Tallahassee, FL, United States
Tallahassee, FL, United States
Time filter
Source Type

News Article | September 20, 2017

Citilabs, a leading mobility analytics solution provider, announced today that they have inked an agreement with location data provider SafeGraph to incorporate smartphone app movement data into Citilabs’ Streetlytics mobility analytics platform. Streetlytics leverages information from billions of GPS, cellular, connected car, Bluetooth and ground truth data to measure and paint a complete picture of the moving population. SafeGraph maintains the world’s largest and most accurate dataset on human movement, to power both machine learning & human analysts. “SafeGraph’s goal is to fuel companies interested in answering difficult questions related to human movement. To be included in the Citilabs’ Streetlytics solution is a great indication that we are succeeding in that goal,” said SafeGraph CEO Auren Hoffman. He continued, “We look forward to a long and mutually beneficial partnership with Citilabs.” Industries as far ranging as advertising, mobility services, insurance, real estate, and auto manufacturing are leveraging the power of Streetlytics. It provides direct access to nation-wide hour-by-hour moving population insights including origin-destination movements, home locations, road level volumes, speeds and travel routes. “Citilabs is excited to be adding SafeGraph data into our Streetlytics solution,” said CEO Michael Clarke. “Every layer of data adds additional insights. Including data of the quality SafeGraph provides is a real win for us and our clients.” One of those clients is Geopath, a not-for-profit that provides state-of-the-art measurement to the out of home advertising industry. “We are truly excited about the addition of SafeGraph to the Streelytics solution,” said Geopath President, Kym Frank. “The data we are receiving from Citilabs is already quite robust, and the diversification of location data sources used in our methodology will only increase the resolution of the industry’s population measurement.” ABOUT CITILABS At Citilabs, we build robust solutions that empower meaningful change for the betterment of communities and organizations by understanding the movement of people, goods and vehicles. Citilabs’ solutions allow users to measure, manage and predict how people move and goods flow, advising the transportation, advertising, insurance, real estate, smart cities and automotive industries. Headquartered in Sacramento, with offices in Atlanta, Tallahassee, Abu Dhabi, Milan, and Singapore, Citilabs has a 40-year history as a global industry leader and supports more than 2,500 clients in more than 70 countries. For more information, visit ABOUT SAFEGRAPH SafeGraph is building the world’s largest and most accurate ground truth dataset on human movement to power machine learning and human analysts. Co-founded by Auren Hoffman and Brent Perez, SafeGraph is located in San Francisco. For more information, visit ABOUT GEOPATH Founded in 1933, Geopath is the industry standard that powers a smarter OOH marketplace through state-of-the art audience location measurement, deep insights, and innovative market research. The organization is headquartered in New York and governed by a tripartite board comprised of advertisers, agencies, and media companies spanning the entire United States.

Xu X.,Nanjing Southeast University | Xu X.,Utah State University | Chen A.,Utah State University | Zhou Z.,Citilabs | Cheng L.,Nanjing Southeast University
Journal of Advanced Transportation | Year: 2014

Recent empirical studies have revealed that travel time variability plays an important role in travelers' route choice decisions. To simultaneously account for both reliability and unreliability aspects of travel time variability, the concept of mean-excess travel time (METT) was recently proposed as a new risk-averse route choice criterion. In this paper, we extend the mean-excess traffic equilibrium model to include heterogeneous risk-aversion attitudes and elastic demand. Specifically, this model explicitly considers (1) multiple user classes with different risk-aversions toward travel time variability when making route choice decisions under uncertainty and (2) the elasticity of travel demand as a function of METT when making travel choice decisions under uncertainty. This model is thus capable of modeling travelers' heterogeneous risk-averse behaviors with both travel choice and route choice considerations. The proposed model is formulated as a variational inequality problem and solved via a route-based algorithm using the modified alternating direction method. Numerical analyses are also provided to illustrate the features of the proposed model and the applicability of the solution algorithm. Copyright © 2012 John Wiley & Sons, Ltd.

Zockaie A.,Northwestern University | Saberi M.,Monash University | Mahmassani H.S.,Northwestern University | Jiang L.,Citilabs | And 2 more authors.
Transportation Research Record | Year: 2015

To forecast the impact of congestion pricing schemes, it is essential to capture user responses to these schemes and the resulting dynamics of traffic flow on the network. The responses of users must include route, departure time, and mode choices. To capture the effects of these decisions, this paper lays out a framework for the integration of the relevant elements of an activity-based model (ABM) with a dynamic traffic assignment (DTA) model and a simulation framework to support the analysis and evaluation of various pricing schemes. In this paper, a multicriterion dynamic user equilibrium traffic assignment model is used; the model explicitly considers heterogeneous users who seek to minimize travel time, out-of-pocket cost, and travel time reliability in the underlying route choice framework. In addition to the methodological developments, various demand and supply parameters are estimated and calibrated for the selected application network (the Greater Chicago, Illinois, network). This paper showcases the integration of ABM components and a DTA in one coherent modeling framework for the implementation and evaluation of congestion pricing in an actual large-scale network.

Chen A.,Utah State University | Chen A.,Tongji University | Xu X.,Utah State University | Xu X.,Nanjing Southeast University | And 2 more authors.
Transportmetrica A: Transport Science | Year: 2013

Stepsize determination is an important component of algorithms for solving several mathematical formulations. In this article, a self-adaptive Armijo strategy is proposed to determine an acceptable stepsize in a more efficient manner. Instead of using a fixed initial stepsize in the original Armijo strategy, the proposed strategy allows the starting stepsize per iteration to be self-adaptive. Both the starting stepsize and the acceptable stepsize are thus allowed to decrease as well as increase by making use of the information derived from previous iterations. This strategy is then applied to three well-known algorithms for solving three traffic equilibrium assignment problems with different complexity. Specifically, we implement this self-adaptive strategy in the link-based Frank-Wolfe algorithm, the route-based disaggregate simplicial decomposition algorithm and the route-based gradient projection algorithm for solving the classical user equilibrium problem, the multinomial logit-based stochastic user equilibrium (MNL SUE) and the congestion-based C-logit SUE problem, respectively. Some numerical results are also provided to demonstrate the efficiency and applicability of the proposed self-adaptive Armijo stepsize strategy implemented in traffic assignment algorithms. © 2013 Hong Kong Society for Transportation Studies Limited.

Chen A.,Utah State University | Zhou Z.,Citilabs | Ryu S.,Utah State University
International Journal of Sustainable Transportation | Year: 2011

The traffic equilibrium problem plays an important role in urban transportation planning and management. It predicts vehicular flows on the transportation network by assigning travel demands given in terms of an origin-destination trip table to routes in a network according to some behavioral route choice rules. In this paper, we enhance the realism of the traffic equilibrium problem by explicit modeling various physical and environment restrictions as side constraints. These side constraints are a useful means for describing queuing and congestion effects, restraining traffic flows to limit the amount of emissions, and modeling different traffic control policies. A generalized side-constrained traffic equilibrium (GSCTE) model is presented and some characterizations of the equilibrium solutions are discussed. The model is formulated as a variational inequality problem and solved by a predictor-corrector decomposition algorithm. Two numerical experiments are conducted to demonstrate some properties of the GSCTE model and the convergence properties of the decomposition algorithm. © Taylor & Francis Group, LLC.

Chen A.,Utah State University | Zhou Z.,Citilabs | Xu X.,Utah State University
Computers and Operations Research | Year: 2012

Gradient projection (GP) algorithm has been shown as an efficient algorithm for solving the traditional traffic equilibrium problem with additive route costs. Recently, GP has been extended to solve the nonadditive traffic equilibrium problem (NaTEP), in which the cost incurred on each route is not just a simple sum of the link costs on that route. However, choosing an appropriate stepsize, which is not known a priori, is a critical issue in GP for solving the NaTEP. Inappropriate selection of the stepsize can significantly increase the computational burden, or even deteriorate the convergence. In this paper, a self-adaptive gradient projection (SAGP) algorithm is proposed. The self-adaptive scheme has the ability to automatically adjust the stepsize according to the information derived from previous iterations. Furthermore, the SAGP algorithm still retains the efficient flow update strategy that only requires a simple projection onto the nonnegative orthant. Numerical results are also provided to illustrate the efficiency and robustness of the proposed algorithm. © Published by Elsevier Ltd.

Xu X.,Utah State University | Chen A.,Utah State University | Zhou Z.,Citilabs | Bekhor S.,Technion - Israel Institute of Technology
Transportation Research Record | Year: 2012

This paper develops path-based algorithms to solve the C-logit stochastic user equilibrium (SUE) problem on the basis of an adaptation of the gradient projection method. The algorithms' strategies for step size determination differ. Three strategies are investigated: (a) predetermined step size, (b) Armijo line search, and (c) self-adaptive line search. The algorithms are tested on the well-known Winnipeg (Manitoba, Canada) network. Two sets of experiments are conducted: (a) a computational comparison of different line search strategies and (b) the impact of different modeling specifications for route overlapping (a flow-independent or a flow-dependent commonality factor). The results indicate that the path-based algorithm with the self-adaptive step size strategy performs better than the other step size strategies. The paper shows that, depending on the model parameters, particularly the commonality factor parameter, the C-logit SUE flows may be quite different from the multinomial logit SUE flows.

Signal timing and lane allocation are most important settings at signalized intersections to control the operation. Efficiently operated traffic signals and reasonably designed lane markings can reduce congestion and bring about significant payoffs in time and energy benefits. The design of signal timing plan and lane allocation pattern should be complementary to each other; however, existing research works have been concentrated on signal optimization, and few of them considered the impact of lane allocation pattern. This paper proposed an optimization model for the integration design of signal timing plan and lane allocation pattern at signalized intersections. A Genetic Algorithms (GA) model is developed and validated with the Cube transportation software suites. A fully optimized intersection design, including cycle length, phase durations, phase sequence, permitted movements, lane allocations, and shared movements, can be generated according to the assigned traffic flows and geometric properties at the intersection. A set of constrains are set up to guarantee feasibility of the optimal signal timing plan and lane allocation pattern design.

Zhou Z.,Citilabs | Chen A.,Utah State University | Bekhor S.,Technion - Israel Institute of Technology
Transportmetrica | Year: 2012

This article considers the stochastic user equilibrium (SUE) problem with the route choice model based on the C-logit function. The C-logit model has a simple closed-form analytical probability expression and requires relatively lower calibration efforts and represents a more realistic route choice behaviour compared with the multinomial logit model. This article proposes two versions of the C-logit SUE model that captures the route similarity using different attributes in the commonality factors. The two versions differ with respect to the independence assumption between cost and flow. The corresponding stochastic traffic equilibrium models are called the length-based and congestion-based C-logit SUE models, respectively. To formulate the length-based C-logit SUE model, an equivalent mathematical programming formulation is proposed. For the congestion-based C-logit SUE model, we provide two equivalent variational inequality formulations. To solve the proposed formulations, a new self-adaptive gradient projection algorithm is developed. The proposed formulations and new solution algorithm are tested in two well-known networks. Numerical results demonstrate the validity of the formulations and solution algorithm. © 2011 Copyright Taylor and Francis Group, LLC.

Loading Citilabs collaborators
Loading Citilabs collaborators