Sub-1 GHz Indoor RSSI-Based Localization: An Experimental Evaluation of Trilateration, Multilateration, and Machine Learning Fingerprinting Methods

As wireless radiofrequency-based localization techniques continue to attract interest, a plethora of approaches including received signal strength indicator (RSSI) trilateration and multilateration, phase, time-of-arrival, and machine learning models have been explored for indoor localization. However, there has been no comprehensive experimental investigations that compared the accuracy of these methods in a practical Internet of Things (IoT) wireless sensor network. Herein, we present a holistic evaluation of localization techniques in an indoor smart home environment, based on off-the-shelf 868/915 MHz transceivers. First, the hardware limitations, such as the antenna and RSSI radiation patterns and the effects of multipath reflections are experimentally investigated, identifying the optimal node placement. A practical RSSI recording and forwarding scheme is proposed and implemented using microcontroller units, showing a frugal approach for joint sensing and communication, with under 420 ms cycle time. Using this testbed, we compare multilateration approaches for three and four receivers, in both line-of-sight (LOS) and non-LOS links, achieving between 46% and 89% room prediction accuracy, with a minimum mean error of 1.49 m. A machine learning-based approach, using multinomial logistic regression, is then reported with a peak room classification accuracy of 97%–100%, for 25–30 RSSI points. A comparison with state-of-the-art implementations is presented showing a high room localization accuracy at a low hardware complexity, demonstrating the feasibility of RSSI-only localization in resource-constrained IoT networks.