Automated Detection of Porcine Gelatin Using Deep Learning-Based E-Nose to Support Halal Authentication

Abstract

Authenticating gelatin sources is crucial for consumers, particularly those with dietary restrictions or religious concerns, such as avoiding pork-derived ingredients. Porcine gelatin, widely used in food and pharmaceuticals products, poses considerable challenges for authentication due to its prevalence and the difficulty in detecting it, particularly in processed products. As the demand for rapid and reliable food authentication methods grows, the need for efficient and scalable technologies becomes increasingly critical. Notably, the integration of advanced tools, such as deep learning (DL) can enhance the accuracy and efficiency of detecting and classifying gelatin sources. This study developed and evaluated an integrated electronic nose (e-nose) system with a Recurrent Neural Network (RNN) to detect and classify gelatin types based on their sources. The e-nose system utilized an array of gas sensors to capture the unique volatile organic compounds (VOCs) associated with each gelatin type, which were subsequently classified by the RNN. The e-nose system incorporates seven gas sensor modules designed to identify the unique chemical signatures of porcine, bovine, and fish gelatin. The classification performance of the integrated 7-module e-nose system showed promising results based on time points after sample preparation, with accuracy, sensitivity, and AUC of 96.3%, 96.6%, and 98.2% at the 0-hour point, respectively, rising to 99.1% for all three metrics at 2-hour point. The sensitivity of the system also showed an increase over time for single gelatin samples, from 100%, 97.8%, and 91.9% to 98.6%, 99.3%, and 99.3% for pig-derived, cow-derived, and fish gelatin, respectively. For mixed gelatin samples, the system maintained high accuracy, sensitivity, and AUC at 98.2%, 97.9%, and 98.1%, respectively. The results demonstrate that the integrated e-nose system effectively differentiates between gelatin types with high performance in both single and mixed samples. This highlights its potential as a robust tool for gelatin authentication which pave the way to more efficient and reliable methods for ensuring halal compliance.