Who you are is how you travel: A framework for transportation mode detection using individual and environmental characteristics

With the increasing prevalence of geo-enabled mobile phone applications, researchers can collect mobility data at a relatively high spatial and temporal resolution. Such data, however, lack semantic information such as the interaction of individuals with the transportation modes available. On the other hand, traditional mobility surveys provide detailed snapshots of the relation between socio-demographic characteristics and choice of transportation modes. Transportation mode detection is currently approached using features such as speed, acceleration and direction either on their own or in combination with GIS data. Combining such information with socio-demographic characteristics of travellers has the potential of offering a richer modelling framework that could facilitate better transportation mode detection using variables such as age and disability. In this paper, we explore the possibility to include both elements of the environment and individual characteristics of travellers in the task of transportation mode detection. Using dynamic Bayesian Networks, we model the transition matrix to account for such auxiliary data by using an informative Dirichlet prior constructed using data from traditional mobility surveys. Results have shown that it is possible to achieve comparable accuracy with the most widely used classification algorithms while having a rich modelling framework, even in the case of sparse mobility data.     

The generators of paratransit trips by persons with disabilities

Identifying the generators of paratransit trips by persons with disabilities is important to comprehend the current demand patterns and forecast future demand. Only a handful of studies have been conducted so far to identify the generators of paratransit trips and most focused on the home end of the trips. Given some of the inconsistencies in past studies and the scarcity of studies on the generators of trips away from home, this study attempts to identify the generators of paratransit trips beginning and ending at clients’ homes and away from home. It uses an extremely large dataset consisting of 1.91 million trips made by NJ TRANSIT’s Access Link clients, socioeconomic data from the American Community Survey, employment data from the Longitudinal Employer-Household Dynamics, and establishment data from Dun and Bradstreet. The analytical methods include an ordinary least squares model (OLS) and several spatial generalized linear mixed models (GLMM) to identify the characteristics of census block groups associated with Access Link trip generation at home and away from home, Geographic Information System (GIS) analysis to identify the types of establishments located in the immediate vicinity of drop-offs, and a multinomial logit model (MNL) to examine the relationship between the characteristics of the establishments in the vicinity of drop-offs and the characteristics of the dropped-off clients. Together, the various analyses provide useful insights about paratransit trip generators at the macro and micro levels. Some implications of the findings are discussed.     

The role of household members in transporting adults with disabilities in the United States

Because of certain requirements under US federal law, many studies have been published in recent years on the role of fixed-route transit and paratransit in meeting the travel needs of persons with disabilities. Although persons with disabilities are several times more likely to take rides from household members than to take public transit, little research has been conducted to explore the circumstances under which such rides are given or taken. To address this gap in literature, this study examines the role of household members in transporting persons with disabilities in contemporary America. It explores how the circumstances for the ride takers may change in the future, identifies future challenges in providing mobility to persons with disabilities, and examines ways to meet those challenges. Using nationwide data from the 2009 National Household Travel Survey, the study compares the rides taken by persons with disabilities from household members with trips made by other travel modes, the persons who take rides with those who do not take rides, and the drivers who provide rides with those who do not provide rides. Probit models are used for the comparisons. Implications of the findings are discussed in light of potential demographic changes in the future, especially the growth of single-person households and the consequent loss of household support for transportation. Due to similarities in circumstances in other developed countries, an international context to the study is also provided.