Login

2021 RoEduNet Conference: Networking in Education and Research

4–6 Nov 2021
Iasi
Europe/Bucharest timezone

Contact

Session

Technologies for Future Internet

A4
5 Nov 2021, 16:00
Virtual Room A

Virtual Room A

Description

Chair Florin Manolache
TFI Virtual Room A

Presentation materials

There are no materials yet.

  1. 48. Approaching traffic congestion with Double Deep Q-Networks
    Mirabela MEDVEI (Politehnica University of Bucharest)
    05/11/2021, 16:00
    Technologies for Future Internet

    One of the recurring problems of everyday life in big urban areas is the traffic congestion. Nowadays advance in the technologies powering the Internet of Vehicles together with state-of-the-art artificial intelligence algorithms offer the means to improve traffic flow with little changes to the existing infrastructure. This paper proposes a reinforcement learning based solution to traffic...

    Go to contribution page
  2. 58. Deep Learning for Forecasting the Energy Consumption in Public Buildings
    Dr Viorica CHIFU (Technical University of Cluj-Napoca), Dr Cristina Bianca POP (Technical University of Cluj-Napoca), Dr Emil Stefan CHIFU (Technical University of Cluj-Napoca)
    05/11/2021, 16:20
    Technologies for Future Internet
    Paper presentation

    In this paper we propose a deep learning based method to forecast the energy consumption in public buildings, based on past measurements. The method integrates two neural networks, namely a Feed-Forward Neural Network and a Long-
    Short Term Memory Network. Our approach consists of three main steps: data processing, training and validation, and finally the forecasting step. We validated the...

    Go to contribution page
  3. 42. Benchmarking privacy in text classification
    Iulia FLOREA (Politehnica University of Bucharest)
    05/11/2021, 16:40
    Technologies for Future Internet
    Paper presentation

    In most Machine Learning models, the data used for training or testing is public, available to anyone who wishes to see it. New research has improved these models, by adding privacy and distributing the processing load on multiple workers in the cloud. The aim of the paper is to perform an analysis between a classical approach (in which we have access to all the data) and one in which the...

    Go to contribution page
  4. 57. Forecasting the Short-Term Energy Consumption Using Random Forests and Gradient Boosting
    Dr Emil Stefan CHIFU (Technical University of Cluj-Napoca), Dr Viorica Rozina CHIFU (Technical University of Cluj-Napoca), Dr Cristina Bianca POP (Technical University of Cluj-Napoca)
    05/11/2021, 17:00
    Technologies for Future Internet
    Paper presentation

    This paper comparatively analyzes the performance of two machine learning algorithms (i.e. Random Forests and Gradient Boosting) in the field of forecasting the energy consumption based on historical data. The two algorithms are applied
    in order to forecast the energy consumption individually, and then combined together by using a Weighted Average Ensemble Method. The comparison among the...

    Go to contribution page
  5. 59. Swarm Communication using Self Sovereign Identities
    Nicu-Cosmin URSACHE (Faculty of Computer Science, Alexandru Ioan Cuza University)
    05/11/2021, 17:20
    Technologies for Future Internet

    Swarm communication represents a communication paradigm that offers support in building and running executable choreographies that can be used to model business workflows. In the current paper we present how Self Sovereign Identities (SSIs) can be used to improve the Swarm communication. The usage of the SSIs allows us to have a decentralized way to identify entities involved in Swarm...

    Go to contribution page
Building timetable...