Probe Car Data Research Articles

Extrapolation of Local Vehicle Counts Using Probe-Car Data

Extrapolation of Local Vehicle Counts Using Probe-Car Data

Path Travel Time Estimating Method by Incomplete Traffic Data

This study proposes a method estimating stochastic path travel times by using both traffic counter data and probe car data complementarily. A stochastic traffic demand for each O-D pair in a road network is estimated by maximum likelihood estimation with respect to traffic counter data. Stochastic path travel times are addressed as a prior multivariate path travel time distribution. The estimated stochastic path travel time is updated by applying Bayesian inference using observed probe car data. The updated path travel time can be regarded as a posterior multivariate path travel time distribution. Numerical experiments demonstrate inference processes of path travel time and verify our proposed model.

Utilizing MapReduce to Improve Probe-Car Track Data Mining

With the rapidly increasing popularization of the automobile, challenges and greater demands have come to the fore, including traffic congestion, energy crises, traffic safety, and environmental pollution. To address these challenges and demands, enhanced data support and advanced data collection methods are crucial and highly in need. A probe-car serves as an important and effective way to obtain real-time urban road traffic status in the international Intelligent Transportation System (ITS), and probe-car technology provides the corresponding solution through advanced navigation data, offering more possibilities to address the above problems. In addition, massive spatial data-mining technologies associated with probe-car tracking data have emerged. This paper discusses the major problems of spatial data-mining technologies for probe-car tracking data, such as true path restoration and the close correlation of spatial data. To address the road-matching issue in massive probe-car tracking data caused by the strong correlation combining road topology with map matching, this paper presents a MapReduce-based technology in the second spatial data model. The experimental results demonstrate that by implementing the proposed spatial data-mining system on distributed parallel computing, the computational performance was effectively improved by five times and the hardware requirements were significantly reduced.

An analysis of the impact of driving time on the driver's behavior using probe car data

Abstract: Driver's fatigue is an important factor of traffic accidents. Therefore, a fatigue detection system which achieves a small burden on a driver is expected to be developed, which stimulates drivers after long hour driving to take a rest at an appropriate timing when the driver's fatigue is detected. In order to give warning at an appropriate timing, knowledge about the impact of continuous driving hours on driver's behavior should be obtained. Recently, a rapid spread of ITS technologies enables us to analyze driving behavior in detail by using a large quantity of probe car data. This study analyses the impact of continuous driving hours on driving behavior when a vehicle is traveling on an expressway based on the probe car data. It is shown that the continuous driving hour affects driving behavior significantly. From the results, it can be concluded that driver had better take a rest every 5,000 [s]approximately.

Prediction of Fuel Consumption by Analyzing Probe Car Data

Prediction of Fuel Consumption by Analyzing Probe Car Data

Real-time traffic incident detection using a probabilistic topic model

Traffic congestion occurs frequently in urban settings, and is not always caused by traffic incidents. In this paper, we propose a simple method for detecting traffic incidents from probe-car data by identifying unusual events that distinguish incidents from spontaneous congestion. First, we introduce a traffic state model based on a probabilistic topic model to describe the traffic states for a variety of roads. Formulas for estimating the model parameters are derived, so that the model of usual traffic can be learned using an expectation–maximization algorithm. Next, we propose several divergence functions to evaluate differences between the current and usual traffic states and streaming algorithms that detect high-divergence segments in real time. We conducted an experiment with data collected for the entire Shuto Expressway system in Tokyo during 2010 and 2011. The results showed that our method discriminates successfully between anomalous car trajectories and the more usual, slowly moving traffic patterns.

Toward simulating entire cities with behavioral models of traffic

Resilient transportation systems enable quick evacuation, rescue, distribution of relief supplies, and other activities for reducing the impact of natural disasters and for accelerating the recovery from them. The resilience of a transportation system largely relies on the decisions made during a natural disaster. We developed an agent-based traffic simulator for predicting the results of potential actions taken with respect to the transportation system to quickly make appropriate decisions. For realistic simulation, we govern the behavior of individual drivers of vehicles with foundational principles learned from probe-car data. For example, we used the probe-car data to estimate the personality of individual drivers of vehicles in selecting their routes, taking into account various metrics of routes such as travel time, travel distance, and the number of turns. This behavioral model, which was constructed from actual data, constitutes a special feature of our simulator. We built this simulator using the X10 language, which enables massively parallel execution for simulating traffic in a large metropolitan area. We report the use cases of the simulator in three major cities in the context of disaster recovery and resilient transportation.

Estimation of Traffic Situation after Natural Disasters based on Probe-car Data and Vehicle Information and Communication System

Estimation of Traffic Situation after Natural Disasters based on Probe-car Data and Vehicle Information and Communication System

Potential of Plug-in Hybrid Vehicle to Reduce CO2 Emission Estimated from Probe Car Data in Japan

The reduction of CO2 emission by the transport sector is necessary to be realized the low carbon society. In the near future, further CO2 emission reduction is expected by the diffusion of PHEV. The aim of this study was to evaluate the potential of PHEV to reduce CO2 emission based on real-world driving data (probe car data) and simulation. The probe car data of 35 conventional HEVs from April to August in 2011 were analyzed. The type of simulated PHEV system was all electric range, which operated only by battery power as long as available battery capacity was remaining (EV mode) , and then operated like conventional HEV after battery was depleted (HEV mode). Charging frequency was once a day at home after midnight as a realistic scenario. The results showed that the travel distance of 43% was converted to EV mode, and the gasoline consumption was reduced by 44%. The CO2 emission was totally reduced by 17% considering electric power consumption. CO2 emissions of each vehicle were reduced by 1-44%. CO2 reduction amount of each vehicle varied widely reflecting their each own ways of car use and operating conditions. It is indicated that the diffusion of PHEV is a realistic and efficient measure to reduce CO2 emissions in consideration of actual car use and operating conditions. Furthermore, low carbon power supply as well as diffusion of PHEV is more effective to CO2 reduction.

