https://doi.org/10.1051/epjconf/202226613025
Automation strategies and machine learning algorithms towards real-time identification of optically trapped particles
1 Faculdade de Ciências da Universidade do Porto, Rua do Campo Alegre 687, 4169-007 Porto, Portugal
2 INESC TEC, Centre of Applied Photonics, Rua do Campo Alegre 687, 4169-007 Porto, Portugal
* e-mail: jmfoliveira110@gmail.com
Published online: 13 October 2022
To automatically trap, manipulate and probe physical properties of micron-sized particles is a step of paramount importance for the development of intelligent and integrated optomicrofluidic devices. In this work, we aim at implementing an automatic classifier of micro-particles immersed in a fluid based on the concept of optical tweezers. We describe the automation steps of an experimental setup together with the implemented classification models using the forward scattered signal. The results show satisfactory accuracy around 80% for the identification of the type and size of particles using signals of 250 milliseconds of duration, which paves the path for future improvements towards real-time analysis of the trapped specimens.
© The Authors, published by EDP Sciences
This is an Open Access article distributed under the terms of the Creative Commons Attribution License 4.0, which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.
