Exploring Travel Mode Preference of External Trips for Smart City Transportation Planning: Sejong, Korea

In the face of growing concerns about urban problems, smart cities have emerged as a promising solution to address the challenges, for future sustainable societies in cities. Since the early 2000s, 67 local governments in Korea have been participating in smart city projects, as of 2019. The Sejong 5-1 Living Area smart city was selected as one of two pilot national demonstration smart cities. The main objectives of this study are to introduce the Sejong 5-1 Living Area smart city project that is currently in the planning stage, present travel and mode preferences focusing on external trips in a smart city context to be built, and analyze a mode choice model according to the socioeconomic characteristics of individual travelers. One of the distinguishing features of the Sejong smart city is its transportation design concept of designating a sharing car-only district within the city to limit private vehicle ownership to about one-third of residents, while bus rapid transit (BRT) plays a central role in mobility for external trips among four transport modes including private cars, BRT, carsharing, and ridesharing. This study was analyzed using the stated preference survey data under hypothetical conditions by reflecting the unique characteristics of the Sejong smart city transportation policy. Approximately two-thirds of respondents in the survey preferred to spend less than 1.25 USD, traveling less than 35 min on BRT trips. On the basis of the survey data, we developed a mixed logit mode choice model and found the overall model estimates to be statistically significant and reasonable. All people-specific variables examined in this study were associated with mode choices for external commuting trips, including age, income, household size, major mode, driving ability, and presence of preschoolers.

How equitable are the distributions of the physical activity and accessibility benefits of bicycle infrastructure?

Background Cycling for transport provides many health and social benefits – including physical activity and independent access to jobs, education, social opportunities, health care and other services (accessibility). However, some population groups have less opportunity to reach everyday destinations, and public transport stops, by bicycle – owing in part to their greater aversion to riding amongst motor vehicle traffic. Health equity can therefore be improved by providing separated cycleway networks that give more people the opportunity to access places by bicycle using traffic-free routes. The aim of this study was to assess the health equity benefits of two bicycle infrastructure development scenarios – a single cycleway, and a complete network of cycleways – by examining the distributions of physical activity and accessibility benefits across gender, age and income groups. Methods Travel survey data collected from residents in Sydney (Australia) were used to train a predictive transport mode choice model, which was then used to forecast the impact of the two intervention scenarios on transport mode choice, physical activity and accessibility. The latter was measured using a utility-based measure derived from the mode choice model. The distributions of the forecast physical activity and accessibility benefits were then calculated across gender, age and income groups. Results The modelled physical activity and accessibility measures improve in both intervention scenarios. However, in the single cycleway scenario, the benefits are greatest for the male, high-income and older age groups. In the complete network scenario, the benefits are more equally distributed. Forecast increases in cycling time are largely offset by decreases in walking time – though the latter is typically low-intensity physical activity, which confers a lesser health benefit than moderate-intensity cycling. Conclusions Separated cycleway infrastructure can be used to improve health equity by providing greater opportunities for transport cycling in population groups more averse to riding amongst motor vehicle traffic. Disparities in the opportunity to access services and economic/social activities by bicycle – and incorporate more physical activity into everyday travel – could be addressed with connected, traffic-free cycleway networks that cater to people of all genders, ages and incomes.

Incorporating MNL Model into Random Forest for Travel Mode Detection

Mode choice models have been used widely to forecast the relative probabilities of using available travel modes. These depend on mode-related and traveler-related characteristics. On the other hand, smartphones are increasingly being used to collect sensors’ data relating to trips made after selection of a suitable mode. Such sensors’ data may be correlated with decision-making process of travelers regarding travel mode selection. Discrete Choice Modelling is used to simulate this decision-making process by computing utilities of various travel alternatives, and then calculating their respective probabilities of being selected. In this paper, multinomial logit (MNL) mode choice model is utilized to enhance the prediction capacity of supervised learning algorithm i.e. Weighted Random Forest. To make the procedure less energy-intensive, GPS data was used only to locate the origin and destination of any trip, to be incorporated in mode choice model. Afterwards only accelerometer data was utilized in feature selection for the learning algorithm. One tenth of the classified data was used to train the algorithm whereas rest was used to test it. Results suggested that with incorporation of MNL, the overall prediction accuracy of learning algorithm was increased from 93.75% to 99.08%.

