Cloud-based real-time heart monitoring and ECG signal processing
- 1 October 2016
- conference paper
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE) in 2016 IEEE SENSORS
Abstract
In this study, an embedded system has been developed to facilitate real-time arrhythmia detection. It performs electrocardiogram (ECG) signal processing and alerts the patient's doctor of ventricular tachycardia (VT) via wireless messaging. The signal processing first involves the Pan-Tompkins algorithm for R-peak detection and then utilizes a template-matching algorithm for PVC detection. By using a healthy beat, the template-matching algorithm generates two templates, the QRS complex and the interval between two R-peaks. The two templates are then correlated with the QRS complex and RR-interval of each heartbeat, and a low correlation indicates a PVC. All algorithms are implemented on the TI CC3200 LaunchPad, a low-cost Wi-Fi board. When three or more consecutive PVCs are detected, a short-message-service (SMS) system is activated. Cloud-based apps are used to send a text message from the LaunchPad to a cell phone. Benchmark records from the MIT-BIH arrhythmia database are used for design validation. MATLAB is used to simulate the signal processing algorithms, and Code Composer Studio is utilized to implement the design on the LaunchPad, where the algorithms are programmed in C. The experimental results using the LaunchPad were 99.1% QRS sensitivity and 81.7% PVC sensitivity. This study suggests a viable, low-complexity solution for real-time heart monitoring and arrhythmia detection.Keywords
This publication has 8 references indexed in Scilit:
- High-Precision Real-Time Premature Ventricular Contraction (PVC) Detection System Based on Wavelet TransformJournal of Signal Processing Systems, 2013
- A low-complexity data-adaptive approach for premature ventricular contraction recognitionSignal, Image and Video Processing, 2013
- Arrhythmia Identification with Two-Lead Electrocardiograms Using Artificial Neural Networks and Support Vector Machines for a Portable ECG Monitor SystemSensors, 2013
- Robust Detection of Premature Ventricular Contractions Using a Wave-Based Bayesian FrameworkIEEE Transactions on Biomedical Engineering, 2009
- Finding Features for Real-Time Premature Ventricular Contraction Detection Using a Fuzzy Neural Network SystemIEEE Transactions on Neural Networks, 2009
- The impact of the MIT-BIH Arrhythmia DatabaseIEEE Engineering in Medicine and Biology Magazine, 2001
- Characterization of signals from multiscale edgesIEEE Transactions on Pattern Analysis and Machine Intelligence, 1992
- A Real-Time QRS Detection AlgorithmIEEE Transactions on Biomedical Engineering, 1985