References of "Bouvry, Pascal 50001021"
     in
Bookmark and Share    
Full Text
Peer Reviewed
See detailProtection of Personal Data in High Performance Computing Platform for Scientific Research Purposes
Paseri, Ludovica; Varrette, Sébastien UL; Bouvry, Pascal UL

in Proc. of the EU Annual Privacy Forum (APF) 2021 (2021, June)

The Open Science projects are also aimed at strongly encouraging the use of Cloud technologies and High Performance Computing (HPC), for the benefit of European researchers and universities. The emerging ... [more ▼]

The Open Science projects are also aimed at strongly encouraging the use of Cloud technologies and High Performance Computing (HPC), for the benefit of European researchers and universities. The emerging paradigm of Open Science enables an easier access to expert knowledge and material; however, it also raises some challenges regarding the protection of personal data, considering that part of the research data are personal data thus subjected to the EU’s General Data Protection Regulation (GDPR). This paper investigates the concept of scientific research in the field of data protection, with regard both to the European (GDPR) and national (Luxembourg Data Protection Law) legal framework for the compliance of the HPC technology. Therefore, it focuses on a case study, the HPC platform of the University of Luxembourg (ULHPC), to pinpoint the major data protection issues arising from the processing activities through HPC from the perspective of the HPC platform operators. Our study illustrates where the most problematic aspects of compliance lie. In this regard, possible solutions are also suggested, which mainly revolve around (1) standardisation of procedures; (2) cooperation at institutional level; (3) identification of guidelines for common challenges. This research is aimed to support legal researchers in the field of data protection, in order to help deepen the understanding of HPC technology’s challenges and universities and research centres holding an HPC platform for research purposes, which have to address the same issues. [less ▲]

Detailed reference viewed: 90 (6 UL)
Full Text
Peer Reviewed
See detailComparing elementary cellular automata classifications with a convolutional neural network
Comelli, Thibaud; Pinel, Frederic UL; Bouvry, Pascal UL

in Proceedings of International Conference on Agents and Artificial Intelligence (ICAART) (2021, February 05)

Elementary cellular automata (ECA) are simple dynamic systems which display complex behaviour from simple local interactions. The complex behaviour is apparent in the two-dimensional temporal evolution of ... [more ▼]

Elementary cellular automata (ECA) are simple dynamic systems which display complex behaviour from simple local interactions. The complex behaviour is apparent in the two-dimensional temporal evolution of a cellular automata, which can be viewed as an image composed of black and white pixels. The visual patterns within these images inspired several ECA classifications, aimed at matching the automatas’ properties to observed patterns, visual or statistical. In this paper, we quantitatively compare 11 ECA classifications. In contrast to the a priori logic behind a classification, we propose an a posteriori evaluation of a classification. The evaluation employs a convolutional neural network, trained to classify each ECA to its assigned class in a classification. The prediction accuracy indicates how well the convolutional neural network is able to learn the underlying classification logic, and reflects how well this classification logic clusters patterns in the temporal evolution. Results show different prediction accuracy (yet all above 85%), three classifications are very well captured by our simple convolutional neural network (accuracy above 99%), although trained on a small extract from the temporal evolution, and with little observations (100 per ECA, evolving 513 cells). In addition, we explain an unreported ”pathological” behaviour in two ECAs. [less ▲]

Detailed reference viewed: 88 (8 UL)
Full Text
Peer Reviewed
See detailA Distributed Pareto-based Path Planning Algorithm for Autonomous Unmanned Aerial Vehicles (Extended Abstract)
Samir Labib, Nader UL; Danoy, Grégoire UL; Brust, Matthias R. UL et al

Scientific Conference (2021, January 07)

Autonomous Unmanned Aerial Vehicles (UAVs) are in increasing demand thanks to their applicability in a wide range of domains. However, to fully exploit such potential, UAVs should be capable of ... [more ▼]

Autonomous Unmanned Aerial Vehicles (UAVs) are in increasing demand thanks to their applicability in a wide range of domains. However, to fully exploit such potential, UAVs should be capable of intelligently planning their collision-free paths as that impacts greatly the execution quality of their applications. While being a problem well addressed in literature, most presented solutions are either computationally complex centralised approaches or ones not suitable for the multiobjective requirements of most UAV use-cases. This extended abstract introduces ongoing research on a novel distributed Pareto path planning algorithm incorporating a dynamic multi-criteria decision matrix allowing each UAV to plan its collision-free path relying on local knowledge gained via digital stigmergy. The article presents some initial simulations results of a distributed UAV Traffic Management system (UTM) on a weighted multilayer network. [less ▲]

