Wireless Electrocardiograph Monitoring Based on Wavelet Convolutional Neural Network

Recently, cardiovascular diseases (CVD) have drawn high concerns from diversity of disciplines due to acute and fatal characteristics. Rapidly accumulating evidence suggests that CVD threats human health without any symptom. Finding a way to forestall it or notice ongoing warning becomes significant. Electrocardiograph (ECG) monitoring is one of the commonly used techniques to address this problem. The aim of this project is to explore various deep learning models with data collected from our developed wearable ECG patch: IREALCARE. We applied new dataset and tested the performance of existing Convolutional Neural Network (CNN) and Long Short-term Memory (LSTM) models. However, current models are not able to identify two main classes (class S and A), resulting in 58.0% mean accuracy. To overcome this drawback, a Wavelet Based Convolutional Neural Network (WBCNN) is proposed and the final mean accuracy reaches 77.7%.

[1]  Jan Nedoma,et al.  Non-Invasive Fetal Monitoring: A Maternal Surface ECG Electrode Placement-Based Novel Approach for Optimization of Adaptive Filter Control Parameters Using the LMS and RLS Algorithms , 2017, Sensors.

[2]  Shraddha Singh,et al.  Classification of ECG Arrhythmia using Recurrent Neural Networks , 2018 .

[3]  F. Lombardi,et al.  Holter Monitoring and Loop Recorders: From Research to Clinical Practice. , 2016, Arrhythmia & electrophysiology review.

[4]  Ronald R. Coifman,et al.  Signal and image representation in combined spaces , 1998 .

[5]  Snehal Thalkar,et al.  Various Techniques for Removal of Power Line Interference From ECG Signal , 2013 .

[6]  Sergey Ioffe,et al.  Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift , 2015, ICML.

[7]  A. O. Barut,et al.  New “Coherent” States associated with non-compact groups , 1971 .

[8]  Engin Avci,et al.  Classification of ECG signal by using machine learning methods , 2018, 2018 26th Signal Processing and Communications Applications Conference (SIU).

[9]  Abdulhamit Subasi,et al.  Medical Decision Support System for Diagnosis of Heart Arrhythmia using DWT and Random Forests Classifier , 2016, Journal of Medical Systems.

[10]  C. Li,et al.  Detection of ECG characteristic points using wavelet transforms. , 1995, IEEE transactions on bio-medical engineering.

[11]  B Pyakillya,et al.  Deep Learning for ECG Classification , 2017 .

[12]  Aggelos K. Katsaggelos,et al.  Detection of atrial fibrillation in ECG hand-held devices using a random forest classifier , 2017, 2017 Computing in Cardiology (CinC).

[13]  Elnaz Jahani Heravi,et al.  Guide to Convolutional Neural Networks , 2017 .

[14]  Robert X. Gao,et al.  Discrete Wavelet Transform , 2011 .

[15]  Sabir Jacquir,et al.  Automatic detection of P, QRS and T patterns in 12 leads ECG signal based on CWT , 2016, Biomed. Signal Process. Control..

[16]  Saroj Kumar Pandey,et al.  ECG Arrhythmia Classification Using Artificial Neural Networks , 2019 .

[17]  Rickey E Carter,et al.  An artificial intelligence-enabled ECG algorithm for the identification of patients with atrial fibrillation during sinus rhythm: a retrospective analysis of outcome prediction , 2019, The Lancet.

[18]  P. Nandhini,et al.  Diagnosis of Cardiovascular Diseases Based on R-R Interval Using ECG Signals , 2014 .

[19]  Özal Yildirim,et al.  A novel wavelet sequence based on deep bidirectional LSTM network model for ECG signal classification , 2018, Comput. Biol. Medicine.