Loading...
| Friend's email | |
| Your name | |
| Your email | |
| enter code | |
This page was sent successfuly
- Type of Document: M.Sc. Thesis
- Language: Farsi
- Document No: 51496 (05)
- University: Sharif University of Technology
- Department: Electrical Engineering
- Advisor(s): Gholampour, Iman
- Abstract:
- Predicting traffic condition is one of the most important topics for traffic engineers and is a vital part of smart city. Extracting traffic behavior and realizing new traffic behaviors plays undeniable parts in big decision making of cities. On the other hand, progress of new technologies and devices for controlling and monitoring traffic caused the volume of traffic related data to grow exponentially. Velocity and variety of these data made normal data mining solution to fail in modeling and performing well. New data era has changed the view of large numbers of science and engineering majors. Traffic engineering also needs big data analytics for process of its own big data. Thus the need for ways to conquer three major challenges is sensed more than ever. These challenges are: Velocity, Variety and Volume. In this thesis, the goal is to achieve a new way to overcome these challenges.Analysis and extracting patterns of city traffic and recognizing anomalies with usage of machine learning and topics modeling is been studied in this research. In designing analysis solution challenges with respect to big data is been considered. In these models monthly and weekly patterns are considered. Traffic information mostly are related to speed control camers and cameras of Tarh traffic. These data is been analyzed with topic models and dominant patterns is been extracted. Then these patterns is used to train machine learning models for anomaly detection. To assess the performance of this system different scenarios is been analyzed. Accuracy of the proposed models is been measured up to 0.974 with AuROC metric
- Keywords:
- Big Data ; Topic Model ; Anomaly Detection ; Machine Learning ; Traffic Analysis ; Traffic Prediction
Digital Object List
-
محتواي کتاب
- view
Bookmark