@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} } @misc{HeitzmannKallweitBrunnetal.2025, author = {Heitzmann, Sebastian and Kallweit, Stephan and Brunn, Andr{\´e} and Holst, Gerhard and Leiter, Nina and Wohlschl{\"a}ger, Maximilian and Versen, Martin}, title = {Erweiterung eines FD-FLIM Messsystems durch MQTT Anbindung eines Roboters zur automatischen Sortierung von Altholzklassen}, series = {Tagungsband AALE 2025: Menschenzentrierte Automation im digitalen Zeitalter}, journal = {Tagungsband AALE 2025: Menschenzentrierte Automation im digitalen Zeitalter}, doi = {10.33968/2025.16}, pages = {147 -- 156}, year = {2025}, abstract = {Ziel des Projektes Fluoreszenz ID von Altholz (FrIDAH)5 ist die Entwicklung eines Demonstrators gewesen, welcher die automatisierte Sortierung von Altholzproben gem{\"a}ß der Altholzverordnung unter Verwendung der Messung von Fluoreszenzabklingzeiten erm{\"o}glicht. In diesem Beitrag werden der entwickelte Messaufbau, die Software, das Automatisierungssystem, sowie der Klassifikator vorgestellt. Die Ergebnisse zeigen, dass die verwendete Technologie zur zuverl{\"a}ssigen Klassifikation von Altholz geeignet ist und f{\"u}r die automatisierte Sortierung angewendet werden kann.}, language = {de} } @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} }