Detailed reference viewed: 153 (30 UL)
Full Text
Peer Reviewed
See detailCommunity Detection in Complex Networks: A Survey on Local Approaches
Esmaeilzadeh Dilmaghani, Saharnaz UL; Brust, Matthias R. UL; Danoy, Grégoire UL et al

Scientific Conference (2021)

Early approaches of community detection algorithms often depend on the network’s global structure with a time complexity correlated to the network size. Local algorithms emerged as a more efficient ... [more ▼]

Early approaches of community detection algorithms often depend on the network’s global structure with a time complexity correlated to the network size. Local algorithms emerged as a more efficient solution to deal with large-scale networks with millions to billions of nodes. This methodology has shifted the attention from global structure towards the local level to deal with a network using only a portion of nodes. Investigating the state-of-the-art, we notice the absence of a standard definition of locality between community detection algorithms. Different goals have been explored under the local terminology of community detection approaches that can be misunderstood. This paper probes existing contributions to extract the scopes where an algorithm performs locally. Our purpose is to interpret the concept of locality in community detection algorithms. We propose a locality exploration scheme to investigate the concept of locality at each stage of an existing community detection workflow. We summarized terminologies concerning the locality in the state-of-the-art community detection approaches. In some cases, we observe how different terms are used for the same concept. We demonstrate the applicability of our algorithm by providing a review of some algorithms using our proposed scheme. Our review highlights a research gap in community detection algorithms and initiates new research topics in this domain. [less ▲]

Detailed reference viewed: 172 (18 UL)
Full Text
Peer Reviewed
See detailInnovation Networks from Inter-organizational Research Collaborations
Esmaeilzadeh Dilmaghani, Saharnaz UL; Piyatumrong, Apivadee UL; Danoy, Grégoire UL et al

in Heuristics for Optimization and Learning (2020)

We consider the problem of automatizing network generation from inter-organizational research collaboration data. The resulting networks promise to obtain crucial advanced insights. In this paper, we ... [more ▼]

We consider the problem of automatizing network generation from inter-organizational research collaboration data. The resulting networks promise to obtain crucial advanced insights. In this paper, we propose a method to convert relational data to a set of networks using a single parameter, called Linkage Threshold (LT). To analyze the impact of the LT-value, we apply standard network metrics such as network density and centrality measures on each network produced. The feasibility and impact of our approach are demonstrated by using a real-world collaboration data set from an established research institution. We show how the produced network layers can reveal insights and patterns by presenting a correlation matrix. [less ▲]

Detailed reference viewed: 104 (17 UL)
Full Text
Peer Reviewed
See detailAutomating the Design of Efficient Distributed Behaviours for a Swarm of UAVs
Duflo, Gabriel UL; Danoy, Grégoire UL; Talbi, El-Ghazali UL et al

in IEEE Symposium Series on Computational Intelligence, Canberra 1-4 December 2020 (2020, December)

The usage of Unmanned Aerial Vehicles (UAVs) is gradually gaining momentum for commercial applications. The vast majority considers a single UAV, which comes with several constraints such as its range of ... [more ▼]

The usage of Unmanned Aerial Vehicles (UAVs) is gradually gaining momentum for commercial applications. The vast majority considers a single UAV, which comes with several constraints such as its range of operations or the number of sensors it can carry. Using multiple autonomous UAVs simultaneously as a swarm makes it possible to overcome these limitations. However, manually designing complex emerging behaviours like swarming is a difficult and tedious task especially for such distributed systems which performance is hardly predictable. This article therefore proposes to automate the design of UAV swarming behaviours by defining a multi-objective optimisation problem, so called Coverage of a Connected-UAV Swarm (CCUS), and designing a Q-Learning based Hyper-Heuristic (QLHH) for generating distributed CCUS heuristics. Experimental results demonstrate the capacity of QLHH to generate efficient heuristics for any instance from a given class. [less ▲]

Detailed reference viewed: 107 (30 UL)
Full Text
Peer Reviewed
See detailLocal Community Detection Algorithm with Self-defining Source Nodes
Esmaeilzadeh Dilmaghani, Saharnaz UL; Brust, Matthias R. UL; Danoy, Grégoire UL et al

in Complex Networks & Their Applications IX (2020, September 01)

