Development of Low-Cost, Ultra-Low-Bandwidth Wearable Biosensors for Continuous Cardiovascular Monitoring in Resource-Constrained Environments

• Sunday Sunday

  Ladoke Akintola University of Technology

  Author

Cardiovascular diseases (CVDs) remain the leading cause of mortality worldwide, claiming approximately 17.9 million lives annually, with low- and middle-income countries bearing a disproportionate burden of this epidemic. While wearable biosensors offer promising solutions for continuous cardiac monitoring, existing systems predominantly rely on cloud-based processing, high-bandwidth transmission, and expensive proprietary hardware, rendering them inaccessible in resource-constrained environments. This research addresses the critical gap between advanced biosensing capabilities and the infrastructural limitations of underserved regions through the development of an integrated hardware-software framework for ultra-low-bandwidth cardiovascular monitoring. The study employed a design-based research methodology combining photoplethysmography (PPG) and single-lead electrocardiography (ECG) sensors with an ARM Cortex-M4 microcontroller platform, implementing hybrid compression algorithms—including autoencoders and differential Huffman coding—to achieve bandwidth reduction exceeding 90% while maintaining signal reconstruction fidelity. The proposed system demonstrated 89.4% diagnostic accuracy for cardiac anomaly classification (arrhythmia, bradycardia, tachycardia) using a lightweight convolutional neural network optimized for on-device inference, with end-to-end latency below 500 ms. By enabling local processing, adaptive compression, and selective transmission, this framework bridges the digital divide in cardiovascular care, offering a replicable, open-source architecture for equitable health monitoring in telehealth applications.

• PDF

Copyright (c) 2026 Sunday Sunday (Author)

This work is licensed under a Creative Commons Attribution 4.0 International License.