Papers by youcef benmouna
International Journal of Communication Networks and Information Security (IJCNIS)
Spectral resources allocation is a major problem in cognitive radio ad hoc networks and currently... more Spectral resources allocation is a major problem in cognitive radio ad hoc networks and currently most of the research papers use meta-heuristics to solve it. On the other side, the term parallelism refers to techniques to make programs faster by performing several computations in parallel. Parallelism would be very interesting to increase the performance of real-time systems, especially for the cognitive radio ad hoc networks that interest us in this work. In this paper, we present a parallel implementation on a multi-core architecture of dynamic programming algorithm applied in cognitive radio ad hoc networks. Our simulations approve the desired results, showing significant gain in terms of execution time. The main objective is to allow a cognitive engine to use an exact method and to have better results compared to the use of meta-heuristics.
The analysis of microscope images can provide useful information concerning health of patients. I... more The analysis of microscope images can provide useful information concerning health of patients. In this paper a new and ecient supervised method for color image segmentation is presented. The segmentation here is to extract leukocytes (white blood cells) and separate its constituents, nucleus and cytoplasm. Since red cells, leukocytes and background had dierent color in image of bone marrow smear, they were extracted according to their own colors. First, we train an SVM in dierent color spaces by a learning set. SVM with xed parameters is used here to yield several classications, and the basic technique consists on information fusion from dierent sources via evidence theory. This combination is performed by integrating uncertainties and redundancies for each one of the color spaces. From the experiments, we achieve good segmentation performances in the entire nucleus and cytoplasm segmentation. We evaluate the segmentation performance of the proposed technique by comparing its resul...
Interference-Aware QoS Guarantees in OFDM-Based Cognitive Radio Networks Based on Branch and Bound
Wireless Personal Communications, 2021
In the past decade, the OFDM access method has been widely used in different types of networks. I... more In the past decade, the OFDM access method has been widely used in different types of networks. Indeed; OFDM is the technology of choice for all major wireless systems, including WIFI, WiMAX, 3G, 4G and 5G. In this paper, we are interested in its application within a cognitive radio networks. The main objective is to provide an acceptable quality of service for the secondary user while minimizing interference with the primary user. This problem has been formulated in the literature in the form of a multi-objective function with three modes of communication (multimedia, reliable and low battery). In this paper, we exploit the efficiency of the bounding operators of the branch and bound method in order to solve this problem. The simulation results showed the effectiveness of our proposal by comparing it with the cuckoo search algorithm which has already been validated in the literature for this type of problem. Our proposal surpasses the cuckoo search algorithm for two modes of communication in terms of fitness and execution time.
Pattern Analysis and Applications, 2019
Bayesian networks (BNs) are one of the most commonly used models for representing uncertainty in ... more Bayesian networks (BNs) are one of the most commonly used models for representing uncertainty in medical diagnosis. Learning the exact structure of a BN is a challenging problem. This paper proposes a multi-threaded branch-and-bound (B&B) method, called parallel cycle-based branch-and-bound (parallel CB-B&B). On the one hand, CB-B&B improves the standard B&B method by leveraging two heuristics, namely the branching strategy and the bounding operators; on the other hand, the learning procedure is alleviated by executing CB-B&B over a set of parallel processors. In comparison with conventional exact structure learning approaches for BN, the obtained results demonstrate that the proposed CB-B&B is efficient. On average, it produces the exact structure for BN three times faster than the standard B&B version. We also present simulations on parallel CB-B&B which show a significant gain in terms of execution time.
New Method for Bayesian Network Learning
International Journal of Pattern Recognition and Artificial Intelligence, 2018
This paper presents a new method for learning the structure of Bayesian Networks. Broadly speakin... more This paper presents a new method for learning the structure of Bayesian Networks. Broadly speaking, we leverage the Branch and Bound (B&B) to derive the best Directed Acyclic Graphs (DAGs) that describes the structure of the network. Our contribution consists in introducing two main heuristics: the first one allows the selection of the graph that has the best score among those that contain less cycles, the second one eliminates the shortest cycle from the selected graph; it aims to reduce the number of explored nodes. Our experimental study asserts that the suggested proposal improves the results for multiple data sets. These facts are confirmed by the reduction of the computation time and the memory overhead.
International Journal of Computer Applications in Technology, 2019
In this paper, we present a Pareto optimal multi-objective optimisation for parallel dynamic prog... more In this paper, we present a Pareto optimal multi-objective optimisation for parallel dynamic programming algorithm applied in cognitive radio ad hoc networks. To measure the performance of our contribution, we have used a multi-core architecture. The parallel version of the dynamic programming is implemented with the concept of Pareto. To select the most compromising solution from the Pareto front, Technique for Order Preference by Similarity to an Ideal Solution (TOPSIS) is used in this paper. We have also implemented a meta-heuristic (cuckoo search) with the Pareto principle in order to validate our proposal. Our simulations approve the desired results, showing significant gain in terms of execution time. The main objective is to allow a cognitive engine to use an exact method and to have better results compared to the use of meta-heuristics while satisfying QoS parameters.
Efficient Branch-and-Bound Algorithm for Task Scheduling in Cloud Computing
2023 13th International Conference on Advanced Computer Information Technologies (ACIT)
Uploads
Papers by youcef benmouna