Abstract:
TTE is essential in intelligent transportation systems (ITS). To accurately estimate travel time for multi-city scenarios, fine-grained Trajectory-based Travel Time Estimation (TTTE) is important. However, dynamic temporal and fine-grained spatial dependencies make it difficult. MetaTTE, a meta learning-based framework, uses a well-designed deep neural network model called DED, which consists of data preprocessing and encoder-decoder network modules, to continuously provide accurate travel time estimation over time. MetaTTE’s generalization ability is enhanced by meta learning techniques using a small number of examples, which opens up new opportunities to improve TTTE performance as traffic conditions and road networks change. A DED model encoder-decoder network captures fine-grained spatial and temporal representations. Our MetaTTE outperforms nine state-of-the-art baselines on Chengdu and Porto datasets by 29.35% and 25.93%, respectively.
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
