M. SAYAD Lamri

Prof

Directory of teachers

Department

Informatics Department

Research Interests

Networks Optimization Metaheuristics Artificial intelligence

Contact Info

University of M'Sila, Algeria

Email : lamri.sayad@univ-msila.dz

On the Web:

  • Google Scholar N/A
  • ResearchGate
    ResearchGate N/A
  • ORCID N/A
  • SC
    Scopus N/A

Recent Publications

2024-10-31

An Adaptative Eps Parameter of DBSCAN Algorithm for Identifying Clusters with Heterogeneous Density

Density-Based Spatial Clustering of Applications with Noise (DBSCAN) is one of the most important data clustering algorithms. Its importance lies in the fact that it can recognize clusters of arbitrary shapes and is not affected by noise in the data. To identify clusters, DBSCAN needs to specify two parameters: the parameter Eps, representing the radius of the circle to identify the neighborhood of each observation. The second parameter of DBSCAN is minpts, which represents the minimum size of the neighborhood for a point to be a seed in a cluster and not a noise. However, the task of determining the adequate value of Eps parameter is not easy and represents a major issue when applying DBSCAN since the accuracy of this algorithm highly depends on the values of its parameters. In this paper, we present a new version of DBSCAN where we need only to specify the minpts parameter, then we use k-nearest neighbors (kNN) algorithm to calculate the value of Eps automatically for every point in the data. This technique not only reduces the number of parameters by eliminating Eps which has been very difficult to determine, but also gives DBSCAN the ability to detect clusters with heterogeneous density. The experimental results show that the proposed method is more efficient and more accurate than the original DBSCAN algorithm.
Citation

M. SAYAD Lamri, (2024-10-31), "An Adaptative Eps Parameter of DBSCAN Algorithm for Identifying Clusters with Heterogeneous Density", [national] Computación y Sistemas , Computación y Sistemas

Read Full Paper
2024-04-01

Placement Optimization of Virtual Network Functions in a Cloud Computing Environment

The use of Network Function Virtualization is constantly increasing in Cloud environments, especially for next-generation networks such as 5G. In this context, the
definition of a deployment scheme defining for each Virtual Network Function (VNF) the appropriate server in order to meet the quality of service requirements. This problem is known in the literature as virtual fetwork function placement. However, proper deployment of VNFs on servers can minimize the number of servers used, but may increase service latency. In this article, we propose a multi-objective integer linear programming model to solve the problem of network function placement. The objective is to find the best compromise between minimizing end-to-end total latency for users and reducing the number of servers used, while ensuring that the maximum number of VNFs is connected in the network. Our proposal to solve the NP-hard problem involves developing an algorithm based on the Particle Swarm Optimization metaheuristic to obtain a polynomial time resolution. By performing tests on a simple VNF deployment problem, we validated the relevance of our optimization model and demonstrated the effectiveness of our algorithm. The results obtained showed that our method provides feasible solutions very close to the exact optimal solutions.
Citation

M. SAYAD Lamri, (2024-04-01), "Placement Optimization of Virtual Network Functions in a Cloud Computing Environment", [national] Journal of Network and Systems Management , Springer US

Read Full Paper

Mitigating congestion in multi-agent traffic signal control: an efficient self-attention proximal policy optimization approach

Traffic congestion is a persistent problem that effects cities worldwide, necessitating innovative solutions. This paper presents a novel traffic light control system using
multi-agent proximal policy optimization with self-attention. Our approach outperforms traditional methods by 30% in reducing waiting times in high-traffic demand scenarios. By utilizing transfer learning and encoding mechanisms for dynamic input size adaptation, our approach enables scalability to larger networks without the need for costly training. This study underscores the potential of our approach as a dependable solution for addressing large-scale traffic congestion challenges.
Citation

M. SAYAD Lamri, (2024-04-01), "Mitigating congestion in multi-agent traffic signal control: an efficient self-attention proximal policy optimization approach", [national] International Journal of Information Technology , Springer Nature

Read Full Paper
2023

A Review About Electric Vehicle Routing Problem with Reinforcement Learning

The Electric Vehicle Routing Problem (EVRP) is a variant of the traditional Vehicle Routing Problem (VRP) that deals explicitly with the routing and scheduling of electric vehicles (EVs). It considers EVs' unique constraints and characteristics, such as limited driving range and the need for battery charging. Reinforcement Learning (RL) is a type of machine learning that involves training an agent to make a series of decisions in an environment to maximize a reward. RL has been successfully applied to various problems, including game-playing, robotics, and decision-making under uncertainty. Some key challenges in RL include dealing with large state and action spaces, balancing exploration and exploitation, and dealing with non-stationary environments. RL has emerged as a promising approach for solving the EVRP in recent years. In the context of the EVRP, the agent could be an electric vehicle, and the environment could be a city with charging stations and customer locations. The agent's decisions encompass selecting the most optimal routes and undertaking specific actions. The reward could measure the efficiency and cost-effectiveness of the routes taken. RL can find near-optimal solutions to the EVRP in a more flexible and adaptable way than traditional optimization methods. In this review article, we will discuss the application of RL to the EVRP, the challenges, and opportunities of using RL for this problem and its variants, the current state of the art in RL-based approaches for the EVRP, and directions for future research.
Citation

