Salem Mohammed

University Mustapha Stambouli of Mascara · Computer Science

Machine translation (henceforward referred to as MT) is one of the important areas of Natural language processing (NLP) that is necessary for cracking the language obstacle and easing inter-lingual communication. This paper sheds light on the approaches used in MT, available in the literature, to encourage researchers to study these techniques. In...

Real-Time Strategy (RTS) games are well-known for their substantially large combinatorial decision and state spaces, responsible for creating significant challenges for search and machine learning techniques. Exploiting domain knowledge to assist in navigating the expansive decision and state spaces could facilitate the emergence of competitive RTS...

Evolution is a powerful problem-solving technique, extensively used for designing racing car controllers, but with a series of challenges: an evaluation function that can separate the best controllers from the rest, and a series of operators that can explore different possibilities in the controller search space. Within the context of the TORCS rac...

The core challenge facing search techniques when used to play Real-Time Strategy (RTS) games is the extensive combinatorial decision space. Several approaches were proposed to alleviate this dimensionality burden, using scripts or action probability distributions, based on expert knowledge. We propose to replace expert-authored scripts with a colle...

The impressive performance of Monte Carlo Tree Search (MCTS) based game-playing agents in high branching-factor domains such as Go, motivated researchers to apply and adapt MCTS to even more challenging domains. Real-time strategy (RTS) games feature a large combinatorial branching factor and a real-time aspect that pose significant challenges to a...

Online planning is an important research area focusing on the problem of real-time decision making, using information extracted from the environment. The aim is to compute, at each decision point, the best decision possible that contributes to the realization of a fixed objective. Relevant application domains include robotics, control engineering a...

Image clustering is considered amongst the most important tasks in medical image analysis and it is regularly required as a starter and vital stage in the computer aided medical image process. In brain Magnetic Resonance Imaging analysis, image clustering is regularly used for estimating and visualizing the brain anatomical structures, to detect pa...

One of emerging challenges in Medical image analysis is clustering. Fuzzy C-means (FCM) algorithm is one of the most popular clustering algorithms because it is efficient, straightforward, and easy to implement. However, FCM is sensitive to initialization and is easily trapped in local optima, such a drawback could be overcome by evolutionary algor...

Resumen-Los simuladores de carreras de coches han sido utilizados durante mucho tiempo como un entorno para probar algoritmos de control autónomo de vehículos. Constituyen un entorno en el para evaluar todo tipo de algoritmos, incluyendo metaheurísticas, como por ejemplo Algoritmos Evolutivos. Sin embargo, el mayor desafío en este tipo de algoritmo...

This work presents an evolutionary approach to optimize the parameters of a Fuzzy-based autonomous driver for the open simulated car racing game (TORCS). Using evolutionary algorithms, we intend to optimize a modular fuzzy agent designed to determine the optimal target speed as well as the steering angle during the race. The challenge in this kind...

When driving a car it is essential to take into account all possible factors; even more so when, like in the TORCS simulated race game, the objective is not only to avoid collisions, but also to win the race within a limited budget. In this paper, we present the design of an autonomous driver for racing car in a simulated race. Unlike previous cont...

Harmony search (HS) is a new meta-heuristic optimization method inspired from improvisation process in jazz music searching for a perfect state of harmony. HS has been improved based on parameters settings updating and hybridization. In this paper, HS and four of its variants are compared via Wilcoxon and Friedman nonparametric tests using benchmar...

In this paper, we solve the nonlinear \(H_\infty\) optimal control with output feedback via the neural network (NN)–least squares method for the affine nonlinear system. The approach is based on successive approximate solution of two Hamilton–Jacobi–Isaacs (HJI) equations, which appear in the \(H_\infty\) optimal output feedback control. Successive...

This paper is dedicated to present an overview of harmony search algorithm and its main variants based on parameters settings updating and hybridization. The considered algorithms are compared via Wilcoxon and Friedman nonparametric tests using benchmark functions. Statistical comparison highlights the Global best harmony search as the best variant...

This paper is dedicated to present one of newly developed evolutionary algorithm; we considered a new way to tune the PID controller of nonlinear systems where the parameters of the controller are optimized using the Artificial Immune Algorithm (AIA) based on the immune system which defends the body against harmful diseases and infections. This wor...

This paper is dedicated to the presentation of enhanced swarm intelligence based training algorithm for Radial basis functions neural networks. The proposed training algorithm (ABC-PP) is hybridization between the Artificial Bees Colony (ABC) and a predator and prey behavior to improve the diversification mechanism of the ABC. Statistical analysis...

This paper is dedicated to present one of newly developed evolutionary algorithm. We consider a new way to tune the PID controller of nonlinear systems where the parameters of PID are optimised using the optimisation method called artificial immune algorithm (AIA). This algorithm is inspired from the immune system defends to the body against harmfu...

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...

The present paper is dedicated to the presentation and implementation of an optimized technique allowing an on-line estimation of a robot manipulator parameters to use them in a computed torque control. Indeed the proposed control law needs the exact robot model to give good performances. The complexity of the robot manipulator and its strong non-l...

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 v...

This paper is dedicated to the optimization of nonlinear controllers basing of an enhanced Biogeography Based Optimization (BBO) approach. Indeed, The BBO is combined to a predator and prey model where several predators are used with introduction of a modified migration operator to increase the diversification along the optimization process so as t...

In this paper, we present a new tuning method for a PID controller of a nonlinear system. The proposed approach is an hybridization of the Artificial Bees Colony (ABC) and the Predator and prey (P\&P) behavior. The employed bees will explore new sources in the search space while running away from their predators. Simulations of the proposed algorit...

This paper is dedicated to present the newly developed evolutionary algorithm: Biogeography based optimization (BBO). It is based on the migration of information between habitats like in Biogeography. The BBO is then used to tune a PID controller of nonlinear systems where the parameters are optimized. Simulations of the proposed algorithm are carr...

The present paper is dedicated to the presentation and implementation of an optimized technique allowing an on-line estimation of a robot manipulator parameters to use them in a computed torque control. Indeed the proposed control law needs the exact robot model to give good performances. The complexity of the robot manipulator and its strong non-l...

The present paper is dedicated for the presentation and implementation of an optimized technique allowing an on-line adjustment of the fuzzy controller parameters. Indeed, we have obtained an on-line optimized zero order Takagi–Sugeno type FIS. This method is simple and safe since, it leads to very quick and efficient optimization technique. A comp...

The aim of this work is the combination of radial basis function networks (RBF) and fuzzy techniques to enhance the sliding mode controllers. In fact, three RBFs networks were used to estimate the model parameters and to respond to model variation and disturbances, a sequential training algorithm based on Kalman filter was implemented, and to elimi...

Le présent article relevant du domaine de l'Automatique en général, et de l'Intelligence Artificielle en particulier, est consacré à l'utilisation des réseaux de neurones pour la commande d'un système dynamique non-linéaire. Il constitue une contribution de l'Intelligence Artificielle pour l'analyse et la commande des systèmes dynamiques. L'approch...