A study on precise indoor positioning with wireless communications using neural network techniques | |
| Author | Gosukonda, Rithish Reddy |
| Call Number | AIT Thesis no.RS-20-03 |
| Subject(s) | Indoor positioning systems (Wireless localization) Bluetooth technology Neural networks (Computer science) |
| Note | A thesis submitted in partial fulfillment of the requirements for the degree of Master of Engineering in Remote Sensing and Geographic Information System |
| Publisher | Asian Institute of Technology |
| Abstract | Indoor localization is emerging as an important application domain for enhanced navigation of people in indoor environments such as buildings and shopping malls. Most indoor localization solutions proposed in previous work do not deliver good accuracy without expensive infrastructure. Ambient wireless received signal strength indication (RSSI) based Bluetooth fingerprinting using smartphone is a low-cost approach to the problem. This study presents a novel approach to transform Received Signal Strength (RSSI) values into images and an indoor localization technique based on Convolutional Neural Network that is proven sufficiently efficient to achieve a low error distance with high test accuracy. Our CNN model has obtained average localization error of 2 meters. This indicates that the proposed CNN model can better handle the instability and variability of RSSls for Bluetooth signals in complex indoor environments. |
| Year | 2020 |
| Type | Thesis |
| School | School of Engineering and Technology (SET) |
| Department | Department of Information and Communications Technologies (DICT) |
| Academic Program/FoS | Remote Sensing (RS) |
| Chairperson(s) | Miyazaki, Hiroyuki; |
| Examination Committee(s) | Apichon Witayangkurn;Mozumder, Chitrini; |
| Scholarship Donor(s) | Asian Institute of Technology Fellowship; |
| Degree | Thesis (M.Eng.) - Asian Institute of Technology, 2020 |