@inproceedings{HeitzmannWohlschlaegerLeiteretal.2024, author = {Heitzmann, Sebastian and Wohlschl{\"a}ger, Maximilian and Leiter, Nina and L{\"o}der, Martin G. J. and Versen, Martin and Laforsch, Christian}, title = {Classification of Foods and Plastics using FD-FLIM and Neural Networks}, series = {2024 IEEE Sensors Applications Symposium (SAS)}, booktitle = {2024 IEEE Sensors Applications Symposium (SAS)}, publisher = {IEEE}, doi = {10.1109/SAS60918.2024.10636453}, pages = {1 -- 6}, year = {2024}, abstract = {Plastics and foods can be differentiated by their material characteristic fluorescence properties, especially their fluorescence lifetimes. An areal measurement of fluorescent lifetimes of these materials can be done using Frequency-Domain Fluorescence Lifetime Imaging Microscopy (FD-FLIM). Up until now, most plastic detection is done using NIR or X-ray, while most applications of FD-FLIM are in biomedicalfields. The application of FD-FLIM in a food safety setting presents a promising approach to the detection of plastic contaminants. A Multilayer Perceptron (MLP) based neural network is developed to reliably identify the presence of plastic in a food/plastic sample via FD-FLIM. Features like the mean, median, standard deviation, variance, range, and interquartile range are calculated from the intensity image, the phase shift and modulation index along with the according phase- and modulation-dependent fluorescence lifetimes from the FD-FLIM data. For training, test and validation, a total of 3520 FD-FLIM measurements have been taken at 445nm excitation of sixteen samples with the labels food and plastic. To rank the performance of the 3888 trained networks, Fl-score, accuracy, precision, and recall are used as metrics. The best performing network reaches a Fl-score of 98.86\% proving that a differentiation of foods and plastics using a MLP classification based on FD- FLIM data is possible with a low error rate.}, 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} } @inproceedings{VersenKipfelsberger2024, author = {Versen, Martin and Kipfelsberger, Stefan}, title = {An Applied Examination Format for Measurement Technologies}, series = {Proceedings of the 12th International Conference on Physics Teaching in Engineering Education PTEE 2024}, booktitle = {Proceedings of the 12th International Conference on Physics Teaching in Engineering Education PTEE 2024}, editor = {Sch{\"a}fle, Claudia and Stanzel, Silke and Junker, Elmar and Lux, Christine}, url = {http://nbn-resolving.de/urn:nbn:de:bvb:861-opus4-25878}, pages = {96 -- 101}, year = {2024}, abstract = {A written exam in measurement technologies usually includes problems for operational amplifier circuits, error propagation, signal analysis and analog to digital conversion. During corona, teaching changed from presence lectures to remote lectures and examination formats changed, too. Instead of a written exam, student project exams were proposed. The projects included a computer aided temperature measurement with operational amplifier circuits, a calibration procedure, error propagation and a written report. The student project exams were successful and the students' feedback was so positive that the student project exams are going to be continued.}, language = {en} } @inproceedings{BouwmanHoogenboomFuhrmannetal.2024, author = {Bouwman, Wim and Hoogenboom, Jacob and Fuhrmann, Tina A. and Gelbord, Todd and Hettich, Christian and Sum, J{\"u}rgen and J{\"o}dicke, Bernd and Kautz, Christian and Neff, Julia L. and Krocker, Georg and Oostinga, Jeroen B. and Ruhe, Tim and D{\"u}ser, David and Schneider, Andreas Karl Peter and Suhonen, Sami and Tiili, Juho and Versen, Martin and Kipfelsberger, Stefan and Wendlandt, Michael}, title = {Proceedings of the 12th International Conference on Physics Teaching in Engineering Education PTEE 2024}, editor = {Sch{\"a}fle, Claudia and Stanzel, Silke and Junker, Elmar and Lux, Christine}, url = {http://nbn-resolving.de/urn:nbn:de:bvb:861-opus4-24648}, pages = {110}, year = {2024}, abstract = {The Proceedings of the 12th PTEE conference 2024 in Rosenheim present 15 articles from a wide range of actual topics in physics teaching - from artificial intelligence, innovative teaching and examination methods, lab experiments, tutorials to thoughts on what would be desirable to know, when you start teaching (activating) physics.