食品科学 ›› 2024, Vol. 45 ›› Issue (13): 229-238.doi: 10.7506/spkx1002-6630-20230701-005

• 包装贮运 • 上一篇    

基于CNN-GRU-AE的蓝莓货架期预测模型研究

张润泽, 冯国红, 付晟宏, 王宏恩, 高珊, 朱玉杰, 刘中深   

  1. （1.东北林业大学机电工程学院，黑龙江 哈尔滨 150040；2.东北林业大学土木与交通学院，黑龙江 哈尔滨 150040；3.黑龙江农业工程职业学院生物制药学院，黑龙江 哈尔滨 150025）
  • 发布日期:2024-07-12
  • 基金资助:
    国家自然科学基金面上项目（32071685）；黑龙江省自然科学基金项目（LH2020C050）

Convolutional Neural Network-Gated Recurrent Unit-Attention basedModel for Blueberry Shelf Life Prediction

ZHANG Runze, FENG Guohong, FU Shenghong, WANG Hong’en, GAO Shan, ZHU Yujie, LIU Zhongshen   

  1. (1. College of Mechanical and Electrical Engineering, Northeast Forestry University, Harbin 150040, China; 2. College of Civil Engineering and Transportation, Northeast Forestry University, Harbin 150040, China; 3. School of Biopharmaceutical Sciences, Heilongjiang Agricultural Engineering Vocational College, Harbin 150025, China)
  • Published:2024-07-12

RichHTML

18

PDF (PC)

77

摘要： 为探究贮藏于不同温度条件下蓝莓的品质变化及货架期，以‘自由’蓝莓为研究对象，测定其在0、4、25 ℃条件下的颜色参数、质量损失率、腐败率、质地参数等共计21 个品质指标。通过5 种具有自带特征选择功能的机器学习算法，筛选出7 个影响货架期的关键特征作为模型的输入变量，构建基于注意力（attention，AE）机制的卷积神经网络（convolutional neural network，CNN）和门控循环单元（gated recurrent unit，GRU）的蓝莓货架期预测模型。结果表明，与原始GRU相比，CNN-GRU-AE模型的平均绝对误差、均方误差和平均绝对百分比误差分别降低了75.83%、91.46%、61.58%，决定系数增加了2.25%。说明添加注意力机制并与CNN结合后的GRU模型显著提高了货架期的预测精度。本研究可为蓝莓在不同贮藏温度条件下的货架期制定提供理论支持，并为剩余货架期的预测提供技术帮助。

关键词: 蓝莓；货架期预测；卷积神经网络；门控循环单元；注意力机制

Abstract: In order to investigate the quality changes and shelf life of blueberries stored in different temperature, 21 quality indexes, including color parameters, mass loss rate, spoilage rate and texture parameters, were measured on “Freedom” blueberries at three storage temperatures (0, 4 and 25 ℃). Using five machine learning algorithms with a self-contained function of feature selection, seven key features affecting the shelf life were selected as input variables to construct a shelf life prediction model using gated recurrent unit (GRU) alone or in combination with convolutional neural network (CNN) and/or attention (AE) mechanism. The results showed that compared with the GRU model, the mean absolute error (MAE), mean square error (MSE) and mean absolute percentage error (MAPE) of the CNN-GRU-AE model decreased by 75.83%, 91.46%, 61.58%, respectively, and the coefficient and determination increased by 2.25%, indicating significantly improved accuracy of shelf-life prediction. This study provides theoretical support for the shelf life prediction of blueberries at different storage temperatures.

Key words: blueberry; shelf life prediction; convolutional neural network; gated recurrent unit; attention mechanism

中图分类号: 

京ICP备14027880号-3　京公网安备 11010202009729号
地址：北京市丰台区洋桥70号 中国食品杂志社《食品科学》编辑部　邮编：100068
电话：010-83155446/47/48/49/50　 传真：010-83155436　 Email：foodsci@126.com
本系统由北京玛格泰克科技发展有限公司设计开发　技术支持：support@magtech.com.cn