Traffic Prediction using Time-Space Diagram: A Convolutional Neural Network Approach

Abstract

Traffic prediction is a major component of any traffic management system. With the increase in data sources and advancement in connectivity, data analysis and machine learning approaches for traffic prediction have gained a lot of attention. Most of the existing data analysis approaches in traffic prediction rely on aggregated inputs such as flow and density, with limited studies using the individual vehicle-level data. The time-space diagram of the vehicles can be constructed from the connected vehicles’ data. This plot is comprehensive and contains all the information about traffic flow dynamics at both microscopic and macroscopic levels. Accordingly, this study introduces a deep learning-based methodology to directly predict the traffic state based on the time-space diagram with the use of convolutional neural networks (CNN). The time-space diagram is directly used as the input to the traffic prediction model using a CNN. The prediction capability of the proposed model is compared with multilayer perceptron, support vector regression, and autoregressive integrated moving average, and the results indicate a superior capability of CNN in predicting flow and density across all possible values of these parameters.

Optimizing The Utilization of Third Runway in Soekarno Hatta International Airport Using Time Space Analysis

“…Second, time space analysis is a method to calculate runway capacity using runway occupancy time and if the distance between plane is known. This method is one of popular methods to calculate runway capacity or to predict traffic in transportation management system [3]. This method is conducted by Tengku Annisa, Mohammardeza, Safrilah, and Andrej.…”

“…This method is conducted by Tengku Annisa, Mohammardeza, Safrilah, and Andrej. In their research, they using input from time-space diagram to CNN model [3]. Time space analysis can be used to calculate runway capacity in different configuration of runway (departure only, arrival only, mixed configuration) [4].…”

Spatio-Temporal Traffic Flow Prediction in Madrid: An Application of Residual Convolutional Neural Networks

“…Traffic flow prediction can be considered as using past and current flow data to predict traffic in the near future [13]. Many studies have proposed various traffic flow prediction methodologies [14] for both short-(seconds to 1 h) and long-term (more than 1 h) estimation. Short-term traffic flow prediction has recently received increasing scientific and research interest, which is mainly due to several advances in the application of artificial intelligence in this field [15].…”

Back to the Future: Predicting Traffic Shockwave Formation and Propagation Using a Convolutional Encoder-Decoder Network

“…The encoding convolutional layers extract the main features and abstracts the input, while the deconvolution layers decode the abstract input and predict the shockwave propagation. The proposed network is deep, and the skip-layer connections provide the opportunity to [10] propagate the gradient to the beginning layers of the network. The skip-layer connections address the vanishing gradient problem in very deep networks.…”