Search results for " Networks"

showing 4 items of 2754 documents

Recognizing Video Resolution by Monitoring Memory Metrics in Mobile Clients

2019

Content delivery is one of the most successful applications in mobile networks. Mobile edge servers are significantly contributing to the improvement of this type of applications, by also performing resolution adaptations as a function of the radio link quality observed by the users. In this paper, we face the problem of dynamically tracking the perceived video resolution by mobile clients in a mobile edge environment to guarantee an agreed Service Level Agreement (SLA). To this purpose, we propose a protocol-agnostic approach, based on monitoring some memory metrics of a running video streaming process at the mobile client, for identifying the time-varying resolution of the video content.

working set size mobile edge computing video resolution MLP networks memory metricsMobile edge computingSettore ING-INF/03 - TelecomunicazioniComputer sciencebusiness.industryRadio Link ProtocolWorking set sizeProcess (computing)Display resolutionlaw.inventionService-level agreementlawServerEnhanced Data Rates for GSM EvolutionbusinessComputer network2019 Fourth International Conference on Fog and Mobile Edge Computing (FMEC)
researchProduct

Compression and load balancing for efficient sparse matrix-vector product on multicore processors and graphics processing units

2021

We contribute to the optimization of the sparse matrix-vector product by introducing a variant of the coordinate sparse matrix format that balances the workload distribution and compresses both the indexing arrays and the numerical information. Our approach is multi-platform, in the sense that the realizations for (general-purpose) multicore processors as well as graphics accelerators (GPUs) are built upon common principles, but differ in the implementation details, which are adapted to avoid thread divergence in the GPU case or maximize compression element-wise (i.e., for each matrix entry) for multicore architectures. Our evaluation on the two last generations of NVIDIA GPUs as well as In…

workload balancingMulti-core processorComputer Networks and CommunicationsComputer sciencesparse matrix-vector productParallel computingLoad balancing (computing)coordinate sparse matrix formatSparse matrix vectorcompressionExascale computingComputer Science ApplicationsTheoretical Computer ScienceComputational Theory and MathematicsCompression (functional analysis)Product (mathematics)Graphicsgraphics processing units (GPUs)multicoreprocessors (CPUs)Software
researchProduct

Pratique et sémantique de la culture informationnelle

2015

In this paper, we present a formative experience in information literacy that can build on lasting from a reflexive, comparative approach skills; analytic and dialectic. On the theoretical side, we propose to reconcile the theories of human activity with simondiennes theories of technical culture. Trace analysis of learners permit to construct a summary ontology digital skills and shows the relevance of a semantic device training, which is part of the prospect of convergence between information cultures transliteracy kind.

écriture numériquesocial networkstrainingtransliteracydigital traces[SHS.INFO]Humanities and Social Sciences/Library and information sciencesformationculture numériquereflexivity[SHS.INFO] Humanities and Social Sciences/Library and information sciencesréseaux sociauxtraces numériques[ SHS.INFO ] Humanities and Social Sciences/Library and information sciencestranslittératieréflexivitédigital writingdigital culture
researchProduct

On-Demand Security Framework for 5GB Vehicular Networks

2023

Building accurate Machine Learning (ML) at-tack detection models for 5G and Beyond (5GB) vehicular networks requires collaboration between Vehicle-to-Everything (V2X) nodes. However, while operating collaboratively, ensuring the ML model’s security and data privacy is challenging. To this end, this article proposes a secure and privacy-preservation on-demand framework for building attack-detection ML models for 5GB vehicular networks. The proposed framework emerged from combining 5GB technologies, namely, Federated Learning (FL), blockchain, and smart contracts to ensure fair and trustedinteractions between FL servers (edge nodes) with FL workers (vehicles). Moreover, it also provides an ef…

—5G and Beyond Vehicular Networks: Computer science [C05] [Engineering computing & technology]Blockchain[SPI] Engineering Sciences [physics]Security and Privacy: Sciences informatiques [C05] [Ingénierie informatique & technologie]Federated Learning5G and Beyond Vehicular Networks
researchProduct