Performance of Deep Neural Networks in the Analysis of Vehicle Traffic Volume
- October 25, 2018
- Posted by: RSIS
- Category: Computer Science and Engineering
International Journal of Research and Scientific Innovation (IJRSI) | Volume V, Issue X, October 2018 | ISSN 2321–2705
Adrian Bosire1, George Okeyo2, and Wilson Cheruiyot3
1Department of Computer Science, Kiriri Womens University of Science and Technology, Kenya.
2 & 3 School of Computer Science and Information Technology, Jomo Kenyatta University of Agriculture and Technology, Kenya
Abstract– The major problem of vehicle traffic congestions is the increased time wasted in the queues and the resultant high cost of resources used during the same period. Therefore, this research seeks to evaluate the viability of Deep Neural Networks in the performance analysis of vehicle traffic volume. This will assist in effective and efficient traffic monitoring, travel-time forecasting and traffic management. Deep Neural Networks (DNN) offer an optimal option for alleviating the problem of traffic congestion. Although Artificial Neural Networks (ANN) usually encounter setbacks such as local optimum thereby resulting in short term forecasting this can be effectively overcome by using an appropriate training algorithm with correctly configured parameters for the kind of data under consideration. The data is divided into samples for training, validation and testing, after which the overall performance is evaluated using the Mean Squared Error (MSE). The results obtained will help in the evaluation of the practicability of using DNNs in analyzing vehicle traffic flow. Eventually, this can be leveraged for time-forecasting of traffic conditions and also mitigate traffic build-up.
Keywords – Artificial Intelligence, Deep Neural Network, Performance analysis, Traffic volume.
Vehicle traffic congestion is a nuisance to the society with extended effects both environmentally and socially. The domain of vehicle transport presents challenges such as the increased travel time and consequent high cost of resources incurred at such a time due to the poor traffic queue management. The changing factors in this dynamic environment as represented in variables such as the weather, accidents or incidents and even unscheduled events may result into unforeseen traffic snarl-ups which may limit us to short term forecasting which should not be the case. Essentially, we should have a reliable means to forecast with due consideration to such factors that may inhibit the prediction accuracy in order to attain a traffic queue management model which sustains the dynamic nature of the environment.