published journal article
conference paper
published journal article
Peer-to-peer (P2P) ridesharing is a recently emerging travel alternative that can help accommodate the growth in urban travel demand and at the same time alleviate problems such as excessive vehicular emissions. Prior ridesharing projects suggest that the demand for ridesharing is usually shifted from transit, but its true benefits are realized when the demand shifts from single-occupancy vehicles. This study investigated the potential of shifting demand from private autos to transit by providing a general modeling framework that found routes for private vehicle users that were a combination of P2P ridesharing and transit. The Los Angeles Metro Red Line in California was considered for a case study because it has recently shown declining ridership trends. For successful implementation of a ridesharing system, strategically selecting locations for individuals to get on and off the rideshare vehicles is crucial, along with an appropriate pricing structure for the rides. The study conducted a parametric analysis of the application of real-time P2P ridesharing to feed the Los Angeles Metro Red Line with simulated demand. A mobile application with an innovative ride-matching algorithm was developed as a decision support tool that suggested transit-rideshare and rideshare routes.
conference paper
A multicommodity discrete kinematic wave model that possesses the theoretical rigor and computational efficiency inherent in the kinematic wave theory is proposed for simulating network traffic flow. In this model, fluxes through boundaries and junctions are computed systematically under the supply-demand framework. In addition, traffic is modeled by commodity type so that the effects of geometric characteristics of a road network on traffic dynamics can be captured. Although traffic is not ordered down to the vehicle level as in existing kinematic wave simulation models, the noncompliance with the first-in-first-out property in this model is still of the order of At, the time increment. Hence travel times in the average sense can be defined from cumulative curves. Finally, the evolution of traffic dynamics in a sample road network is shown to demonstrate the stability, numerical convergence, and soundness of the proposed network kinematic wave model.
published journal article
Recently, road scene-graph representations used in conjunction with graph learning techniques have been shown to outperform state-of-the-art deep learning techniques in tasks including action classification, risk assessment, and collision prediction. To enable the exploration of applications of road scene-graph representations, we introduce roadscene2vec: an open-source tool for extracting and embedding road scene-graphs. The goal of roadscene2vec is to enable research into the applications and capabilities of road scene-graphs by providing tools for generating scene-graphs, graph learning models to create spatio-temporal scene-graph embeddings, and tools for visualizing and analyzing scene-graph-based methodologies. The capabilities of roadscene2vec include (i) customized scene-graph generation from either video clips or data from the CARLA simulator, (ii) multiple configurable spatio-temporal graph embedding models and baseline CNN-based models, (iii) built-in functionality for using graph and sequence embeddings for risk assessment and collision prediction applications, (iv) tools for evaluating transfer learning, and (v) utilities for visualizing scene-graphs and analyzing the explainability of graph learning models. We demonstrate the utility of roadscene2vec for these use cases with experimental results and qualitative evaluations for both graph learning models and CNN-based models. roadscene2vec is available at https://github.com/AICPS/roadscene2vec.
published journal article
We present a new way of modeling local labor markets by linking the space of workers’ skills and the physical space of cities. The key lesson of our analysis is that firms exploit workers in these two spaces by setting wages that are below the competitive level. The degree of monopsony power depends on the elasticity of the firm’s labor pool, which is inversely related to the costs workers incur in commuting and acquiring skills. Our analysis thus shows how socioeconomic ghettos emerge as workers with poor skill matches are also those who incur the highest commuting costs.
published journal article
There is interest in understanding which characteristics of metropolitan areas impact the length of time or distance residents spend commuting. We utilize two measures recently introduced to the urban literature capturing distinct dimensions of employment decentralization –the level of employment deconcentration and employment spatial dispersion in metropolitan areas – to assess how they are related to commuting patterns across metropolitan areas. These two measures of urban/metropolitan spatial structure avoid challenges in identifying “job centers” and allow for a more systematic investigation of how employment decentralization affects commuting patterns. Furthermore, we detect key differences for the implications of these measures for commuting across 329 US metropolitan regions based on their population size. We find that greater employment deconcentration in very small MSAs is associated with longer commute times and distances, whereas greater employment deconcentration in large or very large MSAs is associated with shorter commutes. And whereas spatial dispersion is not related to commute times in very small MSAs, greater spatial dispersion is associated with longer commutes in very large MSAs. This study also shows that the spatial pattern of employment in regions, captured by these new measures, is associated with the proportion of very short and very long duration commutes.
published journal article
published journal article
conference paper
A systematic approach is developed to transform data in the existing yellow-page databases to a point-based GIS database on activity supply, Such a database is needed for an activity-based travel forecasting system and for disaggregate accessibility analysis. First, the linkage between activity types and business types is established. According to this lookup relationship, businesses and services associated with certain activity types can be selected, These records are then geocoded by address-matching in a GIS and the locations supplying those activities are pinned down. Technical issues, such as difficulty in linking businesses to activities, long term projection, and address-matching, are discussed and potential solutions are provided. Finally, issues that need to be addressed when attempting to develop an activity-based forecasting system are examined from the perspective of activity supply.