Highway Speed Prediction Using Gated Recurrent Unit Neural Networks

Jeong, Myeong‐Hun; Lee, Tae Young; Jeon, Seung-Bae; Youm, Minkyo

doi:10.3390/app11073059

Cited by 31 publications

(13 citation statements)

References 26 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Elman NN, TDNN and NARX NN) claiming its superiority in performance and stability. Highway traffic predictions are made in [24] using GRU applying digital tachograph (DTG) data recorded for one month and comprising 300 million records. The research demonstrates GRU superiority over ARIMA and LSTM in prediction error, scalability and computational cost due to its simple model with fewer parameters.…”

Section: Related Workmentioning

confidence: 99%

Traffic speed prediction using GARCH‐GRU hybrid model

Ali,

Yusof,

Wilson

et al. 2023

IET Intelligent Trans Sys

View full text Add to dashboard Cite

Traffic speed prediction is an integral part of an intelligent transportation system (ITS) because an advanced knowledge of traffic speed can help taking proactive preventive steps to avoid impending problems and it can also help in trip planning. Traffic speed data comprises a time series that may be modelled using any statistical or machine learning technique. In most of the cases, however, the performance of such models is bottlenecked due to heteroskedasticity usually present in such datasets. ARCH/GARCH family of models are generally used to model variance in such data. This paper presents a novel technique, termed as GARCH‐GRU, based on additive decomposition that splits data into random (residual) and deterministic parts. Random part is normalized using rolling standard deviation. GARCH (1, 1) is used to predict conditional variance of the residual and the predicted variance is then used in the basic model equation along with normalized residual that mimic white noise as required by the model. The data other than residual is modelled using a GRU model. The approach is applied to two datasets corresponding to a downtown road and a motorway. For comparison, the same datasets are exposed to three classical techniques; seasonal ARIMA, CNN and GRU techniques. The results demonstrate that the GARCH‐GRU technique outperforms others for random data of downtown road but fails to handle dynamic variations present in the motorway data.

show abstract

Section: Related Workmentioning

confidence: 99%

Traffic speed prediction using GARCH‐GRU hybrid model

Ali,

Yusof,

Wilson

et al. 2023

IET Intelligent Trans Sys

View full text Add to dashboard Cite

show abstract

“…Gated recurrent unit (GRU) network, as a variant of the classical recurrent neural network LSTM, has a simpler structure with fewer parameters and faster convergence, which can speed up the iterative process of the model ( 13 ). At present, several scholars use LSTM or other neural network models to study the driving intention and trajectory of HDVs and determine the optimal combination of hyperparameters through experience or experiments ( 14 – 16 ). However, when the input variables are changed, the given combination of hyperparameters may lead to the learning effect and prediction accuracy of the model being no longer optimal.…”

Section: Problem Descriptionmentioning

confidence: 99%

Bayesian Global Optimization Gated Recurrent Unit Model for Human-Driven Vehicle Lane-Change Trajectory Prediction Considering Hyperparameter Optimization

Chen

Zhao

et al. 2023

Transportation Research Record: Journal of the Transportation R

View full text Add to dashboard Cite

To address the low accuracy and inefficiency of current lane-change trajectory prediction methods for human-driven vehicles, this study develops a neural network lane-change trajectory prediction model with hyperparametric optimization capability using Bayesian optimization and gated recurrent units to consider the effect of lane-change intention on vehicle lane-change behavior and to predict it. The proposed model was instantiated using trajectory data of 8,721 vehicles. The results show that the overall recognition accuracy of intention recognition under the optimal input is 93.54%, and the recognition accuracy of keeping straight, left lane-change and right lane-change is 95.59%, 91.72%, and 93.30%, respectively. The root mean square errors of the predicted and actual trajectories to the left and to the right under the optimal input are 0.2582 and 0.2957, respectively. This paper demonstrates that, for the intention recognition module, the low-dimensional input enables the model to obtain high prediction accuracy, while for the trajectory prediction module, the high-latitude input enables the model to obtain a low prediction error. The developed trajectory prediction model can be used to assist in driving decision-making, path planning, and so forth.

show abstract

“…The network of many styles and shapes is developed by changing its structure. The current RNNs are a long-term dependency problem [19]. The weight converges at zero while it deviates at infinity as the time lag increases.…”

Section: Design Of Gru-dosd Techniquementioning

confidence: 99%

Intelligent DoS Attack Detection with Congestion Control Technique for VANETs

Gopi¹,

Mathapati²,

Prasad³

et al. 2022

Computers, Materials &Amp; Continua

View full text Add to dashboard Cite

Vehicular Ad hoc Network (VANET) has become an integral part of Intelligent Transportation Systems (ITS) in today's life. VANET is a network that can be heavily scaled up with a number of vehicles and road side units that keep fluctuating in real world. VANET is susceptible to security issues, particularly DoS attacks, owing to maximum unpredictability in location. So, effective identification and the classification of attacks have become the major requirements for secure data transmission in VANET. At the same time, congestion control is also one of the key research problems in VANET which aims at minimizing the time expended on roads and calculating travel time as well as waiting time at intersections, for a traveler. With this motivation, the current research paper presents an intelligent DoS attack detection with Congestion Control (IDoS-CC) technique for VANET. The presented IDoS-CC technique involves two-stage processes namely, Teaching and Learning Based Optimization (TLBO)-based Congestion Control (TLBO-CC) and Gated Recurrent Unit (GRU)-based DoS detection (GRU-DoSD). The goal of IDoS-CC technique is to reduce the level of congestion and detect the attacks that exist in the network. TLBO algorithm is also involved in IDoS-CC technique for optimization of the routes taken by vehicles via traffic signals and to minimize the congestion on a particular route instantaneously so as to assure minimal fuel utilization. TLBO is applied to avoid congestion on roadways. Besides, GRU-DoSD model is employed as a classification model to effectively discriminate the compromised and genuine vehicles in the network. The outcomes from a series of simulation analyses highlight the supremacy of 142 CMC, 2022, vol.72, no.1 the proposed IDoS-CC technique as it reduced the congestion and successfully identified the DoS attacks in network.

show abstract

Highway Speed Prediction Using Gated Recurrent Unit Neural Networks

Cited by 31 publications

References 26 publications

Traffic speed prediction using GARCH‐GRU hybrid model

Traffic speed prediction using GARCH‐GRU hybrid model

Bayesian Global Optimization Gated Recurrent Unit Model for Human-Driven Vehicle Lane-Change Trajectory Prediction Considering Hyperparameter Optimization

Intelligent DoS Attack Detection with Congestion Control Technique for VANETs

Contact Info

Product

Resources

About