Convolutional Autoencoding and Gaussian Mixture Clustering for Unsupervised Beat-to-Beat Heart Rate Estimation of Electrocardiograms from Wearable Sensors
Jun Zhong,
Dong Hai,
Jiaxin Cheng,
Changzhe Jiao,
Shuiping Gou,
Yongfeng Liu,
Hong Zhou,
Wenliang Zhu
Affiliations
Jun Zhong
Suzhou Institute of Biomedical Engineering and Technology, Chinese Academy of Sciences, Suzhou 215163, China
Dong Hai
Suzhou Institute of Biomedical Engineering and Technology, Chinese Academy of Sciences, Suzhou 215163, China
Jiaxin Cheng
Key Laboratory of Intelligent Perception and Image Understanding of Ministry of Education of China, School of Artificial Intelligence, Xidian University, Xi’an 710071, China
Changzhe Jiao
Key Laboratory of Intelligent Perception and Image Understanding of Ministry of Education of China, School of Artificial Intelligence, Xidian University, Xi’an 710071, China
Shuiping Gou
Key Laboratory of Intelligent Perception and Image Understanding of Ministry of Education of China, School of Artificial Intelligence, Xidian University, Xi’an 710071, China
Yongfeng Liu
Suzhou Institute of Biomedical Engineering and Technology, Chinese Academy of Sciences, Suzhou 215163, China
Hong Zhou
Suzhou Institute of Biomedical Engineering and Technology, Chinese Academy of Sciences, Suzhou 215163, China
Wenliang Zhu
Suzhou Institute of Biomedical Engineering and Technology, Chinese Academy of Sciences, Suzhou 215163, China
Heart rate is one of the most important diagnostic bases for cardiovascular disease. This paper introduces a deep autoencoding strategy into feature extraction of electrocardiogram (ECG) signals, and proposes a beat-to-beat heart rate estimation method based on convolution autoencoding and Gaussian mixture clustering. The high-level heartbeat features were first extracted in an unsupervised manner by training the convolutional autoencoder network, and then the adaptive Gaussian mixture clustering was applied to detect the heartbeat locations from the extracted features, and calculated the beat-to-beat heart rate. Compared with the existing heartbeat classification/detection methods, the proposed unsupervised feature learning and heartbeat clustering method does not rely on accurate labeling of each heartbeat location, which could save a lot of time and effort in human annotations. Experimental results demonstrate that the proposed method maintains better accuracy and generalization ability compared with the existing ECG heart rate estimation methods and could be a robust long-time heart rate monitoring solution for wearable ECG devices.
