外文摘要：Peanuts, sourced from various regions, exhibit noticeable differences in quality owing to the impact of their natural environments. This study proposes a fast and nondestructive detection method to identify peanut quality by combining an electronic nose system with a hyperspectral system. First, the electronic nose and hyperspectral systems are used to gather gas and spectral information from peanuts. Second, a module for extracting gas and spectral information is designed, combining the lightweight multi-head transposed attention mechanism (LMTA) and convolutional computation. The fusion of gas and spectral information is achieved through matrix combination and lightweight convolution. A hybrid neural network, named UnitFormer, is designed based on the information extraction and fusion processes. UnitFormer demonstrates an accuracy of 99.06 %, a precision of 99.12 %, and a recall of 99.05 %. In conclusion, UnitFormer effectively distinguishes quality differences among peanuts from various regions, offering an effective technological solution for quality supervision in the food market.
外文关键词：deep learning;Peanut quality determination;Nondestructive testing;Information fusion
作者：Wang, Zi;Yu, Yang;Liu, Junqi;Zhang, Qinglun;Guo, Xiaoqin;Yang, Yixin;Shi, Yan
作者单位：Univ Elect Sci & Technol China;Northeast Elect Power Univ
期刊名称：FOOD CHEMISTRY
期刊影响因子：0.0
出版年份：2024
出版刊次：447
原文传递申请：江苏省科技资源（工程技术文献）统筹服务平台