ECG segmentation algorithm based on bidirectional hidden semi-Markov model

被引:6
作者
Huo, Rui [1 ]
Zhang, Liting [2 ]
Liu, Feifei [3 ]
Wang, Ying [1 ]
Liang, Yesong [1 ]
Wei, Shoushui [1 ]
机构
[1] Shandong Univ, Sch Control Sci & Engn, Jinan, Peoples R China
[2] Shandong Univ, Shandong Prov Hosp, Dept Cardiol, Jinan, Peoples R China
[3] Shandong Jianzhu Univ, Sch Sci, Jinan, Peoples R China
基金
中国国家自然科学基金; 国家重点研发计划;
关键词
ECG signal; Segmentation; Hidden semi-markov model; Viterbi algorithm; CVDs;
D O I
10.1016/j.compbiomed.2022.106081
中图分类号
Q [生物科学];
学科分类号
07 ; 0710 ; 09 ;
摘要
Accurate segmentation of electrocardiogram (ECG) waves is crucial for cardiovascular diseases (CVDs). In this study, a bidirectional hidden semi-Markov model (BI-HSMM) based on the probability distributions of ECG waveform duration was proposed for ECG wave segmentation. Four feature-vectors of ECG signals were extracted as the observation sequence of the hidden Markov model (HMM), and the statistical probability distribution of each waveform duration was counted. Logistic regression (LR) was used to train model parameters. The starting and ending positions of the QRS wave were first detected, and thereafter, bidirectional prediction was employed for the other waves. Forwardly, ST segment, T wave, and TP segment were predicted. Backwardly, P wave and PQ segments were detected. The Viterbi algorithm was improved by integrating the recursive formula of the forward prediction and backward backtracking algorithms. In the QT database, the proposed method demonstrated excellent performance (Acc = 97.98%, F1 score of P wave = 98.37%, F1 score of QRS wave = 97.60%, F1 score of T wave = 97.79%). For the wearable dynamic electrocardiography (DCG) signals collected by the Shandong Provincial Hospital (SPH), the detection accuracy was 99.71% and the F1 of each waveform was above 99%. The experimental results and real DCG signal validation confirmed that the proposed new BI-HSMM method exhibits significant ability to segment the resting and DCG signals; this is conducive to the detection and monitoring of CVDs.
引用
收藏
页数:13
相关论文
共 50 条
[41]   H∞ control of singularly perturbed systems using deficient hidden semi-Markov model [J].
Men, Yunzhe ;
Sun, Jian .
NONLINEAR ANALYSIS-HYBRID SYSTEMS, 2024, 52
[42]   A predictive Hidden semi-Markov Model for bridges subject to chloride-induced deterioration [J].
Guo, Chunhui ;
Liang, Zhenglin ;
Zeng, Junqi ;
Song, Minyuan ;
Xue, Zongqi .
2021 21ST INTERNATIONAL CONFERENCE ON SOFTWARE QUALITY, RELIABILITY AND SECURITY COMPANION (QRS-C 2021), 2021, :751-756
[43]   Robust hidden semi-Markov modeling of array CGH data [J].
Ding, Jiarui ;
Shah, Sohrab P. .
2010 IEEE INTERNATIONAL CONFERENCE ON BIOINFORMATICS AND BIOMEDICINE, 2010, :603-608
[44]   Hidden semi-Markov models for machinery health diagnosis and prognosis [J].
Dong, M ;
He, D .
TRANSACTIONS OF THE NORTH AMERICAN MANUFACTURING RESEARCH INSTITUTION OF SME, VOL 32, 2004, 2004, :199-206
[45]   Modified hidden semi-Markov models for motor wear prognosis [J].
Wu, X. ;
Li, Y. ;
Teng, W. .
PROCEEDINGS OF THE INSTITUTION OF MECHANICAL ENGINEERS PART J-JOURNAL OF ENGINEERING TRIBOLOGY, 2012, 226 (J2) :174-179
[46]   Estimating hidden semi-Markov chains from discrete sequences [J].
Guédon, Y .
JOURNAL OF COMPUTATIONAL AND GRAPHICAL STATISTICS, 2003, 12 (03) :604-639
[47]   Hidden semi-Markov model-based methodology for multi-sensor equipment health diagnosis and prognosis [J].
Dong, Ming ;
He, David .
EUROPEAN JOURNAL OF OPERATIONAL RESEARCH, 2007, 178 (03) :858-878
[48]   Unsupervised hidden semi-Markov model for automatic beat onset detection in 1D Doppler ultrasound [J].
Katebi, Nasim ;
Marzbanrad, Faezeh ;
Stroux, Lisa ;
Valderrama, Camilo E. ;
Clifford, Gari D. .
PHYSIOLOGICAL MEASUREMENT, 2020, 41 (08)
[49]   Detection of LDoS Attacks Based on Wavelet Energy Entropy and Hidden Semi-Markov Models [J].
Wu Z.-J. ;
Li H.-J. ;
Liu L. ;
Zhang J.-A. ;
Yue M. ;
Lei J. .
Ruan Jian Xue Bao/Journal of Software, 2020, 31 (05) :1549-1562
[50]   Hidden Semi-Markov Models-Based Visual Perceptual State Recognition for Pilots [J].
Gao, Lina ;
Wang, Changyuan ;
Wu, Gongpu .
SENSORS, 2023, 23 (14)