Vehicle Near-miss Situation Prediction from Probe-car Data Using Statistical Machine Learning

Vehicle Near-miss Situation Prediction from Probe-car Data Using Statistical Machine Learning

Route Identification of Freight Vehicle's Tour Using GPS Probe Data and its Application to Evaluation of on and off Ramp Usage of Expressways

GPS-based probe car data is useful for studying traffic situations that roadside sensors cannot detect. However, the ambiguity in the map-matching and route identification processing of link-based probe data analysis has been a difficult problem especially in urban areas with many high-density roads and elevated roads. Unlike situations in which navigation systems are to be developed, in offline analysis, there are cases where a real-time constraint is not imposed. This means we can refer to data from any time of day of a vehicle tour and use much more computer resources than would be available for real-time embedded systems. In this paper, a new method of map-matching and the route identification based on dynamic programming is proposed and its effectiveness is shown in comprehensive field data tests.

Development of Calculating Method of Travel Time Reduction Benefit When Using CNS: By Using Taxi Probe Car Data of UTIS

Development of Calculating Method of Travel Time Reduction Benefit When Using CNS: By Using Taxi Probe Car Data of UTIS

Constructing Two-layered Freight Traffic Network Model from Truck Probe Data

The road network in the Keihanshin area (the second most populated urban region in Japan encompassing the metropolitan areas of the cities of Osaka in Osaka prefecture, Kobe in Hyōgo Prefecture, and Kyoto in Kyoto prefecture) is modeled as two layers from the viewpoint of the frequency of use of roads by freight vehicles. This model was derived,tested and validated from the probe car data of 300 trucks operated by 21 freight companies in the Keihanshin area. The two layers are called high-frequency-network and low-frequency-network layers. Characteristics, such as the density of probe data, average driving time, and speed of both network layers, were estimated. This analysis revealed that trucks spend a duration about 6 times longer on the high-frequency network even though it is 1/4 the size of the low-frequency network. The instantaneous velocity histograms indicated a significant difference in speeds between the two network layers of 25.03 km/h in the high-frequency layer and 16.87 km/h in the low-frequency layer. Service-level evaluations, reliability analysis, and route-selection modeling should become easier to deal with in the future by introducing these layered networks.

Examination of the Applicability of Probe Car Data to Assessment of the Effects of Road-Safety Projects

To achieve “the safest roads in the world”, the government of Japan has been addressing projects aimed at reducing annual traffic fatalities to below 5,000 by 2012, working hand-in-hand with the private sector. In this study, the potential for application of probe car data in quantitative assessment of project impacts is investigated after collecting such data from taxis and lorries. It is demonstrated that the changes in vehicle behaviors leading to accidents are indicated quantitatively at high-accident locations through the before-and-after projects. Probe car data therefore have the potential for application in measuring the effects of road safety projects.

Formulation and Validation of Model for Calculating the Number of Probe Cars Considering Traffic Information Update Frequency

Probe cars are very effective tools in traffic information gathering. Probe cars can collect the traffic condition data without using roadside sensors but with only using their own equipped sensors. By using probe cars, it is expected that the accuracy of traffic information will be improved and the area coverage of the traffic information service will be increased, and many experimental probe car data collection projects have been implemented. However, the number of probe cars required for adequate information update frequency has not been theoretically discussed. This paper formulates the probabilistic relationships among the traffic volume of probe cars, the area coverage, and the update frequency of traffic information provision. This formulation calculates the adequate number of probe cars to realize traffic information services in advance considering two major service factors: area coverage and update frequency. This paper also validates the theoretical formulation with experimental probe car data collected in a taxi monitoring system.

Analysis of Delivery Activities of Trucks Using Probe Car Data

This study aims to analyze delivery activities of freight trucks by using probe car data including drivers' working status and obtain the basic informationeeded for solving the vehicle routing and scheduling problems.Two truck companies of different operations were studied, one which mainly hauls goods over medium-to-long distances and the other which hauls goods along regular routes to locations inside the city.The following information was revealed through the analysis; 1.Fluctuation of travel speeds, 2.Distribution of arrival times to destination facilities, 3.Distnbution of loading and unloading times and 4.Behavioral patterns of keeping the designated time windows.

Estimation of Link Performance Function by Using Probe-Car Data

In this study, we estimated the link performance function and investigated its reproducibility using probe-car data. The estimated results showed high variability. One of the main factors which cause the variability was the link capacity settings, and it might be essential to modify the link capacity properly referring to the observed daily traffic volumes. The signal cycle was another factor, and it is, therefore, required to set the link length appropriately to reduce its effect. Thus, probe-car data seems to be useful to estimate the link performance function and check its validity.

The Model Analysis on Route choice behavior based on Probe-Car Data

Analysis on route choice behavior is the key to analyzing travel behavior and traffic demand on road networks. The data from the probe-car systems are very useful for making it clear. In this study we analyze the route choice behaviors, especially the accuracy of the travel time information drivers use for route choicc and the fits of several route choice models The result indicates that drivers use rather rough information on expected travel conditions for route choice, and that necessity of analysis on dynamic route choice behavior and framework of route choice process.