Dynamic Wavelet Neural Network Model for Traffic Flow Forecasting

Jiang, Xiang; Adeli, Hojjat

doi:10.1061/(asce)0733-947x(2005)131:10(771)

Cited by 336 publications

(172 citation statements)

References 30 publications

Supporting

Mentioning

168

Contrasting

Unclassified

Order By: Relevance

“…Of course these methods are more complex than other two and their implementation are costly (Hosseini, 2014). A hybrid of neural network with other prediction models like fuzzy model (Stathopoulos, 2008), wavelet model (Jiang, 2005) and ARIMA model (Zeng, 2008) are one of these methods. Actually no comprehensive method has been proposed yet for traffic flow prediction which could lead to very accurate solutions in all traffic conditions (Stathopoulos, 2008).…”

Section: Hybrid Prediction Methodsmentioning

confidence: 99%

Sensor Data Fusion Using Mutual Information Algorithm

Shabanian¹,

Hosseini²

2015

CeN

View full text Add to dashboard Cite

Traffic flow prediction is one of the congestion avoidance methods in highways. According to previous studies, no comprehensive model has been proposed for traffic flow prediction which can prevent congestion in many different traffic conditions. Using data fusion to reduce prediction error is an interesting idea to solve this problem. In this paper, a new hybrid algorithm based on mutual informat ion for traffic flow prediction will be proposed and compared with various types of previous hybrid algorithms and predictors. The Mutual Information (MI) algorithm is used to calculate the interdependency of data, so we expect this new hybrid algorithm to have high precisio n in comparison with others. Simulations will be implemented based on real data in MATLAB environment

show abstract

Section: Hybrid Prediction Methodsmentioning

confidence: 99%

Sensor Data Fusion Using Mutual Information Algorithm

Shabanian¹,

Hosseini²

2015

CeN

View full text Add to dashboard Cite

show abstract

“…RBF neural network learning algorithm is generally divided into two categories: (1) The number of hidden layer neurons is growing gradually, under the training objectives to achieve the adjustment of weights and thresholds;(2) The number of neurons in the hidden layer is determined (the same as the number of training samples), and the threshold value of the hidden layer is also determined. The weights and thresholds of the output layer are solved by the linear equations.…”

Section: 2rbf Neural Networkmentioning

confidence: 99%

Traffic Flow Prediction Based on Combined Model of ARIMA and RBF Neural Network

Wang¹

2017

Proceedings of the 2017 2nd International Conference on Machinery, Electronics and Control Simulation (MECS 2017)

View full text Add to dashboard Cite

In this paper, a combined model of ARIMA and RBF neural network is proposed by combined the good linear fit ability of ARIMA and the strong dynamic nonlinear mapping ability of RBF neural network. The velocity of microwave is predicted in real time with the consideration of the temporal characteristics of traffic flow by the models.The results indicate that the Mean Absolute Percentage Error of combined model is lower, and the goodness of fit of combined model is higher. Keywords: traffic engineering, traffic flow prediction, Combined Model, ARIMA model, RBF neural network model 1.IntroductionIn order to solve the traffic problems such as traffic congestion and traffic accidents, Intelligent Transportation System (ITS) has been developed and applied to practice. The core research on ITS is traffic control and guidance, and short-term traffic flow prediction is the data foundation and decision support of traffic control and guidance system.In recent years, domestic and overseas experts and scholars have proposed a variety of combinatorial models or improved models. Xiaomo Jiang et al.[1] proposed a neural network combined with wavelet analysis for traffic flow prediction; Yanru Zhang et al.[2] used a modified gradient boosting regression tree to predict travel time; Yisheng Lv et al. [3] used a deep learning model for traffic flow prediction, which combines BP neural network and stack automatic encoders; Wu Wei [4] proposed a PSO-PLS (particle swarm optimization-partial least squares regression) combination forecasting method. Sun Liguang et al. [5] proposed a double-layer update mechanism which used a recursive regression method to update the sub-model coefficients and weighting coefficient; Zhang Jinglei et al.[6] used a three-tier structure of the RBF neural network for non-linear combination of RBF and ARIMA; Chen Gang [7] used BP neural network to amend error of the gray prediction model. Qian Wei et al [8] combined BP neural network model and GM (1,1) model with a variable weight coefficients form.In many prediction models, ARIMA model can reflect the trend of traffic flow time series, and it is easy to apply to traffic flow forecasting, while RBF neural network model has strong dynamic non-linear mapping ability, and it has high satisfaction and accuracy to stochastic sample. Based on the good linear fitting ability of ARIMA model and the powerful dynamic nonlinear mapping ability of RBF neural network model, this paper builds models and uses the speed-based traffic flow state identification

show abstract

“…This model use passenger flow data in each monitoring period over the past four days to forecast the data of the next weekday. [4,5] Take Sihuidong station for an example, take,we can get 22 sets of passenger flow data of Sihuidong in March, each group of 17 numbers.Take the date group 1~15 to use as the input of BP neural network training data, then use the date group 16~19 and group 17~20 and group 18~21 respectively as the simulation input and the prediction value of groups 22, finally compare with real data and analysis of BP neural network to predict the hourly traffic volume.…”

Section: Data Preprocessing and Statistical Analysismentioning

confidence: 99%

Analysis and Comparison of Urban Rail Transit Passenger Flow Forecast based on Multiple Methods

Cui¹,

Li²

2017

Proceedings of the 2017 6th International Conference on Energy, Environment and Sustainable Development (ICEESD 2017)

View full text Add to dashboard Cite

Abstract. Passenger flow forecast is an important and functional part of urban rail transit operation and management, excellent and accurate passenger flow forecast can guide the operation management to achieve high efficiency and safety. This article mainly discusses the three forecasting models commonly used for passenger flow forecast. In addition, passenger flow data of Beijing urban rail transit were used to do statistical analysis and prediction. Finally, the prediction accuracy, advantages and disadvantages of the three models are compared.

show abstract

Dynamic Wavelet Neural Network Model for Traffic Flow Forecasting

Cited by 336 publications

References 30 publications

Sensor Data Fusion Using Mutual Information Algorithm

Sensor Data Fusion Using Mutual Information Algorithm

Traffic Flow Prediction Based on Combined Model of ARIMA and RBF Neural Network

Analysis and Comparison of Urban Rail Transit Passenger Flow Forecast based on Multiple Methods

Contact Info

Product

Resources

About