Development of Edge Runtime Learning Systems for an Artificial Nose Classifying Drinks

Mediterranean Conference on Embedded Computing (MECO), pp. 1–5

Abstract

Smart adaptive systems are evolving rapidly. In addition to high-performance artificial intelligence from the cloud, smart edge devices are increasingly developing. They are capable of handling constantly more complex classification or even learning tasks independently. After answering the question of how this knowledge can be learned or used at the edge, it must also be determined how this knowledge can be exchanged with a cloud. We would like to investigate this exchange of knowledge between several Edge Runtime Learning Artificial Noses and a cloud intelligence in further experiments. For this purpose, we describe an improvement of our former approaches for an artificial nose. Especially, we implemented a resource-efficient edge nose with lazy learning algorithms on a microcontroller and enabled learning at runtime. This new nose achieves classification rates of up to 92 %, almost as good as the resource-intensive previous version, and forms the basis for research into the knowledge exchange between different edge and cloud AI devices and the processes involved.

Authors 10

1. Rüdiger Machhamer

   Trier University of Applied Sciences

   Affiliation as printed

   Institute for Software Systems (ISS), Trier University of Applied Sciences - Environmental Campus Birkenfeld, Birkenfeld, Rhineland Palatinate Germany

2. Marcel Garling

   Trier University of Applied Sciences

   Affiliation as printed

   Institute for Software Systems (ISS), Trier University of Applied Sciences - Environmental Campus Birkenfeld, Birkenfeld, Rhineland Palatinate Germany

3. Levin Czenkusch

   Trier University of Applied Sciences

   Affiliation as printed

   Institute for Software Systems (ISS), Trier University of Applied Sciences - Environmental Campus Birkenfeld, Birkenfeld, Rhineland Palatinate Germany

4. Kristof Ueding

   Trier University of Applied Sciences

   Affiliation as printed

   Institute for Software Systems (ISS), Trier University of Applied Sciences - Environmental Campus Birkenfeld, Birkenfeld, Rhineland Palatinate Germany

5. Achim Guldner

   Trier University of Applied Sciences

   Affiliation as printed

   Institute for Software Systems (ISS), Trier University of Applied Sciences - Environmental Campus Birkenfeld, Birkenfeld, Rhineland Palatinate Germany

6. Azhar Latif
   Affiliation as printed

   Dimvadersgatan 48, Göteborg, Sweden

7. Anke Schmeink Aachen ISEK Research and Teaching Area

   RWTH Aachen University

   Affiliation as printed

   ISEK Research and Teaching Area, RWTH Aachen University, Germany

8. Stefan Naumann

   Trier University of Applied Sciences

   Affiliation as printed

   Institute for Software Systems (ISS), Trier University of Applied Sciences - Environmental Campus Birkenfeld, Birkenfeld, Rhineland Palatinate Germany

9. Klaus-Uwe Gollmer

   Trier University of Applied Sciences

   Affiliation as printed

   Institute for Software Systems (ISS), Trier University of Applied Sciences - Environmental Campus Birkenfeld, Birkenfeld, Rhineland Palatinate Germany

10. Guido Dartmann

    Trier University of Applied Sciences

    Affiliation as printed

    Institute for Software Systems (ISS), Trier University of Applied Sciences - Environmental Campus Birkenfeld, Birkenfeld, Rhineland Palatinate Germany