Abstract
[Objective] To achieve real-time, non-destructive, and high-precision monitoring of multiple quality indicators of kiwifruit during storage and to address the problems of strong destructiveness, obvious lag, and the difficulty of a single data source and model to balance comprehensiveness and accuracy in conventional detection methods, a kiwifruit quality testing method integrating wireless sensor network (WSN), hyperspectral imaging, and Harris hawk optimization (HHO)-optimized deep extreme learning machine (DELM) is proposed. [Methods] Firstly, a WSN and hyperspectral imaging collaborative acquisition system is established to obtain kiwifruit storage environment parameters (temperature and humidity), fruit surface sensing data (firmness and skin color), and hyperspectral image data. Secondly, the spectral data are preprocessed by the standard normal variance (SNV) combined with the first derivative, and the competitive adaptive re-weighted sampling (CARS) algorithm is employed to extract characteristic wavelengths for feature dimensionality reduction. Finally, a multi-source data fusion model for kiwifruit quality testing is established by optimizing the DELM with the HHO algorithm. [Results] The HHO-DELM model on the test dataset achieves correlation coefficients of 0.972, 0.915, 0.903, and 0.926 for soluble solids content, firmness, acidity, and color difference (e value) in the prediction dataset, with root mean square errors (RMSEs) of 0.486 ° Brix, 12.980 N/cm2, 0.062, and 0.023, respectively, and residual prediction deviation (RPD)>3.0 for all indicators. The established method reaches the classification overall accuracy of 99.3 % (Kappa =0.991), significantly outperforming DELM, partial least square regression (PLSR), support vector machine (SVM), and random forest (RF). Under different storage conditions (cold and room temperature), the method shows the prediction accuracy fluctuations ≤2.5 %, demonstrating excellent robustness. [Conclusion] This method integrates the real-time monitoring of WSN, the multidimensional information acquisition of hyperspectral imaging, and the high-precision prediction of HHO-DELM, enabling non-destructive testing of multiple quality indicators of kiwifruit throughout the storage period, thus meeting industrial requirements for rapid on-site detection and dynamic monitoring.
Publication Date
5-15-2026
First Page
136
Last Page
144
DOI
10.13652/j.spjx.1003.5788.2026.60006
Recommended Citation
Huajuan, CAO; Nanshan, LIU; and Quan, ZHAO
(2026)
"Non-destructive testing of kiwifruit storage quality integrating WSN and HHO-DELM,"
Food and Machinery: Vol. 42:
Iss.
4, Article 17.
DOI: 10.13652/j.spjx.1003.5788.2026.60006
Available at:
https://www.ifoodmm.cn/journal/vol42/iss4/17
References
[1] 陈玥瑶,夏静静,韦芸,等.近红外光谱法无损检测平谷产大桃品质方法研究 [J].分析化学,2023,51(3):454-462.CHEN Y Y,XIA J J,WEI Y,et al.Research on nondestructive quality test of Pinggu peach by near-infrared spectroscopy [J].Chinese Journal of Analytical Chemistry,2023,51(3):454-462.
[2] 陈月圆,赵武奇,贾梦科,等.低温等离子体处理的鲜切猕猴桃片货架期预测模型 [J].中国食品学报,2022,22(1):179-188.CHEN Y Y,ZHAO W Q,JIA M K,et al.Shelf life prediction model of fresh-cut kiwifruit slices treated with low-temperature plasma [J].Journal of Chinese Institute of Food Science and Technology,2022,22(1):179-188.
[3] 温锦丽,曹炜玉,王月,等.基于主成分分析与聚类分析的软枣 猕 猴 桃 果 实 品 质 综 合 评 价 [J].食 品 工 业 科 技,2024,45(1):247-257.WEN J L,CAO W Y,WANG Y,et al.Comprehensive evaluation of fruit quality of Actinidia arguta based on principal component analysis and cluster analysis [J].Science and Technology of Food Industry,2024,45(1):247-257.
