Rapid identification of counterfeited beef using deep learning-aided spectroscopy: Detecting colourant and curing agent adulteration

• Published in: Food and chemical toxicology 2023-11, Vol.181, p.114088-114088, Article 114088
• Main Authors: Jo, Eunjung, Lee, Youngjoo, Lee, Yumi, Baek, Jaewoo, Kim, Jae Gwan
• Format: Article
• Language: English
• Subjects: Colourant; Curing agent; Deep learning; Diffuse reflectance spectra; Food fraud; Meat safety
• ISSN: 0278-6915; 1873-6351
• DOI: 10.1016/j.fct.2023.114088

The adulteration of meat products using colourants and curing agents has heightened concerns over food safety, thereby necessitating the development of advanced detection methods. This study introduces a deep-learning-based spectroscopic method for swiftly identifying counterfeit beef altered to appear fresh. The experiment involved 60 beef samples, half of which were artificially adulterated using a colouring solution. Despite meticulous analysis of the beef's colour attributes, no significant differences were observed between the fresh and adulterated samples. However, our method, utilising a 344–1040 nm spectral range, achieved a classification accuracy of 98.84%. To enhance practicality, we employed gradient-weighted class activation mapping and identified the 580–600 nm range as particularly influential for classification. Remarkably, even when we narrowed the input to the model to this spectral range, a high level of classification accuracy was maintained. To further validate the model's robustness and generalisability, we allocated 70 beef samples to an external validation set. Comparative performance analysis revealed that our model outperformed traditional machine learning algorithms, such as SVM and logistic regression, by 9.3% and 28.4%, respectively. Overall, this study offers invaluable insights for detecting counterfeited beef, thereby contributing to the preservation of meat product quality and integrity within the food industry. •Novel deep-learning-driven spectroscopic approach for identifying adulterated beef.•Diffuse reflectance spectra of adulterated beef differ from those of fresh beef.•Gradient-weighted class activation mapping identified 580–600 nm as significant.•The 580–600 nm spectral region holds critical information on beef quality.•Model's robustness and applicability validated through external validation set.