Khaled Mellouli - Academia.edu (original) (raw)

inproceedings by Khaled Mellouli

Papers by Khaled Mellouli

International Journal of Computational Intelligence and Applications

Medical & Biological Engineering & Computing, 2022

This study presents an efficient solution for the integrated recovery room planning and schedulin... more This study presents an efficient solution for the integrated recovery room planning and scheduling problem (IRRPSP). The complexity of the IRRPSP is caused by several sources. The problem combines the assignment of patients to recovery rooms and the scheduling of caregivers over a short-term planning horizon. Moreover, a solution of the IRRPSP should respect a set of hard and soft constraints while solving the main problem such as the maximum capacity of recovery rooms, the maximum daily load of caregivers, the treatment deadlines, etc. Thus, the need for an automated tool to support the decision-makers in handling the planning and scheduling tasks arises. In this paper, we present an exhaustive description of the epidemiological situation within the Kingdom of Saudi Arabia, especially in Jeddah Governorate. We will highlight the importance of implementing a formal and systematic approach in dealing with the scheduling of recovery rooms during extreme emergency periods like the COVID-19 era. To do so, we developed a mathematical programming model to present the IRRPSP in a formal way which will help in analyzing the problem and lately use its solution for comparison and evaluation of our proposed approach. Due to the NP-hard nature of the IRRPSP, we propose a hybrid three-level approach. This study uses real data instances received from the Department of Respiratory and Chest Diseases of the King Abdulaziz Hospital. The computational results show that our solution significantly outperforms the results obtained by CPLEX software with more than 1.33% of satisfied patients on B1 benchmark in much lesser computation time (36.27 to 1546.79 s). Moreover, our proposed approach can properly balance the available nurses and the patient perspectives.

Lecture Notes in Computer Science, 2001

... used for the detection, localization and recognition of objects in a given area [1]. Handling... more ... used for the detection, localization and recognition of objects in a given area [1]. Handling information collected by different sensors requires an evidence gathering process, called a multisensor data fusion process, in ... Truth Airplane Helicopter Airplane Rocket S1 o1 o2 o3 o4 ...

Lecture Notes in Computer Science, 2008

Frequent Itemset Mining (FIM) problem has been extensively tackled in the context of perfect data... more Frequent Itemset Mining (FIM) problem has been extensively tackled in the context of perfect data. However, real applications showed that data are often imperfect (incomplete and/or uncertain) which leads to the need of FIM algorithms that process imperfect databases. In this paper we propose a new algorithm for mining frequent itemsets from databases including exactly one evidential attribute. An evidential attribute is an attribute that could have uncertain values modelled via the evidence theory, i.e., a basic belief assignment. We introduce in this paper a variant of the structure Belief Itemset Tree (BIT) for mining frequent itemsets from evidential data and we lead some experiments that showed efficiency of our mining algorithm compared to the existing ones.

Lecture Notes in Computer Science, 2012

In this paper, we present and define the bi-objective Green Vehicle Routing Problem GVRP in the c... more In this paper, we present and define the bi-objective Green Vehicle Routing Problem GVRP in the context of green logistics. The bi-objective GVRP states for the problem of finding routes for vehicles to serve a set of customers while minimizing the total traveled distance and the co2 emissions. We review emission factors and techniques employed to estimate co2 emissions and integrate them into the GVRP definition and model. We apply the NSGA-II evolutionary algorithm to solve GVRP benchmarks and perform statistical analysis to evaluate and validate the obtained results. The results show that the algorithm obtain good results and prove the explicit interest grant to emission minimization objective.

This paper extends the decision tree technique to an uncertain environment where the uncertainty ... more This paper extends the decision tree technique to an uncertain environment where the uncertainty is represented by belief functions as interpreted in the Transferable Belief Model (TBM). This so-called belief decision tree is a new classification method adapted to uncertain data. We will be concerned with the construction of the belief decision tree from a training set where the knowledge about the instances' classes is represented by belief functions, and its use for the classification of new instances where the knowledge about the attributes' values is represented by belief functions. Keywords: Belief Functions, Decision Tree, Belief Decision Tree, Classification, Transferable Belief Model. 1 Introduction Several learning methods have been developed to ensure classification. Among these, the decision tree method may be one of the most commonly used in supervised learning approaches. Indeed decision trees are characterized by their capability to break down a complex decis...

