Short-Term Traffic Flow Prediction Using the Modified Elman Recurrent Neural Network Optimized Through a Genetic Algorithm

Abstract

Traffic stream determining is an essential part of the intelligent transportation management system. Precise prediction of traffic flow provides a basis for other tasks, like forecasting travel time. While traditional methods have some merits for improving traffic prediction precision in some ways, high precision, considering different circumstances, is still difficult to achieve. This paper presents a short-term traffic flow prediction model based on the Modified Elman Recurrent Neural Network model (GA-MENN) to deal with this practical problem. In GA-MENN, the algorithm of Elman Recurrent Neural Network is modified, optimized through the Genetic Algorithm (GA) and considered weather conditions, weekday, hour and day's classification to forecast the vehicle velocity in Tehran streets and highways. The traffic data were collected from the online Google Map API service for 139 routs in 7 districts in Tehran. The method improves prediction precision and also lowers the prediction error rate, according to experimental results. Exploratory outcomes verify the superior performance of the proposed traffic condition prediction model over Regression Multi-layer Perceptron, Linear Regression, Logistic Regression, Probabilistic Neural Network, Regression Generalized Feedforward, Time-lag Recurrent Network, Support Vector Machine model, Elman neural network, K-NN model, ARIMA, Kalman filter model, Convolutional Neural Networks (CNNs), SARIMA, and Long Short-Term Memory (LSTM) model. To the best of our knowledge, this is the first occasion when that traffic stream is gauged in urban roads and avenues in this specific way.

Road Traffic Forecast Based on Meteorological Information through Deep Learning Methods

“…Sadeghi-Niaraki et al presented a short-term traffic flow prediction model [14] based on the modified Elman recurrent neural network (ERNM) model to improve traffic prediction model precision. They used a modified ERNM method optimized through a genetic method, and they considered weather conditions, weekday, hour and day's classification to forecast the vehicle velocity in Tehran streets and highways, but they did not forecast traffic fluxes.…”

“…Table 2 summarizes the information about the related work documented in terms of the dataset used, the processing techniques that were used and the learning process objective. This analysis allows to perceive different forecasting objective [13,15,21,22], works that did not sufficiently detail the dataset used or the conditions of use [17,19] or were developed for very different road models [14,18], so our option was to test several deep learning methods in order to evaluate them in terms of accuracy and efficiency.…”

Long Short-term Cognitive Networks

“…Instead of the error backpropagation, we can use metaheuristic approaches to train a model. There exists a range of interesting studies including [40] where the authors used Genetic Algorithm or [15] where Ant Colony Optimisation was employed. Interesting research was delivered by Abdulkarim and Engelbrecht [1] who concluded their study on the application of dynamic Particle Swarm Optimisation to neural network training by stating, that for the time series they tested, dynamic Particle Swarm Optimisation ensured forecasting error to be the same for a standard neural architecture and a recurrent one.…”

Interval type-2 fuzzy computational model for real time Kalman filtering and forecasting of the dynamic spreading behavior of novel Coronavirus 2019

“…The increasing in complexity of real-world applications has motivated the development of computational intelligence techniques based on artificial neural networks [1] , fuzzy logic [2] , evolutionary computation [3] , [4] , and others, as useful tools for solution of practical problems [5] , [6] , [7] , [8] , [9] . Recently, the combination of different intelligent systems with traditional computational approaches has been proposed in different fields of research in order to develop more efficient tools [10] , [11] , [12] , [13] . In the context of computational modeling of experimental data, type-2 fuzzy systems have attracted considerable attention by researches due to its interpretable rule-based structure with capability to treat nonlinearity and uncertainty [14] , [15] , [16] .…”