Forecast of Bus Passenger Traffic Based on Exponential Smoothing and Trend Moving Average Method

Abstract:

Two prediction models, exponential smoothing and trend moving average method, are selected for bus passenger traffic prediction. An analysis is made from aspects of basic idea, basic theory and so on. With the bus passenger traffic of Anqing, underlying index is used to compare the prediction accuracy of two models. The results demonstrate that trend moving average method has better effect on bus passenger traffic prediction. Therefore, the trend moving average method is rational and effective on the bus passenger traffic prediction.

• Periodical: Applied Mechanics and Materials (Volumes 433-435)
• Pages: 1374-1378
• DOI: https://doi.org/10.4028/www.scientific.net/AMM.433-435.1374
• Online since: October 2013
• Authors: Sheng Yang Ge, Chang Jiang Zheng, Mao Mao Hou
• Keywords: Bus Passenger Traffic, Exponential Smoothing, Trend Moving Average Method, Underlying Index

References

[1] Srinivarsan D, etc. Demand forecasting using fuzzy neural computation with special emphasis on week end and public holiday forecasting. IEEE Transactions on Power Systems, 1995, 10(4).

DOI: 10.1109/59.476055

[2] Kim K H, Park J K, Hwang K J, et al. Implementation of hybrid short-term forecasting system using artificial neural networks and fuzzy expert systems. IEEE Transactions on Power Systems, 1995, 10(3): 1534-1539.

DOI: 10.1109/59.466492

[3] Fuzzy logic toolbox user's guide version 2 for use with Matlab 5. 2, The Mathworks, Inc. (1998).

[4] Koutsopoulos, H N, Odoni, A, and Wilson, N H M. (1985). Determination of head-ways as function of time varying characteristics on a transit network., Computer sched-uling of public transport 2, J M Rousseau, ed, North-Holl and, Amsterdam, 391-414.

[5] Ceder, A and Tal. Timetable synchronization for buses., Computer-aided scheduling of public transport, N H M. Wilson, ed, Springer, New York, (1998).