Résultat de la recherche
3 recherche sur le tag
'Genetic Algorithms' 
Visionner les documents numériques
Affiner la recherche Générer le flux rss de la recherche
Partager le résultat de cette recherche Interroger des sources externesContribution au développement d'algorithmes d'optimisation basés sur le partitionnement adaptatif circulaire. / Djalil Boudjehem
Titre : Contribution au développement d'algorithmes d'optimisation basés sur le partitionnement adaptatif circulaire. Type de document : texte imprimé Auteurs : Djalil Boudjehem, Auteur ; N. Mansouri, Directeur de thèse Editeur : Constantine : Université Mentouri Constantine Année de publication : 2007 Importance : 93 f. Format : 30 cm. Note générale : 01 Disponible à la salle de recherche 02 Disponibles au magazin de la B.U.C. 01 CD Langues : Français (fre) Catégories : Français - Anglais
ElectroniqueTags : Contrôle Transformation Algorithmes génétiques Recherche aleatoire Partitionnement dynamique Discrétisation circulaire Optimum global Recherche globale Réduction de l'ordre Codage réél Controle diffusif Random search dynamic partitioning circular design global optimum local search order reduction real coding genetic algorithms diffusive control Index. décimale : 621 Electronique Résumé :
Adaptive partitioning algorithms, works on the basis of a successive reduction of the initial feasible region, in such away to select each time the sub-region that may contain the global optimum of a non convex problem. In this thesis we propose an approach to improving the performances of an adaptive partitioning algorithm. The main idea developed here, is to use the information given a set of the best individuals in a given candidate population solution to enhance the algorithm speed of convergence and precision. The process implemented consists in building sub-regions in dynamic manner guided by the the best individuals, where the region that is more probably containing the global optimum will be selected for repartitioning farther more. This construction uses the inclusion propriety of interval analysis, where the integration of such methods in the proposed algorithms permit improving in a considerable way their convergence. A number of adaptive partitioning algorithms were developed, and most of them are based on a new technique which we call ’the generalized circular design’. these algorithms have the objective to reducing the time needed to attain the a near neighbor of the global optimum. We proposed also, a new technique based on reducing the order of the optimization problem. This problem is transformed to an other problem with `a virtual representation of second order, where optimizing in space of order two is much better and easier. Hence, the obtained solution is transformed again to its original order, in order to obtain the final solution. The proposed algorithms in this thesis, were tested with success in different problems of the litterateur, Physics, Mechanics and the diffusive pseudo invariant control. These algorithms permitted to find with certitude a near neighborhood of the global optimum.Diplôme : Doctorat en sciences En ligne : ../theses/electronique/BOU4894.pdf Format de la ressource électronique : Permalink : https://bu.umc.edu.dz/md/index.php?lvl=notice_display&id=2752 Contribution au développement d'algorithmes d'optimisation basés sur le partitionnement adaptatif circulaire. [texte imprimé] / Djalil Boudjehem, Auteur ; N. Mansouri, Directeur de thèse . - Constantine : Université Mentouri Constantine, 2007 . - 93 f. ; 30 cm.
