Abstract:
The study of indoor localization has been extensively studied, either in terms of wireless technologies or localization
techniques. The accuracy is then challenged when the monitored object is actively moving. Previously, we studied a continuous
and low-power fingerprint-based indoor localization system using IEEE 802.15.4 (FILS15.4), which has been integrated into a smart
environmental IoT platform. Although fingerprint-based localization offers a great advantage in its simplicity, it relies on real-time signal
strength measurements and databases. Thus, it suffers challenges in accuracy when the object is continuously moving. In this study,
we focus on developing dynamic positioning, where users continuously move from one room to another. Due to human movements,
the fluctuation of the link quality indicator (LQI) can affect the detection accuracy. To avoid false detection, we propose a movement
validation method by checking the variance of the LQI and accelerometer to differentiate the cause of fluctuations and increase the
detection accuracy. For experiments, we run the test-bed of FILS15.4 on a two-floor layout. Five to six receivers were allocated to detect
multiple users. The results show that the system yields 96.2% accuracy using six receivers simultaneously. Thus, it gives sufficient
detection accuracy even for dynamic conditions.
