Xianyuan Zhan

Understanding urban human activity and mobility patterns using large-scale location-based data from online social media

Location-based check-in services enable individuals to share their activity-related choices providing a new source of human activity data for researchers. In this paper urban human mobility and activity patterns are analyzed using location-based data collected from social media applications (e.g. Foursquare and Twitter). We first characterize aggregate activity patterns by finding the distributions of different activity categories over a city geography and thus determine the purpose-specific activity distribution maps. We then characterize individual activity patterns by finding the timing distribution of visiting different places depending on activity category. We also explore the frequency of visiting a place with respect to the rank of the place in individuals visitation records and show interesting match with the results from other studies based on mobile phone data.

Use of Social Media Data to Explore Crisis Informatics

Microblogs posted to Twitter after the tornado in Moore, Oklahoma, on May 20, 2013, were analyzed in this study. The potential of social media data was explored for the extraction of relevant and useful information during natural disasters and as an additional data source for better understanding of individual behavior during a crisis. Data records were attributed to user groups, and the most frequently used words were ranked to track the variation of common interests for each user group. In addition, the data were classified into different content categories, and the temporal variation patterns were analyzed. A sentiment analysis, which revealed variations in public mood and perception over time, was conducted to quantify the sentiment in the data. The techniques presented can be applied to the analysis of similar major social crises and natural disasters (e.g., hurricanes and earthquakes) to provide valuable complementary information in crisis awareness and response to users, first responders, and emergency preparedness agencies. Different stakeholders can determine the needs and activities of people during disasters by using the proposed method with the help of social media data.

Characterizing Urban Dynamics Using Large Scale Taxicab Data

Understanding urban dynamics is of fundamental importance for the efficient operation and sustainable development of large cities. In this paper, we present a comprehensive study on characterizing urban dynamics using the large scale taxi data in New York City. The pick-up and drop-off locations are firstly analyzed separately to reveal the general trip pattern across the city and the existence of unbalanced trips. The inherent similarities among taxi trips are further investigated using the two-step clustering algorithm. It builds up the relationship among detached areas in terms of land use types, travel distances and departure time. Moreover, human mobility pattern are inferred from the taxi trip displacements and is found to follow two stages: an exponential distribution with short trips and a truncated power law distribution for longer trips. The result indicates that the taxi trip may not fully represent human mobility and is heavily affected by trip expenses and the urban form and geography.

A Graph-Based Approach to Measuring the Efficiency of an Urban Taxi Service System

Taxi service systems in big cities are immensely complex due to the interaction and self-organization between taxi drivers and passengers. An inefficient taxi service system leads to more empty trips for drivers and longer waiting time for passengers and introduces unnecessary congestion on the road network. In this paper, we investigate the efficiency level of the taxi service system using real-world large-scale taxi trip data. By assuming a hypothetical system-wide recommendation system, two approaches are proposed to find the theoretical optimal strategies that minimize the cost of empty trips and the number of taxis required to satisfy all the observed trips. The optimization problems are transformed into equivalent graph problems and solved using polynomial time algorithms. The taxi trip data in New York City are used to quantitatively examine the gap between the current system performance and the theoretically optimal system. The numerical results indicate that, if system-wide information between taxi drivers and passengers was shared, it is possible to reduce 60%-90% of the total empty trip cost depending on different objectives, and one-third of all taxis required to serve all observed trips. The existence of destructive competition among taxi drivers is also uncovered in the actual taxi service system. The huge performance gap suggests an urgent need for a system reconsideration in designing taxi recommendation systems.

Citywide Traffic Volume Estimation Using Trajectory Data

Traffic volume estimation at the city scale is an important problem useful to many transportation operations and urban applications. This paper proposes a hybrid framework that integrates both state-of-art machine learning techniques and well-established traffic flow theory to estimate citywide traffic volume. In addition to typical urban context features extracted from multiple sources, we extract a special set of features from GPS trajectories based on the implications of traffic flow theory, which provide extra information on the speed-flow relationship. Using the network-wide speed information estimated from a travel speed estimation model, a volume related high level feature is first learned using an unsupervised graphical model. A volume re-interpretation model is then introduced to map the volume related high level feature to the predicted volume using a small amount of ground truth data for training. The framework is evaluated using a GPS trajectory dataset from 33,000 Beijing taxis and volume ground truth data obtained from 4,980 video clips. The results demonstrate effectiveness and potential of the proposed framework in citywide traffic volume estimation.

Understanding Social Influence in Activity Location Choice and Lifestyle Patterns Using Geolocation Data from Social Media

Social media check-in services have enabled people to share their activity-related choices providing a new source of human activity and social networks data. Geo-location data from these services offers us information, in new ways, to understand social influence on individual choices. In this paper, we investigate the extent of social influence on individual activity and life-style choices from social media check-in data. We first collect user check-ins and their social network information by linking two social media systems (Twitter and Foursquare) and analyze the structure of the underlying social network. We next infer user check-in and geo life-style patterns using topic models. We analyze the correlation between the social relationships and individual-level patterns. We investigate whether or not two individuals have similar activity choice and geo life-style patterns if they are socially connected. We find that the similarity between two users, in their check-in behavior and life-style patterns, increases with the increase of the friendship probability.

Direct transportation economic impacts of highway networks disruptions using public data from the United States

ABSTRACT This article presents a sequential method to estimate the direct transportation economic impacts (DTEI) related to transportation due to disruptions in highway networks used by trucks and cars. The main input is the Freight Analysis Framework version 3, best public data for truck movements in the United States. The method considers multicommodity flows in an equilibrium framework, associates monetary values to changes in traffic conditions that are specific to each user type, and links truck flows with commodity flows. This approach can consider transportation analysis zones smaller than those presented in the Freight Analysis Framework. A real-world numerical example is presented to estimate the DTEI due to severe floods that occurred in 2008 and disrupted key segments of the highway network in the northwestern Indiana region.

Multiclass, simultaneous route and departure time choice dynamic traffic assignment with an embedded spatial queuing model

ABSTRACT This paper develops a complementarity formulation for a multi-user class, simultaneous route and departure time choice dynamic user equilibrium (DUE) model. A path-based multiclass cell transmission model (mCTM) is embedded to propagate the traffic flow on the network. Heterogeneous user classes are incorporated in the new formulation and heterogeneity is based on different preferred arrival times, cost perception for travel time, early and late arrival penalties. Multiple model properties have been showed. The proposed model is solved as an equivalent non-monotone variational inequality (VI) problem defined on a product set. A modified proximal point algorithm is used to solve the proposed non-monotone VI problem. Numerical results show that the solution approach is able to find the equilibrium or close to equilibrium solutions. The new formulation and solution approach show the feasibility of solving the multiclass DUE problem for general traffic networks.

Dynamics of functional failures and recovery in complex road networks

We propose a new framework for modeling the evolution of functional failures and recoveries in complex networks, with traffic congestion on road networks as the case study. Differently from conventional approaches, we transform the evolution of functional states into an equivalent dynamic structural process: dual-vertex splitting and coalescing embedded within the original network structure. The proposed model successfully explains traffic congestion and recovery patterns at the city scale based on high-resolution data from two megacities. Numerical analysis shows that certain network structural attributes can amplify or suppress cascading functional failures. Our approach represents a new general framework to model functional failures and recoveries in flow-based networks and allows understanding of the interplay between structure and function for flow-induced failure propagation and recovery.