Please wait a minute...
Front. Inform. Technol. Electron. Eng.  2014, Vol. 15 Issue (7): 564-573    DOI: 10.1631/jzus.C1300264
    
ECG quality assessment based on a kernel support vector machine and genetic algorithm with a feature matrix
Ya-tao Zhang, Cheng-yu Liu, Shou-shui Wei, Chang-zhi Wei, Fei-fei Liu
School of Control Science and Engineering, Shandong University, Jinan 250061, China; School of Mechanical, Electrical & Information Engineering, Shandong University, Weihai 264209, China; Institute of Cellular Medicine, Newcastle University, Newcastle upon Tyne, NE1 4LP, UK
Download:   PDF(0KB)
Export: BibTeX | EndNote (RIS)      

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%.

Key wordsECG quality assessment      Kernel support vector machine      Genetic algorithm      Power spectrum      Cross validation     
Received: 21 September 2013      Published: 10 July 2014
CLC:  TP181  
Cite this article:

Ya-tao Zhang, Cheng-yu Liu, Shou-shui Wei, Chang-zhi Wei, Fei-fei Liu. ECG quality assessment based on a kernel support vector machine and genetic algorithm with a feature matrix. Front. Inform. Technol. Electron. Eng., 2014, 15(7): 564-573.

URL:

http://www.zjujournals.com/xueshu/fitee/10.1631/jzus.C1300264     OR     http://www.zjujournals.com/xueshu/fitee/Y2014/V15/I7/564


基于非线性支持向量机和遗传算法的移动ECG质量评估

研究目的:为减少移动设备采集的ECG信号造成的误报警,避免远程心电监控中心的误诊和诊疗资源浪费,提高诊断准确率和效率,首先必须评估ECG信号质量。本文采用频域、时域相结合的ECG特征分析,结合非线性支持向量机(kernelsupportvectormachine, KSVM)和遗传算法,实现对ECG的质量分类。
创新要点:运用频域和时域相结合的ECG特征分析。对具有易于识别特征(如导联脱落)的ECG信号,直接依据该特征得出分类结果;对依据简单特征无法评判的ECG信号,提取复杂时、频域特征组成特征矩阵,运用KSVM进行分类。
方法提亮:根据ECG特征是否易于识别,分步骤采用根据特征直接分类和非线性支持向量机智能分类技术,降低算法复杂度和运算量(图1)。结合频域和时域,在ECG特征空间选择与扩展上进行了有效提升(公式4)。运用遗传算法优化了SVM参数。
重要结论:时、频域结合的特征分析能够较全面地反映ECG特征。KSVM智能分类技术能够有效提高分类精度。

关键词: ECG质量评估,  非线性支持向量机,  遗传算法,  功率谱,  交叉验证 
[1] Muhammad Asif Zahoor Raja, Iftikhar Ahmad, Imtiaz Khan, Muhammed Ibrahem Syam, Abdul Majid Wazwaz. Neuro-heuristic computational intelligence for solving nonlinear pantograph systems[J]. Front. Inform. Technol. Electron. Eng., 2017, 18(4): 464-484.
[2] Gang Xiong, Yu-xiang Hu, Le Tian, Ju-long Lan, Jun-fei Li, Qiao Zhou. A virtual service placement approach based on improved quantum genetic algorithm[J]. Front. Inform. Technol. Electron. Eng., 2016, 17(7): 661-671.
[3] Hamid Tabatabaee, Mohammad Reza Akbarzadeh-T, Naser Pariz. Dynamic task scheduling modeling in unstructured heterogeneous multiprocessor systems[J]. Front. Inform. Technol. Electron. Eng., 2014, 15(6): 423-434.
[4] Guangdong Tian, Hua Ke, Xiaowei Chen. Fuzzy cost-profit tradeoff model for locating a vehicle inspection station considering regional constraints[J]. Front. Inform. Technol. Electron. Eng., 2014, 15(12): 1138-1146.
[5] Da-yu Xu, Shan-lin Yang, Ren-ping Liu. A mixture of HMM, GA, and Elman network for load prediction in cloud-oriented data centers[J]. Front. Inform. Technol. Electron. Eng., 2013, 14(11): 845-858.
[6] Ozoemena Anthony Ani, He Xu, Yi-ping Shen, Shao-gang Liu, Kai Xue. Modeling and multiobjective optimization of traction performance for autonomous wheeled mobile robot in rough terrain[J]. Front. Inform. Technol. Electron. Eng., 2013, 14(1): 11-29.
[7] Ommolbanin Yousefi, Mirbahadorgholi Aryanezhad, Seyed Jafar Sadjadi, Arash Shahin. Developing a multi-objective, multi-item inventory model and three algorithms for its solution[J]. Front. Inform. Technol. Electron. Eng., 2012, 13(8): 601-612.
[8] Hossein Ghaffarian, Mohsen Soryani, Mahmood Fathy. Planning VANET infrastructures to improve safety awareness in curved roads[J]. Front. Inform. Technol. Electron. Eng., 2012, 13(12): 918-928.
[9] Xiao-hong Tan, Rui-min Shen, Yan Wang. Personalized course generation and evolution based on genetic algorithms[J]. Front. Inform. Technol. Electron. Eng., 2012, 13(12): 909-917.
[10] Zheng-min Kong, Liang Zhong, Guang-xi Zhu, Li Ding. Differential multiuser detection using a novel genetic algorithm for ultra-wideband systems in lognormal fading channel[J]. Front. Inform. Technol. Electron. Eng., 2011, 12(9): 754-765.
[11] Yuan-hong Shen, Xiao-hu Yang. A self-optimizing QoS-aware service composition approach in a context sensitive environment[J]. Front. Inform. Technol. Electron. Eng., 2011, 12(3): 221-238.
[12] Lei Zhang, Mattias Lampe, Zhi Wang. A hybrid genetic algorithm to optimize device allocation in industrial Ethernet networks with real-time constraints[J]. Front. Inform. Technol. Electron. Eng., 2011, 12(12): 965-975.
[13] Ellips Masehian, Davoud Sedighizadeh. Multi-objective robot motion planning using a particle swarm optimization model[J]. Front. Inform. Technol. Electron. Eng., 2010, 11(8): 607-619.