M. SAYAD Lamri, (2023), "A Review About Electric Vehicle Routing Problem with Reinforcement Learning", [national] Tobacco Regulatory Science (TRS) , abdelkader.kaddour@univ-msila.dz

Read Full Paper
2022

Improving text classification using text summarization

The classification problem has been widely studied in data mining, machine learning, and information retrieval communities with applications in several domains, such as target marketing, medical diagnosis, newsgroup filtering, and document organization. In this work, we take up the challenge of improving Text Classification (TC) using Text Summarizing (TS).
Citation

M. SAYAD Lamri, Nassim Zellal, , (2022), "Improving text classification using text summarization", [international] NTIC'22 , Abdalhafid Boussouf Universty, Mila, Algeria

Read Full Paper
2020

A Chemical Reaction Algorithm to Solve the Router Node Placement in Wireless Mesh Networks

This paper considers the problem of router node placement (WMN-RNP) in wireless mesh networks (WMN). A wireless mesh network consists of three kinds of nodes: mesh clients, mesh routers and gateways interconnected via radio links. The problem considered in this paper is the following: given a set of mesh clients deployed in a rectangular area, determine the best placement of mesh routers so that both client coverage and network connectivity are maximized. This issue is known to be NP-hard since it can be modeled as a facility location problem. To solve this issue, we propose to use a metaheuristic technique inspired from the interactions between molecules in chemical reactions to reach a low stable energy state, namely Chemical Reaction Optimization algorithm (CRO). A simulation tool has been developed to compare the performance of our CRO algorithm to the existing Genetic Algorithm (GA) and Simulated Annealing (SA). Simulation results show that our proposed algorithm can improve client coverage by 4.5% to 18% (3% to 17% respectively) and network connectivity by 5% to 61% (4.5% to 41% respectively) when compared to GA algorithm (SA algorithm respectively).
Citation

M. SAYAD Lamri, (2020), "A Chemical Reaction Algorithm to Solve the Router Node Placement in Wireless Mesh Networks", [national] Mobile networks and applications , Springer US

Read Full Paper
2019

An electromagnetism-like mechanism algorithm for the router node placement in wireless mesh networks

In this paper, we consider the problem of mesh router placement in a wireless mesh network (WMN). The latter is an emerging networking technology consisting of three kinds of nodes: mesh clients, mesh routers and gateways. Mesh routers form a backbone to forward data between client nodes and the external network. Therefore, the optimization of mesh routers positions strongly influences the performance of the WMN. Since this issue has already been proved as being computationally NP-hard to solve, the use of non-exact methods (such as heuristics and metaheuristics) is indispensable. In this sense, our current work consists to apply and adapt the electromagnetism-like mechanism (EM) metaheuristic to solve the router node placement issue. The idea is to consider a population of solutions encoded as particles subject to attractions and repulsions as in electromagnetic systems. Finally, we have evaluated our proposed approach by simulating different scenarios under various settings. The obtained results indicate that the proposed EM algorithm outperforms the existing particle swarm intelligence algorithm and genetic algorithm in defining near optimal positions for mesh routers with regard to coverage and connectivity.
Citation

M. SAYAD Lamri, (2019), "An electromagnetism-like mechanism algorithm for the router node placement in wireless mesh networks", [national] Soft Computing , Springer US

Read Full Paper
2018

Towards router node placement using firefly optimization algorithm in wireless mesh networks

.



.
Citation

M. SAYAD Lamri, (2018), "Towards router node placement using firefly optimization algorithm in wireless mesh networks", [international] International symposium on informatics and its applications , msila

Read Full Paper

Les approches et outils pour l'evaluation des performances des systèmes informatiques et les réseaux de communication

..
Citation

M. SAYAD Lamri, (2018), "Les approches et outils pour l'evaluation des performances des systèmes informatiques et les réseaux de communication", [national] Doctoriales de recherche opérationnelle , Béjaia

Read Full Paper

Placement optimization of wireless mesh routers using firefly optimization algorithm

This paper addresses the problem of optimal router nodes placement (RNP) in a wireless mesh network. This issue consists to determine the optimal positions of mesh routers that allow the optimization of the network performance with regards to client coverage and network connectivity. To solve this issue, a bio-inspired algorithm, called Firefly optimization algorithm, has been applied since it is an NP-hard issue. The obtained results demonstrate the effectiveness of our proposed approach when compared to the existing genetic algorithm.
Citation

M. SAYAD Lamri, (2018), "Placement optimization of wireless mesh routers using firefly optimization algorithm", [international] 2018 International Conference on Smart Communications in Network Technologies (SaCoNeT) , EL OUED

Read Full Paper

A simulated annealing algorithm for the placement of dynamic mesh routers in a wireless mesh network with mobile clients

