Analysis and Prediction of Vehicular Big Data for Smart City

• Main Author: Apriandy Angdresey
• Other Authors: P. K. Sahoo
• Format: Others
• Language: en_US
• Published: 2017
• Online Access: http://ndltd.ncl.edu.tw/handle/29s78y

碩士 === 長庚大學 === 資訊工程學系 === 105 === Traffic congestion is a problem in big cities, this problem arises because the number of vehicles is not balanced by the growth of road, besides that due to several unforeseen incidents, such as an accident. Thereby causing congestion. However, at present the development and use of positioning technology and sensors can help to collect huge amount of Vehicular Ad Hoc Network (VANET) traffic data in a real time basis. Large volume of real-time data at a tremendous speed can be gathered to help of roadside units using wireless sensors and on-board units of the vehicles. In our works, we propose an algorithm to predict the possible of traffic density by analyzing the VANET Big Data, by using classication and data mining models. We have designed several designs on graph theory, for classication, of the existing traffic by measurement of the affinity vector of each existing intersection and road segment. The results of our experiments show that our proposed method has better performance in terms of the accuracy.