Abstract:
Fine timing measurement (FTM) uses round-trip time (RTT) measurements to precisely range Wi-Fi devices. Radio wave multipath propagation produces inaccurate timing information, degrading ranging performance.
In this study, we use a neural network (NN) to adaptively learn different indoor measurement patterns and produce enhanced ranging outputs from raw FTM measurements. The NN is trained using unsupervised learning and sensor data from location service users.
Thus, training data collection is simplified. The experimental results showed that short-term unlabeled data collection can learn the pattern in raw FTM measurements and improve ranging results.
The method reduced raw distance measurements and well-calibrated ranging results requiring ground truth data by 47–50% and 17–29%, respectively. Positioning errors were 17–30% lower than in the well-calibrated ranging scenario.
Note: Please discuss with our team before submitting this abstract to the college. This Abstract or Synopsis varies based on student project requirements.
Did you like this final year project?
To download this project Code with thesis report and project training... Click Here