Challenges in Behaviour Modelling of Mode Choice Model - A Peek into Indian Scenario

Mode choice model is one of the crucial steps in the process for Transportation demand modelling. It fore-tell the share of trips attracted to public transportation. Mode choice models compacts very closely with the human choice making behaviour and this continues to attract researchers for further exploration of individual choice making process. The objective of this paper is to observe keenly on the challenges that a modeller will face in Indian scenario. A variety of models are available for prediction. But with the close review it is observed that all these models work either at aggregate level or disaggregate level which works on certain assumptions. This is definitely not going to reflect the actual mode choice behaviour. The particular characters that makes a difference from the world scenario discussed in this paper are diversity in decision making of individual, diversity in socio-economic characteristics, pride and prejudices in mindset that affect the false representation of data, concept of ridesharing and the inhibition in acceptance of the same, travel distance and mode availability in urban and rural scenario. It can be concluded that selecting a model that depict the true nature of commuter is a challenging process. The well-known models available can be trained and calibrated to suit to the need of Indian scenario. Use of machine learning and data mining could be a very useful tool in this model building as all the required changes can be incorporated efficiently

How Equitable Are the Distributions of the Physical Activity and Accessibility Benefits of Bicycle Infrastructure?

BackgroundCycling for transport provides many health and social benefits – including physical activity and independent access to jobs, education, social opportunities, health care and other services (accessibility). However, inequalities exist for some population groups in the opportunity to reach everyday destinations, and public transport stops, by bicycle – owing in part to their greater aversion to riding in amongst motor vehicle traffic. Health equity can therefore be improved by providing separated cycleway networks that give people the opportunity to access places by bicycle using traffic-free routes. The aim of this study was to assess the health equity benefits of two bicycle infrastructure development scenarios – a single cycleway, and a complete network of cycleways – by examining the distribution of physical activity and accessibility benefits across gender, age and income groups.MethodsTravel survey data collected from residents in Sydney (Australia) were used to train a predictive transport mode choice model, which was then used to forecast the impact of the two scenarios on transport mode choice, physical activity and accessibility. Accessibility was measured using a utility-based accessibility measure derived from the mode choice model. The distribution of forecast physical activity and accessibility benefits was then calculated across gender, age and income groups.ResultsThe modelled physical activity and accessibility measures improve in both intervention scenarios. However, in the single cycleway scenario, the benefits are greatest for the male, high-income and older age groups. In the complete network scenario, the benefits are more equally distributed. Forecast increases in cycling time are largely offset by decreases in walking time – though the latter is typically low-intensity physical activity, which confers a lesser health benefit than moderate-intensity cycling.ConclusionsSeparated cycleway infrastructure can be used to improve health equity by providing greater opportunities for transport cycling in population groups more averse to riding amongst motor vehicle traffic. Disparities in the opportunity to access services and economic/social activities by bicycle – and incorporate more physical activity into everyday travel – could be addressed with connected, traffic-free cycleway networks that cater to people of all genders, ages and incomes.

A two-stage residential location and transport mode choice model with exposure to traffic-induced air pollution

Air pollution is an increasing concern to urban residents. In response, residents are beginning to adapt their travel behaviour and to consider local air quality when choosing a home. We study implications of such behaviour for the morphology of cities and population exposure to traffic-induced air pollution. To do so, we propose a spatially explicit and integrated residential location and transport mode choice model for a city with traffic-induced air pollution. Intra-urban spatial patterns of population densities, transport mode choices, and resulting population exposure are analysed for urban settings of varying levels of health concern and air pollution information available to residents. Numerical analysis of the feedback between residential location choice and transport mode choice, and between residents' choices and the subsequent potential impact on their own health suggests that increased availability of information on spatially variable traffic-induced health concerns shifts population towards suburban areas with availability of public transport. Thus, health benefits result from reduced population densities close to urban centres in this context. To mitigate population exposure, our work highlights the need for spatially explicit information on peoples' air pollution concerns and, on this basis, spatially differentiated integrated land use and transport measures.

A two-stage residential location and transport mode choice model with exposure to traffic-induced air pollution

Air pollution is an increasing concern to urban residents. In response, residents are beginning to adapt their travel behaviour and to consider local air quality when choosing a home. We study implications of such behaviour for the morphology of cities and population exposure to traffic-induced air pollution. To do so, we propose a spatially explicit and integrated residential location and transport mode choice model for a city with traffic-induced air pollution. Intra-urban spatial patterns of population densities, transport mode choices, and resulting population exposure are analysed for urban settings of varying levels of health concern and air pollution information available to residents. Numerical analysis of the feedback between residential location choice and transport mode choice, and between residents' choices and the subsequent potential impact on their own health suggests that increased availability of information on spatially variable traffic-induced health concerns shifts population towards suburban areas with availability of public transport. Thus, health benefits result from reduced population densities close to urban centres in this context. To mitigate population exposure, our work highlights the need for spatially explicit information on peoples' air pollution concerns and, on this basis, spatially differentiated integrated land use and transport measures.