TY - CHAP A1 - Leiter, Nina A1 - Dietlmeier, Maximilian A1 - Wohlschläger, Maximilian A1 - Löder, Martin G.J. A1 - Versen, Martin A1 - Laforsch, Christian T1 - Development of a Neural Network for Automatic Classification of Post-Consumer Wood Using Rapid-FLIM T2 - 2023 IEEE Sensors Applications Symposium (SAS) N2 - 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. KW - fluorescence KW - Fluorescence KW - Microscopy KW - Neural networks KW - MLP KW - Current measurement KW - Feature extraction KW - Loss measurement KW - Post-consumer wood classification KW - Rapid-FLIM KW - Rapid-Fluorescence Lifetime Imaging Microscopy KW - Time measurement Y1 - 2023 U6 - https://doi.org/10.1109/SAS58821.2023.10254174 SP - 1 EP - 6 ER - TY - CHAP A1 - Wohlschläger, Maximilian A1 - Leiter, Nina A1 - Dietlmeier, Maximilian A1 - Löder, Martin G.J. A1 - Versen, Martin A1 - Laforsch, Christian T1 - Comparison of Two Classification Methods Trained with FD-FLIM Data to Identify and Distinguish Plastics from Environmental Materials T2 - 2023 International Joint Conference on Neural Networks (IJCNN) N2 - Previous research on identifying plastic types and differentiating plastics from environmental material is promising by utilizing the specific fluorescence lifetime, but the evaluation still has to be automated. Therefore, an automated Gaussian analysis is developed for evaluating frequency-domain fluorescence lifetime images of plastics and environmental materials. Furthermore, we applied a “Multilayer Perceptron” and “Random Forest Classifier” to the data resulting from the Gaussian analysis of the frequency domain fluorescence lifetime imaging microscopy data. The classification results show high F1-scores, whereby the best “Multilayer Perceptron” and “Random Forest Classifier” achieved an F1-score of 90%. Thus, identifying and differentiating plastics and environmental materials is possible by applying a “Multilayer Perceptron” or “Random Forest Classifier” to the Gaussian-analyzed imaged fluorescence lifetime data. KW - Fluorescence KW - Microscopy KW - Plastics KW - FD-FLIM KW - Neural networks KW - Environment KW - Frequency-domain analysis KW - Gaussian analysis KW - MLP KW - Multilayer perceptrons KW - Random forests KW - RFC Y1 - 2023 U6 - https://doi.org/10.1109/IJCNN54540.2023.10191054 SP - 1 EP - 9 ER -