Review of spatio-temporal models for short-term traffic forecasting

Chang, Gang; Shouhui, Wang; Xiao, Xiaobo

doi:10.1109/icite.2016.7581298

Cited by 7 publications

(6 citation statements)

References 23 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Some statistical theories, including the history average ARMA model, Kalman filtering model, linear regression, and non-parametric regression [43], are the first ones that were introduced into traffic flow forecasting. They are relatively simple due to the assumption of the same patterns and characteristics of the future conditions as that of the historical flow data [44].…”

Section: A Problems Defined Without Spatial Dependencymentioning

confidence: 99%

Spatio-Temporal Feature Engineering for Deep Learning Models in Traffic Flow Forecasting

Mu,

Aljeri,

Boukerche

2024

IEEE Access

View full text Add to dashboard Cite

In the past decade, modern transportation systems have employed various cutting-edge deeplearning approaches for traffic flow prediction. Due to its significant temporal correlations, researchers have mainly focused on extracting temporal features from traffic flow data. As a result, time-series models based on deep learning methods like Gated Recurrent Unit (GRU), Long-Term Short-Term Memory (LSTM), and Temporal Convolutional Networks (TCN) have been introduced as solutions for traffic flow prediction. However, the spatial features of the road network have also shown an impact on the prediction, leading to the application of deep learning methods on spatial dependency modeling for this problem. This paper defines the traffic flow forecasting problem, considering both time-series information with and without spatial information and the corresponding techniques of current solutions to depict spatio-temporal traffic dependency. We propose a new taxonomy of spatial and temporal dependencies in the fine-grained subcategory and the methods depicting them based on neural network-based models. Furthermore, we highlight the architecture of spatial and temporal ensembles in Spatio-temporal modelling based on the finegrained categories obtained. We point out several open issues and future directions of traffic flow forecasting, such as graph reconstruction, temporal and spatial information data balance, and multi-model spatial and temporal correlations.

show abstract

Section: A Problems Defined Without Spatial Dependencymentioning

confidence: 99%

Spatio-Temporal Feature Engineering for Deep Learning Models in Traffic Flow Forecasting

Mu,

Aljeri,

Boukerche

2024

IEEE Access

View full text Add to dashboard Cite

show abstract

“…The road network illustrates the connection between several intersections (nodes) and road segments (edges), with the arrangement of direction, as in the directed graph [17][18][19][20]. To reach a destination in the road network, vehicles need to pass several nodes whether directly connected or not by its edges.…”

Section: Literature Review 21 Road Networkmentioning

confidence: 99%

Personalized Route Recommendation Using F-AHP-Express

et al. 2022

View full text Add to dashboard Cite

The route recommendation system helps the driver find the best route between origin and destination. A recommendation system often suggests its decision without considering some criteria. This paper proposes a multicriteria decision-making method, namely Fuzzy—Analytic Hierarchy Process—Express (F-AHP-Express) for recommending a personal travel route from several alternative routes. It is calculated based on the driving preferences of a driver and road conditions for each road segment. We compare the F-AHP-Express to others; Fuzzy—Analytic Hierarchy Process (F-AHP) and Fuzzy—Analytic Hierarchy Process—Technique for Others Preference by Similarity to Ideal Solution (F-AHP-TOPSIS), for its recommendation results, time processing, agility, and complexity. Our experiments show that F-AHP-Express could deliver similar recommendation results compared to other methods, and it is additionally the fastest method. F-AHP-Express is 45% and 23% faster than F-AHP and F-AHP-TOPSIS, respectively. F-AHP-Express not only has the fastest time processing among the others but also has the least judgments in agility testing. It needs 37.5% and 16.67% fewer judgments from F-AHP and F-AHP-TOPSIS, respectively. Moreover, AHP-Express has a complexity of O(n), meanwhile, the others have O(n2) for their complexity. Thus, the results show that F-AHP-Express is the best method for recommending a personal route.

show abstract

“…Nonparametric models mainly include the most traditional statistical machine learning methods and the most popular artificial intelligence algorithms. Support vector machine (SVM) [21,22], K-nearest neighbor (KNN) [23,24], and artificial neural network (ANN) are the most widely used ones [25].…”

Section: Related Workmentioning

confidence: 99%

Short-Term Traffic Speed Prediction Method for Urban Road Sections Based on Wavelet Transform and Gated Recurrent Unit

Luo

et al. 2020

Mathematical Problems in Engineering

View full text Add to dashboard Cite

As a core component of the urban intelligent transportation system, traffic prediction is significant for urban traffic control and guidance. However, it is challenging to achieve accurate traffic prediction due to the complex spatiotemporal correlation of traffic data. A road section speed prediction model based on wavelet transform and neural network is, therefore, proposed in this article to improve traffic prediction methods. The wavelet transform is used to decompose the original traffic speed data, and then the coefficients obtained after the decomposition are used to reconstruct the high-frequency random sequences and the low-frequency trend sequence. Secondly, a GRU neural network is constructed to learn the trend of low-frequency sequence. The spatiotemporal correlation between input data is extracted by adjusting the input of the model. Meanwhile, an ARMA model is used to fit unstable random fluctuations of high-frequency sequences. Last of all, the prediction results of the two models are added together to obtain the final prediction result. The proposed prediction model is validated by using road section speed data based on the floating car data collected in Ningbo. The results show that the proposed model has high accuracy and robustness.

show abstract

Review of spatio-temporal models for short-term traffic forecasting

Cited by 7 publications

References 23 publications

Spatio-Temporal Feature Engineering for Deep Learning Models in Traffic Flow Forecasting

Spatio-Temporal Feature Engineering for Deep Learning Models in Traffic Flow Forecasting

Personalized Route Recommendation Using F-AHP-Express

Short-Term Traffic Speed Prediction Method for Urban Road Sections Based on Wavelet Transform and Gated Recurrent Unit

Contact Info

Product

Resources

About