SVM based on the GA. Adv. Mater. Res., 433-440:4124-4128.