An Evaluation of HTM and LSTM for Short-Term Arterial Traffic Flow Prediction

Abstract

Recent years have seen the emergence of two significant technologies: big data systems capable of storing, retrieving, and processing large amounts of data, and machine learning algorithms capable of learning and predicting complex sequences. In combination, these technologies present new opportunities to leverage the increasingly large amounts of traffic volume data to improve traffic flow prediction and the detection of anomalous traffic flows. In this paper, we investigate and evaluate the use of hierarchical temporal memory (HTM) for short-term prediction of traffic flows over real-world Sydney Coordinated Adaptive Traffic System data on arterial roads in the Adelaide metropolitan area in South Australia. Results are compared with those from long-short-term memory (LSTM). Extended experimentation with LSTM network configurations in both batch learning and online learning modes provide results with superior predictive performance over previous usage of LSTM and other deep learning techniques for short-term traffic flow prediction. In addition, we argue that HTM has potential as an effective tool for short term traffic flow prediction with results on par with LSTM and improvements when traffic flow distributions change.