Identification of tea quality at different picking periods: A hyperspectral system coupled with a multibranch kernel attention network

Yanwei Wang; Yuqi Ren; Siyuan Kang; Chongbo Yin; Yan Shi; Hong Men

doi:10.1016/j.foodchem.2023.137307

Identification of tea quality at different picking periods: A hyperspectral system coupled with a multibranch kernel attention network

Food Chem. 2024 Feb 1:433:137307. doi: 10.1016/j.foodchem.2023.137307. Epub 2023 Sep 1.

Authors

Yanwei Wang¹, Yuqi Ren², Siyuan Kang³, Chongbo Yin⁴, Yan Shi⁵, Hong Men⁶

Affiliations

¹ School of Automation Engineering, Northeast Electric Power University, Jilin 132012, China; Institute of Advanced Sensor Technology, Northeast Electric Power University, Jilin 132012, China. Electronic address: 1202100045@neepu.edu.cn.
² School of Automation Engineering, Northeast Electric Power University, Jilin 132012, China; Institute of Advanced Sensor Technology, Northeast Electric Power University, Jilin 132012, China. Electronic address: 2019303010404@neepu.edu.cn.
³ School of Automation Engineering, Northeast Electric Power University, Jilin 132012, China; Institute of Advanced Sensor Technology, Northeast Electric Power University, Jilin 132012, China; Bionic Sensing and Pattern Recognition Team, Northeast Electric Power University, Jilin 132012, China. Electronic address: 2020303010402@neepu.edu.cn.
⁴ School of Bioengineering, Chongqing University, Chongqing 400044, China. Electronic address: yincbjiayou@cqu.edu.cn.
⁵ School of Automation Engineering, Northeast Electric Power University, Jilin 132012, China; Institute of Advanced Sensor Technology, Northeast Electric Power University, Jilin 132012, China; Bionic Sensing and Pattern Recognition Team, Northeast Electric Power University, Jilin 132012, China. Electronic address: shiyan@neepu.edu.cn.
⁶ School of Automation Engineering, Northeast Electric Power University, Jilin 132012, China; Institute of Advanced Sensor Technology, Northeast Electric Power University, Jilin 132012, China. Electronic address: menhong@neepu.edu.cn.

PMID: 37683489
DOI: 10.1016/j.foodchem.2023.137307

Abstract

The material content and nutritional composition of tea vary during different picking periods, leading to variations in tea quality. The absence of rapid evaluation methods for identifying tea quality at different picking periods hinders the smooth operation and maintenance of agricultural production and market sales. In this work, hyperspectral technology combined with the multibranch kernel attention network (MBKA-Net) is proposed to identify the overall quality of tea during different picking periods. First, spectral information of six different tea picking periods is obtained using a hyperspectral system. Second, the multibranch kernel attention (MBKA) method is proposed, which effectively mines spectral features through multiscale adaptive extraction and achieves classification of tea at different picking periods. Finally, MBKA-Net achieves outstanding performance with 96.18% accuracy, 97.14% precision, and 97.18% recall. In conclusion, MBKA-Net combined with a hyperspectral system provides an effective detection method for identifying the quality of tea at different picking periods.

Keywords: Hyperspectral system; Multibranch kernel attention network; Nondestructive testing; Spectral information identification; Tea quality.

MeSH terms

Agriculture*
Tea*

Substances

Tea