Spatiotemporal Cleaning of PIR Sensor Data for Elderly Movement Monitoring

This study presents a robust framework designed to address the limitations of passive infrared (PIR) sensors in home-based elderly monitoring, particularly focusing on false detections and sensor blind times, which compromise data accuracy. While PIR sensors are low-cost and privacy-preserving, their inherent inaccuracies hinder their use in reliable monitoring systems. To overcome these challenges, we propose a novel spatiotemporal data cleaning framework that integrates non-deterministic tracking (NDT) and late-binding adjustment (LBA). This framework enhances the quality and accuracy of sensor data by filtering out false positives and omissions through analysis of walking speed and sensor connectivity. Simulations demonstrated significant improvements in movement tracking accuracy, and real-world experiments involving three elderly participants further validated the framework’s practicality. The experiments confirmed that the proposed method can remove errors such as false positives and false negatives from PIR sensors. It can achieve 90% accuracy in tracking the movements of elderly people, highlighting the potential for this framework to be applied in the real world. The key scientific contribution of this research lies in the development of a scalable, non-wearable indoor tracking solution that reduces the need for dense sensor arrays, making it cost-effective and adaptable to existing infrastructure with minimal modifications. This framework contributes to advancing the field of indoor localization and offers a reliable solution for sensor-based monitoring systems, especially in elderly care, addressing the urgent needs of an aging global population.