This work proposes a new indoor positioning system, named KLIP, that uses the ${K}$ -means clustering algorithm to split the environment into different sets of log-distance propagation models in order to better characterize the indoor environment and further improve the position estimation using Bayesian inference. Our proposed method is validated in a large-scale, real-world scenario composed of Bluetooth Low Energy (BLE)-based devices. We demonstrate, throughout the paper, that the addition of location information of training points to the received signal strength indicator (RSSI) as an attribute for the clustering step improves the positioning accuracy. Moreover, the obtained results show that our solution outperforms the naive Bayesian estimation up to 12% – regarding the positioning accuracy – and the broadly deployed ${k}$ NN for reduced training dataset size – regarding both accuracy and online processing time. In this sense, KLIP proves to be an efficient and scalable alternative when both site-survey effort and energy consumption constraints must be taken into account.
Indoor Positioning Systems (IPSs) are designed to provide solutions for location-based services. Wireless local area network (WLAN)-based positioning systems are the most widespread around the globe and are commonly found to have a ready-to-use infrastructure composed mostly of access points (APs). They advertise useful information, such as the received signal strength (RSS), that is processed by adequate location algorithms, which are not always capable of achieving the desired localization error only by themselves. In this sense, this paper proposes a new method to improve the accuracy of IPSs by optimizing the arrangement of APs over the environment using an enhanced probability-based algorithm. From the assumption that a log-distance path loss model can reasonably describe, on average, the distribution of RSS throughout the environment, we build a simulation framework to analyze the impact, on the accuracy, of the main factors that constitute the positioning algorithm, such as the number of reference points (RPs) and the number of samples of RSS collected per test point. To demonstrate the applicability of the proposed solution, a real-world testbed dataset is used for validation. The obtained results for accuracy show that the trends verified via simulation strongly correlate to the verified in the dataset processing when allied with an optimal configuration of APs. This indicates our method is capable of providing an optimal factor combination—through early simulations—for the design of more efficient IPSs that rely on a probability-based positioning algorithm.
Indoor positioning systems (IPSs) are vital for location-based services in complex spaces such as retail, healthcare, and logistics, but traditional IPSs require intensive, time-consuming offline fingerprinting that limits scalability. This article proposes optimized positioning technique integrating model-based and pairwise selection (OPTIMAPS), a novel solution utilizing Bluetooth low energy (BLE) technology without the need for predeployment RSSI collection or site surveys. OPTIMAPS relies on a log-distance path loss model, with model parameters automatically determined from environmental geometry and signal diversity analysis. The system employs a nearest-neighbor (NN) estimator for fast, robust initialization, followed by sequential least squares programming (SLSQP) for constrained nonlinear optimization within a restriction circle based on testbed granularity. A key innovation is the use of the Chebyshev metric and mean pairwise distance for RSSI vector discrimination, enhancing accuracy. OPTIMAPS was validated in a 720 m2 real-world testbed, using 15 BLE access points (APs) and 148 distinct testing locations. The system achieved an average positioning error (APE) of 2.65 m, competitive with state-of-the-art techniques and superior to other survey-free methods in anchor density (AD)-normalized error. Computational complexity scales linearly with environmental size, significantly outperforming metaheuristic optimizers like genetic algorithms, which scale quadratically or worse. Spatial analysis showed SLSQP reduced errors by over 30% in challenging, multipath-rich rooms, with negligible overhead in open spaces. Statistical tests demonstrated OPTIMAPS’ robustness and practical deployability, confirming it as a scalable, accurate, and energy-efficient IPS for diverse, dynamic indoor environments.
Indoor Positioning Systems (IPSs) are designed to provide solutions for location-based services. Wireless local area network (WLAN)-based positioning systems are the most widespread around the globe and are commonly found to have a ready-to-use infrastructure composed mostly of access points (APs). They provide useful information on signal strength to be processed by adequate location algorithms, which are not always capable of achieving the desired localization error only by themselves. In this sense, this paper proposes a new method to improve the accuracy of IPSs by optimizing some of their most relevant infrastructure components. Included are the arrangement of APs over the environment, the number of reference points (RPs), and the number of samples per location estimation test. A simulation environment is also proposed, in which the impact of key influencing factors on system accuracy is analyzed. Finally, a case study is simulated to validate an optimal combination of design parameters and its compliance with the requirements of localization error and the limited number of access points. Our simulation results clearly show that the desired localization accuracy, which is set as a goal, can be achieved while maintaining the factors already mentioned at minimal levels, which decreases both system deployment costs and computational effort.