Analysis of Passenger Flow Prediction of Transit Buses Along a Route Based on Time Series

  • Reshma Gummadi
  • Sreenivasa Reddy Edara
Conference paper
Part of the Advances in Intelligent Systems and Computing book series (AISC, volume 701)


India’s transport sector has a prominent role in transportation of passengers. Andhra Pradesh State Road Transport Corporation (APSRTC) is a major transportation in the state. State has many routes, and there are so many towns on a particular route. Most of the population mainly depends on transportation system; hence, it is necessary to predict the occupancy percentage of the transit buses in a given particular period for the convenience of passengers. There is a need of advancement in transportation services for effective maintainability. Identifying passenger occupancies on a different number of buses is found to be a major problem. A promising approach is the technique of forecasting the data from previous history and the better predictive mining technology must be applied to analyze the passenger to predict the passenger flow. In this work, ARIMA-based method is analyzed for studying the APSRTC transit bus occupancy rate.


Transit buses Passenger flow ARIMA 


  1. 1.
    Al-Deek, H., D’Angelo, M., Wang, M.: Travel time prediction with non-linear time series. In: Proceedings of the ASCE 1998 5th International Conference on Applications of Advanced Technologies in Transportation, Newport Beach, CA, pp. 317–324 (1998)Google Scholar
  2. 2.
    Chien, S.I.J., Kuchipudi, C.M.: Dynamic travel time prediction with real-time and historic data. J. Transport. Eng. 129(6), 608–616 (2003)Google Scholar
  3. 3.
    Bin, Y., Zhongzhen, Y., Baozhen, Y.: Bus arrival time prediction using support vector machines. J. Intell. Transport. Syst. 10(4), 151–158 (2006)Google Scholar
  4. 4.
    Chen, S. et al.: The Time Series Forecasting: From the Aspect of Network. arXiv:1403.1713 (2014)
  5. 5.
    Vagropoulos, S.I., Chouliaras, G.I., Kardakos, E.G., Simoglou, C.K., Bakirtzis, A.G.: Comparison of SARIMAX, SARIMA, Modified SARIMA and ANN-based Models for short-term PV generation forecasting. In: IEEE International Energy Conference, Leuven pp. 1–6 (2016)Google Scholar
  6. 6.
    Takaomi, H., Takashi, K., Masanao, O., Shingo, M.: Time series prediction using DBN and ARIMA. In: International Conference on Computer Application Technologies, IEEE (2015)Google Scholar

Copyright information

© Springer Nature Singapore Pte Ltd. 2018

Authors and Affiliations

  1. 1.Acharya Nagarjuna UniversityGunturIndia
  2. 2.Department of Computer Science & EngineeringAcharya Nagarjuna UniversityGunturIndia

Personalised recommendations