TY - GEN
T1 - Forecasting Daily Travel Mode Choice of Kuantan Travellers by Means of Machine Learning Models
AU - Mohd Ali, Nur Fahriza
AU - Mohd Sadullah, Ahmad Farhan
AU - Majeed, Anwar P.P.Abdul
AU - Mohd Razman, Mohd Azraai
AU - Choong, Chun Sern
AU - Muazu Musa, Rabiu
N1 - Publisher Copyright:
© 2022, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.
PY - 2022
Y1 - 2022
N2 - In transportation studies, forecasting users’ mode choice in daily commute is crucial in order to manage traffic problems due to high number of private vehicles on the road. Conventional statistical techniques have been widely used in order to study users’ mode choice; however, the choice of the most appropriate forecasting method still remains a significant concern. In this paper, we investigate the application of a number of machine learning models, namely Random Forest (RF), Tree, Naïve Bayes (NB), Logistic Regression (LR), k-Nearest Neighbour (k-NN), Support Vector Machine (SVM), as well as Artificial Neural Networks (ANN) in predicting the daily travel mode choice in Kuantan. The data was collected from a survey of Revealed/Stated Preferences (RPSP) Survey among Kuantan travellers in which eight features were taken into consideration in the present study. The classifiers were trained on the collected dataset by using five-folds cross-validation method to predict the daily mode choice. It was shown from this preliminary study that the RF, as well as ANN classifiers, could provide satisfactory classification accuracies to up to 70% in comparison to the other models evaluated. Therefore, it could be concluded that the evaluated features are rather important in deciding the travel model choice of Kuantan travellers.
AB - In transportation studies, forecasting users’ mode choice in daily commute is crucial in order to manage traffic problems due to high number of private vehicles on the road. Conventional statistical techniques have been widely used in order to study users’ mode choice; however, the choice of the most appropriate forecasting method still remains a significant concern. In this paper, we investigate the application of a number of machine learning models, namely Random Forest (RF), Tree, Naïve Bayes (NB), Logistic Regression (LR), k-Nearest Neighbour (k-NN), Support Vector Machine (SVM), as well as Artificial Neural Networks (ANN) in predicting the daily travel mode choice in Kuantan. The data was collected from a survey of Revealed/Stated Preferences (RPSP) Survey among Kuantan travellers in which eight features were taken into consideration in the present study. The classifiers were trained on the collected dataset by using five-folds cross-validation method to predict the daily mode choice. It was shown from this preliminary study that the RF, as well as ANN classifiers, could provide satisfactory classification accuracies to up to 70% in comparison to the other models evaluated. Therefore, it could be concluded that the evaluated features are rather important in deciding the travel model choice of Kuantan travellers.
KW - Machine learning
KW - Mode choice
KW - Private vehicles
KW - Public transport
UR - http://www.scopus.com/inward/record.url?scp=85112555985&partnerID=8YFLogxK
U2 - 10.1007/978-981-33-4597-3_89
DO - 10.1007/978-981-33-4597-3_89
M3 - Conference Proceeding
AN - SCOPUS:85112555985
SN - 9789813345966
T3 - Lecture Notes in Electrical Engineering
SP - 979
EP - 987
BT - Recent Trends in Mechatronics Towards Industry 4.0 - Selected Articles from iM3F 2020
A2 - Ab. Nasir, Ahmad Fakhri
A2 - Ibrahim, Ahmad Najmuddin
A2 - Ishak, Ismayuzri
A2 - Mat Yahya, Nafrizuan
A2 - Zakaria, Muhammad Aizzat
A2 - P. P. Abdul Majeed, Anwar
PB - Springer Science and Business Media Deutschland GmbH
T2 - Innovative Manufacturing, Mechatronics and Materials Forum, iM3F 2020
Y2 - 6 August 2020 through 6 August 2020
ER -