Browsing by Author "Boustil, Amel"

Now showing 1 - 4 of 4

An enhanced whale optimization algorithm with opposition-based learning for LEDs placement in indoor VLC systems
(Elsevier, 2023) Benayad, Abdelbaki; Boustil, Amel; Meraihi, Yassine; Mirjalili, Seyedali; Yahia, Selma; Taleb, Sylia Mekhmoukh
Visible Light Communication (VLC) is a new technology that has attracted lately much interest from researchers and academics. It allows communication between users using photo-detectors (PDs) as receivers and light emitting diodes (LEDs) as transmitters. The deployment of LEDs in indoor VLC Systems is an important issue that affects the coverage of the network. In this article, we propose an improved version of Whale Optimization Algorithm, named EWOA, to resolve the LEDs placement problem in indoor visible light communication (VLC) systems. The EWOA is based on the integration of chaotic map concept and Opposition based learning method (OBL) into the standard WOA to improve its optimization performance. By taking into account the user throughput and coverage metrics while employing several produced instances and evaluating results against some meta-heuristics, the usefulness of EWOA was confirmed. The meta-heuristics that we used in the comparison are WOA, (MRFO) Manta Ray Foraging Optimizer, (CHIO) Herd immunity coronavirus optimizer, (MPA) Marine Predator Algorithm, (BA) Bat Algorithm, and (PSO) Particle Swarm Optimizer. The results showed that EWOA is more effective in finding optimal LEDs positions.
Handling qualitative conditional preference queries in SPARQL: Possibilistic logic approach
(2023) Touazi, Faycal; Boustil, Amel
Because of the rise in data volume of knowledge bases that are being published as a result of Open Data initiatives, new approaches are required to assist users in locating the items that most closely matches their preference criteria. In many approaches, the user is called to supply quantitative weights that may not be known in advance to manage the ranking of results. Contrary to the quantitative technique, preference criteria are sometimes more intuitive and can be conveyed more readily under the qualitative approach. We are interested in this paper to the problem of evaluating SPARQL qualitative preference queries over user preferences in SPARQL. Many approaches address this problem based on dif- ferent frameworks as CP-net, skyline, fuzzy set and top-k. This article outlines a novel approach for dealing with SPARQL preference queries, where preferences are represented through symbolic weights using the possibilistic logic frame- work. It is possible to manage symbolic weights without using numerical values where a partial ordering is used instead. This approach is compared to numerous other approaches, including those based on skylines, fuzzy sets, and CP-nets
Solving the LEDs placement problem in indoor VLC system using a hybrid coronavirus herd immunity optimizer
(Springer Nature, 2024) Benayad, Abdelbaki; Boustil, Amel; Meraihi, Yassine; Yahia, Selma; Mekhmoukh Taleb, Sylia; Ait Saadi, Amylia; Ramdane-Cherif, Amar
Visible light communication (VLC) is a developing technology enabling simultaneous illumination and communication between users. This is achieved by employing light emitting diodes (LEDs) as transmitters and photo-detectors (PDs) as receivers. In indoor visible light communication (VLC) systems, a significant challenge is the deployment of a various number of LEDs that accommodate different numbers of users. This particular problem falls under the category of Non-deterministic polynomial-time hard (NP-hard), making it difficult to find exact solutions in a reasonable amount of time. As a result, employing approximation approaches, particularly meta-heuristics, proves to be a suitable and effective way to address this challenge. In this paper, we propose a hybrid approach (ICHIO-FA) based on the combination of improved coronavirus herd immunity optimizer (ICHIO) with firefly algorithm (FA) for solving the LEDs placement problem in an indoor VLC system. In the proposed ICHIO-FA algorithm, the chaotic map concept is adopted to increase the chaotic stochastic behavior of the CHIO. Moreover, the opposition-based learning (OBL) mechanism is applied to enhance the convergence speed of CHIO and explore the search space effectively. Finally, FA is used as a local search method for ICHIO to avoid trapping into local optima. The effectiveness of the proposed ICHIO-FA algorithm is tested on several scenarios under different settings, taking into account the throughput and user coverage metrics. Simulation results demonstrate the accuracy and superiority of the ICHIO-FA approach in finding optimal LEDs positions when compared with the standard CHIO, FA, particle swarm optimization (PSO), genetic algorithm (GA), marine predators algorithm (MPA), whale optimization algorithm (WOA), manta ray foraging optimization (MRFO), bat algorithm (BA), grey wolf optimizer (GWO), and simulated annealing (SA).
Web apis composition based on Knowledge Graph Word Embedding and Entity Linking
(Institute of Electrical and Electronics Engineers Inc, 2023) Boustil, Amel; Tabet, Youcef
Relying on ontological relationships which ensure the matching between parameters of Web API operations (inputs and outputs) is not enough to achieve semantic composition in the context of a Knowledge base (KB). In this paper, these parameters of Web API operations are related to entities of a given KB and the word embedding is integrated with the semantic ontological relationships between these entities to extend the user query to their similar entities. Extending the query by equivalent, plugIn, and contextual entities guides the process of generating the dependency graph composition. Our composition approach adds semantics and enhances the matchmaking algorithm within the KB context. Grounded on a developed dataset, our experiments show the accuracy of our composition algorithm.