Abstract The paper presents the analysis of traffic data for determining classes of time series of traffic flow intensity for use in traffic forecasting employing neural networks. Data from traffic detectors on the main access road to the city of Gliwice in the period of past year is the basis for statistical analysis. Four classes of time series are proposed as representative of the traffic flow. The time series map temporarily smoothed detector counts. Different smoothing periods are used to retain the dynamic characteristics of the flows. A neural network is developed to classify incoming traffic data into the proposed time series classes. The specific time series implies a traffic control or management strategy, which indicates the capability of the NN to work out decisions for use in Intelligent Transportation Systems (ITS) applications.
Traffic Flow Analysis Based on the Real Data Using Neural Networks
2012-01-01
8 pages
Article/Chapter (Book)
Electronic Resource
English
traffic flow analysis , traffic flow classification , prediction , time series , neural network Computer Science , Information Systems Applications (incl. Internet) , Simulation and Modeling , Artificial Intelligence (incl. Robotics) , Computers and Society , Computer Appl. in Administrative Data Processing , System Performance and Evaluation
Traffic Flow Analysis Based on the Real Data Using Neural Networks
British Library Conference Proceedings | 2012
|Classification and Prediction of Traffic Flow Based on Real Data Using Neural Networks
Tema Archive | 2012
|Real-Time Traffic Sign Recognition Using Convolutional Neural Networks
Springer Verlag | 2021
|Freeway Traffic Data Prediction Using Neural Networks
British Library Conference Proceedings | 1995
|