scholarly journals Intercity Travel Demand Analysis Model

2014 ◽  
Vol 6 ◽  
pp. 108180
Author(s):  
Ming Lu ◽  
Hai Zhu ◽  
Xia Luo ◽  
Lei Lei
Keyword(s):  
Logit Model ◽  
Short Distance ◽  
Travel Demand ◽  
Mode Choice ◽  
Urban Traffic ◽  
Demand Analysis ◽  
Analysis Model ◽  
Demand Forecast ◽  
Main Mode ◽  
Intercity Travel

It is well known that intercity travel is an important component of travel demand which belongs to short distance corridor travel. The conventional four-step method is no longer suitable for short distance corridor travel demand analysis for the time spent on urban traffic has a great impact on traveler's main mode choice. To solve this problem, the author studied the existing intercity travel demand analysis model, then improved it based on the study, and finally established a combined model of main mode choice and access mode choice. At last, an integrated multilevel nested logit model structure system was built. The model system includes trip generation, destination choice, and mode-route choice based on multinomial logit model, and it achieved linkage and feedback of each part through logsum variable. This model was applied in Shenzhen intercity railway passenger demand forecast in 2010 as a case study. As a result, the forecast results were consistent with the actuality. The model's correctness and feasibility were verified.

scholarly journals Applying FEATHERS for Travel Demand Analysis: Model Considerations

2018 ◽  
Vol 8 (2) ◽  
pp. 211 ◽  
Author(s):  
Qiong Bao ◽  
Bruno Kochan ◽  
Yongjun Shen ◽  
Lieve Creemers ◽  
Tom Bellemans ◽  
...  
Keyword(s):  
Travel Demand ◽  
Demand Analysis ◽  
Analysis Model

scholarly journals Comparison of Four Types of Artificial Neural Network and a Multinomial Logit Model for Travel Mode Choice Modeling

2018 ◽  
Vol 2672 (49) ◽  
pp. 101-112 ◽  
Author(s):  
Dongwoo Lee ◽  
Sybil Derrible ◽  
Francisco Camara Pereira
Keyword(s):  
Neural Networks ◽  
Logit Model ◽  
Travel Demand ◽  
Mode Choice ◽  
Multinomial Logit Model ◽  
Multinomial Logit ◽  
Choice Modeling ◽  
Probabilistic Neural Networks ◽  
Ann Models ◽  
Artificial Neural

Discrete choice modeling is a fundamental part of travel demand forecasting. To date, this field has been dominated by parametric approaches (e.g., logit models), but non-parametric approaches such as artificial neural networks (ANNs) possess much potential since choice problems can be assimilated to pattern recognition problems. In particular, ANN models are easily applicable with their higher capability to identify nonlinear relationships between inputs and designated outputs to predict choice behaviors. This article investigates the capability of four types of ANN model and compares their prediction performance with a conventional multinomial logit model (MNL) for mode choice problems. The four ANNs are: backpropagation neural networks (BPNNs), radial basis function networks (RBFNs), probabilistic neural networks (PNNs), and clustered probabilistic neural networks (CPNNs). To compare the modeling techniques, we present the algorithmic differences of each ANN technique, and we assess their prediction accuracy with a 10-fold cross-validation method. Furthermore, we assess the contribution of explanatory variables by conducting sensitivity analyses on significant variables. The results show that ANN models outperform MNL, with prediction accuracies around 80% compared with 70% for MNL. Moreover, PNN performs best out of all ANNs, especially to predict underrepresented modes.

Week-Long Mode Choice Behavior: Dynamic Random Effects Logit Model

2019 ◽  
Vol 2673 (10) ◽  
pp. 736-744 ◽  
Author(s):  
Ali Shamshiripour ◽  
Nima Golshani ◽  
Ramin Shabanpour ◽  
Abolfazl (Kouros) Mohammadian
Keyword(s):  
Random Effects ◽  
Logit Model ◽  
Choice Behavior ◽  
Predictive Power ◽  
Travel Demand ◽  
Mode Choice ◽  
Multinomial Logit Model ◽  
Static Model ◽  
Random Effects Model ◽  
Accuracy Indices

Modeling travelers’ mode choice behavior is an important component of travel demand studies. In an effort to account for day-to-day dynamics of travelers’ mode choice behavior, the current study develops a dynamic random effects logit model to endogenously incorporate the mode chosen for a day into the utility function of the mode chosen for the following day. A static multinomial logit model is also estimated to examine the performance of the dynamic model. Per the results, the dynamic random effects model outperforms the static model in relation to predictive power. According to the accuracy indices, the dynamic random effects model offers the predictive power of 60.0% for members of car-deficient households, whereas the static model is limited to 43.1%. Also, comparison of F1-scores indicates that the predictive power of the dynamic random effects model with respect to active travels is 47.1% whereas that of the static model is as low as 15.0%. The results indicate a significant day-to-day dynamic behavior of transit users and active travelers. This pattern is found to be true in general, but not for members of car-deficient households, who are found more likely to choose the same mode for two successive days.

