A Mobile Based Expert System to Estimate the Travel Risk Applying Imbalance Data Classification
Publish place: 1st National Road Its Congress
Publish Year: 1393
نوع سند: مقاله کنفرانسی
زبان: English
View: 713
This Paper With 6 Page And PDF Format Ready To Download
- Certificate
- من نویسنده این مقاله هستم
این Paper در بخشهای موضوعی زیر دسته بندی شده است:
استخراج به نرم افزارهای پژوهشی:
شناسه ملی سند علمی:
RMTO01_070
تاریخ نمایه سازی: 1 مهر 1394
Abstract:
In this paper the data of transportation and accidents in Tehran-Bazargan highway is considered. This dataset is imbalance, i.e., there are two classes that one of them is outnumbered the second one. In these cases the minority class has the highest value but the accuracy of algorithms for this class is very low and in fact they are incapable of classifying the minority one. This study inspects firstly, traffic of the accidents in Tehran-Bazargan road that have been gathered by the police between 2010 and 2013. Secondly, we propose a mobile based expert system that receives the GPS information of mobile phone inside the vehicle and some properties of the road and based on the trained imbalanced classification algorithms and important information which gathered from different stakeholders such as road and construction organization, police and municipality. The proposed system predicts the risk of accidents for different segments based on the real conditions. It is worth mentioning that in the algorithmic level of this system, ensemble and famous decision tree algorithms are applied based on the different pre-processing methods and the suitable metrics for measurements of superiority for each algorithm are evaluated using WEKA software. The results show that Random Forest, Decorate and Bagging algorithms produce the best results.
Authors
Sima Sharifirad
Master student of computer science Amirkabir University of Technology, Tehran, Iran
Mehdi Ghatee
Department of Computer Science, Amirkabir University of Technology, Tehran, Iran
مراجع و منابع این Paper:
لیست زیر مراجع و منابع استفاده شده در این Paper را نمایش می دهد. این مراجع به صورت کاملا ماشینی و بر اساس هوش مصنوعی استخراج شده اند و لذا ممکن است دارای اشکالاتی باشند که به مرور زمان دقت استخراج این محتوا افزایش می یابد. مراجعی که مقالات مربوط به آنها در سیویلیکا نمایه شده و پیدا شده اند، به خود Paper لینک شده اند :