Li Jingwei, Tauqeer Iqbal Muhammad, Shao Zhiyu, Yu Haidong
College of Electrical, Energy and Power Engineering, Yangzhou University, Yangzhou 225100, China.
J Imaging. 2025 May 17;11(5):159. doi: 10.3390/jimaging11050159.
Chemical oxygen demand (COD) serves as a key indicator of organic pollution in water bodies, and its rapid and accurate detection is crucial for environmental protection. Recently, ultraviolet-visible (UV-Vis) spectroscopy has gained popularity for COD detection due to its convenience and the absence of chemical reagents. Meanwhile, deep learning has emerged as an effective approach for automatically extracting spectral features and predicting COD. This paper proposes transforming one-dimensional spectra into two-dimensional spectrum images and employing convolutional neural networks (CNNs) to extract features and model automatically. However, training such deep learning models requires a vast dataset of water samples, alongside the complex task of labeling this data. To address these challenges, we introduce a transfer learning model based on VGG-16 for spectrum images. In this approach, parameters in the initial layers of the model are frozen, while those in the later layers are fine-tuned with the spectrum images. The effectiveness of this method is demonstrated through experiments conducted on our dataset, where the results indicate that it significantly enhances the accuracy of COD prediction compared to traditional methods and other deep learning methods such as partial least squares regression (PLSR), support vector machine (SVM), artificial neural network (ANN), and CNN-based methods.
化学需氧量（COD）是水体有机污染的关键指标，其快速准确检测对环境保护至关重要。近年来，紫外可见（UV-Vis）光谱法因其便捷性和无需化学试剂的特点，在COD检测中受到广泛关注。与此同时，深度学习已成为自动提取光谱特征和预测COD的有效方法。本文提出将一维光谱转换为二维光谱图像，并采用卷积神经网络（CNN）自动提取特征和建模。然而，训练此类深度学习模型需要大量水样数据集，以及对这些数据进行标注的复杂任务。为应对这些挑战，我们引入了一种基于VGG-16的光谱图像迁移学习模型。在该方法中，模型初始层的参数被冻结，而后续层的参数则通过光谱图像进行微调。通过在我们的数据集上进行实验，验证了该方法的有效性，结果表明，与传统方法以及偏最小二乘回归（PLSR）、支持向量机（SVM）、人工神经网络（ANN）和基于CNN的方法等其他深度学习方法相比，该方法显著提高了COD预测的准确性。