2017 IEEE/ACS 14th International Conference on Computer Systems and Applications (AICCSA)

The most dangerous emergency situations are those threatening a high population in complex and la... more The most dangerous emergency situations are those threatening a high population in complex and large scale buildings. Traditional evacuation plans seem to be inefficient and lack of flexibility owing to the difficulty in predicting both the behavior of evacuees and building status in such disasters. The emergence of smart building and technologies can help to design real-time evacuation guidance systems. They will provide shortest routes for evacuees regarding their position in the building by avoiding crowd and fire propagation. We propose a guidance system based on an ant colony optimizer. Experiments are performed to illustrate the ability of this intelligent guidance system in providing realistic plans according to the building parameters. Also, the decision maker can assess the safety of a given building by simulating evacuation process.

Resume: Le domaine de l’identification de la similarite a ete considere comme un sujet de recherc... more Resume: Le domaine de l’identification de la similarite a ete considere comme un sujet de recherche fortement recommande dans les domaines du Web semantique, de l’intelligence artificielle et de la litterature linguistique. Dans le domaine du Web semantique ou les ontologies interviennent pour la modelisation des connaissances, la mesure de [Wup 94] a l’avantage d’etre simple a implementer et d’avoir aussi de bonnes performances comparativement a d’autres mesures de similarite [Lin 98]. Neanmoins, cette mesure presente l’inconvenient suivant : dans certaines situations, la valeur de similarite de deux elements d’une ontologie contenus dans le voisinage depasse la valeur de similarite de deux elements contenus dans la meme hierarchie. Cette situation est inadequate dans le cadre de la recherche de l’information. Afin de pallier a ce probleme, nous proposons une nouvelle mesure de similarite en se basant sur la mesure de Wu et Palmer. Nous avons applique notre mesure sur une ontologie...

World Academy of Science, Engineering and Technology, International Journal of Computer, Electrical, Automation, Control and Information Engineering, 2007

The belief K-modes method (BKM) approach is a new clustering technique handling uncertainty in th... more The belief K-modes method (BKM) approach is a new clustering technique handling uncertainty in the attribute values of objects in both the cluster construction task and the classification one. Like the standard version of this method, the BKM results depend on the chosen initial modes. So, one selection method of initial modes is developed, in this paper, aiming at improving the performances of the BKM approach. Experiments with several sets of real data show that by considered the developed selection initial modes method, the clustering algorithm produces more accurate results. Keywords—Clustering, Uncertainty, Belief function theory, Belief K-modes Method, Initial modes selection.

Resume. Un probleme important de la production automatique de regles de classification concerne l... more Resume. Un probleme important de la production automatique de regles de classification concerne la duree de generation de ces regles ; en effet, les algorithmes mis en œuvre produisent souvent des regles pendant un certain temps assez long. Nous proposons une nouvelle methode de classification a partir d’une base de donnees images. Cette methode se situe a la jonction de deux techniques : l’algebre de P-tree et l’arbre de decision en vue d’accelerer le processus de classification et de recherche dans de grandes bases d’images. La modelisation que nous proposons se base, d’une part, sur les descripteurs visuels tels que la couleur, la forme et la texture dans le but d’indexer les images et, d’autre part, sur la generation automatique des regles de classification a l’aide d’un nouvel algorithme C4.5(P-tree). Pour valider notre methode, nous avons developpe un systeme baptise C.I.A.D.P-tree qui a ete implemente et confronte a une application reelle dans le domaine du traitement d’image...

Association rule mining (ARM) problem has been extensively tackled in the context of perfect data... more Association rule mining (ARM) problem has been extensively tackled in the context of perfect data. However, real applications showed that data are often imperfect (incomplete and/or uncertain) which leads to the need of ARM algorithms that process imperfect databases. In this paper we propose a new algorithm for mining frequent itemsets from evidential databases. We introduce a new structure called RidLists that is the vertical representation of the evidential database. Our structure is adapted to itemsets belief computation which makes the mining algorithm more ecient. Experimental results showed that our proposed algorithm is ecient in comparison with the only evidential ARM algorithm in the literature [10].

La recherche d’informations pertinentes sur le web est considérée comme un nouveau besoin de la s... more La recherche d’informations pertinentes sur le web est considérée comme un nouveau besoin de la société de l’information. Les méthodes de traitement d’informations fondées sur les statistiques ne sont plus suffisantes pour répondre aux besoins des utilisateurs afin de manipuler (rechercher, traduire, résumer...) les informations sur le web. Un constat tend à s’imposer : introduire plus de sémantique pour la recherche d’informations pertinentes issues des textes. En effet, lorsque l’utilisateur du web lance sa requête, il s’attend généralement à trouver précisément ce qu’il cherche, c’est à dire trouver « l’information pertinente », sans qu’il soit submergé par un volume de réponses non-maîtrisables et ingérables. Dans ce travail, nous présentons une approche permettant la recherche de documents sur le web prenant en compte des critères temporels. Notre approche est parente des projets en cours visant à améliorer les résultats des moteurs de recherche [Lawrence et al., 2001] [Glover ...

