1. How to submit my research paper? What’s the process of publication of my paper?
The journal receives submitted manuscripts via email only. Please submit your research paper in .doc or .pdf format to the submission email: jtle@ejournal.net.
2.Can I submit an abstract?
The journal publishes full research papers. So only full paper submission should be considered for possible publication...[Read More]

Traffic Accident Time Series Prediction Model Based on Combination of ARIMA and BP and SVM

Xiaorui Shao 1, Lester L Boey 2, and Yifei Luo 2
1. Information collaboration Engineering, Pukyong national university, Busan city, South of Korea
2. Master Degree in Predictive Analytics, Curtin University, Perth, Australia
Abstract—Intelligent transportation is an important part of the smart city. Predict the traffic accidents accurately which contributes to the scientific management of the city and utilizes the public spaces more efficiently. In this paper, construct a combination forecasting model by using the reciprocal variance method based on Autoregressive Integrated Moving Average Model(ARIMA). Using the constructed combination model to predict traffic events related index. Firstly, ARIMA and BP, ARIMA and Support Vector Machine(SVM) models are established, Through comparing, The SVM model is better than a BP neural network model, So, establish the ARIMA (2, 2, 2) and SVM combination model. Also establish the ARIMA (2, 2, 2) and SVM, BP neutral network combination model. The experimental results show that we can improve the accuracy of predicting traffic events related index time series through combination model generally. The ARIMA (2, 2, 2) and SVM, BP neural network combination model, is more accurate than each of single model, also than ARIMA (2, 2, 2) and SVM combination model. We can adopt ARIMA and SVM, BP neural network to predict traffic events index accurately.
 
Index Terms—ARIMA, BP, SVM, combination prediction model

Cite: Xiaorui Shao, Lester L Boey, and Yifei Luo, "Traffic Accident Time Series Prediction Model Based on Combination of ARIMA and BP and SVM," Journal of Traffic and Logistics Engineering,  Doi: 10.18178/jtle.K4002
 
 
Copyright © 2018-2019 Journal of Traffic and Logistics Engineering, All Rights Reserved