A practical approach based on Bluetooth Low Energy and Neural Networks for indoor localization and targeted devices’ identification by smartphones

With the constant development of innovative technologies and the resulting growth of new services available on the market, applications that aim to control devices employing smartphones include more extensive selection menus increasingly. This condition can lead to non-intuitive use of the system. As a result, the user may reap an adverse experience while practicing these applications. An indoor tracking system must create a control method with a dynamic user interface and estimate the device pointed to by a smartphone. The use of Bluetooth Low Energy (BLE) and the fingerprinting technique, based on Received Signal Strength Indication (RSSI) values, can be a feasible solution for indoor localization. Furthermore, to obtain ever more precise indoor localization systems, there is continuous research on artificial neural networks’ employment as they adapt more quickly to changes in the RSSI values. This paper proposes a new approach to control devices through smartphones based on the joint application of BLE, fingerprinting, and neural networks. The system offers a dynamic user interface that changes according to the target device through sensors commonly located in modern smartphones. © 2022 Elsevier B.V.