@inproceedings{WohlschlaegerLeiterDietlmeieretal.2023, author = {Wohlschl{\"a}ger, Maximilian and Leiter, Nina and Dietlmeier, Maximilian and L{\"o}der, Martin G.J. and Versen, Martin and Laforsch, Christian}, title = {Comparison of Two Classification Methods Trained with FD-FLIM Data to Identify and Distinguish Plastics from Environmental Materials}, series = {2023 International Joint Conference on Neural Networks (IJCNN)}, booktitle = {2023 International Joint Conference on Neural Networks (IJCNN)}, doi = {10.1109/IJCNN54540.2023.10191054}, pages = {1 -- 9}, year = {2023}, abstract = {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.}, language = {en} } @inproceedings{LeiterDietlmeierWohlschlaegeretal.2023, author = {Leiter, Nina and Dietlmeier, Maximilian and Wohlschl{\"a}ger, Maximilian and L{\"o}der, Martin G.J. and Versen, Martin and Laforsch, Christian}, title = {Development of a Neural Network for Automatic Classification of Post-Consumer Wood Using Rapid-FLIM}, series = {2023 IEEE Sensors Applications Symposium (SAS)}, booktitle = {2023 IEEE Sensors Applications Symposium (SAS)}, doi = {10.1109/SAS58821.2023.10254174}, pages = {1 -- 6}, year = {2023}, abstract = {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.}, language = {en} } @inproceedings{LeiterSchwarzVersenetal.2024, author = {Leiter, Nina and Schwarz, Jonas and Versen, Martin and Risse, Michael and L{\"o}der, Martin G.J. and Laforsch, Christian}, title = {A non-destructive approach to wood origin differentiation using FD-FLIM}, series = {2024 IEEE Sensors Applications Symposium (SAS)}, booktitle = {2024 IEEE Sensors Applications Symposium (SAS)}, publisher = {IEEE}, doi = {10.1109/SAS60918.2024.10636550}, pages = {1 -- 6}, year = {2024}, abstract = {Wood auto-fluorescence, primarily attributed to lignin, presents a distinctive feature. Different wood species exhibit variations in lignin distribution. Frequency-Domain Fluorescence Lifetime Imaging Microscopy is effective in distinguishing wood species based on their fluorescence characteristics. This study investigates the potential to differentiate the origins of beech, spruce, and larch through phase-dependent fluorescence decay times. Therefore the zero hypothesis H0 is tested: The phase dependent fluorescence lifetimes of samples from the same species but varying in origin are equal. To determine the fluorescence characteristics of woods of different origins, wood samples of the species Fagus sylvatica L. (beech), Larix decidua Mill. (larch), and Picea abies (L.) H. Karst. (spruce) from Germany, Austria, the Netherlands, Spain, Sweden, New Zealand and Romania were analyzed. The wood samples were analyzed with a FD-FLIM camera setup, including a laser source emitting at an excitation wavelength of 445 nm. Employing Analysis-of-Variance hypothesis testing on fluorescence lifetime data for each wood species, the results indicate that 23 out of 35 origin pairs could be distinguished at a 5\% significance level. While acknowledging the challenges of origin-based differentiation, the findings emphasize the promising potential of fluorescence lifetime imaging microscope as a valuable tool in this context. Moving forward, a more intricate approach to sample differentiation should involve acquiring detailed information about the samples, including associated temperature and precipitation profiles, and soil composition.}, language = {en} } @misc{LeiterHeitzmannVersenetal.2025, author = {Leiter, Nina and Heitzmann, Sebastian and Versen, Martin and Wohlschl{\"a}ger, Maximilian and L{\"o}der, Martin G.J. and Laforsch, Christian}, title = {Identification of Microplastic Contamination in Food using FD-FLIM}, series = {2025 IEEE Sensors Applications Symposium (SAS)}, journal = {2025 IEEE Sensors Applications Symposium (SAS)}, publisher = {IEEE}, doi = {10.1109/SAS65169.2025.11105138}, pages = {1 -- 5}, year = {2025}, abstract = {Microplastics have emerged as a significant environmental concern, particularly due to their potential impact on food safety and human health. This study uses frequency-domain fluorescence lifetime imaging microscopy to investigate the presence and effects of microplastics in four food types—ham, honey, fish, and lettuce. Samples were prepared with known quantities of high-density polyethylene particles, and their phase-dependent fluorescence lifetimes were analyzed to distinguish between contaminated and uncontaminated food. The results indicate that fluorescence lifetime analysis can effectively identify microplastic contamination, revealing distinct fluorescence characteristics for each food matrix. This research underscores the importance of innovative detection methods in ensuring food safety, highlighting the need for further studies on automated microplastic detection.}, language = {en} }