Document Details

Document Type : Thesis 
Document Title :
HYBRID METHODS FOR ROAD TRAFFIC PREDICTION AND ANALYSIS USING GPS BIG DATA
الطرق الهجينة للتنبؤ بحركة المرور وتحليلها باستخدام البيانات الكبيرة من نظام تحديد المواقع العالمي
 
Subject : Faculty of Computing and Information Technology 
Document Language : Arabic 
Abstract : Mobility is a major dimension of smart city designs and developments. Transportation analysis and prediction play an important part in mobility research and development. Recent years have seen many new types of transportation data emerging, such as social media and GPS data. This data contains hidden knowledge and it can be used in many applications to improve city operations. Road traffic prediction is one aspect of smart city operations. Researchers have traditionally used single statistical traffic flow prediction methods that work well only under specific conditions. Recently, machine learning methods have been used for prediction. Some works have emerged in recent years on combining these methods into various hybrid methods. However, these works are in their infancy and require further investigations. More importantly, these hybrid methods have mostly been developed on standalone machines, limiting the data and problem sizes that can be addressed, as well as the accuracy that can be achieved. The aim of this research is to improve GPS-data based road traffic analysis and prediction methods using big data technologies. Specifically, we propose and implement a hybrid model for road traffic prediction on Spark, a distributed big data computing platform. The hybrid model is based on ARIMA (Auto-Regressive Integrated Moving Average) and SVR (Support Vector Regression) methods. The performance of our hybrid model is compared to the individual ARIMA and SVR models, and improvements in the prediction accuracies have been achieved. Furthermore, we give a review of the traffic flow prediction and modeling methods and discuss the limitations of each method. A review of the various types of transportation traffic data sources is provided. Notable big data analysis tools including the Apache Spark platform are described. A tutorial for hybrid prediction methods is provided. Conclusions are drawn, and future directions are given. . 
Supervisor : Dr. Rashid Mahmud 
Thesis Type : Master Thesis 
Publishing Year : 1440 AH
2019 AD 
Co-Supervisor : Dr. Ayad human race 
Added Date : Wednesday, July 31, 2019 

Researchers

Researcher Name (Arabic)Researcher Name (English)Researcher TypeDr GradeEmail
بدور مجمل السلميAl-Salami, Badour ResearcherMaster 

Files

File NameTypeDescription
 44832.pdf pdf 

Back To Researches Page