A review on multi-sensor data fusion for wearable health monitoring

The growing demand for accurate, continuous, and non-invasive health monitoring has propelled multi-sensor data fusion to the forefront of healthcare technology. This review aims to provide an overview of the development of fusion frameworks and common terminology used in fusion literature. The review introduces the fusion classification standards and methods that are most relevant to algorithm development. Applications of the reviewed fusion frameworks in fields such as defense, autonomous driving, and robotics are also briefly covered to provide contextual information on the various fusion methodologies that have been developed in this field. This review aims to provide a comprehensive analysis of multi-sensor data fusion methodologies applied to health monitoring systems, focusing on key algorithms, applications, challenges, and future directions. We examine commonly used fusion techniques-including Kalman filters, Bayesian networks, and machine learning models. By integrating data from various sources, these fusion approaches enhance the reliability, accuracy, and resilience of health monitoring systems. However, challenges such as data quality and differences in acquisition systems have arisen, which have called for intelligent fusion algorithms in recent years. The review finally converges on the applications of fusion algorithms in biomedical inference tasks such as heartbeat detection, respiration rate estimation, sleep apnea detection, arrhythmia detection, and atrial fibrillation detection. The insights presented in this review are expected to guide the development of next-generation multi-sensor fusion systems for health monitoring.