Fingerprint-based indoor positioning system using BLE: real deployment study

Abstract

There are a myriad of applications where the localization of interior surroundings is vital in the era of smart cities Bluetooth low energy (BLE) technology is designed for short-range wireless communication, low energy consumption, low cost hardware design and simple deployment with respect to other technologies. This paper presents a low cost BLE fingerprint-based indoor positioning system, where a minimum number of Beacons are deployed in different test bed subareas with different conditions. Collected measured received signal strength indicator (RSSI) signals received from all beacons in each grid cell of all areas of interest are stored. We experimented two deterministic matching algorithms: k-nearest neighbors (KNN) and weighted algorithm (WKNN), to match previously collected RSSI readings with the RSSI at mobile unknown location, to determine where the user is. Experiments results show that WKNN algorithm manages to obtain less mean and standard deviation positioning error for all subareas, that experiencing different conditions of obstructions, reflections, and interferences.

Fingerprinting-based indoor localization: A Deep Learning Approach

“…By identifying the most accurate match, the system can estimate the user's location [16]. Various machine learning algorithms can be employed, such as knearest neighbors (KNN) [38], Naive Bayes [17], random forests [18], Support Vector Machines (SVM) [19]. Although conventional machine learning algorithms improve the accuracy and robustness of the fingerprinting approach in handling challenges such as signal attenuation, interference, and multipath effects [21], deep learning (DL) algorithms offer several advantages over conventional machine learning algorithms in this context.…”