Multi-task learning approach for optical luminescence sensing
Francesca Venturini, Umberto Michelucci, Michael Baumgärtner · Zürcher Hochschule für Angewandte Wissenschaften digital collection (Zurich University of Applied Sciences) · 2020
Luminescence-based sensors for measuring oxygen concentration are widely used both in industry and research due to the practical advantages and sensitivity of this type of sensing. The measuring principle is the luminescence quenching by oxygen molecules, which results in a change of the luminescence decay time and intensity. In the classical approach, this change is related to an oxygen concentration using complicated models. These models, which in most of the cases are non-linear, are parametrized through device-specific constants that are different for each sensor. This work explores an entirely new artificial intelligence approach and demonstrates the feasibility of oxygen sensing through machine learning. For this purpose, a multi-task learning neural network was specifically developed and trained on a large amount of data. The results show that with this approach it is possible to reach an accuracy comparable to that with the conventional approach. However, a significant advantage over the latter is that the network also learns the interdependencies of influencing parameters that no longer have to be measured separately and used to correct the results. The approach described in this work demonstrates the applicability of artificial intelligence and multi-task learning to sensing technology and paves the road for the next generation of sensors.