}, language = {en} } @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{WohlschlaegerKhanLeiteretal.2023, author = {Wohlschl{\"a}ger, Maximilian and Khan, Yamna and Leiter, Nina and Versen, Martin and L{\"o}der, Martin and Laforsch, Christian}, title = {Development of a BLOB-detection algorithm based on DoG to detect Plastic in an environmental matrix using FD-FLIM}, series = {Optica Sensing Congress 2023 (AIS, FTS, HISE, Sensors, ES)}, booktitle = {Optica Sensing Congress 2023 (AIS, FTS, HISE, Sensors, ES)}, doi = {10.1364/ES.2023.EW4E.4}, year = {2023}, abstract = {The direct identification of plastics in an environmental matrix is heavily researched. We successfully developed a BLOB-detection algorithm based on differences of Gaussians to identify HDPE particles in an artificial environmental matrix using FD-FLIM.}, language = {en} } @inproceedings{WohlschlaegerKhanLeiteretal.2023, author = {Wohlschl{\"a}ger, Maximilian and Khan, Yamna and Leiter, Nina and Versen, Martin and L{\"o}der, Martin and Laforsch, Christian}, title = {Combining BLOB-Detection and MLP to Detect and Identify Plastics in an Environmental Matrix}, series = {2023 IEEE Sensors Applications Symposium (SAS)}, booktitle = {2023 IEEE Sensors Applications Symposium (SAS)}, doi = {10.1109/SAS58821.2023.10254171}, pages = {1 -- 5}, year = {2023}, abstract = {Environmental pollution by plastics is an increasing problem. However, state-of-the-art methods have significant disadvantages in detecting and identifying plastics directly in an environmental matrix. In this study, we propose a blob detection algorithm in combination with a neural network for fast and automated identification of plastics and non-plastics in a single fluorescence lifetime image. Therefore an artificial environmental matrix is prepared that contains soil, grass, spruce and HDPE (high density polyethylene) particles. Several FD-FLIM (frequency domain fluorescence lifetime imaging microscopy) images are taken, and the detection algorithm and the neural network are applied. We successfully demonstrated the suitability of the thresholding algorithm and the binary classification of the HDPE particles directly in the environmental matrix.}, language = {en} } @inproceedings{SchwarzWohlschlaegerLeiteretal.2023, author = {Schwarz, Jonas and Wohlschl{\"a}ger, Maximilian and Leiter, Nina and Auer, Veronika and Risse, Michael and Versen, Martin}, title = {Frequency Domain Fluorescence Lifetime Imaging Microscopy (FD-FLIM) analysis of Quercus robur samples for origin differentiation purposes}, series = {Optica Sensing Congress 2023 (AIS, FTS, HISE, Sensors, ES)}, booktitle = {Optica Sensing Congress 2023 (AIS, FTS, HISE, Sensors, ES)}, doi = {10.1364/AIS.2023.JTu4A.10}, year = {2023}, abstract = {Increasing demand for wood products requires methods to determine its harvest origin and ensure sustainable and legal sourcing. In 15 out of 21 cases, the origin of Quercus robur was differentiable in FD-FLIM studies.}, language = {en} } @inproceedings{LeiterWohlschlaegerDietlmeieretal.2023, author = {Leiter, Nina and Wohlschl{\"a}ger, Maximilian and Dietlmeier, Maximilian and Versen, Martin and L{\"o}der, Martin and Laforsch, Christian}, title = {Comparative Analysis of Fluorescence Properties of Post-Consumer Wood Using FD-FLIM}, series = {2023 IEEE Sensors Applications Symposium (SAS)}, booktitle = {2023 IEEE Sensors Applications Symposium (SAS)}, doi = {10.1109/SAS58821.2023.10254052}, pages = {1 -- 6}, year = {2023}, abstract = {The FD-FLIM technique has a high potential for automated post-consumer wood sorting. A problem of analysing post-consumer wood fluorescence properties is the uncertainty of the post-consumer wood category as the origin of the samples are unknown. In this study, the fluorescence properties of actual post-consumer wood is compared with prepared wood samples. The post-consumer wood samples display slightly different fluorescence intensities and lifetimes due to environmental influences and a higher sample diversity. For improved training of evaluation algorithms for post-consumer wood sorting, the prepared sample set should be extended or the post-consumer wood should be additionally analysed in the laboratory.}, 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} }