Mohammed Salem

Work place: University of Oran, Faculty of Exact and Applied Sciences, Oran, 31000, Algeria



Research Interests: Artificial Intelligence, Evolutionary Computation, Computer Architecture and Organization, Data Structures and Algorithms, Models of Computation


Mohammed Salem was born in Mascara, Algeria in 1974; he received an Engineer degree in computer science from Sidi Bel Abbes University Algeria on 1999 and Master degree in Industrial computing from Oran University on 2007. 

His research fields are the evolutionary computation and the application of artificial intelligence in identification and control of nonlinear systems. 

He joined the Science & technology Faculty (Computer science department) University of Mascara, Algeria; he is also a Research Member of the Laboratory of Research in Industrial Computing and Networks University of Oran.

Author Articles
Predator and Prey Modified Biogeography Based Optimization Approach (PMBBO) in Tuning a PID Controller for Nonlinear Systems

By Mohammed Salem Mohamed F. Khelfi

DOI:, Pub. Date: 8 Oct. 2014

In this paper an enhanced approach based on a modified biogeography optimization with predator and prey behavior (PMBBO) is presented. The approach uses several predators with new proposed prey’s movement formula. The potential of using a modified predator and prey model is to increase the diversification along the optimization process so to avoid local optima and reach the optimal solution quickly. The proposed approach is used in tuning the gains of PID controller for nonlinear systems (Mass spring damper and an inverted pendulum) and has given remarkable results when compared to genetic algorithm and classical BBO.

[...] Read more.
Sequential Adaptive RBF-Fuzzy Variable Structure Control Applied to Robotics Systems

By Mohammed Salem Mohamed F. Khelfi

DOI:, Pub. Date: 8 Aug. 2014

In this paper, we present a combination of sequential trained radial basis function networks and fuzzy techniques to enhance the variable structure controllers dedicated to robotics systems. In this aim, four RBFs networks were used to estimate the model based part parameters (Inertia, Centrifugal and Coriolis, Gravity and Friction matrices) of a variable structure controller so to respond to model variation and disturbances, a sequential online training algorithm based on Growing-Pruning "GAP" strategy and Kalman filter was implemented. To eliminate the chattering effect, the corrective control of the VS control was computed by a fuzzy controller. Simulations are carried out to control three degrees of freedom SCARA robot manipulator where the obtained results show good disturbance rejection and chattering elimination.

[...] Read more.
Other Articles