Answers are grounded in this paper and cite their sources.
This research demonstrates high predictive accuracy in detecting food adulteration using impedance sensors and advanced machine learning methods.
Food adulteration in commodities such as pepper poses significant economic and public health risks, necessitating robust detection technologies. This study presents an approach combining electrical impedance spectroscopy (EIS) and advanced machine learning techniques for detecting black pepper adulteration. Electrical impedance measurements were performed on pepper samples with varying adulteration levels (60%100% purity) across frequencies of 150 kHz using a custom-designed impedance sensor. Distinct impedance response patterns correlated to adulteration levels were observed. A specialized neural network model, named Adulteration Detection Machine Intelligence Network (ADMiNet), was developed, employing Principal Component Analysis (PCA) for dimensionality reduction and data augmentation techniques for robustness enhancement. The model was trained using Mean Squared Error (MSE) loss and the Adam optimizer with early stopping. Evaluation using Root Mean Square Error (RMSE = 5.84), Mean Absolute Error (MAE = 4.25), and coefficient of determination (R2 = 0.943) indicated high predictive accuracy, demonstrating the effectiveness of EIS combined with machine learning to detect adulteration. This research provides a cost-effective and accurate solution, offering significant potential applications in food safety monitoring and food fraud detection.
No takes yet. Share an insight, caveat, or question.
Zhenjun Sun (2025) studied this question.
Synapse has enriched 10 related papers. Consider them for comparative context: