Traffic Flow Correlation Analysis of K Intersections Based on Deep Learning
An Intelligent transportation system is one of the indispensable systems of smart cities. The most important goal of an intelligent transportation system is to effectively reduce traffic congestion. This paper presents an analysis of traffic congestion based on traffic flows. According to the result of this analysis, the intersection correlation in a specific area can be deduced. This analysis method more effectively than the traditional method finds the relationship between the intersections according to traffic information, so through deep neural network classify intersection congestion levels, the accuracy rate is higher than 96.7%.
KeywordsIntelligent transportation system Deep neural network
This research was supported in part by the Ministry of Science and Technology, Taiwan, ROC, under grant MOST 105-2221-E-324-009-MY2 and MOST 107-2221-E-324-003-MY2.
- 3.Smart cities USA Homepage. http://smartamerica.org/teams/smart-cities-usa/. Accessed 30 June 2018
- 5.Taipei City Government’s Public Database Homepage. http://data.taipei/. Accessed 15 Feb 2018
- 15.Keras Homepage. https://github.com/fchollet/keras. Accessed 20 Feb 2018