Abstract
Short‐term traffic flow prediction is an effective means for intelligent transportation system (ITS) to mitigate traffic congestion. However, traffic flow data with temporal features and periodic characteristics are vulnerable to weather effects, making short‐term traffic flow prediction a challenging issue. However, the existing models do not consider the influence of weather changes on traffic flow, leading to poor performance under some extreme conditions. In view of the rich features of traffic data and the characteristic of being vulnerable to external weather conditions, the prediction model based on traffic data has certain limitations, so it is necessary to conduct research studies on traffic flow prediction driven by both the traffic data and weather data. This paper proposes a combined framework of stacked autoencoder (SAE) and radial basis function (RBF) neural network to predict traffic flow, which can effectively capture the temporal correlation and periodicity of traffic flow data and disturbance of weather factors. Firstly, SAE is used to process the traffic flow data in multiple time slices to acquire a preliminary prediction. Then, RBF is used to capture the relation between weather disturbance and periodicity of traffic flow so as to gain another prediction. Finally, another RBF is used for the fusion of the above two predictions on decision level, obtaining a reconstructed prediction with higher accuracy. The effectiveness and robustness of the proposed model are verified by experiments.
Highlights
In recent years, with the continuous increase of vehicle ownership, the conflict between road resources and travel demand is becoming increasingly acute, which leads to the increasingly serious traffic congestion and even hinders the development of social economy
Statistical models include historical average (HA) and autoregressive integrated moving average (ARIMA). e former takes the statistical average value at a certain time slip in the past as the predicted value, while the latter establishes mathematical model based on the time series. is kind of method has been widely used for a long time because it can reveal the periodic changes of traffic flow data
(2) Incorporating the stacked autoencoder (SAE) and radial basis function (RBF) to capture the features of traffic flow and weather conditions: considering the effectiveness of combination modeling based on deep learning, we use SAE to learn the temporal correlation in traffic flow, RBF to learn the periodic evolution under weather disturbance, and another RBF to realize the decision-level data fusion of the former models. is combined framework can effectively learn the periodicity and temporal correlation of traffic flow and the disturbance of weather conditions so as to improve the accuracy and robustness of the prediction model
Summary
With the continuous increase of vehicle ownership, the conflict between road resources and travel demand is becoming increasingly acute, which leads to the increasingly serious traffic congestion and even hinders the development of social economy. ITS is an effective means to alleviate traffic congestion, and short-term traffic flow prediction is the key to it. E existing short-term traffic flow prediction models can be mainly divided into 3 categories: statistical models, traditional machine learning models, and deep learning models. Is kind of method has been widely used for a long time because it can reveal the periodic changes of traffic flow data. In 1970s, Ahmed et al [1] firstly applied ARIMA on short-term traffic flow prediction problem. Voort et al [2] combined Kohonen maps with ARIMA and proposed the KARIMA method to forecast traffic flow. Williams et al [3] proposed seasonal ARIMA for traffic flow prediction on expressway. Min et al [4] proposed GSTARIMA for shortterm traffic flow prediction in urban network. For further extraction on spatiotemporal correlation, Duan et al [5] proposed an extended space-time ARIMA for short-term
Sign-in/Register to view highlights & summary Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
