Jing Teng

Historical Travel Time Based Bus-Arrival-Time Prediction Model

Bus-arrival-time information service is a key component of an Advanced Public Transportation System (APTS). Instantaneous and accurate prediction of bus-arrival-time can improve the quality of transit service. With the input of tested historical bus travel time, a combined bus-arrival-time prediction model is promoted with a self adaptive exponential smoothing algorithm to predict interzone-section travel time and a statistical algorithm for multi-section travel time prediction. An experiment was conducted to compare the performance between the multi-section travel time (MSTT) based model and the sum of multi section travel time (STT) based model, with measures of mean error (ME), mean absolute error (MAE), and mean absolute percentage error (MAPE). The prediction results show that the MSTT based model outperformed the historical multi STT based model in terms of accuracy, reliability and precision.

Tendency-Based Approach for Link Travel Time Estimation

AbstractFrom the historical bus trajectories, it was found that the headway bias amplified as buses travel on the route. When controls on buses are unavailable, the following buses will maintain the movement tendency toward their previous one, whether being closer to, farther away, or stable, judged by the running state in which buses fall. A tendency-based model for link travel time estimation was proposed, and three tendency-based corrections were introduced in the model, which are the long-term tendency, the short-term tendency, and the combined-term tendency. Then, contrast experiments were conducted in which the boundary of the running state is a control variable to show the performance of the tendency-based model under different boundary values. The experiment results show that, with the increase of the boundary value, the degree of improvement of the tendency-based mode to the historical data–based model first increases, then decreases, and converges to zero finally. The optimal boundary value for ...

Using CVIS to improve bus schedule adherence: a predictive control strategy and its hardware in-the-loop field tests

The ability of buses to adhere to their advertised schedule is vital to the bus operations. In this paper, an adaptive control strategy is proposed to dynamically adjust bus speed and traffic signal timings along the path of a running bus to improve its schedule adherence. The strategy relies on real-time location and speed information of buses provided by cooperative vehicle infrastructure system (CVIS) and uses key-time nodes calculated by back-stepping of planned arrival times to dynamically update signal timing plans to keep the bus running on time. A hardware-in-the-loop (HIL) field test was conducted to evaluate the developed strategy and the results are encouraging.

Coordinated Optimization of Bus Headways for Passenger Corridors

Passenger corridors carry high-density passenger volumes and they are intensive superposition sections of passenger OD demands in the transit network. In order to balance supply and demand distribution between different bus routes on the same passenger corridor, the optimization methodology of headways need be studied. This paper set up a bus coordination dispatching model for passenger corridors and then applied GA as the optimizing algorithm. A real case study was given to illustrate the application of the methodology and the results show that the model and algorithm are feasible and effective.

Organization of a Shuttle Bus under the Condition of Operation Interruption to Urban Rail Transit

When an urban rail transit (URT) is interrupted, it can cause great delays and may result in heavy casualties. The shuttle bus is considered to be an effective way to connect the fault section. The passenger flow characteristics of the line, the departure frequency and the fitted out vehicles of the shuttle bus are the key points for emergency decision-making. To solve those problems, this paper made a Stated Preference (SP) survey to figure out the demand characteristics of passengers. A route choice model was designed to forecast passenger demand based on historical URT origin/destination (OD) data and SP data, and the optimization method for considering and not considering the constraint of the number of bus vehicles was given. A case study in Shanghai showed that the proposed method can meet the distributary demand caused by train delay and save the number of bus vehicles dispersed when operation interruption occurs.

Scheduling of Feeder Vehicles for Intermodal Services for Special Events

During special events, shuttle services provided by a feeder bus system can be very useful for providing passengers access to the mass rapid transit system, especially passengers in suburban areas where regular transit service is not usually available. During Expo 2010 Shanghai in China, such shuttle services connected the major terminals and the expected locations of passenger generation. Because of constrained vehicle resources and the staggered characteristics of peak hours, the free time spans of regular vehicles were used to complete the fixed feeder timetables. An integer-linear programming model was developed to obtain the optimal schedules of the feeder vehicles, and an associated coordination mechanism was proposed to adjust the model-developed schedules to obtain feasible solutions. This model was applied to the feeder system in Jiading district during Expo 2010 Shanghai. The results showed that the temporary feeder system could serve Expo passengers with a relatively high level of service without causing evident degradation in the regular bus service.

The study on key problems in forecasting export containers in a region of China

Forecasting network data traffic is an important part of the function of planning and managing information systems. However, the contents of network data are so stochastic and complex that it is very difficult to establish stable functions to describe the mapping relationship between data flows and associated causal influences. In this paper, a multi-layer feed forward neural networks (NN) model is put forward to identify such relationship and the corresponding learning rule of NN, back-propagation (BP) algorithm, is given. In addition necessary estimation and validation processes are designed to ensure the successful implementation of the model proposed. The paper elucidates the application of NN model around the case of forecasting China west railway Transportation Management Information Systems (TMIS) network traffic. The predictive results obtained demonstrate that the NN model and the solution algorithm are very applicable for information planning on the TMIS network in west China.

Estimating Bus Travel Speed under Information Collection Environment

Public transit, as a major part of urban transportation, plays an irreplaceable role. Government and transit agencies are trying to make transit be more competitive through offering faster service. Travel speed, which directly reflects the service level and key specifications of public transit, is influenced by many factors. The factors affecting bus speed are analyzed from three aspects: links, intersections, and stations. On the basis of these, analytical mode models are established and through parameter transformation, the multiple linear regression model contains reciprocals of travel speed, intensity of passengers, density of stations, relative density of intersections. Time period is validated and tested by using automatic vehicle location data, geographic data, smart card data, and signal timing data obtained from the Shanghai 49 bus line. Test results show that the model can reflect the actual operation. In the end of this paper, quantitative analysis of the impact of each factor on speed is done and some suggestions are proposed for increasing bus travel speed.

Performance Evaluation at Bus Route Level: Considering Carbon Emissions

Considering carbon emissions as a product output of bus systems, the study proposed an approach integrating Mobile-5 and data envelopment analysis (DEA) model to evaluate the performance of buses at a route level. With archived operation records and manual surveyed data from Jiangyin, the approach proved to be efficient in evaluating the technical efficiency of bus routes. It could serve as an significant supplement to the traditional bus performance evaluation methodology.

Bus travel time prediction based on state recognition

Bus running state is always influenced by traffic flow. Traffic flow state evolution directly leads to the variation of bus speed, thereby affecting bus progress. Some investigations implied that there is a certain relationship between the bus speed and other traffic vehicle speed on the road. However, the relationship is different due to individual forms of road cross-sections, the number of lanes, and the traffic flow characteristics. Based on this mechanism and the forecast of road traffic flow data provided by intelligent transportation system (ITS), a state recognition-based model for travel time prediction is proposed, and three running states are introduced in the model. Finally, the bus travel time predicted by the proposed model are assessed with real-world data collected from bus route number 53 in Wuxi city. Results show that the proposed model outperforms the history data-based model, especially when the bus running state falls unstable; the model achieves satisfactory performance.