Feature selection‐based approach for urban short‐term travel speed prediction

Zheng, Liang; Zhu, Chuang; Zhu, Nianyong; He, Tian; Ni, Dong; Huang, Helai

doi:10.1049/iet-its.2017.0059

Cited by 28 publications

(22 citation statements)

References 52 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Recently GA were applied for spatial [44][45][46] and temporal [47] feature selection. The PSO approach was applied by Chan et al [48,49] and recently combined with GA by Zheng et al [50].…”

Section: Class 3: Wrapper Feature Selection Methodsmentioning

confidence: 99%

Feature selection and extraction in spatiotemporal traffic forecasting: a systematic literature review

Pavlyuk

2019

Eur. Transp. Res. Rev.

View full text Add to dashboard Cite

A spatiotemporal approach that simultaneously utilises both spatial and temporal relationships is gaining scientific interest in the field of traffic flow forecasting. Accurate identification of the spatiotemporal structure (dependencies amongst traffic flows in space and time) plays a critical role in modern traffic forecasting methodologies, and recent developments of data-driven feature selection and extraction methods allow the identification of complex relationships. This paper systematically reviews studies that apply feature selection and extraction methods for spatiotemporal traffic forecasting. The reviewed bibliographic database includes 211 publications and covers the period from early 1984 to March 2018. A synthesis of bibliographic sources clarifies the advantages and disadvantages of different feature selection and extraction methods for learning the spatiotemporal structure and discovers trends in their applications. We conclude that there is a clear need for development of comprehensive guidelines for selecting appropriate spatiotemporal feature selection and extraction methods for urban traffic forecasting.

show abstract

Section: Class 3: Wrapper Feature Selection Methodsmentioning

confidence: 99%

Feature selection and extraction in spatiotemporal traffic forecasting: a systematic literature review

Pavlyuk

2019

Eur. Transp. Res. Rev.

View full text Add to dashboard Cite

show abstract

“…To address this problem, non-parametric regression has shown remarkable advantages in various traffic state forecasting practices. Zheng et al proposed three classic non-parametric models to improve traffic speed prediction performance with reduced data dimensionality [15]. A Bayesian network approach was presented for traffic flow prediction [16].…”

Section: Literature Reviewmentioning

confidence: 99%

A Multitask Learning Model for Traffic Flow and Speed Forecasting

Zhang

Zhu

et al. 2020

IEEE Access

View full text Add to dashboard Cite

Intelligent Transportation Systems (ITS) research and applications benefit from accurate shortterm traffic state forecasting. To improve the forecasting accuracy, this paper proposes a deep learning based multitask learning Gated Recurrent Units (MTL-GRU) with residual mappings. To enhance the performance of the MTL-GRU, feature engineering is introduced to select the most informative features for the forecasting. Then, based on real-world datasets, numerical results show that the MTL-GRU can well estimate traffic flow and speed simultaneously, and performs better than other counterparts. Experiments also show that the deep learning based MTL-GRU model can overpower the bottleneck caused by enlarging training datasets and continue to gain benefits. The results suggest the proposed MTL-GRU model with residual mappings is promising to forecast short-term traffic state. INDEX TERMS Short-term traffic forecasting, deep learning, multitask learning, feature engineering.

show abstract

“…where Ci is the concentration of the i-th pollutant, g/m 3 ; Qv volumetric exhaust emissions, m 3 /h. The calculation of the amount of harmful emissions emitted by the transport stream according to the methods [6,7] is based on the generally accepted indicator mpi -the emission of the i-th pollutant by one car per unit of distance traveled (g/km), which is called mileage emission [1]:…”

Section: Theorymentioning

confidence: 99%

“…There are two types of methods that assess the level of air pollution by traffic: methods that estimate the concentration of pollutants in the roadside territory [1,3,4,5] and methods that estimate the amount of pollutant emissions by automobile road [1,2,6,7,8,9]. The methods of the first type are focused on assessing the quality of atmospheric air, in which pollutants can be present not only from the exhaust gases of vehicles, but also emissions from stationary sources [10], therefore, their use for assessing the quality of RDTE on RSN elements in settlements is limited and can be used for certain conditions.…”

Section: Introductionmentioning

confidence: 99%

The method of calculating emissions of pollutants from road transport in an urban environment

Teterina

Parsaev

2019

MATEC Web Conf.

View full text Add to dashboard Cite

To assess the quality of road traffic organization on environmental indicators, two methods of five regulations operating in the Russian Federation, which take into account the parameters of traffic flow, affecting the volume of emissions Pollutants. The parameter that affects the results of calculations in both methods is the average speed of movement. In real-world conditions on urban highways there are areas where the traffic flow is uneven (braking, acceleration, stopping), which entails an increase in the amount of pollutants from vehicles. At the same time, this uneven traffic is largely due to the existing the road design and traffic engineering on certain elements of the road network. This is the basis for the development of a methodology for calculating pollutant emissions to assess the quality of the traffic engineering, taking into account the uneven flow of traffic.

show abstract

Feature selection‐based approach for urban short‐term travel speed prediction

Cited by 28 publications

References 52 publications

Feature selection and extraction in spatiotemporal traffic forecasting: a systematic literature review

Feature selection and extraction in spatiotemporal traffic forecasting: a systematic literature review

A Multitask Learning Model for Traffic Flow and Speed Forecasting

The method of calculating emissions of pollutants from road transport in an urban environment

Contact Info

Product

Resources

About