Filters








7 Hits in 5.7 sec

Distributed temporal graph analytics with GRADOOP

Christopher Rost, Kevin Gomez, Matthias Täschner, Philip Fritzsche, Lucas Schons, Lukas Christ, Timo Adameit, Martin Junghanns, Erhard Rahm
2021 The VLDB journal  
Built on a distributed dataflow system, large temporal graphs can be processed on a shared-nothing cluster.  ...  A declarative analytical language called GrALa allows analysts to flexibly define analytical graph workflows by composing different operators that support temporal graph analysis.  ...  Tegra [36] provides ad hoc queries on arbitrary time windows on evolving graphs, represented as a sequence of immutable snapshots.  ... 
doi:10.1007/s00778-021-00667-4 fatcat:3rbroxyhpzc5hlxkrasqicqbre

D1.1: COLLABS Innovations for Industrial IoT Systems1

Miloš Radovanović, Wafa Ben Jaballah, George Bravos, Erwan Le-Disez, Ernesto Gomez Marin, Erwin Moed, Md Masoom Rabbani, Valerio Senni, Fabio Federici, George Spanoudakis, Konstantinos Fysarakis, Martin Wimmer (+2 others)
2021 Zenodo  
Section 9 concludes the deliverable with a summary of the impacts of the new SotA on project implementation and the outlook of its contribution.  ...  It thus contains one section for each technological area listed as a target for advance in Section 1.4.1. of the proposal which describes the project's offerings beyond the SotA.  ...  Ezeme et al. (2019) present a deep learning approach to distributed anomaly detection based on RNNs, introducing a multi-node ad-hoc network that uses a novel offloading scheme to bring an online anomaly  ... 
doi:10.5281/zenodo.5256842 fatcat:xf4y27mcjvbwvfjxy7lo4kwqw4

D1.1 - State of the Art Analysis

Danilo Ardagna
2021 Zenodo  
., devices with intelligence and data processing capabilities), providing resource efficiency, performance, data privacy, and security guarantees.  ...  It examines the standardisation and opensource landscape, where many of the emerging standards are mainly focused on the network layer, also highlighting opportunities for open-source community involvement  ...  on ML are favoured over analytical models.  ... 
doi:10.5281/zenodo.6372377 fatcat:f6ldfuwivbcltew4smiiwphfty

Modeling the 3D Milky Way using Machine Learning with Gaia and infrared surveys [article]

David Cornu
2020 arXiv   pre-print
In a second part, I will propose a new method for reconstructing the 3D extinction distribution of the MW based on Convolutional Neural Networks (CNN).  ...  Our ML classifier is based on Artificial Neural Networks (ANN) and uses IR data from the Spitzer space telescope to reconstruct the YSO classification automatically from given examples.  ...  They reveal some of the major limitations of these approaches: (i) it is difficult to recover spatially coherent structures between line of sights without adding an ad-hoc correlation, (ii) once a first  ... 
arXiv:2010.01431v2 fatcat:pd7w4q3nijdp5mrxozon2z3mmq

Automated methodologies for mapping convolutional neural networks on reconfigurable hardware

Stylianos Venieris, Christos-Savvas Bouganis, Engineering And Physical Sciences Research Council
2019
The contributions of this work include: an analytical model for representing both ConvNet workloads and hardware mappings, together with a ConvNet-to-FPGA toolflow for the automated generation of ConvNet  ...  architectural optimisations for state-of-the-art ConvNets with irregular connectivity, together with the corresponding mapping methodology; and a toolflow for the parallel deployment of multiple ConvNets on  ...  In this respect, we investigate the performance efficiency of f-CNN x on Zynq Z-7045 in relation to the widely used NVIDIA Tegra X1 (TX1).  ... 
doi:10.25560/68017 fatcat:425voo5tg5cebp7mmcrqpdilsy

Managing Event-Driven Applications in Heterogeneous Fog Infrastructures

Patrick Wiener, York Sure-Vetter
2022
This allows to evolve present event processing systems and advances the democratization of event-driven [...]  ...  Based on the widely used event processing paradigm, event-driven applications allow to analyze data in the form of event streams in order to extract relevant information in a timely manner.  ...  This provided the ability to exploit computational resources in close proximity and in an ad-hoc fashion when needed. Operation Phase.  ... 
doi:10.5445/ir/1000143430 fatcat:3v3zq5irrbgj7lrdebxc63fo3i

Hardware/Software Design of Dynamic Real-Time Schedulers for Embedded Multiprocessor Systems

Primiano <1986> Tucci, Antonio Corradi
2013
One of these has been represented by timekeeping. In this regard, a further contribution is represented by a novel data structure, called addressable binary heap (ABH).  ...  The first contribution is represented by an open-source scheduling framework, which is capable of realizing complex multiprocessor scheduling policies, such as G-EDF, on conventional operating systems  ...  In this sense, if we narrow the focus to more specific and constrained scenarios, such as the embedded real-time one, the introduction of an ad-hoc infrastructure which properly masquerades the underlying  ... 
doi:10.6092/unibo/amsdottorato/5594 fatcat:prerpsgocfcu3ccjismfneefxy