A platform for research: civil engineering, architecture and urbanism
A platform for research: civil engineering, architecture and urbanism
Method Research on Traffic Volume Forecasting Based on Bio-LSTM
https://orcid.org/http://orcid.org/0000-0001-9196-9850
https://orcid.org/http://orcid.org/0000-0003-4375-9060
https://orcid.org/http://orcid.org/0000-0001-7129-3451
https://orcid.org/http://orcid.org/0000-0001-9760-0771
https://orcid.org/http://orcid.org/0000-0001-6129-9606
Nowadays, urban traffic management plays an important role to improve traffic system efficiency and ensure safety, and decision-making about that is based on the adequate understanding for traffic condition. Traffic volume is the representation of current traffic operation, so it is of great significance to master traffic volume in advance and accurately. The developments of computer and Deep-Learning provided support for traffic forecasting. Firstly, the principle of Long Short-Term Memory neural network (LSTM) to overcome “gradients vanishment/explosion” is analyzed. And then Bio-LSTM is used to forecast the traffic volume of a certain road in the next 24 h. Finally, the Wavelet Neural Network is used to predict the same data of this road. The two series of prediction results are compared, it is showed that Bio-LSTM for prediction has the advantages of simple operation, convenient adjustment of key parameters and higher prediction accuracy.
Method Research on Traffic Volume Forecasting Based on Bio-LSTM
https://orcid.org/http://orcid.org/0000-0001-9196-9850
https://orcid.org/http://orcid.org/0000-0003-4375-9060
https://orcid.org/http://orcid.org/0000-0001-7129-3451
https://orcid.org/http://orcid.org/0000-0001-9760-0771
https://orcid.org/http://orcid.org/0000-0001-6129-9606
Nowadays, urban traffic management plays an important role to improve traffic system efficiency and ensure safety, and decision-making about that is based on the adequate understanding for traffic condition. Traffic volume is the representation of current traffic operation, so it is of great significance to master traffic volume in advance and accurately. The developments of computer and Deep-Learning provided support for traffic forecasting. Firstly, the principle of Long Short-Term Memory neural network (LSTM) to overcome “gradients vanishment/explosion” is analyzed. And then Bio-LSTM is used to forecast the traffic volume of a certain road in the next 24 h. Finally, the Wavelet Neural Network is used to predict the same data of this road. The two series of prediction results are compared, it is showed that Bio-LSTM for prediction has the advantages of simple operation, convenient adjustment of key parameters and higher prediction accuracy.
Method Research on Traffic Volume Forecasting Based on Bio-LSTM
https://orcid.org/http://orcid.org/0000-0001-9196-9850
https://orcid.org/http://orcid.org/0000-0003-4375-9060
https://orcid.org/http://orcid.org/0000-0001-7129-3451
https://orcid.org/http://orcid.org/0000-0001-9760-0771
https://orcid.org/http://orcid.org/0000-0001-6129-9606
Nowadays, urban traffic management plays an important role to improve traffic system efficiency and ensure safety, and decision-making about that is based on the adequate understanding for traffic condition. Traffic volume is the representation of current traffic operation, so it is of great significance to master traffic volume in advance and accurately. The developments of computer and Deep-Learning provided support for traffic forecasting. Firstly, the principle of Long Short-Term Memory neural network (LSTM) to overcome “gradients vanishment/explosion” is analyzed. And then Bio-LSTM is used to forecast the traffic volume of a certain road in the next 24 h. Finally, the Wavelet Neural Network is used to predict the same data of this road. The two series of prediction results are compared, it is showed that Bio-LSTM for prediction has the advantages of simple operation, convenient adjustment of key parameters and higher prediction accuracy.
Method Research on Traffic Volume Forecasting Based on Bio-LSTM
Lecture Notes in Civil Engineering
Guo, Wei (editor) / Qian, Kai (editor) / Li, Xiao (author) / Li, Chaoyang (author) / Wang, Tao (author) / Zhang, Yi (author) / Xi, Changqin (author)
International Conference on Green Building, Civil Engineering and Smart City ; 2022 ; Guilin, China
2022-09-08
12 pages
Article/Chapter (Book)
Electronic Resource
English
| DOAJ | 2018
Gaussian Processes for Short-Term Traffic Volume Forecasting
| British Library Online Contents | 2010