Efficient deep learning based method for multi‐lane speed forecasting: a case study in Beijing

Lu, Wenqi; Yi, Ziwei; Wan, Lei; Gu, Yuanli; Rui, Yikang

doi:10.1049/iet-its.2020.0410

Cited by 12 publications

(8 citation statements)

References 51 publications

(67 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In this section, a comparative analysis was performed with CWRNN [58], T‐GCN [50], WL+GRU+ARIMA [55], NARX [13], and RBFNN [12] models to verify the robustness and accuracy of the hybrid model presented here. It should be noted that the results were compared with the mentioned models with the available data.…”

Section: Resultsmentioning

confidence: 99%

A hybrid deep and machine learning model for short‐term traffic volume forecasting of adjacent intersections

Mirzahossein

Gholampour

Sajadi

et al. 2022

IET Intelligent Trans Sys

View full text Add to dashboard Cite

Despite complex fluctuations, missing data, and maintenance costs of detectors, traffic volume forecasting at intersections is still a challenge. Moreover, most existing forecasting methods consider an isolated intersection instead of multiple adjacent ones. By accurately forecasting the volume of short-term traffic, a low-cost method can be provided to solve the problems of congestion, delay, and breakdown of detectors in the road transport system. This paper outlines a novel hybrid method based on deep learning to estimate short-term traffic volume at three adjacent intersections. The gated recurrent unit (GRU) and long short-term memory (LSTM) bilayer network with wavelet transform (WL) noise reduction algorithm (WL+GRU-LSTM) are used to analyze raw traffic volume data. The WL+GRU-LSTM is constructed by comparing different machine learning and deep learning methods. A comparative study was used to choose the model's network structure, training technique, and optimizer type. To prove the model's accuracy and resilience, it was compared with the leading short-term traffic forecasting approaches. Experimental results confirm that the WL+GRU-LSTM model can forecast complex traffic volume fluctuations in different approaches of intersections with an accuracy of over 94%. It also shows better results compared to current methods. The proposed model could replace intermediate loop detectors.

show abstract

Section: Resultsmentioning

confidence: 99%

A hybrid deep and machine learning model for short‐term traffic volume forecasting of adjacent intersections

Mirzahossein

Gholampour

Sajadi

et al. 2022

IET Intelligent Trans Sys

View full text Add to dashboard Cite

show abstract

“…With the development of big data, the nonparametric methods for traffic flow prediction are shifting from ANNs to deep learning methods [35][36][37][38][39]. For example, Huang et al [14] proposed a deep architecture with a deep belief network (DBN) at the bottom and a multitask regression layer at the top.…”

Section: Nonparametric Methodsmentioning

confidence: 99%

A Novel Hybrid Model for Predicting Traffic Flow via Improved Ensemble Learning Combined with Deep Belief Networks

Rui

et al. 2021

Mathematical Problems in Engineering

Self Cite

View full text Add to dashboard Cite

The intelligent transportation system (ITS) plays an irreplaceable role in alleviating urban traffic congestion and realizing sustainable urban development. Accurate and efficient short-term traffic state forecasting is a significant issue in ITS. This study proposes a novel hybrid model (ELM-IBF) to predict the traffic state on urban expressways by taking advantage of both deep learning models and ensemble learning framework. First, a developed bagging framework is introduced to combine several deep belief networks (DBNs) that are utilized to capture the complicated temporal characteristic of traffic flow. Then, a novel combination method named improved Bayesian fusion (IBF) is proposed to replace the averaging method in the bagging framework since it can better fuse the prediction results of the component DBNs by assigning the reasonable weights to DBNs at each prediction time interval. Finally, the proposed hybrid model is validated with ground-truth traffic flow data captured by the remote traffic microwave sensors installed on the multiple road sections of 2nd Ring Road in Beijing. The experimental results illustrate that the ELM-IBF method can effectively capture sharp fluctuations in the traffic flow. Compared with several benchmark models (e.g., artificial neural network, long short-term memory neural network, and DBN), the ELM-IBF model reveals better performance in forecasting single-step-ahead traffic volume and speed. Additionally, it is proved that the ELM-IBF model is capable of providing stable and high-quality results in multistep-ahead traffic flow prediction.

show abstract

“…Specifically, it can effectively capture the temporal correlations of different time scales and the spatial correlations among different parking lots by the two parallel ConvLSTM components. An illustration in other field is RF‐CWRNN [27], a method for multi‐lane speed forecasting combining clockwork recurrent neural network and random forest. Although these RNN‐based models have contributed to outstanding improvement in accuracy, a flexible weight assignment of the dependency in time series data remains challenges, especially the long‐term ones.…”

Section: Literature Reviewmentioning

confidence: 99%

A parking occupancy prediction method incorporating time series decomposition and temporal pattern attention mechanism

Ye,

Kuang,

et al. 2023

IET Intelligent Trans Sys

View full text Add to dashboard Cite

Parking occupancy prediction is an important reference for travel decisions and parking management. However, due to various related factors, such as commuting or traffic accidents, parking occupancy has complex change features that are difficult to model accurately, thus making it difficult for parking occupancy to be accurately predicted. Moreover, how to give appropriate weights to these changing features in prediction becomes a new challenge in the era of machine learning. To tackle these challenges, a parking occupancy prediction method called time series decomposition–long and short‐term memory neural network (LSTM)–temporal pattern attention mechanism, which consists of three modules, namely 1) time series decomposition: modelling parking occupancy changes by extracting features such as trend, period, and effect; 2) encoder: extracting temporal correlations of feature sequences with LSTM; 3) temporal pattern attention mechanism: assigning attention to different features, are proposed. The evaluation results of 30 parking lots in Guangzhou city show that the proposed model 1) improves accuracy over the baseline model LSTM by 9.14% on average; 2) performs outstanding in four prediction time intervals and six types of parking lots, proving its validity and generality; 3) demonstrates its rationality and interpretability through ablation experiments and Shapley additive explanation.

show abstract

Efficient deep learning based method for multi‐lane speed forecasting: a case study in Beijing

Cited by 12 publications

References 51 publications

A hybrid deep and machine learning model for short‐term traffic volume forecasting of adjacent intersections

A hybrid deep and machine learning model for short‐term traffic volume forecasting of adjacent intersections

A Novel Hybrid Model for Predicting Traffic Flow via Improved Ensemble Learning Combined with Deep Belief Networks

A parking occupancy prediction method incorporating time series decomposition and temporal pattern attention mechanism

Contact Info

Product

Resources

About