Cardiovascular diseases (CVDs) are a leading cause of mortality worldwide, necessitating innovative solutions for early detection and continuous monitoring. This research aims to develop an Android-based remote cardiac monitoring device for real-time electrocardiogram (ECG) signal acquisition, transmission, and analysis. The system comprises hardware for acquiring ECG signals, algorithms for processing and machine learning models for anomaly classification. The hardware unit captures ECG data using electrodes and sensors. The signals are filtered, processed, and transmitted to the cloud infrastructure enabling real-time monitoring and analysis. Machine learning models including support vector machines, ensemble methods and Artificial neural networks are trained on ECG datasets to classify signals and detect cardiac abnormalities. Comprehensive testing validates the system's capabilities in real-time signal acquisition, processing, anomaly detection and data transmission. The integration of hardware, algorithms and machine learning enables round-the-clock monitoring of cardiac activity, facilitating prompt interventions and improved patient outcomes. This affordable and user-friendly system demonstrates potential for enhanced accessibility and effectiveness of preventive cardiac care.
Read full abstract