Surprising insights in community structures of complex networks have raised tremendous interest in developing various kinds of community detection algorithms. Considering the growing size of existing ... [more ▼]

Surprising insights in community structures of complex networks have raised tremendous interest in developing various kinds of community detection algorithms. Considering the growing size of existing networks, local community detection methods have gained attention in contrast to global methods that impose a top-down view of global network information. Current local community detection algorithms are mainly aimed to discover local communities around a given node. Besides, their performance is influenced by the quality of the source node. In this paper, we propose a community detection algorithm that outputs all the communities of a network benefiting from a set of local principles and a self-defining source node selection. Each node in our algorithm progressively adjusts its community label based on an even more restrictive level of locality, considering its neighbours local information solely. Our algorithm offers a computational complexity of linear order with respect to the network size. Experiments on both artificial and real networks show that our algorithm gains moreover networks with weak community structures compared to networks with strong community structures. Additionally, we provide experiments to demonstrate the ability of the self-defining source node of our algorithm by implementing various source node selection methods from the literature. [less ▲]

Detailed reference viewed: 79 (13 UL)
Full Text
Peer Reviewed
See detailPerformance Analysis of Distributed and Scalable Deep Learning
Mahon, S.; Varrette, Sébastien UL; Plugaru, Valentin UL et al

in 20th IEEE/ACM Intl. Symp. on Cluster, Cloud and Internet Computing (CCGrid'20) (2020, May)

With renewed global interest for Artificial Intelligence (AI) methods, the past decade has seen a myriad of new programming models and tools that enable better and faster Machine Learning (ML). More ... [more ▼]

With renewed global interest for Artificial Intelligence (AI) methods, the past decade has seen a myriad of new programming models and tools that enable better and faster Machine Learning (ML). More recently, a subset of ML known as Deep Learning (DL) raised an increased interest due to its inherent ability to tackle efficiently novel cognitive computing applications. DL allows computational models that are composed of multiple processing layers to learn in an automated way representations of data with multiple levels of abstraction, and can deliver higher predictive accuracy when trained on larger data sets. Based on Artificial Neural Networks (ANN), DL is now at the core of state of the art voice recognition systems (which enable easy control over e.g. Internet-of- Things (IoT) smart home appliances for instance), self-driving car engine, online recommendation systems. The ecosystem of DL frameworks is fast evolving, as well as the DL architectures that are shown to perform well on specialized tasks and to exploit GPU accelerators. For this reason, the frequent performance evaluation of the DL ecosystem is re- quired, especially since the advent of novel distributed training frameworks such as Horovod allowing for scalable training across multiple computing resources. In this paper, the scalability evaluation of the reference DL frameworks (Tensorflow, Keras, MXNet, and PyTorch) is performed over up-to-date High Performance Comput- ing (HPC) resources to compare the efficiency of differ- ent implementations across several hardware architectures (CPU and GPU). Experimental results demonstrate that the DistributedDataParallel features in the Pytorch library seem to be the most efficient framework for distributing the training process across many devices, allowing to reach a throughput speedup of 10.11 when using 12 NVidia Tesla V100 GPUs when training Resnet44 on the CIFAR10 dataset. [less ▲]

Detailed reference viewed: 142 (13 UL)
Full Text
Peer Reviewed
See detailPrivacy and Security of Big Data in AI Systems:A Research and Standards Perspective
Esmaeilzadeh Dilmaghani, Saharnaz UL; Brust, Matthias R. UL; Danoy, Grégoire UL et al

in 2019 IEEE International Conference on Big Data (Big Data), 9-12 December 2019 (2020, February 24)

Detailed reference viewed: 325 (27 UL)
Full Text
Peer Reviewed
See detailEvolving a Deep Neural Network Training Time Estimator
Pinel, Frédéric UL; Yin, Jian-xiong; Hundt, Christian UL et al

in Communications in Computer and Information Science (2020, February)

We present a procedure for the design of a Deep Neural Net- work (DNN) that estimates the execution time for training a deep neural network per batch on GPU accelerators. The estimator is destined to be ... [more ▼]

