Gel strength prediction in ultrasonicated chicken mince: Fusing near-infrared and Raman spectroscopy coupled with deep learning LSTM algorithm
Xorlali Nunekpeku, Wei Zhang, Jiayu Gao, Selorm Yao‐Say Solomon Adade, Huanhuan Li, Quansheng Chen
Abstract
The meat processing industry faces challenges in maintaining the gel quality in minced chicken products, which affects consumer appeal and overall product quality. This study investigates the use of ultrasonic treatment to improve the gel quality of minced chicken and employs Near-Infrared (NIR) and Raman spectroscopy for rapid, non-destructive gel strength assessment. Initially, ultrasonic treatment was applied at various durations, with optimal results observed at approximately 30 min, significantly improving gel strength, texture profile, and reducing centrifugal loss rate. To comprehensively assess gel strength, Convolutional Neural Network (CNN) and Long Short-Term Memory (LSTM) models were established using individual NIR and Raman spectral data, as well as their fusion. The LSTM model with fused NIR-Raman data demonstrated superior performance (Rp 2 = 0.9882, RPD = 9.2091), outperforming individual techniques and CNN-based models. This study demonstrates that ultrasonic treatment can effectively improve minced chicken gel quality, while the fusion of NIR and Raman spectroscopy coupled with LSTM deep learning offers a reliable, non-destructive, and rapid method for predicting gel strength. This approach addresses the industry's need for innovative quality assessment methods, potentially improving product quality and consumer satisfaction in the processed chicken market.