2020
DOI: 10.1109/access.2020.3038788
|View full text |Cite
|
Sign up to set email alerts
|

Truck Traffic Flow Prediction Based on LSTM and GRU Methods With Sampled GPS Data

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
2
1
1
1

Citation Types

0
24
0

Year Published

2021
2021
2024
2024

Publication Types

Select...
5
3
1

Relationship

0
9

Authors

Journals

citations
Cited by 60 publications
(24 citation statements)
references
References 36 publications
0
24
0
Order By: Relevance
“…First, the length of hidden vector is set to 2, 4, 8, 16, 32, 64, 128 or 256 when other parameters are set at default values. Second, the number of epoch is set to 5,10,15,20,25,30,45 and 50 when the batch_size is set to default and the length of hidden vector is fixed with best values. Third, the batch_size is set to 2, 4, 8, 16, 32, 64, 128, or 256 when other parameters are fixed with best values.…”
Section: B Prediction Resultsmentioning
confidence: 99%
See 1 more Smart Citation
“…First, the length of hidden vector is set to 2, 4, 8, 16, 32, 64, 128 or 256 when other parameters are set at default values. Second, the number of epoch is set to 5,10,15,20,25,30,45 and 50 when the batch_size is set to default and the length of hidden vector is fixed with best values. Third, the batch_size is set to 2, 4, 8, 16, 32, 64, 128, or 256 when other parameters are fixed with best values.…”
Section: B Prediction Resultsmentioning
confidence: 99%
“…Tian [29] applied the LSTM to predict the traffic flow with 15-min, 30-min, 45-min and 60-min intervals, and the prediction results showed that the LSTM demonstrated more excellent generalization capability than RW, SVM, SAE and single hidden layer Feed Forward Neural Network (FFNN). Wang [30] made a traffic flow prediction by using the sampled GPS data and the results showed that the LSTM and Gated Recursive Unit (GRU) performed better than ARIMA and SVR. The LSTM model has more accurate prediction results than GRU.…”
Section: Introductionmentioning
confidence: 99%
“…The GRU model has better performance for countries like India, Russia, Mexico, and the United Kingdom. Wang et al [ 6 ] Proposed a new approach for truck traffic flow prediction, paper authors noticed that LSTM and GRU have better performance compared to existing approach based on support vector machine (SVM) or Autoregressive integrated moving average (ARIMA). Regarding financial time series modeling, the number of papers, including LSTM and GRU is very important.…”
Section: Related Workmentioning
confidence: 99%
“…The result showed that the LSTM prediction model achieved the highest accuracy and generalized best among these models. Wang et al [45]used the LSTM and the gated recurrent unit (GRU) models on trucks' GPS data. As a result, the average prediction accuracy throughout both peak and offpeak periods, LSTM is better than GRU with improved accuracy of 4.1%.…”
Section: Literature Reviewmentioning
confidence: 99%