We present a procedure for the design of a Deep Neural Net- work (DNN) that estimates the execution time for training a deep neural network per batch on GPU accelerators. The estimator is destined to be embedded in the scheduler of a shared GPU infrastructure, capable of providing estimated training times for a wide range of network architectures, when the user submits a training job. To this end, a very short and simple representation for a given DNN is chosen. In order to compensate for the limited degree of description of the basic network representation, a novel co-evolutionary approach is taken to fit the estimator. The training set for the estimator, i.e. DNNs, is evolved by an evolutionary algorithm that optimizes the accuracy of the estimator. In the process, the genetic algorithm evolves DNNs, generates Python-Keras programs and projects them onto the simple representation. The genetic operators are dynamic, they change with the estimator’s accuracy in order to balance accuracy with generalization. Results show that despite the low degree of information in the representation and the simple initial design for the predictor, co-evolving the training set performs better than near random generated population of DNNs. [less ▲]

Detailed reference viewed: 108 (12 UL)
Full Text
Peer Reviewed
See detailBayesian optimisation to select Rössler system parameters used in Chaotic Ant Colony Optimisation for Coverage
Rosalie, Martin; Kieffer, Emmanuel UL; Brust, Matthias R. UL et al

in Journal of Computational Science (2020), 41

Detailed reference viewed: 123 (26 UL)
Full Text
Peer Reviewed
See detailTackling Large-Scale and Combinatorial Bi-Level Problems With a Genetic Programming Hyper-Heuristic
Kieffer, Emmanuel UL; Danoy, Grégoire UL; Brust, Matthias R. UL et al

in IEEE Transactions on Evolutionary Computation (2020), 24(1), 44--56

Detailed reference viewed: 88 (12 UL)
Full Text
Peer Reviewed
See detailAutonomous Flight of Unmanned Aerial Vehicles Using Evolutionary Algorithms
Gaudín, Américo; Madruga, Gabriel; Rodríguez, Carlos et al

in High Performance Computing (2020)

This article explores the application of evolutionary algorithms and agent-oriented programming to solve the problem of searching and monitoring objectives through a fleet of unmanned aerial vehicles. The ... [more ▼]

This article explores the application of evolutionary algorithms and agent-oriented programming to solve the problem of searching and monitoring objectives through a fleet of unmanned aerial vehicles. The subproblem of static off-line planning is studied to find initial flight plans for each vehicle in the fleet, using evolutionary algorithms to achieve compromise values between the size of the explored area, the proximity of the vehicles, and the monitoring of points of interest defined in the area. The results obtained in the experimental analysis on representative instances of the surveillance problem indicate that the proposed techniques are capable of computing effective flight plans. [less ▲]

Detailed reference viewed: 170 (29 UL)
Full Text
Peer Reviewed
See detailReducing overfitting and improving generalization in training convolutional neural network under limited sample sizes in image recognition
Thanapol, Panissara UL; Lavangnananda, Kittichai; Bouvry, Pascal UL et al

in 5th International Conference on Information Technology, Bangsaen 21-22 October 2020 (2020)

Detailed reference viewed: 63 (3 UL)
Full Text
Peer Reviewed
See detailA Cooperative Coevolutionary Approach to Maximise Surveillance Coverage of UAV Swarms
Stolfi Rosso, Daniel UL; Brust, Matthias R. UL; Danoy, Grégoire UL et al

in IEEE 17th Annual Consumer Communications & Networking Conference CCNC 2020, Las Vegas, NV, USA, January 10-13, 2020 (2020)

Detailed reference viewed: 95 (13 UL)
Full Text
Peer Reviewed
See detailDesign Challenges of Trustworthy Artificial Intelligence Learning Systems
Brust, Matthias R. UL; Bouvry, Pascal UL; Danoy, Grégoire UL et al

in Intelligent Information and Database Systems - 12th Asian Conference ACIIDS 2020, Phuket, Thailand, March 23-26, 2020, Companion Proceedings (2020)

Detailed reference viewed: 93 (14 UL)
Full Text
Peer Reviewed
See detailNGAP: a novel hybrid metaheuristic algorithm for round-trip carsharing fleet planning
Changaival, Boonyarit UL; Danoy, Grégoire UL; Kliazovich et al

in GECCO '20: Genetic and Evolutionary Computation Conference, Companion Volume, Cancún, Mexico, July 8-12, 2020 (2020)

Detailed reference viewed: 90 (12 UL)
Full Text
Peer Reviewed
See detailAutomated design of efficient swarming behaviours: a Q-learning hyper-heuristic approach
Duflo, Gabriel UL; Danoy, Grégoire UL; Talbi, El-Ghazali UL et al

in GECCO '20: Genetic and Evolutionary Computation Conference, Companion Volume, Cancún, Mexico, July 8-12, 2020 (2020)

Detailed reference viewed: 95 (14 UL)