This paper presents a teaching-learning-based optimization algorithm for discrete large-scale multi-objective problems (DLM-TLBO). Unlike the previous variants, the learning strategy used by each individual and the acquired knowledge are defined based on its level. The proposed approach is used to solve a bi-objective object clustering task (B-OCT) in a swarm robotic system, as a case study. The simple robots have as mission the gathering of a number of objects distributed randomly, while respecting two objectives: maximizing the clustering quality, and minimizing the energy consumed by these robots. The simulation results of the proposed algorithm are compared to those obtained by the well-known algorithm NSGA-II. The results show the superiority of the proposed DLM-TLBO in terms of the quality of the obtained Pareto front approximation and convergence speed.

With the huge increase of large-scale multimedia over Internet, especially images, building Content-Based Image Retrieval (CBIR) systems for large-scale images has become a big challenge. One of the drawbacks associated with CBIR is the very long execution time. In this article, we propose a fast Content-Based Image Retrieval system using Spark (CBIR-S) targeting large-scale images. Our system is composed of two steps. (i) image indexation step, in which we use MapReduce distributed model on Spark in order to speed up the indexation process. We also use a memory-centric distributed storage system, called Tachyon, to enhance the write operation (ii) image retrieving step which we speed up by using a parallel k-Nearest Neighbors (k-NN) search method based on MapReduce model implemented under Apache Spark, in addition to exploiting the cache method of spark framework. We have showed, through a wide set of experiments, the effectiveness of our approach in terms of processing time.

Volunteer computing (VC) has become a relatively mature technique of distributed computing. It is based on exploiting the idle time of ordinary online machines with the consent of their owners. Target applications are generally scientific projects requiring a huge amount of computational resources. Existing VC platforms raise several challenges. This work attempts to bring solutions for two defeats. The first one is the involvement of volunteers; the decreasing of participants affects the global performances. To cope with this, a new social volunteer computing environment is proposed in order to involve more volunteers. The second addressed problem is the task scheduling, which aims to optimize the use of resources. The proposed algorithm generates for each resource's class, a number of tasks whose cost of execution reflects the momentary capacity of the resources. The new solutions are validated through a theory of number's project, called “Collatz Conjecture.”

With the huge increase of large-scale multimedia over Internet, especially images, building Content-Based Image Retrieval (CBIR) systems for large-scale images has become a big challenge. One of the drawbacks associated with CBIR is the very long execution time. In this article, we propose a fast Content-Based Image Retrieval system using Spark (CBIR-S) targeting large-scale images. Our system is composed of two steps. (i) image indexation step, in which we use MapReduce distributed model on Spark in order to speed up the indexation process. We also use a memory-centric distributed storage system, called Tachyon, to enhance the write operation (ii) image retrieving step which we speed up by using a parallel k-Nearest Neighbors (k-NN) search method based on MapReduce model implemented under Apache Spark, in addition to exploiting the cache method of spark framework. We have showed, through a wide set of experiments, the effectiveness of our approach in terms of processing time.

Over the past few years, multicore systems have become increasingly powerful and thereby very useful in high-performance computing. However, many applications, such as some linear algebra algorithms, still cannot take full advantage of these systems. This is mainly due to the shortage of optimization techniques dealing with irregular control structures. In particular, the well-known polyhedral model fails to optimize loop nests whose bounds and/or array references are not affine functions. This is more likely to occur when handling sparse matrices in their packed formats. In this article, we propose using 2d-packed layouts and simple affine transformations to enable optimization of triangular and banded matrix operations. The benefit of our proposal is shown through an experimental study over a set of linear algebra benchmarks.