Neural-network models for classification and forecasting of freeway traffic flow stability

Florio, L.; Mussone, Lorenzo

doi:10.1016/0967-0661(95)00221-9

Cited by 56 publications

(35 citation statements)

References 15 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Therefore, an antibody with a higher affinity value and a lower similarity value has a good likelihood of entering the memory cells. The affinity between the antibody and antigen is defined as (20).…”

Section: Cia In Selecting Parametersmentioning

confidence: 99%

“…As mentioned above that the process underlying interurban traffic flow is complicated to be captured by a single linear statistical algorithm, the artificial neural networks (ANN) models, able to approximate any degree of complexity and without prior knowledge of problem solving, have received much attention and been considered as alternatives for traffic flow forecasting models [14,[18][19][20][21][22][23]. ANN is based on a model of emulating the processing of the human neurological system to determine related numbers of vehicle and temporal characteristics from the historical traffic flow patterns, especially for nonlinear and dynamic evolutions.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Application of seasonal SVR with chaotic immune algorithm in traffic flow forecasting

Hong

2010

Neural Comput & Applic

View full text Add to dashboard Cite

Accurate forecasting of inter-urban traffic flow has been one of the most important issues globally in the research on road traffic congestion. Because the information of inter-urban traffic presents a challenging situation, the traffic flow forecasting involves a rather complex nonlinear data pattern, particularly during daily peak periods, traffic flow data reveals cyclic (seasonal) trend. In the recent years, the support vector regression model (SVR) has been widely used to solve nonlinear regression and time series problems. However, the applications of SVR models to deal with cyclic (seasonal) trend time series had not been widely explored. This investigation presents a traffic flow forecasting model that combines the seasonal support vector regression model with chaotic immune algorithm (SSVRCIA), to forecast inter-urban traffic flow. Additionally, a numerical example of traffic flow values from northern Taiwan is used to elucidate the forecasting performance of the proposed SSVRCIA model. The forecasting results indicate that the proposed model yields more accurate forecasting results than the seasonal autoregressive integrated moving average, back-propagation neural network, and seasonal Holt-Winters models. Therefore, the SSVRCIA model is a promising alternative for forecasting traffic flow.

show abstract

Section: Cia In Selecting Parametersmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Application of seasonal SVR with chaotic immune algorithm in traffic flow forecasting

Hong

2010

Neural Comput & Applic

View full text Add to dashboard Cite

show abstract

“…--mapping from a R" to R 2 for reconstruction of vehicular flow-density and speed-density relationship [15,16,35]; lane occupation models [17]; recognition of the state of traffic flow [15], --time series prediction [15,27,5,30], --function approximation for accident risk evaluation [31,33,34,28], number of violations at signalised intersections [32], analysis of saturation flow at signalized intersections [23]; driver behaviour [36]; user behaviour in transport modal choice [1], prediction of flow data in a traffic network [27].…”

Section: Applications Experiencedmentioning

confidence: 99%

A review of feedforward neural networks in transportation research

Mussone

1999

Elektrotech. Inftech.

Self Cite

View full text Add to dashboard Cite

The paper reports applications of neural networks in transportation research and shows the author's specific experience and applications of neural networks for many fields concerning transport and traffic theory. By using the interpolation capability of neural networks it is possible to extract relationships present in data according to particular conditions and to the features of used variables. A comparison between applications anda discussion about problems and difficulties arising with the use of feedforward neural networks are carried out. The aim is to underline that some results are obtainable exactly by using neural network capabilities and can be translated to other fields without great difficulties.

show abstract

“…Florio and Mussone [1] introduced weather data into neural networks and considered the interaction between many weather and traffic variables. Although, in theory, this model could simulate every possible scenario, prediction errors were high ranging from 33 to 39% for density and flow respectively.…”

Section: Introductionmentioning

confidence: 99%

“…Significant research has been dedicated over the years on freeway speed modeling; this research has discussed the effects of traffic mix (the percentage of cars, trucks, buses and so on) on speeds as well as the interaction between speed and volume [1][2][3][4]. Trucks, in particular, have been found to affect speed distributions considerably and have been systematically studied [5][6][7].…”

Section: Introductionmentioning

confidence: 99%

Does Information on Weather Affect the Performance of Short-Term Traffic Forecasting Models?

2011

View full text Add to dashboard Cite

Although weather, traffic mix and speed variability across lanes are largely considered as significant determinants of traffic flow characteristics on freeways, they have not been incorporated into short-term traffic forecasting models. We evaluate the effects of weather and traffic mix on the predictability of traffic speed using several vector autoregressive moving average models with exogenous variables. Results indicate that including exogenous variables in the forecasting models only marginally improves their prediction performance, while modeling innovations such as Vector and Bayesian estimation improves the models significantly.

show abstract

Neural-network models for classification and forecasting of freeway traffic flow stability

Cited by 56 publications

References 15 publications

Application of seasonal SVR with chaotic immune algorithm in traffic flow forecasting

Application of seasonal SVR with chaotic immune algorithm in traffic flow forecasting

A review of feedforward neural networks in transportation research

Does Information on Weather Affect the Performance of Short-Term Traffic Forecasting Models?

Contact Info

Product

Resources

About