高光谱成像
人工智能
黄曲霉毒素
机器学习
卷积神经网络
特征选择
深度学习
偏最小二乘回归
预处理器
模式识别(心理学)
计算机科学
特征(语言学)
人工神经网络
随机森林
数学
数据预处理
可解释性
特征提取
回归
算法
弹性网正则化
人类健康
支持向量机
回归分析
随机梯度下降算法
食品
作者
Min Pang,Yingge Wang,Mengke Li,Li Xu,Chun Gao,Shaotong Jiang,Zhi Zheng,Lili Cao
标识
DOI:10.1016/j.crfs.2025.101209
摘要
ABSTRACT Aflatoxin contamination in peanuts poses serious health risks, requiring rapid, non-destructive detection methods. This study developed a hyperspectral imaging (HSI) approach combined with deep learning for quantitative aflatoxin analysis in moldy peanuts. The dynamic degradation of nutrients during mold growth was monitored, and correlations between physicochemical properties, aflatoxin levels, and spectral features were investigated. Various preprocessing methods and feature selection techniques were compared, evaluating conventional machine learning (Partial Least Squares Regression (PLSR), Random Forest (RF), Least Absolute Shrinkage and Selection Operator (LASSO)) against a convolutional neural network (CNN). The CNN model, optimized with median filtering and genetic algorithm-based feature selection, achieved superior performance (R 2 p = 0.972, RMSEp = 8.203, RPDp = 2.738). The proposed HSI-CNN framework provides an efficient, non-destructive solution for high-throughput aflatoxin quantification, supporting industrial food safety monitoring.
科研通智能强力驱动
Strongly Powered by AbleSci AI