Short-Term Traffic Prediction Using Long Short-Term Memory Neural Networks

Abbas, Zainab; Al-Shishtawy, Ahmad; Girdzijauskas, Šarūnas; Vlassov, Vladimir

doi:10.1109/bigdatacongress.2018.00015

Cited by 33 publications

(16 citation statements)

References 21 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…If the longitude of the GPS point is within the candidate-state longitude range, then flagx is 1; otherwise, it is set to 0, and if the latitude of the GPS point is within the candidate-state latitude range, then flagy is 1. At this point, the calculation of Pos l,a is as in (6).…”

Section: Algorithm 1 the Pseudocode Of The Improved Pagerankmentioning

confidence: 99%

“…In most traffic congestion predictions, only time series data are considered, such as LSTM and GRU. Z. Abbas et al proposed and compared three models for short-term road traffic density prediction based on long short-term memory (LSTM) neural networks [6]. R. Fu et al used LSTM and gated recurrent unit (GRU) neural network methods to predict short-term traffic flow [7].…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Traffic Congestion Forecasting in Shanghai Based on Multi-Period Hotspot Clustering

Zhang

Chen

2020

IEEE Access

View full text Add to dashboard Cite

Traffic congestion has become increasingly prominent. Effective prediction of road congestion will provide a great reference for urban road planning and residents' travel. Taxi trajectory data objectively reflect the travel routes of the residents of a city. With good temporal and spatial characteristics and high timeliness, these data have become important in the study of urban spatio-temporal characteristics. In this paper, the PageRank-K clustering algorithm is used to analyse hotspots and cluster hotspots of a region. The shortest-distance matching algorithm based on the transition probability is used for map matching; then, the average speed of the road sections can be calculated, and the direction of taxis can be determined. The Dual_XGBoost model is used for traffic congestion prediction. Finally, we compared our model with similar models. We take roads in Shanghai as the test object. The results show that our method is faster in training, can predict congestion at any time and is more sensitive to long-term features than the other models.

show abstract

Section: Algorithm 1 the Pseudocode Of The Improved Pagerankmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Traffic Congestion Forecasting in Shanghai Based on Multi-Period Hotspot Clustering

Zhang

Chen

2020

IEEE Access

View full text Add to dashboard Cite

show abstract

“…With the rapid development of data storage and data processing techniques, the real-time traffic can be obtained by various sensors such as infrastructure sensors, mobile sensors, loop sensors, microwave sensors and traffic cameras and so on [4]. As a ubiquitous kind of mobile sensor, the floating cars can provide speed, time and position information to probe a city's rhythm and pulse [5], [6].…”

Section: Introductionmentioning

confidence: 99%

A Multiscale-Grid-Based Stacked Bidirectional GRU Neural Network Model for Predicting Traffic Speeds of Urban Expressways

et al. 2021

View full text Add to dashboard Cite

In recent decades, studies on short-term traffic speed forecasting of the large-scale road are a new challenge for researchers and engineers. Especially based on deep learning neural networks, studies on short-term traffic forecasting have achieved mush-room growth. This study proposes a stacked Bidirectional Gated Recurrent Unit neural network model to predict the traffic speed of the expressway over different estimation time intervals in an effective manner. By building a multiscale-grid model, it can take less time to derive a set of key traffic parameters of different scales to predict traffic speed of the various-scale road. The speed prediction of small-scale sections can cover more detailed road spatial features preparing for Vehicle Navigation System, and the speed prediction of large-scale sections can establish the real-time traffic control strategies. In order to validate the effectiveness of the proposed model, we use the floating car data, with an updating frequency of 1 minute from the urban freeway of Beijing, for model training and testing. The experimental results show that the stacked BiGRU network with the multiscale-grid model enables to capture the spatial-temporal characteristics of traffic speed efficiently. Furthermore, the BiGRU with two layers (BiGRU-2L) outperforms benchmark models in the prediction of the traffic speed, which presents a significant advantage in reducing the overfitting problem, decreasing the excessive time-consuming and improving the effective use of limited computation resources.

show abstract

“…Although modelling and prediction of the aggregated IoT traffic from several applications have been studied [11] [12] in the context of building smart cities and smart homes recently, these work are all based on mathematical models. Several data-driven models, such as deep learning [13] [14] have been proposed in the context of smart transportation. However, the focus has been on predicting vehicular traffic congestion, which cannot be used straightforwardly for predicting IoT data traffic due to the different features of the time sequences of IoT data and vehicular traffic.…”

Section: Introductionmentioning

confidence: 99%

Predicting Internet of Things Data Traffic Through LSTM and Autoregressive Spectrum Analysis

Jin

Wang

et al. 2020

NOMS 2020 - 2020 IEEE/IFIP Network Operations and Management Symposium

View full text Add to dashboard Cite

The rapid increase of Internet of Things (IoT) applications and services has led to massive amounts of heterogeneous data. Hence, we need to rethink how IoT data influences the network. In this paper, we study the characteristics of IoT data traffic in the context of smart cities. Aiming at analyzing the influence of IoT data traffic on the access and core network, we generate various IoT data traffic according to the characteristics of different IoT applications. Based on the analysis of the inherent features of the aggregated IoT data traffic, we propose a Long Short-Term Memory (LSTM) model combined with autoregressive spectrum analysis to predict the IoT data traffic. In this model, the autoregressive spectrum analysis is used to estimate the minimum length of the historical data needed for predicting the traffic in the future, which alleviates LSTM's performance deterioration with the increase of sequence length. A sliding window enables predicting the longterm tendency of IoT data traffic while keeping the inherent features of the data traffic. The evaluation results show that the proposed model converges quickly and can predict the variations of IoT traffic more accurately than other methods and the general LSTM model.

show abstract

Short-Term Traffic Prediction Using Long Short-Term Memory Neural Networks

Cited by 33 publications

References 21 publications

Traffic Congestion Forecasting in Shanghai Based on Multi-Period Hotspot Clustering

Traffic Congestion Forecasting in Shanghai Based on Multi-Period Hotspot Clustering

A Multiscale-Grid-Based Stacked Bidirectional GRU Neural Network Model for Predicting Traffic Speeds of Urban Expressways

Predicting Internet of Things Data Traffic Through LSTM and Autoregressive Spectrum Analysis

Contact Info

Product

Resources

About