Loading...
| Friend's email | |
| Your name | |
| Your email | |
| enter code | |
This page was sent successfuly
- Type of Document: M.Sc. Thesis
- Language: Farsi
- Document No: 57719 (05)
- University: Sharif University of Technology
- Department: Electrical Engineering
- Advisor(s): Atarodi, Mojtaba
- Abstract:
- In the present thesis, the issue of locating end devices in the LoRa IoT network is examined using the received signal strength (RSS) approach. Recent advancements in machine learning techniques have revolutionized the localization field, enabling researchers to achieve better performance in non-line-of-sight (NLOS) and multipath interference conditions compared to traditional methods such as RSS and time difference of arrival (TDOA). This research first aims to reduce the position estimation error by appropriately scaling the received signal strength values on the public Antwerp dataset and to obtain a trained model for real-time localization of end devices. After introducing an appropriate feature scaling method, a simulation of an area covering 9 square kilometers with four fixed gateways is performed. The error obtained from this environment, similar to the public Antwerp dataset, exceeds 270 meters, which creates limitations for many applications. To reduce these limitations, this research first estimates the position using the four fixed gateways and then, by employing drones, achieves an average position estimation error of less than 10 meters in the simulation
- Keywords:
- Received Signal Strength ; Localization ; Machine Learning ; Internet of Things ; Low-Power Wide-Area Network (LPWAN) ; LoRa Technology
Digital Object List
-
محتواي کتاب
- view
Bookmark