首页    期刊浏览 2024年12月05日 星期四
登录注册

文章基本信息

  • 标题:Predicting the Road Traffic Density Based on Twitter Using the TR-P Method
  • 本地全文:下载
  • 作者:Arief Wibowo ; Edi Winarko ; Azhari
  • 期刊名称:International Journal of Computer Science and Network Security
  • 印刷版ISSN:1738-7906
  • 出版年度:2017
  • 卷号:17
  • 期号:8
  • 页码:63-67
  • 出版社:International Journal of Computer Science and Network Security
  • 摘要:This study contains work activities in order to build models of prediction system of traffic density based on twitter text data. The Traffic Road-Prediction (TR-P) method we have proposed consists of extracting and mining text data on road traffic. Based on the patterns that have been found from the learning process, we build a prediction model of road traffic density using text mining approach. The result of learning model validation using k-fold method has an accuracy of 96.31%, while the highest model testing accuracy reaches 91.34%. The road traffic density conditions of the proposed system have been visualized into several color classes of road traffic density, such as red, orange, yellow and green. This visualization makes it easier for users to understand the level of road traffic density resulting from predicted systems that have been built.
  • 关键词:Text Classification; Data Mining; Road Traffic Density Prediction; TR-P Method.
国家哲学社会科学文献中心版权所有