Time filter

Source Type

Yang P.,Beihang University | Zhu T.,Beijing Transportation Information Center | Wan X.,Beihang University | Wang X.,Beihang University
Proceedings - International Conference on Tools with Artificial Intelligence, ICTAI | Year: 2015

Call detail records (CDRs) containing mass position information allow us to reveal characteristics about the city dynamics and human behaviors, which are crucial for policy decisions such as urban planning and transportation engineering. Being able to identify the trajectory and significant places is of prime importance. In this paper, we aim to extract trajectory from anonymized call detail records and adopt two-step clustering to obtain significant places from multi-day data. We propose a new method for mining trajectory by identifying users' stop and move state based on location gradient, which can be applied to users with low communication frequency. We analyze the feature of real CDR data and propose novel methods for noise handling. Home Time and Work Time are extracted from statistics of users' mobility pattern to recognize their significant places including home and work of a single day. Utilizing the characteristic of cyclical mobility, we conduct a cluster analysis to identify users' significant places which are not limited to one home or one work based on multi-day data. We run four experiments to show the robustness and stability of our method. During both typical stop and move period, our method performs better than state-of-art method. © 2014 IEEE. Source

Song Z.,Beihang University | Zhu T.,Beihang University | Wu D.,Beijing Transportation Information Center | Lius S.,Beihang University
Proceedings - International Conference on Tools with Artificial Intelligence, ICTAI | Year: 2015

Traffic speed is one of the most essential parameters representing traffic conditions in intelligent traffic system (ITS). In recent years, there have been several approaches estimating traffic speed based on cellular network signaling data. However, the accuracy of these approaches is unsatisfactory because they have a poor performance in filtering out noisy data and minimizing deviations of traffic speed values' trend in adjacent time intervals. In this paper, a new approach is proposed to solve the two problems above. The approach filters out noisy data according to educated judgment, and adopts a modified Kalman filter algorithm to minimize the deviations. The performance study on real data sets of Beijing shows that the accuracy of the proposed approach is higher when compared with existing two notable estimation approaches. Further the approach will contribute to developing intelligent navigation systems and pursuing artificial intelligence applications. © 2014 IEEE. Source

Wang J.-C.,Beijing Transportation Information Center
Jiaotong Yunshu Xitong Gongcheng Yu Xinxi/Journal of Transportation Systems Engineering and Information Technology | Year: 2015

Nowadays using taxi booking app with Smartphone is a new way to take a taxi and it becomes more and more popular in Beijing. A data process model is put forward and the orders of taxi booking app is analyzed to find out the timely and spatial characteristics, such as night-peak, a low on Saturday and high instantaneity, linear increasement with ring-roads, and non-uniformity of kernel density spatially. This paper also studies the evaluation method of taxi booking app based on its comparison with the basic indexes of taxi management, and evaluates application effect of two periods. Copyright ©2015 by Science Press. Source

Li J.,Beijing Transportation Information Center
ICTIS 2013: Improving Multimodal Transportation Systems - Information, Safety, and Integration - Proceedings of the 2nd International Conference on Transportation Information and Safety | Year: 2013

In order to enhance the application value of the transportation data center further, it was essential to use business intelligence (BI) technology for data mining, analyzing, and displaying. On the basis of summarizing the status and trend of BI technology for data display and analysis, the general methods of the analysis process for the data center were summarized. Taking the taxi meter data of Beijing as an example, the structure of the original data was analyzed and the calculation method for the taxi operation index was put forward. The indexes were put forward, including operation mileage, operation time, number of carrying passengers, income, and so on. They were analyzed from different dimensions using BI technology. The functions of historical data query, report output, and others were provided, supporting the taxi operation management and decision. © 2013 American Society of Civil Engineers. Source

Weng J.-C.,Beijing University of Technology | Liu W.-T.,Beijing Transportation Information Center | Chen Z.-H.,Beijing Transportation Information Center | Rong J.,Beijing University of Technology
Beijing Gongye Daxue Xuebao/Journal of Beijing University of Technology | Year: 2010

The urban floating car data (FCD) collection system is usually constructed on the basis of the taxi dispatch system, and the taxies are serviced as the floating cars. Thus, the floating car data (FCD) collected from the system also include the operation information and status information of taxies. This paper proposes several Floating Car Data based indexes and analysis models for taxi operation. Taking Beijing as a case for study, the paper analyzes the parameters including travel mileage, virtual mileage ratio, time-space distribution on the road-network and the labor intensity of drivers. Then, several important parameters about the taxi operation in Beijing are concluded in this research. These data can provide useful data support for the taxi dispatching management, taxi stop planning, vehicles deployment and general decision making for the management of taxi industry. Source

Discover hidden collaborations