Parsimonious Modeling and Uncertainty Quantification for Transportation Systems Planning Applied to California High-Speed Rail

2012 ◽  
Vol 2266 (1) ◽  
pp. 49-59 ◽  
Author(s):  
Quentin Noreiga ◽  
Mark McDonald
Keyword(s):  
Uncertainty Quantification ◽  
High Speed ◽  
Travel Demand ◽  
Mode Choice ◽  
Demand Model ◽  
Parameter Uncertainties ◽  
Main Mode ◽  
High Speed Rail ◽  
The Impact ◽  
Travel Demand Model

This paper presents a parsimonious travel demand model (PTDM) derived from a proprietary parent travel demand model developed by Cambridge Systematics (CS) for the California high-speed rail system. The purpose of the PTDM is to reduce computational expense for model simulations, optimization and sensitivity analyses, and other repetitive analyses. The PTDM is used to quantify the significance of parameter uncertainties with the use of mean value first-order second moment methods for uncertainty quantification and sensitivity analysis. The PTDM changes the model resolution of the parent travel demand model from a traffic analysis zone to a county-level analysis. The three-step model contains trip frequency, destination choice, and main mode choice models and is calibrated to match the results of the CS model. The main mode choice model predicts primary mode choice results for car, commercial air, conventional rail, and high-speed rail. The PTDM uses data and models similar to parent models to show how uncertainty in travel demand model predictions can be quantified. This paper does not attempt to assess the reliability of parent model forecasts, and the results should not be used to evaluate uncertainty in the California High-Speed Rail Authority's rider ship and revenue forecasts. However, the uncertainty quantification methodology presented here, when applied to the CS model, can be used to quantify the impact of parameter uncertainty on the forecast results.

scholarly journals Exploring Influencing Factors of Intercity Mode Choice from View of Entire Travel Chain

2021 ◽  
Vol 2021 ◽  
pp. 1-13
Author(s):  
Xiaowei Li ◽  
Siyu Zhang ◽  
Yao Wu ◽  
Yuting Wang ◽  
Wenbo Wang
Keyword(s):  
Logit Model ◽  
Unobserved Heterogeneity ◽  
Mode Choice ◽  
Multinomial Logit Model ◽  
Multinomial Logit ◽  
Travel Mode ◽  
Intercity Travel ◽  
Travel Mode Choice ◽  
Mixed Multinomial Logit Model ◽  
Significant Factors

Exploring the influencing factors of intercity travel mode choice can reveal passengers’ travel decision mechanisms and help traffic departments to develop an effective demand management policy. To investigate these factors, a survey was conducted in Xi’an, China, to collect data about passengers’ travel chains, including airplane, high-speed railway (HSR), train, and express bus. A Bayesian mixed multinomial logit model is developed to identify significant factors and explicate unobserved heterogeneity across observations. The effect of significant factors on intercity travel mode choice is quantitatively assessed by the odds ratio (OR) technique. The results show that the Bayesian mixed multinomial logit model outperforms the traditional Bayesian multinomial logit model, indicating that accommodating the unobserved heterogeneity across observations can improve the model fit. The model estimation results show that ticket purchasing method, comfort, punctuality, and access time are random parameters that have heterogeneous effects on intercity travel mode choice.

scholarly journals TRANSIMS Implementation for a Small Network and Comparison with Enhanced Four-Step Model

2014 ◽  
Author(s):  
Mansoureh Jeihani ◽  
Anam Ardeshiri
Keyword(s):  
Transportation Planning ◽  
Travel Demand ◽  
Demand Forecasting ◽  
Initial Step ◽  
Demand Analysis ◽  
Analysis Model ◽  
Step Method ◽  
Traffic Pattern ◽  
Step Model ◽  
Demand Models

