Prediction of Short-Term Traffic Variables Using Intelligent Swarm-Based Neural Networks

Abstract

This brief presents an innovative algorithm integrated with particle swarm optimization and artificial neural networks to develop short-term traffic flow predictors, which are intended to provide traffic flow forecasting information for traffic management in order to reduce traffic congestion and improve mobility of transportation. The proposed algorithm aims to address the issues of development of short-term traffic flow predictors which have not been addressed fully in the current literature namely that: 1) strongly non-linear characteristics are unavoidable in traffic flow data; 2) memory space for implementation of short-term traffic flow predictors is limited; 3) specification of model structures for short-term traffic flow predictors which do not involve trial and error methods based on human expertise; and 4) adaptation to newly-captured, traffic flow data is required. The proposed algorithm was applied to forecast traffic flow conditions on a section of freeway in Western Australia, whose traffic flow information is newly-captured. These results clearly demonstrate the effectiveness of using the proposed algorithm for real-time traffic flow forecasting.Index Terms-Adaptive neural network (NN), evolutionary algorithm, particle swarm optimization, time-varying modeling, traffic flow forecasting, traffic management.

Traffic flow prediction using orthogonal arrays and Takagi-Sugeno neural fuzzy models

“…a) In this paper, the Taguchi method is only used for the design of TS-model. We will apply the Taguchi method to design the neural networks [17][18][19] which are effective for traffic flow forecasting. b) we will analyze the interaction effects between on-road sensors in developing the on-road sensor configuration.…”

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

“…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].…”

Evaluation of Recent Computational Approaches in Short-Term Traffic Forecasting

“…NN is a kind of information processing technique, and it can be trained to learn relationships in a dataset. The NN model has been applied in short-term traffic forecasting for many years, and it has been proven to be effective in solving problems that existing complex relationships, such as traffic flow forecasting [13,[17][18][19]. Since the traffic data with lumpiness may reduce the generalization capability on the short-term traffic flow forecasting on unseen data [20], we applied the exponential smoothing method [21,22] to remove lumpiness in the collected traffic data.…”

“…In the new era of intelligent traffic systems, research has focus on establishing forecasting models to manage the traffic networks [10][11][12]. Many computational approaches have been commonly applied to build forecasting models, such as neural network (NN), generalized additive model (GAM), and autoregressive integrated moving average (ARIMA) [6,[13][14][15][16]. In this paper, above approaches are applied to the traffic data collected on the British freeway (M6) from 1 st to 30 th November in 2014 for evaluation.…”