Transportation Mode Choice Analysis Based on Classification Methods

Zeņina, Nadežda; Borisov, Arkady

doi:10.2478/v10143-011-0041-2

Cited by 8 publications

(2 citation statements)

References 3 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…A discriminant function equivalent to a regression function is obtained as a result of discriminant analysis. The initial group size and quantity are supplied in the discriminant analysis, and the fundamental aim of discriminant analysis is to establish how correctly it is feasible to predict object membership to groups with the provided set of discriminant characteristics ( 47 ). The selection of discriminant variables and the selection of discriminant function are the two most difficult aspects of discriminant analysis.…”

Section: Mode Choice Modelingmentioning

confidence: 99%

Artificial Intelligence Techniques for Predicting Individuals’ Mode Choice Behavior in Mansoura City, Egypt

Elharoun

El-Badawy

Shahdah

2023

Transportation Research Record: Journal of the Transportation R

View full text Add to dashboard Cite

Predicting the choice behavior of individuals is an important step in transportation planning. This study examines the application of artificial intelligence (AI) techniques using machine learning with 10 different classifiers and deep neural networks (DNNs) to predict the travel mode choices of individuals in the city of Mansoura, Egypt, and compares the results with the traditional multinomial logit technique. The data used in this analysis were divided into two sets, training and testing, with a ratio of 67:33. The training dataset contains 10,173 cases, while the testing dataset represents 5,083 cases. The variables used to model mode choice behavior are: total travel time, total travel cost, gender, car ownership, driving license, occupational status, residency, and monthly personal income. The performance of all models is measured on two levels: the individual level, which predicts the overall percent of correct observations, and the aggregate level, which predicts the market shares for each mode. The results show that the DNN model, which takes mode captivity into account, outperforms all the examined models with a prediction accuracy of 97.81%. Additionally, random forest (RF), decision tree (DT), gradient booster (GB), and XGB showed prediction accuracy of over 95%. In addition, all the models were calibrated with different sample sizes. Prediction accuracy increases with increasing sample size, except for the Adaboost classifiers and linear discriminant analysis. With increase in sample size, the prediction accuracy of the RF, DT, GB, and XGB classifiers increases slightly while the DNN prediction accuracy increases significantly.

show abstract

Section: Mode Choice Modelingmentioning

confidence: 99%

Artificial Intelligence Techniques for Predicting Individuals’ Mode Choice Behavior in Mansoura City, Egypt

Elharoun

El-Badawy

Shahdah

2023

Transportation Research Record: Journal of the Transportation R

View full text Add to dashboard Cite

show abstract

“…The choice of urban transportation modes, especially for public transport, is a key element in transportation planning due to its direct impact on the design of urban transportation system structures and its role as the basis for policymaking related to urban transportation planning and management (Chen and Li, 2017). Transport mode choice has received the most attention among all decision processes in transportation behavior-related literature; this focus is because the analysis and prediction of mode choice strongly relate to transportation system policies and mitigation strategies for traffic congestion (Zenina and Borisov, 2011).…”

Section: Introductionmentioning

confidence: 99%

Urban Form and Transportation Energy Consumption in Depok, Indonesia

Putri

Indradjati

2022

IJG

View full text Add to dashboard Cite

By combining transportation energy use per capita for main, side, and weekend activities, this study explores the correlation between transportation energy consumption and urban form at a village scale. Conducted in Depok, a satellite city of the Jabodetabek metropolitan area, Indonesia, four different urban form variables were measured, including population density, land use mix, street connectivity, and public transportation range area. Four other socio-economic variables, i.e., private vehicle ownership, driving license ownership, job type, and monthly income, were also considered in the analysis. Data on individual energy consumption in the transportation sector was acquired through an online questionnaire. The results of correlation analysis and one-way analysis of variance highlighted three main findings related to transportation energy consumption. First, the population density and the street connectivity were found to be correlated with the amount of transportation energy consumed. Second, the middle urban form compactness level outweighed the high compactness level in terms of energy consumption per capita per week. Finally, differences in private vehicle ownership, driving license ownership, and job type resulted in different transportation energy usage.

show abstract

Model for selecting transportation option based on an analysis characteristics of the freight system

Poltavskaya

Lebedeva

2020

IOP Conf. Ser.: Mater. Sci. Eng.

View full text Add to dashboard Cite

The stable economic situation of the enterprise is determined not only by the minimum process costs, but also by the ability to effectively ensure production distribution. When implementing the distribution of goods, it is necessary to solve issues related to delivery, including choosing the option of transportation to the final consumer. The aim of this study is to establish the influence of the characteristics of freight system on the choice of transportation, which is carried out by participants in the transport process, namely, shippers and carriers. The logit model used to assess the need for transportation of goods based on disaggregated data is analyzed. The utility function includes time, cost of transportation and level of service. The evaluation results showed that the main characteristics of the freight system are of statistical significance and allow to determine the main parameters necessary for the decision-making process at the micro level.

show abstract

Transportation Mode Choice Analysis Based on Classification Methods

Cited by 8 publications

References 3 publications

Artificial Intelligence Techniques for Predicting Individuals’ Mode Choice Behavior in Mansoura City, Egypt

Artificial Intelligence Techniques for Predicting Individuals’ Mode Choice Behavior in Mansoura City, Egypt

Urban Form and Transportation Energy Consumption in Depok, Indonesia

Model for selecting transportation option based on an analysis characteristics of the freight system

Contact Info

Product

Resources

About