Skip to content

Machine Learning @ the Extreme Edge

One of the challenges today is real-time and energy-efficient information extraction and processing at the edge by using Artificial Intelligence. However, there is a recent trend to implement machine learning on end-point devices. These end-point devices are located on the extreme edge, the border between the analog (physical world) and the digital world. They consist of one or more sensors and a resource-constrained embedded device, a device with a limited amount of memory, computing power and power consumption. Today's challenge is to develop accurate, energy-efficient machine learning models that can be deployed on these end-point devices.


workflow


Machine Learning at the Extreme Edge (ML@E2dge) looks at how a developer can apply machine learning in the development of accurate, energy-efficient, and intelligent (wireless) (battery-powered) end-point devices and systems. Starting from a case study (estimation of spatio-temporal parameters), a machine learning model is developed, optimized and deployed. In the project, we limit ourselves to a supervised machine learning regression problem. In the project open-source software frameworks such as scikit-learn, TensorFlow and Keras are used, in combination with Edge Impulse Studio. For experiment tracking, the MLOps tool Weights and Biases is used.
The outcome of the project is a data- and machine learning pipeline (workflow) that illustrates how to solve a embedded machine learning problem.

Project Supervisory Group

The supervisory group operates as a soundboard towards the implementation possibilities of the project results.

  • Zorginstelling Heder
  • Centre for Health and Technology, University of Antwerp
  • Capetech BVBA
  • Faculty of Rehabilitation Sciences, Rehabilitation Research Group (Reval), Hasselt University
  • Departement of Rehabilitation Sciences and Physiotherapy Research group MOVANT, University of Antwerp
  • Edge Impulse Inc.
  • Comate Engineering & Design BVBA
  • VR Base
  • Hersenletsel Liga
  • Centre of Expertise The Cycle of Care, Karel de Grote University of Applied Sciences and Arts