This paper proposes a new anytime possibilistic inference algorithm for min-based directed networ... more This paper proposes a new anytime possibilistic inference algorithm for min-based directed networks. Our algorithm departs from a direct adaptation of probabilistic propagation algorithms since it avoids the transformation of the initial network into a junction tree which is known to be a hard problem. The proposed algorithm is composed of several, local stabilization, procedures. Stabilization procedures aim to guarantee that local distributions defined on each node are coherent with respect to the ones of its parents. We provide experimental results which, for instance, compare our algorithm with the ones based on a direct adaptation of probabilistic propagation algorithms.

In this paper a genetic algorithm-based approach is developed to solve the variation of the strad... more In this paper a genetic algorithm-based approach is developed to solve the variation of the straddle carriers problem. This problem is solved in the context of optimizing loading operations of outbound containers in a seaport container terminal. The contribution of the work lies in the formulation and subsequent development of a solution strategy for the problem. A numerical experimentation is carried out in order to evaluate the performance and the efficiency of the solution.

Automated negotiation is a process by which competitors aim to reach agreement by using suitable ... more Automated negotiation is a process by which competitors aim to reach agreement by using suitable strategies. This paper aims to enhance negotiation process by using theoretical techniques that help agents to reach final agreement with shorten trade time. The purpose is to succeed negotiation process with better resource utilization. The proposed techniques are based on game theory to support the decision of rational agents to offer the better acceptable proposal in a specific negotiation thread. The designed model has been evaluated by extensive experiments.

International Journal of Computational Intelligence and Applications

Medical & Biological Engineering & Computing, 2022

This study presents an efficient solution for the integrated recovery room planning and schedulin... more This study presents an efficient solution for the integrated recovery room planning and scheduling problem (IRRPSP). The complexity of the IRRPSP is caused by several sources. The problem combines the assignment of patients to recovery rooms and the scheduling of caregivers over a short-term planning horizon. Moreover, a solution of the IRRPSP should respect a set of hard and soft constraints while solving the main problem such as the maximum capacity of recovery rooms, the maximum daily load of caregivers, the treatment deadlines, etc. Thus, the need for an automated tool to support the decision-makers in handling the planning and scheduling tasks arises. In this paper, we present an exhaustive description of the epidemiological situation within the Kingdom of Saudi Arabia, especially in Jeddah Governorate. We will highlight the importance of implementing a formal and systematic approach in dealing with the scheduling of recovery rooms during extreme emergency periods like the COVID-19 era. To do so, we developed a mathematical programming model to present the IRRPSP in a formal way which will help in analyzing the problem and lately use its solution for comparison and evaluation of our proposed approach. Due to the NP-hard nature of the IRRPSP, we propose a hybrid three-level approach. This study uses real data instances received from the Department of Respiratory and Chest Diseases of the King Abdulaziz Hospital. The computational results show that our solution significantly outperforms the results obtained by CPLEX software with more than 1.33% of satisfied patients on B1 benchmark in much lesser computation time (36.27 to 1546.79 s). Moreover, our proposed approach can properly balance the available nurses and the patient perspectives.

Lecture Notes in Computer Science, 2001

... used for the detection, localization and recognition of objects in a given area [1]. Handling... more ... used for the detection, localization and recognition of objects in a given area [1]. Handling information collected by different sensors requires an evidence gathering process, called a multisensor data fusion process, in ... Truth Airplane Helicopter Airplane Rocket S1 o1 o2 o3 o4 ...

Lecture Notes in Computer Science, 2008

Frequent Itemset Mining (FIM) problem has been extensively tackled in the context of perfect data... more Frequent Itemset Mining (FIM) problem has been extensively tackled in the context of perfect data. However, real applications showed that data are often imperfect (incomplete and/or uncertain) which leads to the need of FIM algorithms that process imperfect databases. In this paper we propose a new algorithm for mining frequent itemsets from databases including exactly one evidential attribute. An evidential attribute is an attribute that could have uncertain values modelled via the evidence theory, i.e., a basic belief assignment. We introduce in this paper a variant of the structure Belief Itemset Tree (BIT) for mining frequent itemsets from evidential data and we lead some experiments that showed efficiency of our mining algorithm compared to the existing ones.

