数字农科院2.0

Multi-Indicator Prediction of Kiwifruit Quality integrating Hyperspectral Analysis and WGAN-GP-MMoE Framework

文献类型： 外文期刊

作者： 刘子涵;陈谦;李佳利;刘浩松;帅博宇;欧阳凌欢;卞子晗;王君怡;于家斌;钱建平

关键词： Fruit quality;Non-destructive evaluation;Hyperspectral analysis;Data augmentation;Multi-task deep learning

期刊名称： FOOD CONTROL

ISSN： 0956-7135

年卷期： 2025 年

页码：

收录情况： SCIE（2025版）

摘要： Currently, hyperspectral imaging technology is commonly applied for the single-indicator evaluation of fruit quality, underutilizing the spectral feature information about intrinsic interrelationships among multiple quality attributes. Meanwhile, multi-indicator collaborative analysis intensifies the scarcity of unified multidimensional label data in deep learning, which limits the performance of quality prediction models. Therefore, this study proposes an integrated non-destructive, real-time multi-indicator prediction framework for postharvest kiwifruit quality under small-sample conditions. Firstly, the synthetic hyperspectral reflectance data and corresponding quality labels, involving Dry Matter (DM), Soluble Solids Content (SSC),and firmness, were generated using WGAN-GP network to enhance the diversity of deep training dataset. Then, through shared and task-specific spectral information extraction, the MMoE-based multi-task model was established to mine the correlation features of different quality indicators, for simultaneously predicting the DM, SSC, and firmness in kiwifruit. Finally, the experimental results demonstrate that the incorporation of synthetic data effectively mitigates the model performance degradation under data-scarce conditions. Further, compared to traditional SVR and MCNN models, the developed MMoE model achieves superior prediction performance. Specifically, on the validation set for the Mixed-CARS-MMoE model, values for DM, SSC, and firmness reach 0.8908, 0.9128, and 0.7492, respectively; the corresponding RMSEs are 0.1442, 0.0699, and 0.1794, and the MAEVs are 0.1324, 0.0546, and 0.1606. The RPD values are 3.0261, 3.3864, and 2.6633 for DM, SSC, and firmness, respectively. This framework offers an efficient, non-destructive approach for online monitoring and quality control of multiple fruit quality indicators, enabling intelligent grading and quality management in agricultural production systems.

分类号：

  • 相关文献

[1]Fluorescence spectroscopy combined with a multi-task deep learning model for rapeseed oil quality analysis. Xinna Jiang,Quancheng Liu,Xingda Cao,Fan Wang,Long Li,Lei Yan,Shuxiang Fan. 2025

[2]A Method of Invasive Alien Plant Identification Based on Hyperspectral Images. Qiao, Xi,Liu, Xianghuan,Wang, Fukuan,Sun, Zhongyu,Yang, Long,Pu, Xuejiao,Huang, Yiqi,Liu, Shuangyin,Qian, Wanqiang. 2023

[3]Semantic Segmentation Based on Temporal Features: Learning of Temporal-Spatial Information From Time-Series SAR Images for Paddy Rice Mapping. Yang, Lingbo,Huang, Ran,Huang, Jingfeng,Lin, Tao,Wang, Limin,Mijiti, Ruzemaimaiti,Wei, Pengliang,Tang, Chao,Shao, Jie,Li, Qiangzi,Du, Xin. 2021

[4]Enhancing leaf area index and biomass estimation in maize with feature augmentation from unmanned aerial vehicle-based nadir and cross-circling oblique photography. Shuaipeng Fei,Shunfu Xiao,Qing Li,Meiyan Shu,Weiguang Zhai,Yonggui Xiao,Zhen Chen,Helong Yu,Yuntao Ma. 2023

[5]OVERSAMPLING METHOD FOR ENVIRONMENTAL MONITORING DATA AUGMENTATION IN CADMIUM -POLLUTED PADDY FIELD. Hao, Peitong,Li, Yue,Xu, Weiman,Li, Cong,Huo, Mingzhu,Zhang, Xiaoyu,An, Yi. 2022

[6]Predicting the reaction rates between flavonoids and methylglyoxal by combining molecular properties and machine learning. Hongkai Zhu,Jingyuan Liu,Mogens L. Andersen,Günther H.J. Peters,Marianne N. Lund. 2023