Travel demand forecasting is a major tool to assist decision makers in transportation planning. While the conventional four-step trip-based approach is the dominant method to perform travel demand analysis, behavioral advances have been made in the past decade. This paper proposes and applies an enhancemnt to the four-step travel demand analysis model called Sub-TAZ. Furthermore, as an initial step toward activity-based models, a TRANSIMS Track-1 approach is implemented utilizing a detailed network developed in Sub-TAZ approach. The conventional four-step, Sub-TAZ, and TRANSIMS models were estimated in a small case study for Fort Meade, Maryland, with zonal trip tables. The models were calibrated and validated for the base year (2005), and the forecasted results for the year (2010) were compared to actual ground counts of traffic volume and speed. The study evaluated the forecasting ability of TRANSIMS versus the conventional and enhanced four-step models and provided critical observations concerning strategies for the further implementation of TRANSIMS.BACKGROUND Traffic pattern prediction is necessary for infrastructure improvement, and travel demand modeling provides tools to forecast travel patterns under various conditions. This modeling involves a series of mathematical equations that represent how people make travel choices. Traditional travel demand models use the four-step method, which was introduced in the 1950s and has been used widely in transportation planning. Although the four-step method has been practical in producing aggregate forecasts, it has some shortcomings. For example, in short-range planning networks, existing and newly constructed roads become congested much faster than forecasted (TRB 2007) and the performance of current four-step models is not always satisfactory. Additionally, these models are not behavioral in nature and as a result they are unable to represent the time chosen for travel, travelers’ responses to demand policies (e.g., toll roads, road pricing, and transit vouchers), non-motorized

scholarly journals Modelling school travel mode choice – the case of hanoi, vietnam

2021 ◽  
Vol 72 (7) ◽  
pp. 778-788
Author(s):  
Nguyen Minh Hieu
Keyword(s):  
Active Transport ◽  
Travel Behavior ◽  
Travel Demand ◽  
Mode Choice ◽  
Dominant Mode ◽  
Growing Up ◽  
Main Mode ◽  
School Buses ◽  
Research Gap ◽  
Children's Travel

The COVID-19 outbreak has resulted in adopting massively social distancing measures to tame the human-to-human transmission of the new coronavirus and protect public health. These intervention policies have caused changes in travel behavior, thereby expressing a need to update profiles of factors associated with mode choice. To respond to this research gap in part, this current study aims to model children’s mode decisions for school trips in the post-pandemic time in Hanoi. As regards mode usage, cycling is the main mode of active transport with a share at 23.3%, doubling the rate of 11% for walking. The dominant mode of traveling to school is the motorized modes (i.e., cars and motorcycles) with a proportion of 60%, meanwhile, school buses account for only 6.2%. As regards the determinants, when growing up, children tend to shift from being driven to traveling actively. The availability of cars increases the likelihood of using other modes compared to cycling. An opposite association is seen for the availability of bicycles. The flexibility in terms of a mother’s job is involved in a higher possibility of being driven for a child. A home-school distance less than 1 km is more suitable for walking compared to cycling; however, an inverse relationship is witnessed for a distance between 1 and 2 km. A distance over 2 km is more appropriate for motorized modes and school buses. To promote active transport to school, children’s travel demand should be taken transport planning into consideration. Developing cycling and walking facilities is essential, especially in urban districts. Additionally, limiting the use of private motorized modes would be useful.

scholarly journals Research on dynamic prediction method for traffic demand based on trip generation analysis

2019 ◽  
Vol 11 (6) ◽  
pp. 168781401985456 ◽  
Author(s):  
Hai-jing Xu ◽  
Wen-yong Li ◽  
Tao Wang ◽  
An-lei Yang
Keyword(s):  
Land Use ◽  
Travel Demand ◽  
Influence Factor ◽  
Prediction Method ◽  
Urban Traffic ◽  
Dynamic State ◽  
Influence Coefficient ◽  
Demand Forecast ◽  
Traffic Demand ◽  
Demand Prediction

The characteristics of the residents’ travel in the information age have changed. The existing urban traffic demand forecast is mainly proceeded using the land property. Based on the main contents of urban residents’ travel survey and the characteristics of traditional residents’ travel demand, this article analyzed the dynamic changes of travel characteristics and the main influencing factors of travel formation of future residents. Combined with the travel influence factor weight of travel generation forecast stage established by the analytic hierarchy process, such as the land use, travel mode composition and travel choice, the location influence coefficient in the model of population, land use, and travel generation in city was modified to characterize the dynamic state of travel demand of residents in the phase of travel generation stage. Then a “dynamic” method for forecasting and analyzing traffic travel demand was put forward to apply to the prediction and evaluation of travel demand in Guilin. The results showed that it can reflect the dynamic characteristics of residents’ travel compared with the traditional travel demand prediction.

Sign in / Sign up

Export Citation Format

Share Document