01 Disponible à la salle de recherche 02 Disponibles au magazin de la B.U.C. 01 CD
Langues : Français (fre)
Catégories : Français - Anglais
ElectroniqueTags : Contrôle Transformation Algorithmes génétiques Recherche aleatoire Partitionnement dynamique Discrétisation circulaire Optimum global Recherche globale Réduction de l'ordre Codage réél Controle diffusif Random search dynamic partitioning circular design global optimum local search order reduction real coding genetic algorithms diffusive control Index. décimale : 621 Electronique Résumé :
Adaptive partitioning algorithms, works on the basis of a successive reduction of the initial feasible region, in such away to select each time the sub-region that may contain the global optimum of a non convex problem. In this thesis we propose an approach to improving the performances of an adaptive partitioning algorithm. The main idea developed here, is to use the information given a set of the best individuals in a given candidate population solution to enhance the algorithm speed of convergence and precision. The process implemented consists in building sub-regions in dynamic manner guided by the the best individuals, where the region that is more probably containing the global optimum will be selected for repartitioning farther more. This construction uses the inclusion propriety of interval analysis, where the integration of such methods in the proposed algorithms permit improving in a considerable way their convergence. A number of adaptive partitioning algorithms were developed, and most of them are based on a new technique which we call ’the generalized circular design’. these algorithms have the objective to reducing the time needed to attain the a near neighbor of the global optimum. We proposed also, a new technique based on reducing the order of the optimization problem. This problem is transformed to an other problem with `a virtual representation of second order, where optimizing in space of order two is much better and easier. Hence, the obtained solution is transformed again to its original order, in order to obtain the final solution. The proposed algorithms in this thesis, were tested with success in different problems of the litterateur, Physics, Mechanics and the diffusive pseudo invariant control. These algorithms permitted to find with certitude a near neighborhood of the global optimum.Diplôme : Doctorat en sciences En ligne : ../theses/electronique/BOU4894.pdf Format de la ressource électronique : Permalink : https://bu.umc.edu.dz/md/index.php?lvl=notice_display&id=2752 Exemplaires (1)
Code-barres Cote Support Localisation Section Disponibilité BOU/4894 BOU/4894 Thèse Bibliothèque principale Thèses Disponible
Titre : Conception des Systèmes d’Inférence Floue par des Approches Hybr ides : Application pour la Commande et la Modélisation des Systèmes Nonlinéaires Type de document : texte imprimé Auteurs : Nesrine Talbi, Auteur ; Khaled Belarbi, Directeur de thèse Editeur : constantine [Algérie] : Université Constantine 1 Année de publication : 2014 Importance : 134 f. Format : 30 cm. Note générale : 2 copies imprimées disponibles Langues : Français (fre) Catégories : Français - Anglais
ElectroniqueTags : Fuzzy rule base Tabu Search Genetic Algorithms Particle Swarm Optimization fuzzy controller monovariable system multivariable system fuzzy modeling Base de règles floues recherche Tabou Algorithmes Génétiques Optimisation par Essaim Particulaire contrôleur flou système monovariable système
multivariable modélisation floue قاعدة من القواعد الغامضة البحث تابو الخوارزميات الجينية سرب الجسيمات الأمثل وحدة التحكم الغامض نظام أحادي المتغير نظام متعدد المتغيرات و النمذجة الغامضةIndex. décimale : 621 Electronique Résumé : The work presented in this thesis revolves mainly around the main areas of modeling and fuzzy control of Takagi-Sugeno zero order for dynamic, complex and highly nonlinear systems.
First, a control law has been proposed using several hybrid algorithms based on the
combination of global search algorithms, Genetic Algorithms (GA) and Particle Swarm
Optimization (PSO) and the local search algorithm the Tabu Search (TS). The hybridization consists to combine the characteristics of these methods (GA -TS and PSO-TS) in order to reap the benefits of success for a good solution in a reduced calculation time, all ensuring the stability, accuracy and robustness controlled systems. For each control structure, examples of simulation applications were presented to justify the validity of the proposed approaches.
These results were compared with other techniques cited in references.
In the second phase, the identification of fuzzy models of Takagi-Sugeno zero-order
approximation for the nonlinear systems was performed using the two hybrid algorithms (GA -TS) and (PSO-TS). The modeling results were compared with those existed in the literature through a performance criterion.Diplôme : Doctorat en sciences En ligne : ../theses/electronique/TAL6467.pdf Format de la ressource électronique : Permalink : https://bu.umc.edu.dz/md/index.php?lvl=notice_display&id=9499 Conception des Systèmes d’Inférence Floue par des Approches Hybr ides : Application pour la Commande et la Modélisation des Systèmes Nonlinéaires [texte imprimé] / Nesrine Talbi, Auteur ; Khaled Belarbi, Directeur de thèse . - constantine [Algérie] : Université Constantine 1, 2014 . - 134 f. ; 30 cm.
