Assistant Professor at University of Science and Culture, Iran📖
Dr. Alireza Rezvanian is an accomplished academic and researcher, serving as an Assistant Professor at the University of Science and Culture (USC) in Tehran, Iran. He holds multiple editorial positions, including Associate Editor for journals such as CAAI Transactions on Intelligence Technology, Human-Centric Computing and Information Sciences, The Journal of Engineering, and Data in Brief. Dr. Rezvanian is actively involved in various professional and scientific activities, including serving as the Director of Information and Scientific Resources at USC and contributing to the IEEE Computer Society Iran Chapter.
Profile
Scopus Profile
Orcid Profile
Google Scholar Profile
Education Background🎓
Dr. Rezvanian completed his Ph.D. in Computer Engineering from Amirkabir University of Technology (Tehran Polytechnic) in 2016, under the guidance of Dr. Mohammad Reza Meybodi. His doctoral thesis focused on “Stochastic Graphs for Social Network Analysis.” He holds a Master’s degree in Computer Engineering from Islamic Azad University of Qazvin (2010), where he specialized in improving Artificial Immune System algorithms using Learning Automata for dynamic environments. He also earned a Bachelor’s degree in Computer Engineering from Bu-Ali Sina University of Hamedan (2007).
Professional Experience🌱
Dr. Rezvanian has extensive teaching and research experience across multiple prestigious institutions. Currently, he is an Assistant Professor at the University of Science and Culture, Tehran. He is also an Adjunct Professor at Amirkabir University of Technology, the University of Tehran, and Tarbiat Modares University. His leadership roles include serving as the Head of the Computer Engineering Department at USC (2021-2023) and as the Director of Information and Scientific Resources at USC since 2023. He has previously held research positions at the Institute for Research in Fundamental Sciences (IPM) and the Niroo Research Institute (NRI).
Dr. Rezvanian’s research interests lie in the areas of complex networks, social network analysis, machine learning, learning automata, data mining, and soft computing. His work focuses on the application of evolutionary algorithms, image processing, and stochastic graphs for modeling social networks. His research aims to provide insights into real-world applications through innovative techniques in network analysis and machine learning.
Author Metrics
1. Robust Fall Detection Using Human Shape and Multi-Class Support Vector Machine
- Authors: H. Foroughi, A. Rezvanian, A. Paziraee
- Conference: Sixth Indian Conference on Computer Vision, Graphics & Image Processing (ICVGIP 2008)
- Year: 2008
- Summary: This paper focuses on a robust fall detection system utilizing human shape and a multi-class support vector machine (SVM) for classifying human body shapes and movements. The system aims to effectively detect falls, which is crucial in healthcare applications like elderly care.
2. Sampling from Complex Networks Using Distributed Learning Automata
- Authors: A. Rezvanian, M. Rahmati, M.R. Meybodi
- Journal: Physica A: Statistical Mechanics and its Applications
- Volume: 396
- Pages: 224–234
- Year: 2014
- Summary: This paper introduces a method for sampling complex networks using distributed learning automata (LA), a technique inspired by machine learning algorithms. The approach aims to enhance network analysis by efficiently exploring and sampling complex graph structures.
3. Minimum Positive Influence Dominating Set and Its Application in Influence Maximization: A Learning Automata Approach
- Authors: M.M.D. Khomami, A. Rezvanian, N. Bagherpour, M.R. Meybodi
- Journal: Applied Intelligence
- Volume: 48 (3)
- Pages: 570–593
- Year: 2018
- Summary: This paper presents a novel approach for solving the Minimum Positive Influence Dominating Set (MPIDS) problem, using learning automata for influence maximization in social networks. The proposed method addresses the optimization challenges in selecting influential nodes for spreading information effectively in network-based applications.
4. CDEPSO: A Bi-population Hybrid Approach for Dynamic Optimization Problems
- Authors: J.K. Kordestani, A. Rezvanian, M.R. Meybodi
- Journal: Applied Intelligence
- Volume: 40 (4)
- Pages: 682–694
- Year: 2014
- Summary: The paper introduces CDEPSO (Cognitive Dynamic Evolutionary Particle Swarm Optimization), a hybrid approach that integrates bi-population evolutionary algorithms to address dynamic optimization problems. The method aims to improve the solution quality and efficiency in environments where the optimization landscape changes over time.
5. Cellular Edge Detection: Combining Cellular Automata and Cellular Learning Automata
- Authors: M. Hasanzadeh Mofrad, S. Sadeghi, A. Rezvanian, M.R. Meybodi
- Journal: AEU-International Journal of Electronics and Communications
- Volume: 69 (9)
- Pages: 1282–1290
- Year: 2015
- Summary: This paper explores the combination of cellular automata (CA) and cellular learning automata (CLA) for edge detection in image processing. The approach leverages the computational power of CA and CLA to enhance the edge detection process in digital images, contributing to improvements in image recognition and processing tasks.
Conclusion