Maghsood Salimi, Doctoral student
As of February 2021, I have started my Ph.D. studies at Mälardalen University's School of Innovation, Design, and Engineering. Additionally, I earned a Master's degree in Computer Science from the University of Tehran.
Currently, I'm a member of the SACSys project at Mälardalen University and I'm working on the safety and security of Cyber-Physical Systems.
My research interests are formal methods, genetic algorithms, automata learning, and modeling and verification of concurrent and distributed systems.
Learning Activation Functions for Adversarial Attack Resilience in CNNs (Jun 2023) Maghsood Salimi, Mohammad Loni, Marjan Sirjani The 22nd International Conference on Artificial Intelligence and Soft Computing (ICAISC 2023)
SARAF: Searching for Adversarial Robust Activation Functions (Jun 2023) Maghsood Salimi, Mohammad Loni, Marjan Sirjani, Antonio Cicchetti, Sara Abbaspour The 6th International Conference on Machine Vision and Applications (ICMVA'2023)
Multi-objective Optimization of Real-Time Task Scheduling Problem for Distributed Environments (Sep 2019) Maghsood Salimi, Amin Majd , Mohammad Loni, Tiberiu Seceleanu, Cristina Seceleanu, Marjan Sirjani, Masoud Daneshtalab, Elena Troubitsyna 6th Conference on the Engineering of Computer Based Systems (ECBS 2019)
ConstScene: Dataset and Model for Advancing Robust Semantic Segmentation in Construction Environments Maghsood Salimi, Mohammad Loni, Antonio Cicchetti, Sara Afshar, Marjan Sirjani 4th edition of the International Conference on Pattern Recognition and Artificial Intelligence (ICPRAI 2024)
Enhancing Object Detection for Autonomous Machines in Private Construction Sites Through Federated Learning Mohammadreza Mohammadi , Maghsood Salimi, Mohammad Loni, Sima Sinaei 13th International Conference on Computer Technologies and Development (TechDev 2024)
Robust Few-Shot Semantic Segmentation for Blurred and Occluded Objects in Construction Environments Maghsood Salimi, Mohammad Loni, Antonio Cicchetti, Marjan Sirjani International Joint Conference on Neural Networks 2025 (IJCNN 2025)