• accessibility
• iot
• beacon
• bluetooth
• ble
• neural networks

We are living in a world where the majority of the information are given in a visual way: lights, colors or screens. IoT devices could play a huge role in the accessibility field to help visually impaired people to navigate in their daily life outside their houses. The goal of this thesis is to investigate the best combination of Hardware and Software to analyze Bluetooth Low Energy (BLE) beacons emitted by some BLE Tags and determine if they are in proximity. In this work we are evaluating the performance, the cost and the effectiveness of collecting BLE beacons, processing them and running Neural Networks and on an embedded device to estimate proximity between people or between a person and a point of interest. Furthermore we want to use the findings to develop a smartphone app capable of helping blind or visually impaired people navigate their way outside their houses. The application must be able to notify the user with a multi-channel feedback its proximity with some point of interests, represented by BLE tags.