Iranian Research Organization for Science and Technology (IROST) Innovative Food Technologies 2783-350X 13 3 2026 04 21 Deep Learning-Enabled Hyperspectral Classification of Zhambons Deep Learning-Enabled Hyperspectral Classification of Zhambons 281 295 1625 10.22104/ift.2025.8010.2255 FA Seyedehsamaneh Shojaeilangari Biomedical Engineering Group, Department of Electrical Engineering and Information Technology, Iranian Research Organization for Science and Technology (IROST) Esmat Kishani Farahani Information Technology and Intelligent Systems Group, Department of Electrical Engineering and Information Technology, Iranian Research Organization for Science and Technology Alireza Basiri Department of Chemical Technologies, Iranian Research Organization for Science and Technology Journal Article 2025 11 23 Food authenticity is a crucial aspect of consumer protection, food safety, and quality assurance. Conventional methods for meat authentication often require destructive, time-consuming, or labor-intensive processes. Hyperspectral imaging, which combines imaging and spectroscopy, has emerged as a non-destructive alternative for food classification. This study investigates the application of hyperspectral imaging for differentiating between beef, chicken, and turkey zhambons using one-dimensional convolutional neural networks and long short-term memory networks. Following preprocessing—including segmentation, noise reduction, and spatial averaging—spectral signatures were extracted and classified using deep learning models and then compared to traditional machine learning approaches. The long short-term architecture demonstrated superior performance by effectively modeling sequential spectral dependencies, achieving 99.94% accuracy in the binary classification of chicken versus beef and 98.12% accuracy in the three-class problem (beef, chicken, and turkey zhambons). The findings highlight the potential of hyperspectral imaging combined with machine learning approaches as an efficient tool for processed meat authentication. Food authenticity is a crucial aspect of consumer protection, food safety, and quality assurance. Conventional methods for meat authentication often require destructive, time-consuming, or labor-intensive processes. Hyperspectral imaging, which combines imaging and spectroscopy, has emerged as a non-destructive alternative for food classification. This study investigates the application of hyperspectral imaging for differentiating between beef, chicken, and turkey zhambons using one-dimensional convolutional neural networks and long short-term memory networks. Following preprocessing—including segmentation, noise reduction, and spatial averaging—spectral signatures were extracted and classified using deep learning models and then compared to traditional machine learning approaches. The long short-term architecture demonstrated superior performance by effectively modeling sequential spectral dependencies, achieving 99.94% accuracy in the binary classification of chicken versus beef and 98.12% accuracy in the three-class problem (beef, chicken, and turkey zhambons). The findings highlight the potential of hyperspectral imaging combined with machine learning approaches as an efficient tool for processed meat authentication. https://jift.irost.ir/article_1625_5ee8dac3ee2c2d98ecc3b0fb691bbd74.pdf