Driving style recognition with privacy protection
The objective of the FYP is to use a myriad of RNN, Long Short-Term Memory networks (LSTMs) to detect between different driving styles and simultaneously include a method to protect the confidentiality of the data captured. Using data collected and filtered through a Kalman Filter, to estimate the p...
Saved in:
| Main Author: | |
|---|---|
| Other Authors: | |
| Format: | Final Year Project |
| Language: | English |
| Published: |
Nanyang Technological University
2021
|
| Subjects: | |
| Online Access: | https://hdl.handle.net/10356/150350 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| Institution: | Nanyang Technological University |
| Language: | English |
| Summary: | The objective of the FYP is to use a myriad of RNN, Long Short-Term Memory networks (LSTMs) to detect between different driving styles and simultaneously include a method to protect the confidentiality of the data captured. Using data collected and filtered through a Kalman Filter, to estimate the position, without showcasing the true location. In addition, by creating a neural network that produces an encoded version of the raw data that can be utilized to be train on working models. With the encoded version of the raw data, the Extended Kalman Filter would be able to produce a hidden version of the driver’s location This would bring about privacy while having the ability to distinguish a driver’s behavior. |
|---|