NL FR EN
www.belgium.be

Project Factsheets

INSERT-BD: Integrating NEETs in Society through Employment, Recruitement and Training in Belgian Defence
MONA: Miniaturized mOtion-triggered eNergy hArvester for wireless communication and battery recharging
SALTO: Secure Active Learning for Territorial Observations

INSERT-BD
Integrating NEETs in Society through Employment, Recruitement and Training in Belgian Defence

  • Theme 1: Employment of NEET (Not in Employment, Education or Training) for Belgian Defence Network
  • Key words: NEET, Sustainable employment, Labour market transitions, Recruitment, Work organisation, Military organisation

  • Duration of the project: 01/12/2021 - 30/11/2023
  • Budget: 199.725 €
  • Coordinator: Ezra Dessers (KULeuven - HIVA)
  • Partner: Delphine Resteigne (Ecole royale militaire - Koninklijke Militaire school ERM-KMS)

Documentation


Event

  • 13-12-2021 | Protocol agreement between Defence and Federal Science Policy

MONA
Miniaturized mOtion-triggered eNergy hArvester for wireless communication and battery recharging

  • Theme 2: Small Energy Harvesting systems for defence applications
  • Key words: energy harvesting and power management, sensor node, battery recharging

  • Duration of the project: 01/01/2022 - 31/12/2023
  • Budget: 399.545 €
  • Coordinator: Jean-Michel Redouté (ULiège - Microsys Laboratory)
  • Partner: Hugues Libotte (FN Herstal (FNH))

Documentation


Event

  • 13-12-2021 | Protocol agreement between Defence and Federal Science Policy

SALTO
Secure Active Learning for Territorial Observations

  • Theme: Theme 3: Space technologies for Defence applications
  • Duration of the project: 01/12/2021 - 01/12/2023
  • Budget: 271.600 €
  • Coordinator: Eric Hallot (Institut Scientifique de Service Public (ISSeP) - Remote Sensing and Geodata)
  • Partners:
    • Benoît Macq (UCLouvain)
    • Olivier Dubois - (Oscars s.a.)

Summary

Satellite images track the changing human footprint on territories, including specific changing features around major infrastructures like harbours or airports. The amount of images and their resolution is continuously increasing.
Unfortunately the size of the teams of analysts assessing the features changes in structured reports (e.g. following the STANAG structuration) remains most of the time constant.
The emergence of Convolutional Deep Neural Networks in AI is an opportunity to partly solve this issue. Automated annotations in image and automated production of structured reports has been recently proposed in the litterature through static AI.
The original approach of SALTO is to address this issue by designing new active learning algorithms which optimize the global analyst annotation budget through an optimal selection of the areas to be annotated.
SALTO will moreover provide an entrusting mechanism for coalitions of analysts sharing the same active learning model. In practice SALTO will provide a prototype of secure active learning implementation which will allow to a pool of analyst to annotate 4 times more data than without SALTO.


Event

  • 13-12-2021 | Protocol agreement between Defence and Federal Science Policy