基于孪生网络对比学习的黄曲霉毒素 B1 光谱智能检测

摘要：黄曲霉毒素是存在于花生、玉米及其衍生物中的有害物质，对健康构成严重威胁。针对这一问题，本文介绍了一 种创新的MSGhostDNN模型，该模型将对比学习与多尺度卷积网络相结合，用于精确检测黄曲霉毒素。该方法大大提高 了特征辨别能力，通过预先训练的模型达到了令人印象深刻的97.87%的检测准确率。通过应用Grad-CAM，该方法进一 步完善了模型，以识别关键波长，尤其是416 nm波长，并将重点放在40个关键波长上，以达到最佳性能，准确率高达 97.46%。该研究还采用了任务降维进行持续学习，从而能够对花生和玉米中的黄曲霉毒素光谱进行有效的持续监测。这 种方法不仅提高了黄曲霉毒素的检测效率，还为类似毒素的快速在线检测开创了先例，为降低黄曲霉毒素暴露带来的健 康风险提供了一种前景广阔的解决方案。

关键词：黄曲霉毒素 B1；高光谱图像；深度学习；对比学习；继续学习。

期刊：Food Chemistry

DOI：https://doi.org/10.1016/j.foodchem.2024.139171

设备：GaiaField

Spectral intelligent detection for aflatoxin B1 via contrastive learning based on Siamese network

Abstract：Aflatoxins, harmful substances found in peanuts, corn, and their derivatives, pose significant health risks. Addressing this, the presented research introduces an innovative MSGhostDNN model, merging contrastive learning with multi-scale convolutional networks for precise aflatoxin detection. The method significantly en hances feature discrimination, achieving an impressive 97.87% detection accuracy with a pre-trained model. By applying Grad-CAM, it further refines the model to identify key wavelengths, particularly 416 nm, and focuses on 40 key wavelengths for optimal performance with 97.46% accuracy. The study also incorporates a task dimensionality reduction approach for continuous learning, allowing effective ongoing aflatoxin spectrum monitoring in peanuts and corn. This approach not only boosts aflatoxin detection efficiency but also sets a precedent for rapid online detection of similar toxins, offering a promising solution to mitigate the health risks associated with aflatoxin exposure.

Keywords：Aflatoxin B1, Hyperspectral images, Deep learning, Contrastive learning, Continue learning.