Evaluation of Factors Affecting Inverse Beacon Fingerprinting Using Route Prediction Algorithm

Conventional Radio Frequency (RF) based fingerprinting still remains one of the most popular methods amongst other indoor positioning techniques due to its inherent accuracy and reliability. However, not much prominence has been shown in analyzing certain factors that may affect the outcome of the fingerprinting method while designing the localization system. In this paper, we conduct a study to infer if a reduced number of receivers equipped with higher gain antennas can provide improved Bluetooth Low Energy (BLE) fingerprinting performance in a complex indoor environment. The evaluation is performed in a standard domestic apartment with an activity centric approach using a single wearable beacon and multiple receivers. A rank based route selection algorithm is used to list the candidate positions or routes that indicate the most likely path on which the subject was travelling. Furthermore, we discuss the benefits of implementing the inverse fingerprinting method with a trajectory based prediction model and also examine the effect of surrounding electrical interference. Experimental results indicate that an increased antenna gain in addition to deploying an adequate number of receivers have a positive effect on the overall ranking accuracy.