Development of a Neural Network for Automatic Classification of Post-Consumer Wood Using Rapid-FLIM
- The economic use of wood is a growing sector, not only because of the significant advantage of wood to retain CO 2 . It is crucial to increase the material recycling of wood in several lifecycles, but currently, there is no reliable post-consumer wood sorting technique in line. This research measures 365 post-consumer wood samples of classes A1-4 four times with the frequency domain fluorescence lifetime imaging microscopy (FD-FLIM) subset method rapid fluorescence lifetime imaging microscopy (Rapid-FLIM). The data is analyzed on their statistical features. Four neural networks based on Multilayer perceptron are then trained and tested with twelve statistical features extracted from the Rapid-FLIM images. The best model for this application contains the optimizer RMSprop, the activation function SELU and the loss function binary crossentropy. The best model of this structure could achieve a false positive ratio of 4.79 % over the ten folds.
Author: | Nina Leiter, Maximilian Dietlmeier, Maximilian Wohlschläger, Martin G.J. Löder, Martin Versen, Christian Laforsch |
---|---|
DOI: | https://doi.org/10.1109/SAS58821.2023.10254174 |
Parent Title (English): | 2023 IEEE Sensors Applications Symposium (SAS) |
Document Type: | Conference Proceeding |
Language: | English |
Publication Year: | 2023 |
Tag: | Current measurement; Feature extraction; Fluorescence; Loss measurement; MLP; Microscopy; Neural networks; Post-consumer wood classification; Rapid-FLIM; Rapid-Fluorescence Lifetime Imaging Microscopy; Time measurement; fluorescence |
First Page: | 1 |
Last Page: | 6 |