透過您的圖書館登入
IP:18.222.158.226
  • 期刊

Research on Short-term Traffic Flow Forecasting Model Based on LSTM

摘要


Reliable short-term traffic flow prediction is one of the important components of intelligent transportation. In order to improve the prediction accuracy of short-term traffic flow and adaptability to different traffic conditions, this paper proposes a short-term traffic flow prediction model based on multi-dimensional influence factors. For the problem of traffic flow prediction in complex transportation systems, this paper uses the 5w model to classify the complex influencing factors in the transportation system, and uses the multi-dimensional related influencing factors of traffic flow together with historical traffic data as the input data of the model. The LSTM model is good at processing "sequence information" and learning long-term dependencies to perform high-precision short-term traffic flow prediction. Experimental results show that compared with the comparison algorithm, the multi-dimensional model has higher prediction accuracy and its average absolute error (MAE) is 11.37, the root mean square error (RMSE) is 13.99, the prediction accuracy rate is more than 90%, and it has good adaptability to different traffic flow states. The predicted value of traffic flow obtained by this model can reflect the trend of actual traffic flow well.

參考文獻


Jinjun Tang, Xinqiang Chen. Traffic-flow-prediction-based-on-combination of support vector machine and data denoising schemes[J]. Physica A, 2019.
LV Y, DUAN Y,KANG W. Traffic flow prediction with big data: a deep learning approach[J]. IEEE Transactions on Intelligent Transportation Systems, 2015, 16(2):865-873
Hochreiter S, Schmidhuber J. Long short-term memory[J]. Neural computation, 1997,9(8):1735-1780
Shen Xiajiong, Zhang Juntao, Han Daojun. Short-term traffic flow prediction model based on gradient boosted regression tree [J]. Computer Science, 2018,06: 222-227.
Wang Xiangxue, Xu Lunhui. Research on Short-term Traffic Flow Forecasting Based on Deep Learning [J]. Transportation System Engineering and Information, 2018,18 (1): 81-88.

延伸閱讀