339 / 2018-12-16 18:25:50

The comparison between two different algorithms of spatio-temporal forecasting for traffic flow prediction

STATIMA, Elman Recurrent Neural Network, traffic flow

全体主题 > Artificial Neural Networks

Nowadays, there is an extensive body of literature that demonstrates the methods of forecasting traffic flows, which includes artificial neu-ral networks, Kalman filtering, support vector regression, (seasonal) ARIMA models. However, seldom articles use two or more than two methods to predict the traffic flows and compare their difference within the forecasting process, which might be the gradually recog-nized as a potentially important research area in the future. As two most commonly adopted methods, STATIMA(Space-Time Auto-regressive Integrated Moving Average) and the Elman Recurrent Neu-ral Network, one of Artificial Neural Networks have been firstly har-nessed to establish the space-time predicting models. Secondly, ac-cording to the successfully trained models, the dissertation conducts the multi-dimensional comparison based on four aspects including: in-terpretability; ease of implementation; running time and instability. Fi-nally, some possible improvements are put forward according to their forecasting performance which also indirectly reflects their unique features and application environments.