Saved in:
| Main Author: | |
|---|---|
| Format: | Recurso digital |
| Language: | English |
| Published: |
Zenodo
2023
|
| Online Access: | https://doi.org/10.5281/zenodo.8156132 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
Table of Contents:
- <p>As urban traffic congestion continues to pose significant challenges worldwide, accurate traffic prediction models are crucial for effective traffic management and efficient transportation systems. This thesis presents a comprehensive study on traffic prediction using SKTIME models, focusing on two prominent datasets: METR-LA and PEMS-BAY.</p> <p><br> The primary objective of this research is to investigate the effectiveness of SKTIME models in predicting traffic patterns and compare their performance across the METR-LA and PEMS-BAY datasets. To achieve this, an in-depth exploration of the datasets was performed, encompassing data preprocessing, feature engineering, and model development. The METR-LA dataset contains real-time traffic data from loop detectors in the Los Angeles area, while the PEMS-BAY dataset encompasses traffic information from various sensors in the San Francisco Bay Area.</p>