[7]High-quality images and data augmentation based on inverse projection transformation significantly improve the estimation accuracy of biomass and leaf area index. Yingpu Che,Qing Wang,Ziwen Xie,Shilin Li,Jinyu Zhu,Baoguo Li,Yuntao Ma. 2023

[8]Early detection of dark-affected plant mechanical responses using enhanced electrical signals. Hongping Li,Nikou Fotouhi,Fan Liu,Hongchao Ji,Qian Wu. 2024

[9]Rep-ViG-Apple: A CNN-GCN Hybrid Model for Apple Detection in Complex Orchard Environments. Bo Han,Ziao Lu,Jingjing Zhang,Rolla Almodfer,Zhengting Wang,Wei Sun,Luan Dong. 2024

[10]Efficient Triple Attention and AttentionMix: A Novel Network for Fine-Grained Crop Disease Classification. Yanqi Zhang,Ning Zhang,Jingbo Zhu,Tan Sun,Xiujuan Chai,Wei Dong. 2025

[11]GAN-MAML strategy for biomass energy production: Overcoming small dataset limitations. Yi Zhang,Yanji Hao,Yu Fu,Yijing Feng,Yeqing Li,Xiaonan Wang,Junting Pan,Yongming Han,Chunming Xu. 2025

[12]The research on enhancing LA estimation accuracy across domains for small sample data based on data augmentation and data transfer integration optimization system. Ai Dong Wang,Rui Jie Li,Xiang Qian Feng,Zi Qiu Li,Wei Yuan Hong,Hua Xing Wu,Dan Ying Wang,Song Chen. 2025

[13]Cotton Yield Prediction with Gaussian Distribution Sampling and Variational AutoEncoder. Yaqi Lan,Xiudong Wang,Lei Gao,Xiaoliang Chen. 2025

[14]Drip Irrigation Scheduling for Tomato Grown in Solar Greenhouse Based on Pan Evaporation in North China Plain. Liu Hao,Duan Ai-wang,Sun Jing-sheng,Wang Yan-cong,Sun Chi-tao,Li Fu-sheng. 2013

[15]Over-expression of GhDWF4 gene improved tomato fruit quality and accelerated fruit ripening. Ye Shu-e,Li Fang,Li Xian-bi,Zhai Yun-lan,Hu Ming-yu,Wei Ting,Deng Sha-sha,Pei Yan,Luo Ming,Hong Qi-bin. 2015

[16]Threshold of Soil Olsen-P in Greenhouses for Tomatoes and Cucumbers. Wu, Xue-Ping,Wu, Hui-Jun,Wang, Xiao-Bin,Li, Yin-Kun,Zhang, Yan-Cai,Li, Ruo-Nan,Wang, Li-Ying,Zhai, Cai-Xia,Chen, Li-Li,Wu, Xue-Ping,Wu, Hui-Jun,Wang, Xiao-Bin.

[17]The effect of three production systems on the postharvest quality and phytochemical composition of Orleans strawberry. Fan, Li,Dube, Claudine,Khanizadeh, Shahrokh,Fan, Li,Fang, Chengquan,Fan, Li,Yu, Cui,Zhang, Maojun,Ranieri, Marta. 2011

[18]Effects of sink demand and nutrient status on leaf photosynthesis of spring-cycle shoot in 'Newhall' navel orange under natural field conditions. Zhang, Wen-Wen,Fu, Xing-Zheng,Peng, Liang-Zhi,Ling, Li-Li,Cao, Li,Ma, Xiao-Huan,Xie, Fa,Li, Cai,Zhang, Wen-Wen,Ma, Xiao-Huan,Xie, Fa,Li, Cai,Fu, Xing-Zheng,Peng, Liang-Zhi,Ling, Li-Li,Cao, Li. 2013

[19]Virtual Cold Chain Method to Evaluate the Effect of Rising Temperature on the Quality Evolution of Peach Fruit. Liu, Hui,Lv, Zhenzhen,Yang, Wenbo,Li, Ang,Liu, Jiechao,Zhang, Qiang,Jiao, Zhonggao. 2023

[20]Declining abundance of pollinating insects drives falls in loquat (Eriobotrya japonica) fruit yields in the Pothwar region of Pakistan. Shahmshad Ahmed Khan,Muhammad Tanveer,Saboor Ahmad,Messaoud Mars,Muhammad Naeem,Zeenat Naveed,Wiebke Schuett,Claudia Drees,Dave Goulson. 2022

作者其他论文 更多>>