Reza Rafeh

Work place: Department of Computer Engineering, Faculty of Engineering, Arak University, Arak, Iran



Research Interests: Computational Science and Engineering, Computational Engineering, Software Construction, Software Design, Software Engineering


Reza Rafeh is a faculty member at Arak University (Iran). He got his PhD from Monash University (Australia). His interesting areas are compiler design, constraint programming and theorem proving. He is the chief editor of Software Engineering Journal as well as an editorial board of Soft Computing Journal.

Author Articles
Using Heuristic-based Search for Zinc Models

By Reza Rafeh Roya Rashidi

DOI:, Pub. Date: 8 Sep. 2013

The Zinc modelling language provides a rich set of constraints, data structures and expressions to support high-level modelling. Zinc is the only modelling language that supports all solving techniques: constraint programming, mathematical methods, and local search. By providing search patterns, it allows users to implement their search methods in a declarative way. There are currently three search patterns implemented in Zinc: backtracking search, branch and bound search, and local search. In this paper we explain how Zinc efficiently implements user-defined local search algorithms.

[...] Read more.
Mass Detection in Lung CT Images Using Region Growing Segmentation and Decision Making Based on Fuzzy Inference System and Artificial Neural Network

By Atiyeh Hashemi Abdol Hamid Pilevar Reza Rafeh

DOI:, Pub. Date: 8 May 2013

Lung cancer is distinguished by presenting one of the highest incidences and one of the highest rates of mortality among all other types of cancers. Detecting and curing the disease in the early stages provides the patients with a high chance of survival. 
This work aims at detecting lung nodules automatically through computerized tomography (CT) image. Accordingly, this article aim at presenting a method to improve the efficiency of the lung cancer diagnosis system, through proposing a region growing segmentation method to segment CT scan lung images. Afterwards, cancer recognition are presenting by Fuzzy Inference System (FIS) for differentiating between malignant, benign and advanced lung nodules. In the following, this paper is testing the diagnostic performances of FIS system by using artificial neural networks (ANNs). Our experiments show that the average sensitivity of the proposed method is 95%.

[...] Read more.
Other Articles