| Paper Name |
A hybrid BLE and Wi-Fi localization system for the creation of study groups in smart libraries |
| Published in |
2016 IEEE International Conference on Indoor Positioning and Indoor Navigation (IPIN) |
| Authors |
Kiril Antevski; Alessandro E.C. Redondi; Razvan Pitic |
| Paper Overview |
This paper proposes a hybrid localization system in smart libraries. The system contains:
- The hybrid BLE and Wi-Fi network infrastructure
- A mobile client application
- The back-end server which is implemented using IBM Node-RED
- The frontend graphical interface
|
| Experiment results |
|
| Methodology |
- Bluetooth-only localization : Leveraging the presence of N BLE beacon devices deployed in the library
- Wi-Fi fingerprint localization : Using three methods to estimate location: (1)k-nearest neighbors (2)k-means clustering (3)PCA-based fingerprinting
- Hybrid Bluetooth and Wi-Fi localization : Calculating error rate for BLE and Wi-Fi in some particular positions.If the result of the estimation is different in these two system, we will chose the one of them which the error rate is lower
- Algorithms for hybrid system : Using many methods for this system.The best method which has the highest accuracy is PCA k-nn hybrid
|
