TY - GEN
T1 - Deep Learning-Based Prediction Models for Freeway Traffic Flow under Non-Recurrent Events
AU - Aljuaydi, Fahad
AU - Wiwatanapataphee, Benchawan
AU - Wu, Yong Hong
N1 - Publisher Copyright:
© 2022 IEEE.
PY - 2022
Y1 - 2022
N2 - This paper concerns predictions of freeway traffic flow under non-recurrent events using multivariate machine learning models, including the multilayer perceptron network and the one-dimensional CNN long short-term memory network. The machine learning architectures and loss functions for training neural networks are presented. The study region is a portion of the Kwinana Freeway northbound in Perth, Western Australia. The study dataset, obtained by matching the timestamp of all available data, has various features, including traffic volume (flow rate), speed, density and road incident. Using the root mean squared error and mean absolute error, results from the two learning models are compared to the baseline model to determine the suitable model for traffic prediction under non-recurrent events.
AB - This paper concerns predictions of freeway traffic flow under non-recurrent events using multivariate machine learning models, including the multilayer perceptron network and the one-dimensional CNN long short-term memory network. The machine learning architectures and loss functions for training neural networks are presented. The study region is a portion of the Kwinana Freeway northbound in Perth, Western Australia. The study dataset, obtained by matching the timestamp of all available data, has various features, including traffic volume (flow rate), speed, density and road incident. Using the root mean squared error and mean absolute error, results from the two learning models are compared to the baseline model to determine the suitable model for traffic prediction under non-recurrent events.
KW - Convolutional Neural Network
KW - Long shortterm memory
KW - MultiLayer Perceptron
KW - Non-recurrent events
KW - Traffic prediction
UR - http://www.scopus.com/inward/record.url?scp=85134310382&partnerID=8YFLogxK
U2 - 10.1109/CoDIT55151.2022.9803892
DO - 10.1109/CoDIT55151.2022.9803892
M3 - Conference contribution
AN - SCOPUS:85134310382
T3 - 2022 8th International Conference on Control, Decision and Information Technologies, CoDIT 2022
SP - 815
EP - 820
BT - 2022 8th International Conference on Control, Decision and Information Technologies, CoDIT 2022
PB - Institute of Electrical and Electronics Engineers Inc.
T2 - 8th International Conference on Control, Decision and Information Technologies, CoDIT 2022
Y2 - 17 May 2022 through 20 May 2022
ER -