Yin Hai, Yang Qihang, Huang Fangyuan, Li Hongjie, Wang Hui, Zheng Huadan, Huang Furong
Department of Optoelectronic Engineering, Jinan University, Guangzhou, Guangdong 510632, China.
Guangdong Experimental High School, Guangzhou, Guangdong 510000, China.
Spectrochim Acta A Mol Biomol Spectrosc. 2025 Feb 15;327:125430. doi: 10.1016/j.saa.2024.125430. Epub 2024 Nov 10.
There are many types of fish maw with significantly varying prices. The specific type directly affects its market value and medicinal efficacy. This paper proposes a fish maw type recognition method based on Wasserstein generative adversarial network combined with gradient penalty (WGAN-GP) and spectral fusion. By collecting Raman and near-infrared (NIR) spectral data of four types of fish maw (Beihai Male Fish Maw, Beihai Female Fish Maw, Yellow Croaker Fish Maw, and Red Mouth Croaker Fish Maw), we used WGAN-GP for data augmentation. The performance of three spectral fusion strategies (data layer, feature layer, and decision layer) was explored based on two one-dimensional convolutional neural network (1D-CNN) models. The results indicate that, after applying data augmentation and expanding the training set to 3,600 samples, the performances of the 1D-VGG (NIR), 1D-VGG (Raman), 1D-ResNet (NIR), and 1D-ResNet (Raman) models all reach optimal levels. The accuracies on the test set are improved by 15.48%, 13.10%, 1.19%, and 5.95%, respectively. Under different fusion strategies, the 1D-VGG (Raman)-1D-VGG (NIR) model at the feature layer and 1D-ResNet (Raman)(1.0)-1D-ResNet (NIR)(1.0) model at the decision layer achieved the same classification results. They exceeded other models in accuracy (98.21%), precision (98.27%), recall (98.21%), and F1-score (98.21%) on the test set. In summary, this study demonstrated the great potential of data enhancement and multimodal spectral data fusion in fish maw type identification, providing analytical tools for the development of fish maw detection equipment based on multimodal techniques.
鱼鳔种类繁多，价格差异显著。其具体种类直接影响其市场价值和药用功效。本文提出了一种基于结合梯度惩罚的瓦瑟斯坦生成对抗网络（WGAN-GP）和光谱融合的鱼鳔种类识别方法。通过收集四种鱼鳔（北海公鱼鳔、北海母鱼鳔、黄鱼鱼鳔和红口鳓鱼鱼鳔）的拉曼光谱和近红外（NIR）光谱数据，我们使用WGAN-GP进行数据增强。基于两个一维卷积神经网络（1D-CNN）模型，探索了三种光谱融合策略（数据层、特征层和决策层）的性能。结果表明，在应用数据增强并将训练集扩展到3600个样本后，1D-VGG（NIR）、1D-VGG（拉曼）、1D-ResNet（NIR）和1D-ResNet（拉曼）模型的性能均达到最优水平。测试集上的准确率分别提高了15.48%、13.10%、1.19%和5.95%。在不同的融合策略下，特征层的1D-VGG（拉曼）-1D-VGG（NIR）模型和决策层的1D-ResNet（拉曼）（1.0）-1D-ResNet（NIR）（1.0）模型取得了相同的分类结果。它们在测试集上的准确率（98.21%）、精确率（98.27%）、召回率（98.21%）和F1分数（98.21%）超过了其他模型。综上所述，本研究证明了数据增强和多模态光谱数据融合在鱼鳔种类识别中的巨大潜力，为基于多模态技术的鱼鳔检测设备开发提供了分析工具。
