Search Results (8)

Graphics Processing Units (GPUs) are employed for their parallel processing capabilities, which are essential to train deep learning (DL) models with large datasets within a reasonable time. However, the diverse GPU architectures exhibit variability in training performance depending on DL models. Furthermore, factors such as the number of GPUs for distributed training and batch size significantly impact training efficiency. Addressing the variability in training performance and accounting for these influential factors are critical for optimising resource usage. This paper presents a scheduling policy for DL training tasks in a heterogeneous GPU cluster. It builds upon a model-similarity-based scheduling policy by implementing a round-based mechanism and job packing. The round-based mechanism allows the scheduler to adjust its scheduling decisions periodically, whereas job packing optimises GPU utilisation by fitting additional jobs into a GPU that trains a small model. Results show that implementing a round-based mechanism reduces the makespan by approximately 29%, compared to the scenario without it. Additionally, integrating job packing further decreases the makespan by 5%. Full article

Graph clustering has received considerable attention recently, and its applications are numerous, ranging from the detection of social communities to the clustering of computer networks. It is classified as an NP-class problem, and several algorithms have been proposed with specific objectives. There also exist various quality metrics for evaluating them. Having clusters with the required density can be beneficial because it permits the effective deployment of resources. This study proposes an approach to partitioning and overlapping clustering of undirected unweighted graphs, allowing users to specify the required density of resultant clusters. This required density is achieved by means of ‘Relative Density’. The proposed algorithm adopts an edge-based approach, commencing with the determination of the edge degree for each edge. The main clustering process is then initiated by an edge with an average degree. A cluster is expanded by considering adjacent edges that can be included while monitoring the relative density of the cluster. Eight empirical networks with diverse characteristics are used to validate the proposed algorithm for both partitioning and overlapping clustering. Their results are assessed using an appropriate metric known as the mean relative density deviation coefficient (MRDDC). This is the first work that attempts to carry out partitioning and overlapping graph clustering, which allows user-specified density. Full article

The use of Unmanned Aerial Vehicles (UAVs) has shown a drastic increase in interest in the past few years. Current applications mainly depend on single UAV operations, which face critical limitations such as mission range or resilience. Using several autonomous UAVs as a swarm is a promising approach to overcome these. However, designing an efficient swarm is a challenging task, since its global behaviour emerges solely from local decisions and interactions. These properties make classical multirobot design techniques not applicable, while evolutionary swarm robotics is typically limited to a single use case. This work, thus, proposes an automated swarming algorithm design approach, and more precisely, a generative hyper-heuristic relying on multi-objective reinforcement learning, that permits us to obtain not only efficient but also reusable swarming behaviours. Experimental results on a three-objective variant of the Coverage of a Connected UAV Swarm problem demonstrate that it not only permits one to generate swarming heuristics that outperform the state-of-the-art in terms of coverage by a swarm of UAVs but also provides high stability. Indeed, it is empirically demonstrated that the model trained on a certain class of instances generates heuristics and is capable of performing well on instances with a different size or swarm density. Full article

In this article, we propose SuSy-EnGaD, a surveillance system enhanced by games of drones. We propose three different approaches to optimise a swarm of UAVs for improving intruder detection, two of them featuring a multi-objective optimisation approach, while the third approach relates to the evolutionary game theory where three different strategies based on games are proposed. We test our system on four different case studies, analyse the results presented as Pareto fronts in terms of flying time and area coverage, and compare them with the single-objective optimisation results from games. Finally, an analysis of the UAVs trajectories is performed to help understand the results achieved. Full article

In a round-trip carsharing system, stations must be located in such a way that allow for maximum user coverage with the least walking distance as well as offer certain degrees of flexibility for returning. Therefore, a balance must be stricken between these factors. Providing a satisfactory system can be translated into an optimization problem and belongs to an NP-hard class. In this article, a novel optimization model for the round-trip carsharing fleet placement problem, called Fleet Placement Problem (FPP), is proposed. The optimization in this work is multiobjective and its NP-hard nature is proven. Three different optimization algorithms: PolySCIP (exact method), heuristics, and NSGA-II (metaheuristic) are investigated. This work adopts three real instances for the study, instead of their abstracts where they are most commonly used. They are two instance:, in the city of Luxembourg (smaller and larger) and a much larger instance in the city of Munich. Results from each algorithm are validated and compared with solution from human experts. Superiority of the proposed FPP model over the traditional methods is also demonstrated. Full article

Identified in 1973, somatostatin (SST) is a cyclic hormone peptide with a short biological half-life. Somatostatin receptors (SSTRs) are widely expressed in the whole body, with five subtypes described. The interaction between SST and its receptors leads to the internalization of the ligand–receptor complex and triggers different cellular signaling pathways. Interestingly, the expression of SSTRs is significantly enhanced in many solid tumors, especially gastro-entero-pancreatic neuroendocrine tumors (GEP-NET). Thus, somatostatin analogs (SSAs) have been developed to improve the stability of the endogenous ligand and so extend its half-life. Radiolabeled analogs have been developed with several radioelements such as indium-111, technetium-99 m, and recently gallium-68, fluorine-18, and copper-64, to visualize the distribution of receptor overexpression in tumors. Internal metabolic radiotherapy is also used as a therapeutic strategy (e.g., using yttrium-90, lutetium-177, and actinium-225). With some radiopharmaceuticals now used in clinical practice, somatostatin analogs developed for imaging and therapy are an example of the concept of personalized medicine with a theranostic approach. Here, we review the development of these analogs, from the well-established and authorized ones to the most recently developed radiotracers, which have better pharmacokinetic properties and demonstrate increased efficacy and safety, as well as the search for new clinical indications. Full article

In this article, we propose a new mobility model, called Attractor Based Inter-Swarm collaborationS (ABISS), for improving the surveillance of restricted areas performed by unmanned autonomous vehicles. This approach uses different types of vehicles which explore an area of interest following unpredictable trajectories based on chaotic solutions of dynamic systems. Collaborations between vehicles are meant to cover some regions of the area which are unreachable by members of one swarm, e.g., unmanned ground vehicles on water surface, by using members of another swarm, e.g., unmanned aerial vehicles. Experimental results demonstrate that collaboration is not only possible but also emerges as part of the configurations calculated by a specially designed and parameterised evolutionary algorithm. Experiments were conducted on 12 different case studies including 30 scenarios each, observing an improvement in the total covered area up to 11%, when comparing ABISS with a non-collaborative approach. Full article

The rapid adoption of Internet of Things (IoT) has encouraged the integration of new connected devices such as Unmanned Aerial Vehicles (UAVs) to the ubiquitous network. UAVs promise a pragmatic solution to the limitations of existing terrestrial IoT infrastructure as well as bring new means of delivering IoT services through a wide range of applications. Owning to their potential, UAVs are expected to soon dominate the low-altitude airspace over populated cities. This introduces new research challenges such as the safe management of UAVs operation under high traffic demands. This paper proposes a novel way of structuring the uncontrolled, low-altitude airspace, with the aim of addressing the complex problem of UAV traffic management at an abstract level. The work, hence, introduces a model of the airspace as a weighted multilayer network of nodes and airways and presents a set of experimental simulation results using three UAV traffic management heuristics. Full article