Open AccessResearch on Time-of-station Prediction of Tram Based on Support Vector Machine
Author(s) -
Kang Yang,
Chongbin Zhao
Publication year - 2019
Publication title -
journal of physics. conference series
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.21
H-Index - 85
eISSN - 1742-6596
pISSN - 1742-6588
DOI - 10.1088/1742-6596/1345/6/062049
Subject(s) - support vector machine , global positioning system , arrival time , computer science , time of arrival , line (geometry) , real time computing , data mining , artificial intelligence , engineering , transport engineering , telecommunications , wireless , mathematics , geometry
At present, the traffic of the T1 line of the trams in Hanyang District of Wuhan City is based on the GPS positioning. The arrival time prediction based on GPS positioning will be biased due to the sudden situation. Based on the GPS data of the tram, this paper proposes a tram-to-station time prediction model based on SVM (Support Vector Machine). The SVM support vector machine model after a large amount of historical data training is used as the time reference and the arrival time. Make dynamic adjustments. Taking the T1 line of the vehicle-based tram in Wuhan Hanyang District as an example, the prediction result of the arrival time prediction model is compared with the prediction result obtained by single GPS positioning. The results show that the model is applied to the prediction of the arrival time of the tram. Good applicability and higher prediction accuracy.