2 copies imprimées disponibles
Langues : Français (fre)
Catégories : Français - Anglais
ElectroniqueTags : Fuzzy rule base Tabu Search Genetic Algorithms Particle Swarm Optimization fuzzy controller monovariable system multivariable system fuzzy modeling Base de règles floues recherche Tabou Algorithmes Génétiques Optimisation par Essaim Particulaire contrôleur flou système monovariable système
multivariable modélisation floue قاعدة من القواعد الغامضة البحث تابو الخوارزميات الجينية سرب الجسيمات الأمثل وحدة التحكم الغامض نظام أحادي المتغير نظام متعدد المتغيرات و النمذجة الغامضةIndex. décimale : 621 Electronique Résumé : The work presented in this thesis revolves mainly around the main areas of modeling and fuzzy control of Takagi-Sugeno zero order for dynamic, complex and highly nonlinear systems.
First, a control law has been proposed using several hybrid algorithms based on the
combination of global search algorithms, Genetic Algorithms (GA) and Particle Swarm
Optimization (PSO) and the local search algorithm the Tabu Search (TS). The hybridization consists to combine the characteristics of these methods (GA -TS and PSO-TS) in order to reap the benefits of success for a good solution in a reduced calculation time, all ensuring the stability, accuracy and robustness controlled systems. For each control structure, examples of simulation applications were presented to justify the validity of the proposed approaches.
These results were compared with other techniques cited in references.
In the second phase, the identification of fuzzy models of Takagi-Sugeno zero-order
approximation for the nonlinear systems was performed using the two hybrid algorithms (GA -TS) and (PSO-TS). The modeling results were compared with those existed in the literature through a performance criterion.Diplôme : Doctorat en sciences En ligne : ../theses/electronique/TAL6467.pdf Format de la ressource électronique : Permalink : https://bu.umc.edu.dz/md/index.php?lvl=notice_display&id=9499 Exemplaires (1)
Code-barres Cote Support Localisation Section Disponibilité TAL/6467 TAL/6467 Thèse Bibliothèque principale Thèses Disponible Documents numériques
texte intégraleAdobe Acrobat PDF
Titre : Etude théorique impliquant les mesures Lidar pour la caractérisation optique et microphysique de l’aérosol désertique Type de document : texte imprimé Auteurs : Samir Zeghbib, Auteur ; S. Bouzid, Directeur de thèse Editeur : constantine [Algérie] : Université Constantine 1 Année de publication : 2014 Importance : 144 f. Format : 30 cm. Note générale : 2 copies imprimées disponibles Langues : Français (fre) Catégories : Français - Anglais
ElectroniqueTags : LIDAR LIDAR (taking by impaction) Klett inversion Mie theory desert aerosols Longtin desert model Chomette desert model genetic algorithms LIDAR (prélevement par mpaction) inversion de Klett théorie de Mie aérosols désertiques le modèle désertique de Longtin le modèle désertique de Chomette les algorithmes génétiques الليدار نضرية كلات "Klett" نضرية مي "Mie" غبار الصحراء نموذج لونتا "Longtin" نموذج شومات "Chomette" Index. décimale : 621 Electronique Résumé :
Aerosols are tiny particles suspended in the air. Like greenhouse effect gas emissions, aerosols play an important role in the radiative balance of the atmosphere. However, is poorly quantified until now which justifies the intensification of efforts to study. In addition to their impact on the climate, aerosols perturb astronomical observations and remote sensing measurements. Several measurement methods have been implemented including the method LIDAR (Light Detection And Ranging), which allows to have 3D maps of their concentration.
The interest of optical LIDAR measurements is to give direct access to the distribution of limit layer and the optical extinction of atmospheric particles. The characterization of micro-physical properties of aerosols (size, concentration) is however less easy, because the size distribution of aerosols intervenes as integral form in the measurement of the optical extinction. However it has been achieved in the case of less complex atmospheres (desert
particles, acids, silica, fog, cloud).
Our attention was based on the study of desert particles characterized a big part of the terrestrial globe, for which we performed a detection of their size distributions using multi-spectral method LIDAR, where wavelengths of laser ranging from UV to IR were fixed in the following values: : (λ = 0.193, 0.694, 1.064, 3.370 and 10.60 μm). For each wavelength, we must have corresponding profile of extinction coefficients.
The stochastic method used to solve the problem of simulation is the method of genetic algorithms which is a more reliable and efficient technical to accelerate dramatically the computing time.
Finally the results of our work were compared with two distribution models that we have considered: the model of Longtin and the model Chomette.
Diplôme : Doctorat en sciences En ligne : ../theses/electronique/ZEG6472.pdf Format de la ressource électronique : Permalink : https://bu.umc.edu.dz/md/index.php?lvl=notice_display&id=9513 Etude théorique impliquant les mesures Lidar pour la caractérisation optique et microphysique de l’aérosol désertique [texte imprimé] / Samir Zeghbib, Auteur ; S. Bouzid, Directeur de thèse . - constantine [Algérie] : Université Constantine 1, 2014 . - 144 f. ; 30 cm.
2 copies imprimées disponibles
Langues : Français (fre)
Catégories : Français - Anglais
ElectroniqueTags : LIDAR LIDAR (taking by impaction) Klett inversion Mie theory desert aerosols Longtin desert model Chomette desert model genetic algorithms LIDAR (prélevement par mpaction) inversion de Klett théorie de Mie aérosols désertiques le modèle désertique de Longtin le modèle désertique de Chomette les algorithmes génétiques الليدار نضرية كلات "Klett" نضرية مي "Mie" غبار الصحراء نموذج لونتا "Longtin" نموذج شومات "Chomette" Index. décimale : 621 Electronique Résumé :
Aerosols are tiny particles suspended in the air. Like greenhouse effect gas emissions, aerosols play an important role in the radiative balance of the atmosphere. However, is poorly quantified until now which justifies the intensification of efforts to study. In addition to their impact on the climate, aerosols perturb astronomical observations and remote sensing measurements. Several measurement methods have been implemented including the method LIDAR (Light Detection And Ranging), which allows to have 3D maps of their concentration.
The interest of optical LIDAR measurements is to give direct access to the distribution of limit layer and the optical extinction of atmospheric particles. The characterization of micro-physical properties of aerosols (size, concentration) is however less easy, because the size distribution of aerosols intervenes as integral form in the measurement of the optical extinction. However it has been achieved in the case of less complex atmospheres (desert
particles, acids, silica, fog, cloud).
Our attention was based on the study of desert particles characterized a big part of the terrestrial globe, for which we performed a detection of their size distributions using multi-spectral method LIDAR, where wavelengths of laser ranging from UV to IR were fixed in the following values: : (λ = 0.193, 0.694, 1.064, 3.370 and 10.60 μm). For each wavelength, we must have corresponding profile of extinction coefficients.
The stochastic method used to solve the problem of simulation is the method of genetic algorithms which is a more reliable and efficient technical to accelerate dramatically the computing time.
Finally the results of our work were compared with two distribution models that we have considered: the model of Longtin and the model Chomette.
Diplôme : Doctorat en sciences En ligne : ../theses/electronique/ZEG6472.pdf Format de la ressource électronique : Permalink : https://bu.umc.edu.dz/md/index.php?lvl=notice_display&id=9513 Exemplaires (1)
Code-barres Cote Support Localisation Section Disponibilité ZEG/6472 ZEG/6472 Thèse Bibliothèque principale Thèses Disponible Documents numériques
texte intégraleAdobe Acrobat PDF
