Name
Abstract | ||
|---|---|---|
Nowadays, an increasing number of location-based services are included in security systems and mobile applications. Various localization mechanisms have been developed, including outdoor satellite navigation system and indoor received signal strength (RSS) based on WiFi and BLE Beacon. However, they can only localize the target while being equipped with a receiver. Instead, passive indoor localization is the device-free technique that can localize a target without carrying any electronic devices in a selected region. In this paper, a scheme for operating passive indoor localization is proposed. In the scheme, the location images are constructed by utilizing channel state information (CSI) while the localization model is built and trained by using deep learning. With the help of convolutional neural networks (CNN), this scheme only requires original CSI amplitude instead of manual extraction of features. We demonstrate the accuracy of this scheme in two typical indoor scenarios. The experimental results show that the proposed scheme achieves an accuracy of more than an average of 94% and 96% respectively in the scenario of the office and the corridory. |
Year | DOI | Venue |
|---|---|---|
2018 | 10.1109/UPINLBS.2018.8559775 | 2018 Ubiquitous Positioning, Indoor Navigation and Location-Based Services (UPINLBS) |
Keywords | DocType | ISSN |
indoor localization,device-free,channel state information,convolutional neural networks | Conference | 2372-1685 |
ISBN | Citations | PageRank |
978-1-5386-3756-2 | 1 | 0.36 |
References | Authors | |
5 | 4 | |
Name | Order | Citations | PageRank |
|---|---|---|---|
| Chenwei Cai | 1 | 1 | 0.36 |
| Li Deng | 2 | 3 | 3.26 |
| Mingyang Zheng | 3 | 1 | 0.36 |
| Shufang Li | 4 | 1 | 0.70 |