T2F-LSTM Method for Long-Term Traffic Volume Prediction

Authors:
Publisher website
Google Scholar
Abstract
Long Short-Term Memory (LSTM) neural network shows excellent performance in learning, processing and classifying time series data but with some limitations such as high computational cost and lack of interpretability. Fuzzy neural networks, which combine the complementary capabilities of both neural networks and fuzzy system, thus constitute a more promising technique for processing traffic flow. This paper presents a Type-2 Fuzzy Long Short-Term Memory (T2F-LSTM) neural network model for long term traffic volume prediction. Type-2 Fuzzy Sets (T2FSs) provide more freedom to describe membership information and process data with higher uncertainty better than traditional fuzzy system does. In this paper, an interval T2FSs is introduced to extract the probability distribution and spatial-temporal characteristics of traffic volume. Using parameters of Closure of Support (CoS) obtained in interval T2FSs, weights of input gate in LSTM neural network are updated and converged to the region with larger slope of the sigmod function fast. The network interpretability is also increased by better control the information flow using motivational factors constructed from the parameters. Experiment conducted with real traffic volume data shows that the proposed model achieves more accurate prediction result and shorter network training time.

This publication has 44 references indexed in Scilit: