基于优化深度神经网络和高光谱成像的红茶发酵品质检测

摘要：红茶的质量在很大程度上依赖于其发酵过程。然而，由于质量监测中涉及人工判断的主观性，实现精确和客观的 评估仍然具有挑战性。为解决这一问题，本研究提出结合高光谱成像和深度学习算法来识别红茶的发酵质量。首先，采 集了英红 9 号红茶在 0-5 小时内五个发酵时间间隔的高光谱数据。随后，基于全光谱和筛选光谱数据，分别使用支持向 量机（（ SVM）、人工神经网络（（ ANN）、偏最小二乘判别分析（（ PLS-DA）和朴素贝叶斯（（ NB）构建了红茶发酵质量检测 模型。此外，还利用深度学习算法，包括卷积神经网络（CNN）、长短期记忆网络（LSTM）、CNN-LSTM以及粒子群优 化（PSO）优化的 CNN-LSTM（PSO-CNN-LSTM），基于光谱图像构建了检测模型。实验结果表明，在红茶发酵质量检 测中，深度学习算法相较于传统机器学习算法具有明显优势。其中，PSO-CNN-LSTM模型表现出最佳的分类性能，在测 试集上的准确率达到96.78%。本研究证明了深度学习与高光谱成像相结合在预测红茶发酵质量方面的巨大潜力，为红茶 发酵过程的有效监测提供了新方法，并为类似领域的其他应用提供了有益的参考。

关键词：红茶；发酵品质鉴定；深度神经网络；粒子群优化

期刊：Infrared Physics and Technology

DOI：https://doi.org/10.1016/j.infrared.2024.105625

设备：GaiaField

Detection of black tea fermentation quality based on optimized deep neural network and hyperspectral imaging

Abstract：The quality of black tea signiffcantly relies on its fermentation process. Nevertheless, achieving precise and objective evaluations remains challenging due to the subjective nature of manual judgment involved in quality monitoring. To address this problem, hyperspectral imaging combined with the deep learning algorithms are proposed to identify the fermentation quality of black tea. Firstly, the hyperspectral data of Yinghong No. 9 black tea during ffve fermentation time intervals within 0–5 h are collected. Then, the Support Vector Machine (SVM), Artiffcial Neural Network (ANN), Partial Least Squares Discriminant Analysis (PLS-DA), and Naive Bayesian (NB) are used to construct black tea fermentation quality detection models based on full spectrum and selected spectrum data. Furthermore, deep learning algorithms including the Convolutional Neural Network (CNN), Long Short-Term Memory (LSTM), CNN-LSTM, and Swarm Optimization (PSO) optimized CNN-LSTM (PSO-CNNLSTM) are also used to build the detection model using the spectral images. The experimental results indicate that deep learning algorithms have obvious advantages over traditional machine learning algorithms in tea fermentation quality detection. Besides, the PSO-CNN- LSTM model shows the best classiffcation performance compared to other algorithms and achieves an accuracy of 96.78% on the test set. This study demonstrates the signiffcant potential of combining deep learning with hyperspectral imaging for predicting black tea fermentation quality. This provides a new approach for effective monitoring of the black tea fermentation process and a useful reference for other applications in similar fields.

Keywords：Black tea; Fermentation quality identiffcation; Deep neural network; Particle swarm optimization