2018
DOI: 10.1109/access.2018.2845863
|View full text |Cite
|
Sign up to set email alerts
|

Improved Deep Hybrid Networks for Urban Traffic Flow Prediction Using Trajectory Data

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
1
1
1
1

Citation Types

2
55
0
1

Year Published

2019
2019
2024
2024

Publication Types

Select...
9
1

Relationship

0
10

Authors

Journals

citations
Cited by 132 publications
(58 citation statements)
references
References 39 publications
2
55
0
1
Order By: Relevance
“…As artificial intelligence technology has developed the adoption of DNN has significantly increased. LSTM is a DNN algorithm, which can be effective for any type of time series data [34]. LSTM is an artificial RNN architecture applied in the field of deep learning.…”
Section: Long Short-term Memory Algorithmmentioning
confidence: 99%
“…As artificial intelligence technology has developed the adoption of DNN has significantly increased. LSTM is a DNN algorithm, which can be effective for any type of time series data [34]. LSTM is an artificial RNN architecture applied in the field of deep learning.…”
Section: Long Short-term Memory Algorithmmentioning
confidence: 99%
“…The inferiority comes from the fact that, the SVR method does not have a sophisticated scheme to learn the underlying spatial dependency, or the long-term temporal dependency. In contrast, CNN has a convolution layer, and LSTM or BDLSTM has a memory and gate to handle the two situations [42,43], respectively. On the other hand, the BDLSTM-CNN based hybrid solution always achieves the lowest error rates of 20% to 22.5%, which implies a forecasting accuracy of 77.5% to 80%.…”
Section: Comparison With the Conventional Methodsmentioning
confidence: 99%
“…They can learn temporal relationships and dependencies from time series data and have been applied to short-term traffic prediction [5,[39][40][41]. Deep learning models combining CNNs and LSTMs are widely used in the literature regarding traffic flow prediction and can capture both the spatial correlations and temporal dependencies of traffic flow variables on road networks [5,36,[42][43][44].…”
Section: Prediction Modelmentioning
confidence: 99%