Nondestructive prediction of physicochemical properties of kimchi sauce with artificial and convolutional neural networks

This study presents a comparison of prediction performances by an artificial neural network (ANN), well-known deep convolutional neural network (D-CNN) models, and four proposed shallow convolutional neural network (S-CNN) models to forecast three key physicochemical properties (PCPs): salinity, °Brix, and moisture content of kimchi sauce (KS). The S-CNN models effectively minimized underfitting issues found in D-CNN models, predicting PCPs with a low error rate even with small image datasets. Furthermore, the ANN model using color values also allowed for competitive predictions. We used two nondestructive prediction strategies: (i) using color values with ANNs for immediate application in small-scale enterprises and (ii) using photographs as input for S-CNN models, allowing for faster and more accurate quality prediction. These results highlight the potential for image-based quality prediction in food science, possibly enhancing the efficiency and accuracy of real-time quality control. Future enhancements could incorporate additional data sources for improved predictive performance.本研究对比了人工神经网络（Artificial Neural Network，ANN）、经典深度卷积神经网络（Deep Convolutional Neural Network，D-CNN）以及四种本文提出的浅层卷积神经网络（Shallow Convolutional Neural Network，S-CNN）模型，以预测泡菜酱（Kimchi Sauce，KS）的三项关键理化性质（Physicochemical Properties，PCPs）：盐度、白利糖度（°Brix）与水分含量。相较于D-CNN模型易出现的欠拟合问题，S-CNN模型可有效缓解该问题，即便在小型图像数据集上仍能实现低误差率的理化性质预测。此外，基于颜色特征的ANN模型也可获得具有竞争力的预测性能。本研究采用两种无损预测策略：其一为结合ANN模型与颜色特征的方案，可直接应用于中小型企业；其二为以图像作为输入的S-CNN模型方案，能够实现更快、更精准的品质预测。上述结果证实了基于图像的品质预测方法在食品科学领域的应用潜力，有望提升实时品质管控的效率与精准度。未来可通过融入更多数据源进一步优化预测性能。