The placement of mesh routers in a mobile mesh network strongly influences the network performance. In particular, when the mesh clients are mobile, this deployment issue becomes more difficult to solve since mesh routers should adapt their locations to the dynamic network topology. In this letter, we propose to apply a simulated annealing algorithm to deal with the dynamic router node placement issue. The performance metrics considered when deploying these routers are: client coverage, network connectivity, and the average distance traveled by routers. Simulation results show a significant performance improvement in terms of client coverage and network connectivity and a considerable decrease in router movements.
Citation

M. SAYAD Lamri, (2018), "A simulated annealing algorithm for the placement of dynamic mesh routers in a wireless mesh network with mobile clients", [national] Internet Technology Letters , John Wiley & Sons, Ltd

Read Full Paper
2017

Optimal Placement of Mesh Routers in a Wireless Mesh Network with Mobile Mesh Clients Using Simulated Annealing

A wireless mesh network (WMN) is a set of three kinds of nodes: clients, routers and gateways. One of the most challenging issues when dealing with a WMN is how to deploy mesh routers when the positions of mesh clients are known. In this paper, we consider a dynamic router node placement problem where, in addition, mesh clients are mobile. To solve this issue, we apply the simulated annealing metaheuristic (SA). At every iteration, clients are moving from their positions to new positions engendering new network topologies. To serve these clients, routers should update their positions by moving according to the new topology. Therefore, SA algorithm is applied to determine the positions of mesh routers every time it is needed. Simulation results demonstrate that the proposed approach is promising in determining optimal positions of mesh routers.
Citation

M. SAYAD Lamri, (2017), "Optimal Placement of Mesh Routers in a Wireless Mesh Network with Mobile Mesh Clients Using Simulated Annealing", [international] 5th International Symposium on Computational and Business Intelligence (ISCBI 2017) , DUBAI

Read Full Paper

IWDRP: An Intelligent Water Drops Inspired Routing Protocol for Mobile Ad Hoc Networks

This paper deals with the problem of routing in Mobile Ad hoc Networks (MANET). A mobile ad hoc network is a collection of mobile devices deployed without any pre-established infrastructure or centralized administration. Routing is a very challenging issue since the appearance of this technology. The main goal of every routing protocol is to find a route between two communicating nodes while optimizing overall performances of the network. This paper introduces a novel routing protocol inspired from the nature and that should deal with the dynamic aspect of MANET. The used approach, called Intelligent Water Drops (IWD), mimics the processes that happen in the natural river systems, particularly, the actions that water drops perform in the rivers to find the shortest path to their destination (sea). In fact, it is observed that water drops of a river often find good paths among lots of possible paths in their ways from a source to a destination. We combined these ideas with a route failure prediction mechanism to develop a new routing protocol for MANETs called IWDRP. This prediction method is based on the received signal strength indicator. Further simulation results show that IWDRP is able to achieve better results in terms of packet delivery, end-to-end delay in comparison with AODV-BFABL. The achievement in this paper has certain reference value to the further study of the routing issue in MANETs.
Citation

M. SAYAD Lamri, (2017), "IWDRP: An Intelligent Water Drops Inspired Routing Protocol for Mobile Ad Hoc Networks", [national] Wireless Personal Communications , Springer US

Read Full Paper
2016

Application des metaheuristiques pour l'optimisation du routage dans les réseaux mobiles ad hoc

.
Citation

M. SAYAD Lamri, (2016), "Application des metaheuristiques pour l'optimisation du routage dans les réseaux mobiles ad hoc", [national] University of M'sila

Read Full Paper

On-Demand Routing Protocol with Tabu Search Based Local Route Repair in Mobile Ad Hoc Networks

This paper tackles the routing issue in mobile ad hoc networks by introducing a novel approach. The most challenging issue, when designing a routing protocol in this context, is the mobility of nodes, which engenders frequent links breakage. Therefore, most of research effort in this field should be conducted in this sense so that routing protocol will not be affected by route failures caused by link disconnections. The proposed routing protocol, called on-demand routing protocol with tabu search based local route repair, uses an intelligent technique to locally repair the failed routes. The idea is to connect the two parts of the failed route using minimum overhead and without generating loops. Hence, when a route is failed, a special packet containing a tabu list of upstream nodes (nodes of the first part the route) is launched with a minimum time-to-leave value. The motivation on using a local route repair approach rather than a new route discovery process is to save delay and to reduce control packet overhead, which leads to less network contention and less packets drop. However, this technique can lead longer routes between nodes, consequently, network performances will be worsened. To avoid this kind of situation, destination node invalidates the route when the number of repairs overtakes a given limit. Simulation results demonstrate that our proposed protocol achieves better in terms of communication delay, packet delivery ratio and control packet overhead than existing AODV-BFABL, DSR and AOMDV.
Citation

M. SAYAD Lamri, (2016), "On-Demand Routing Protocol with Tabu Search Based Local Route Repair in Mobile Ad Hoc Networks", [national] Wireless Personal Communications , Springer US

Read Full Paper
← Back to Researchers List