TY - CHAP A1 - Heitzmann, Sebastian A1 - Wohlschläger, Maximilian A1 - Leiter, Nina A1 - Löder, Martin G. J. A1 - Versen, Martin A1 - Laforsch, Christian T1 - Classification of Foods and Plastics using FD-FLIM and Neural Networks T2 - 2024 IEEE Sensors Applications Symposium (SAS) N2 - 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. KW - fluorescence KW - foods KW - FLIM KW - MLP KW - neural networks Y1 - 2024 U6 - https://doi.org/10.1109/SAS60918.2024.10636453 SP - 1 EP - 6 PB - IEEE ER - TY - GEN A1 - Heitzmann, Sebastian A1 - Kallweit, Stephan A1 - Brunn, André A1 - Holst, Gerhard A1 - Leiter, Nina A1 - Wohlschläger, Maximilian A1 - Versen, Martin T1 - Erweiterung eines FD-FLIM Messsystems durch MQTT Anbindung eines Roboters zur automatischen Sortierung von Altholzklassen T2 - Tagungsband AALE 2025: Menschenzentrierte Automation im digitalen Zeitalter N2 - Ziel des Projektes Fluoreszenz ID von Altholz (FrIDAH)5 ist die Entwicklung eines Demonstrators gewesen, welcher die automatisierte Sortierung von Altholzproben gemäß der Altholzverordnung unter Verwendung der Messung von Fluoreszenzabklingzeiten ermöglicht. In diesem Beitrag werden der entwickelte Messaufbau, die Software, das Automatisierungssystem, sowie der Klassifikator vorgestellt. Die Ergebnisse zeigen, dass die verwendete Technologie zur zuverlässigen Klassifikation von Altholz geeignet ist und für die automatisierte Sortierung angewendet werden kann. Y1 - 2025 U6 - https://doi.org/10.33968/2025.16 SP - 147 EP - 156 ER - TY - JOUR A1 - Leiter, Nina A1 - Wohlschläger, Maximilian A1 - Versen, Martin A1 - Harter, Sonja D. A1 - Kießlich, Tina A1 - Lederer, Franziska A1 - Clauß, Stefanie A1 - Schlosser, Dietmar A1 - Armanu, Emanuel Gheorghita A1 - Eberlein, Christian A1 - Heipieper, Hermann J. A1 - Löder, Martin G. J. A1 - Laforsch, Christian T1 - Effects of defined organic layers on the fluorescence lifetime of plastic materials JF - Analytical and Bioanalytical Chemistry N2 - Plastics have become an integral part of modern life, and linked to that fact, the demand for and global production of plastics are still increasing. However, the environmental pollution caused by plastics has reached unprecedented levels. The accumulation of small plastic fragments—microplastics and nanoplastics—potentially threatens organisms, ecosystems, and human health. Researchers commonly employ non-destructive analytical methods to assess the presence and characteristics of microplastic particles in environmental samples. However, these techniques require extensive sample preparation, which represents a significant limitation and hinders a direct on-site analysis. In this context, previous investigations showed the potential of fluorescence lifetime imaging microscopy (FLIM) for fast and reliable identification of microplastics in an environmental matrix. However, since microplastics receive an environmental coating after entering nature, a challenge arises from organic contamination on the surface of microplastic particles. How this influences the fluorescence signal and the possibility of microplastic detection are unknown. To address this research gap, we exposed acrylonitrile butadiene styrene (ABS) and polyethylene terephthalate (PET) plastic samples to peptides, proteins, bacteria, and a filamentous fungus to induce organic contamination and mimic environmental conditions. We analyzed the fluorescence spectra and lifetimes of the samples using fluorescence spectroscopy and frequency-domain fluorescence lifetime imaging microscopy (FD-FLIM), respectively. Our results demonstrate that reliably identifying and differentiating ABS and PET was possible via FD-FLIM, even in the presence of these biological contaminations. These findings highlight the potential of this technique as a valuable tool for environmental monitoring and plastic characterization, offering a rapid and efficient alternative to currently used analytical methods. Y1 - 2025 U6 - https://doi.org/10.1007/s00216-025-05888-y VL - 417 IS - 16 SP - 3651 EP - 3663 ER - TY - GEN A1 - Leiter, Nina A1 - Heitzmann, Sebastian A1 - Versen, Martin A1 - Wohlschläger, Maximilian A1 - Löder, Martin G.J. A1 - Laforsch, Christian T1 - Identification of Microplastic Contamination in Food using FD-FLIM T2 - 2025 IEEE Sensors Applications Symposium (SAS) N2 - 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. KW - Microplastic KW - Food KW - FLIM KW - fluorescence Y1 - 2025 U6 - https://doi.org/10.1109/SAS65169.2025.11105138 SP - 1 EP - 5 PB - IEEE ER -