Lecture Notes in Computer Science, 2012

In this paper, we present and define the bi-objective Green Vehicle Routing Problem GVRP in the c... more In this paper, we present and define the bi-objective Green Vehicle Routing Problem GVRP in the context of green logistics. The bi-objective GVRP states for the problem of finding routes for vehicles to serve a set of customers while minimizing the total traveled distance and the co2 emissions. We review emission factors and techniques employed to estimate co2 emissions and integrate them into the GVRP definition and model. We apply the NSGA-II evolutionary algorithm to solve GVRP benchmarks and perform statistical analysis to evaluate and validate the obtained results. The results show that the algorithm obtain good results and prove the explicit interest grant to emission minimization objective.

This paper extends the decision tree technique to an uncertain environment where the uncertainty ... more This paper extends the decision tree technique to an uncertain environment where the uncertainty is represented by belief functions as interpreted in the Transferable Belief Model (TBM). This so-called belief decision tree is a new classification method adapted to uncertain data. We will be concerned with the construction of the belief decision tree from a training set where the knowledge about the instances' classes is represented by belief functions, and its use for the classification of new instances where the knowledge about the attributes' values is represented by belief functions. Keywords: Belief Functions, Decision Tree, Belief Decision Tree, Classification, Transferable Belief Model. 1 Introduction Several learning methods have been developed to ensure classification. Among these, the decision tree method may be one of the most commonly used in supervised learning approaches. Indeed decision trees are characterized by their capability to break down a complex decis...

2017 IEEE/ACS 14th International Conference on Computer Systems and Applications (AICCSA)

The most dangerous emergency situations are those threatening a high population in complex and la... more The most dangerous emergency situations are those threatening a high population in complex and large scale buildings. Traditional evacuation plans seem to be inefficient and lack of flexibility owing to the difficulty in predicting both the behavior of evacuees and building status in such disasters. The emergence of smart building and technologies can help to design real-time evacuation guidance systems. They will provide shortest routes for evacuees regarding their position in the building by avoiding crowd and fire propagation. We propose a guidance system based on an ant colony optimizer. Experiments are performed to illustrate the ability of this intelligent guidance system in providing realistic plans according to the building parameters. Also, the decision maker can assess the safety of a given building by simulating evacuation process.

Resume: Le domaine de l’identification de la similarite a ete considere comme un sujet de recherc... more Resume: Le domaine de l’identification de la similarite a ete considere comme un sujet de recherche fortement recommande dans les domaines du Web semantique, de l’intelligence artificielle et de la litterature linguistique. Dans le domaine du Web semantique ou les ontologies interviennent pour la modelisation des connaissances, la mesure de [Wup 94] a l’avantage d’etre simple a implementer et d’avoir aussi de bonnes performances comparativement a d’autres mesures de similarite [Lin 98]. Neanmoins, cette mesure presente l’inconvenient suivant : dans certaines situations, la valeur de similarite de deux elements d’une ontologie contenus dans le voisinage depasse la valeur de similarite de deux elements contenus dans la meme hierarchie. Cette situation est inadequate dans le cadre de la recherche de l’information. Afin de pallier a ce probleme, nous proposons une nouvelle mesure de similarite en se basant sur la mesure de Wu et Palmer. Nous avons applique notre mesure sur une ontologie...

World Academy of Science, Engineering and Technology, International Journal of Computer, Electrical, Automation, Control and Information Engineering, 2007

The belief K-modes method (BKM) approach is a new clustering technique handling uncertainty in th... more The belief K-modes method (BKM) approach is a new clustering technique handling uncertainty in the attribute values of objects in both the cluster construction task and the classification one. Like the standard version of this method, the BKM results depend on the chosen initial modes. So, one selection method of initial modes is developed, in this paper, aiming at improving the performances of the BKM approach. Experiments with several sets of real data show that by considered the developed selection initial modes method, the clustering algorithm produces more accurate results. Keywords—Clustering, Uncertainty, Belief function theory, Belief K-modes Method, Initial modes selection.

Resume. Un probleme important de la production automatique de regles de classification concerne l... more Resume. Un probleme important de la production automatique de regles de classification concerne la duree de generation de ces regles ; en effet, les algorithmes mis en œuvre produisent souvent des regles pendant un certain temps assez long. Nous proposons une nouvelle methode de classification a partir d’une base de donnees images. Cette methode se situe a la jonction de deux techniques : l’algebre de P-tree et l’arbre de decision en vue d’accelerer le processus de classification et de recherche dans de grandes bases d’images. La modelisation que nous proposons se base, d’une part, sur les descripteurs visuels tels que la couleur, la forme et la texture dans le but d’indexer les images et, d’autre part, sur la generation automatique des regles de classification a l’aide d’un nouvel algorithme C4.5(P-tree). Pour valider notre methode, nous avons developpe un systeme baptise C.I.A.D.P-tree qui a ete implemente et confronte a une application reelle dans le domaine du traitement d’image...

Association rule mining (ARM) problem has been extensively tackled in the context of perfect data... more Association rule mining (ARM) problem has been extensively tackled in the context of perfect data. However, real applications showed that data are often imperfect (incomplete and/or uncertain) which leads to the need of ARM algorithms that process imperfect databases. In this paper we propose a new algorithm for mining frequent itemsets from evidential databases. We introduce a new structure called RidLists that is the vertical representation of the evidential database. Our structure is adapted to itemsets belief computation which makes the mining algorithm more ecient. Experimental results showed that our proposed algorithm is ecient in comparison with the only evidential ARM algorithm in the literature [10].

La recherche d’informations pertinentes sur le web est considérée comme un nouveau besoin de la s... more La recherche d’informations pertinentes sur le web est considérée comme un nouveau besoin de la société de l’information. Les méthodes de traitement d’informations fondées sur les statistiques ne sont plus suffisantes pour répondre aux besoins des utilisateurs afin de manipuler (rechercher, traduire, résumer...) les informations sur le web. Un constat tend à s’imposer : introduire plus de sémantique pour la recherche d’informations pertinentes issues des textes. En effet, lorsque l’utilisateur du web lance sa requête, il s’attend généralement à trouver précisément ce qu’il cherche, c’est à dire trouver « l’information pertinente », sans qu’il soit submergé par un volume de réponses non-maîtrisables et ingérables. Dans ce travail, nous présentons une approche permettant la recherche de documents sur le web prenant en compte des critères temporels. Notre approche est parente des projets en cours visant à améliorer les résultats des moteurs de recherche [Lawrence et al., 2001] [Glover ...

This paper proposes a new anytime possibilistic inference algorithm for min-based directed networ... more This paper proposes a new anytime possibilistic inference algorithm for min-based directed networks. Our algorithm departs from a direct adaptation of probabilistic propagation algorithms since it avoids the transformation of the initial network into a junction tree which is known to be a hard problem. The proposed algorithm is composed of several, local stabilization, procedures. Stabilization procedures aim to guarantee that local distributions defined on each node are coherent with respect to the ones of its parents. We provide experimental results which, for instance, compare our algorithm with the ones based on a direct adaptation of probabilistic propagation algorithms.

In this paper a genetic algorithm-based approach is developed to solve the variation of the strad... more In this paper a genetic algorithm-based approach is developed to solve the variation of the straddle carriers problem. This problem is solved in the context of optimizing loading operations of outbound containers in a seaport container terminal. The contribution of the work lies in the formulation and subsequent development of a solution strategy for the problem. A numerical experimentation is carried out in order to evaluate the performance and the efficiency of the solution.

Automated negotiation is a process by which competitors aim to reach agreement by using suitable ... more Automated negotiation is a process by which competitors aim to reach agreement by using suitable strategies. This paper aims to enhance negotiation process by using theoretical techniques that help agents to reach final agreement with shorten trade time. The purpose is to succeed negotiation process with better resource utilization. The proposed techniques are based on game theory to support the decision of rational agents to offer the better acceptable proposal in a specific negotiation thread. The designed model has been evaluated by extensive experiments.

The Green Vehicle Routing Problem (GVRP) is an extension of the standard VRP taking into account ... more The Green Vehicle Routing Problem (GVRP) is an extension of the standard VRP taking into account the awareness of companies and governments of the dangerous effect of gases emissions. The primary objective of the GVRP is to minimize the volume of emitted carbon dioxide (co2) in adding to the optimization of the traveled distance and other functional objectives. In this paper, we model the GVRP as a bi-objective optimization problem for which many solving algorithms can be adapted and applied including deferent variants and extensions of Multi-Objective Genetic Algorithms (MOGAs). We select three elitist MOGAs: Non-dominated Sorting Genetic Algorithm II (NSGA-II), Strength Pareto Evolutionary Algorithm II (SPEA-II) and the Indicator-Based Evolutionary Algorithm (IBEA) to evaluate the quality of the returned Pareto fronts using deferent metrics: computation time, traveled distance, emissions volume, generational distance, spacing, entropy, and contribution. The comparison is performed...