Optimizing Real-Time ECG Data Transmission in Constrained Environments
ECG real-time transmission , Lossless compression , ECG in constrained environments , Power consumption optimization , Adaptive ECG leads selection
ECG monitoring systems have a significant role in detecting cardiovascular diseases and reducing the rate of sudden cardiac deaths through early warnings for heart attacks. One of the critical factors in supporting real-time ECG tracking is to guarantee monitoring system availability. This thesis focuses on battery life extension for a 12 Lead ECG patch utilizing compression and classification approaches. In the compression approach, the ECG patch operational hours are extended by reducing the data size of captured ECG signals to minimize the Bluetooth Low Energy communication airtime and the overall transmission power. Huffman, delta, and base-delta lossless compression techniques are implemented on a Texas Instruments CC2650 Micro-controller Unit using different sampling rates, normal, and abnormal cardiac conditions. The algorithms are evaluated in terms of compression ratio, execution time, and power consumption of the ECG patch. The computer-aided interpretation of ECG signals has become a pivotal tool for physicians in the clinical assessment of cardiovascular diseases during the last decade. Therefore, computerized diagnosis systems depend heavily on machine learning and deep learning models to guarantee high classification accuracy. With the classification approach, we target effective power consumption by controlling the ECG patch mode of operation to reduce the need for a full-fidelity ECG signal. We use a binary classifier to inform the decision to switch between different operational strategies. In addition, we provide a new approach to support energy-efficient ECG monitoring in real-time through the adaptive selection of ECG leads after applying multi-class classification to the raw ECG signals. We deploy CNN model scenarios on MIT-BIH and CODE-test datasets and adjust the number of ECG streamed channels to 1,4, and 8, based on the detected cardiac abnormalities, such as arrhythmias and heart blocks. Our findings show that the base-delta encoding technique outperforms other compression techniques and achieves 70\% data compression on normal ECG data, and up to 50\% on abnormal ECG data with 24 ms. The adaptive selection of ECG channels with CNN models on 1 and 12 leads achieves 77.7\% power saving in the normal cardiac condition and up to 55.5\% for the heart blocks, sinus bradycardia, and sinus tachycardia.