Traffic flow study on CA I5-N from Santa Ana to Anaheim

Yue Qi

doi:10.1117/12.2692435

23 August 2023 Traffic flow study on CA I5-N from Santa Ana to Anaheim

Yue Qi

Proceedings Volume 12784, Second International Conference on Applied Statistics, Computational Mathematics, and Software Engineering (ASCMSE 2023); 1278432 (2023) https://doi.org/10.1117/12.2692435
Event: 2023 2nd International Conference on Applied Statistics, Computational Mathematics and Software Engineering (ASCMSE 2023), 2023, Kaifeng, China

Abstract

In intelligent transportation systems (ITS), accuracy in predicting traffic flow is an important prerequisite for better road planning, calculating estimated arrival times, and reducing traffic congestion. However, in the real world, forecasting real-time traffic flows need to be both accurate and efficient, and traffic data for training is limited in many cases. The accuracy of two mainstream machine learning and deep learning models, random forest and long short-term memory network (LSTM), in predicting small-scale short-term time-series traffic flows is questionable. In this study, the prediction accuracy of the two models was compared by training a total of 5208 data for the whole highway section and 168 data for each small road section separately, but they are both time-series data with one-hour intervals. The results of the study show that when comparing longitudinally, random forest predictions are more accurate for both data, while when comparing horizontally, the random forest has higher accuracy when predicting each road segment’s data with smaller amounts.

Citation Download Citation

Yue Qi "Traffic flow study on CA I5-N from Santa Ana to Anaheim", Proc. SPIE 12784, Second International Conference on Applied Statistics, Computational Mathematics, and Software Engineering (ASCMSE 2023), 1278432 (23 August 2023); https://doi.org/10.1117/12.2692435

ACCESS THE FULL ARTICLE

INSTITUTIONAL
Select your institution to access the SPIE Digital Library.

SELECT YOUR INSTITUTION

PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.

PERSONAL SIGN IN

No SPIE Account? Create one

PURCHASE THIS CONTENT

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE

Includes PDF, HTML & Video, when available