Journal of South China University of Technology (Natural Science Edition) ›› 2018, Vol. 46 ›› Issue (1): 50-57.doi: 10.3969/j.issn.1000-565X.2018.01.007

• Traffic & Transportation Engineering • Previous Articles     Next Articles

Short-Term Forecasting of Subway Traffic Based on K-Nearest Neighbour Pattern Matching

LIN Peiqun CHEN Litian LEI Yongwei   

  1. School of Civil Engineering and Transportation，South China University of Technology，Guangzhou 510640，Guangdong，China
  • Received:2017-04-10 Revised:2017-07-12 Online:2018-01-25 Published:2017-12-01
  • Contact: 林培群(1980-)，男，博士，教授，主要从事车联网、智能交通等研究． E-mail:pqlin@scut.edu.cn
  • About author:林培群(1980-)，男，博士，教授，主要从事车联网、智能交通等研究．
  • Supported by:
    Supported by the National Natural Science Foundation of China(61572233) and the Science and Technology Planning Project of Guangdong Province(2016A050502006，2016A030313786)

PDF

155

Abstract: In order to forecast the subway traffic accurately and better the vehicle scheduling and site management，a short-term forecasting of subway traffic based on K-nearest neighbour pattern matching is proposed． By analyzing the subway traffic data，it is found that the day passenger flow development mode of subway has a certain law．Thus，an adaptive K acquisition algorithm based on the calculation of error rate is proposed，it can improve the uni-versality of the prediction algorithm by automatically obtaining the appropriate K． Finally，Guangzhou South Rail-way Station is taken as an example for the case study． The experimental results show that the method proposed is applicable to the subway passenger flow forecast of two different modes of traffic-holidays and non-holidays，its ave-rage prediction accuracy is about 90%． It can be seen that this method has a good application value．

Key words: subway traffic, short-term forecasting, K-nearest neighbor algorithm, day passenger flow development mode, pattern matching

CLC Number: