TY - GEN
T1 - Automatic Classification of Heartbeats Using ECG Signals via Higher Order Hidden Markov Model
AU - Liao, Ying
AU - Xiang, Yisha
AU - Du, Dongping
N1 - Publisher Copyright:
© 2020 IEEE.
PY - 2020/8
Y1 - 2020/8
N2 - Analysis of heartbeat signals is critical to provide information for the diagnosis of cardiac diseases, e.g., beat detection, segmentation and classification based on electrocardiogram (ECG) signals. This paper proposes an automatic heartbeat classification system based on higher order hidden Markov models (HOHMMs). The proposed system consists of four stages: ECG signal preprocessing stage, HOHMM learning stage, decoding stage, and classification stage. The HOHMM extends the basic hidden Markov model (HMM) by allowing the hidden state to depend on its more distant past, which is used to identify heartbeat patterns utilizing the collected ECG data. The learned HOHMMs are then used to decode and classify new heartbeats with unknown types. A case study is conducted to evaluate the classification performance of the proposed system using MIT-BIH Arrhythmia database. Experimental results show that the developed classification system performs reasonably well, especially for arrhythmia detection.
AB - Analysis of heartbeat signals is critical to provide information for the diagnosis of cardiac diseases, e.g., beat detection, segmentation and classification based on electrocardiogram (ECG) signals. This paper proposes an automatic heartbeat classification system based on higher order hidden Markov models (HOHMMs). The proposed system consists of four stages: ECG signal preprocessing stage, HOHMM learning stage, decoding stage, and classification stage. The HOHMM extends the basic hidden Markov model (HMM) by allowing the hidden state to depend on its more distant past, which is used to identify heartbeat patterns utilizing the collected ECG data. The learned HOHMMs are then used to decode and classify new heartbeats with unknown types. A case study is conducted to evaluate the classification performance of the proposed system using MIT-BIH Arrhythmia database. Experimental results show that the developed classification system performs reasonably well, especially for arrhythmia detection.
KW - ECG
KW - HOHMM
KW - MITBIH Arrhythmia database
KW - heartbeat classification
UR - http://www.scopus.com/inward/record.url?scp=85094097092&partnerID=8YFLogxK
U2 - 10.1109/CASE48305.2020.9216956
DO - 10.1109/CASE48305.2020.9216956
M3 - Conference contribution
AN - SCOPUS:85094097092
T3 - IEEE International Conference on Automation Science and Engineering
SP - 69
EP - 74
BT - 2020 IEEE 16th International Conference on Automation Science and Engineering, CASE 2020
PB - IEEE Computer Society
T2 - 16th IEEE International Conference on Automation Science and Engineering, CASE 2020
Y2 - 20 August 2020 through 21 August 2020
ER -