Short-Term Traffic Flow Forecasting via Multi-Regime Modeling and Ensemble Learning

Lu, Zhenbo; Xia, Jingxin; Wang, Man; Nie, Qinghui; Ou, Jishun

doi:10.3390/app10010356

Cited by 18 publications

(9 citation statements)

References 47 publications

(56 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The traditional ensemble method is to ensemble several different models, then use the same input to predict the model, and then use some common method to determine the final grading result of the ensemble model [18,19]. In this paper, ensemble learning and deep learning are combined, and the final grading result can be produced by combining the gradings of multiple neural networks.…”

Section: Ensemble Learningmentioning

confidence: 99%

An Atmospheric Visibility Grading Method Based on Ensemble Learning and Stochastic Weight Average

Zou

Cao

et al. 2021

Atmosphere

View full text Add to dashboard Cite

In order to adequately characterize the visual characteristics of atmospheric visibility and overcome the disadvantages of the traditional atmospheric visibility measurement method with significant dependence on preset reference objects, high cost, and complicated steps, this paper proposed an ensemble learning method for atmospheric visibility grading based on deep neural network and stochastic weight averaging. An experiment was conducted using the scene of an expressway, and three visibility levels were set, i.e., Level 1, Level 2, and Level 3. Firstly, the EfficientNet was transferred to extract the abstract features of the images. Then, training and grading were performed on the feature sets through the SoftMax regression model. Subsequently, the feature sets were ensembled using the method of stochastic weight averaging to obtain the atmospheric visibility grading model. The obtained datasets were input into the grading model and tested. The grading model classified the results into three categories, with the grading accuracy being 95.00%, 89.45%, and 90.91%, respectively, and the average accuracy of 91.79%. The results obtained by the proposed method were compared with those obtained by the existing methods, and the proposed method showed better performance than those of other methods. This method can be used to classify the atmospheric visibility of traffic and reduce the incidence of traffic accidents caused by atmospheric visibility.

show abstract

Section: Ensemble Learningmentioning

confidence: 99%

An Atmospheric Visibility Grading Method Based on Ensemble Learning and Stochastic Weight Average

Zou

Cao

et al. 2021

Atmosphere

View full text Add to dashboard Cite

show abstract

“…At the same time, many flow prediction models have been introduced in the literature with most of them using regression methodologies such as k-NN (Chang et al, 2012) SVR (Lu et al, 2020) and MLP-ANN (Ding, 2019). However, there are a few disadvantages in using these methods, since the inclusion of non-numeric data obliges for model alteration.…”

Section: State Of the Artmentioning

confidence: 99%

Exploring an Ensemble of Textual Machine Learning Methodologies for Traffic Event Detection and Classification

Kokkinos

Nathanail

2020

Transport and Telecommunication Journal

View full text Add to dashboard Cite

Late research has established the critical environmental, health and social impacts of traffic in highly populated urban regions. Apart from traffic monitoring, textual analysis of geo-located social media responses can provide an intelligent means in detecting and classifying traffic related events. This paper deals with the content analysis of Twitter textual data using an ensemble of supervised and unsupervised Machine Learning methods in order to cluster and properly classify traffic related events. Voluminous textual data was gathered using innovative Twitter APIs and managed by Big Data cloud methodologies via an Apache Spark system. Events were detected using a traffic related typology and the clustering K-Means model, where related event classification was achieved applying Support Vector Machines (SVM), Convolutional Neural Networks (CNN) and Long Short Term Memory (LSTM) networks. We provide experimental results for 2-class and 3-class classification examples indicating that the ensemble performs with accuracy and F-score reaching 98.5%.

show abstract

“…The extremely efficient learning procedure of these models makes them particularly appropriate for traffic forecasting over large datasets. On the other hand, the high parametric sensitivity of models currently utilized for traffic forecasting has also motivated the renaissance of bagging and boosting tree ensembles for the purpose, which are known to be more robust against the variability of their hyper-parameters and less prone to overfitting [256], [257], [258]. Finally, initial evidences of the applicability of automated machine learning tools for efficiently finding precise traffic forecasting models have been recently reported in [259].…”

Section: New Modeling Techniques For Traffic Forecastingmentioning

confidence: 99%

Deep Learning for Road Traffic Forecasting: Does it Make a Difference?

Manibardo¹,

Laña²,

Ser³

2020

Preprint

View full text Add to dashboard Cite

Deep Learning methods have been proven to be flexible to model complex phenomena. This has also been the case of Intelligent Transportation Systems (ITS), in which several areas such as vehicular perception and traffic analysis have widely embraced Deep Learning as a core modeling technology. Particularly in short-term traffic forecasting, the capability of Deep Learning to deliver good results has generated a prevalent inertia towards using Deep Learning models, without examining in depth their benefits and downsides. This paper focuses on critically analyzing the state of the art in what refers to the use of Deep Learning for this particular ITS research area. To this end, we elaborate on the findings distilled from a review of publications from recent years, based on two taxonomic criteria. A posterior critical analysis is held to formulate questions and trigger a necessary debate about the issues of Deep Learning for traffic forecasting. The study is completed with a benchmark of diverse short-term traffic forecasting methods over traffic datasets of different nature, aimed to cover a wide spectrum of possible scenarios. Our experimentation reveals that Deep Learning could not be the best modeling technique for every case, which unveils some caveats unconsidered to date that should be addressed by the community in prospective studies. These insights reveal new challenges and research opportunities in road traffic forecasting, which are enumerated and discussed thoroughly, with the intention of inspiring and guiding future research efforts in this field.

show abstract

Short-Term Traffic Flow Forecasting via Multi-Regime Modeling and Ensemble Learning

Cited by 18 publications

References 47 publications

An Atmospheric Visibility Grading Method Based on Ensemble Learning and Stochastic Weight Average

An Atmospheric Visibility Grading Method Based on Ensemble Learning and Stochastic Weight Average

Exploring an Ensemble of Textual Machine Learning Methodologies for Traffic Event Detection and Classification

Deep Learning for Road Traffic Forecasting: Does it Make a Difference?

Contact Info

Product

Resources

About