[4] 余克强,孟浩,曹晓峰,等.近红外光谱对贮藏期猕猴桃不同深 度 果 肉 色 泽 的 变 化 研 究 [J].光 谱 学 与 光 谱 分 析,2020,40(7):2 240-2 245.YU K Q,MENG H,CAO X F,et al.Near-infrared spectroscopy for analyzing changes of pulp color of kiwifruit in different depths [J].Spectroscopy and Spectral Analysis,2020,40(7):2 240-2 245.
[5] 尚静,孟庆龙,黄人帅,等.光纤光谱技术对猕猴桃品质及成熟度的无损检测 [J].光学精密工程,2021,29(5):1 190-1 198.SHANG J,MENG Q L,HUANG R S,et al.Nondestructive detection for kiwifruit quality and maturity by optical fiber spectroscopy technology [J].Optics and Precision Engineering,2021,29(5):1 190-1 198.
[6] ZHAO Y,KANG Z,CHEN L.Food quality inspection method based on deep learning and hyperspectral imaging [J].Food Engineering Reviews,2022,14:596-616.
[7] HEIDARI A A,MIRJALILI S,FARIS H,et al.Harris hawks optimization:algorithm and applications [J].Future Generation Computer Systems,2019,97:849-872.
[8] LI X,ZHANG L,ZHANG Y.Quality evaluation of kiwifruit maturity using hyperspectral imaging technology [J].Journal of Food Measurement and Characterization,2022,16(3):1 892-1 903.
[9] 韩东,孙晓荣,李建伟.基于粒子群优化的深度极限学习机建模方法 [J].控制工程,2022,29(4):721-727.HAN D,SUN X R,LI J W.Deep extreme learning machine improved by particle swarm optimization algorithm [J].Control Engineering,2022,29(4):721-727.
[10] WANG C,CHEN Y,LIU J.Design of fruit cold chain monitoring system based on wireless sensor network [J].Transactions of the Chinese Society of Agricultural Engineering,2021,37(8):160-166.
[11] ZHAO Y C,KANG Z L,CHEN L,et al.Quality classification of kiwifruit under different storage conditions based on deep learning and hyperspectral imaging technology [J].Journal of Food Measurement and Characterization,2023,17:289-305.
[12] 祝福,刘瑞卿,潘克锋,等.基于极限学习机和晶体结构算法的污染食品早期检测 [J].食品与机械,2025,41(6):68-74.ZHU F,LIU R Q,PAN K F,et al.Early detection of contaminated food based on extreme learning machine and crystal structure algorithm [J].Food & Machinery,2025,41(6):68-74.
[13] 邵园园,王永贤,玄冠涛,等.高光谱成像的猕猴桃货架期快速预测 [J].光谱学与光谱分析,2020,40(6):1 940-1 946.SHAO Y Y,WANG Y X,XUAN G T,et al.Hyperspectral imaging technique for estimating the shelf-life of kiwifruits [J].Spectroscopy and Spectral Analysis,2020,40(6):1 940-1 946.
[14] 程丽娟,刘贵珊,万国玲,等.可见 /近红外高光谱成像技术对长 枣 中 葡 萄 糖 含 量 的 无 损 检 测 [J].发 光 学 报,2019,40(8):1 055-1 063.CHENG L J,LIU G S,WAN G L,et al.Non-destructive detective of glucose contect in Lingwu jujube by Vis/NIR hyperspectral imaging technology [J].Chinese Journal of Luminescence,2019,40(8):1 055-1 063.
[15] 张丽,李志辉,马明星.基于近红外光谱和 FOA-RF 的猪肉新鲜度检测 [J].食品与机械,2025,41(12):51-58.ZHANG L,LI ZH H,MA M X.Pork freshness monitoring based on near-infrared spectroscopy and random forest improved by fruit fly optimization algorithm [J].Food & Machinery,2025,41(12):51-58.
[16] LIU Z,HE Y,CEN H,et al.Deep feature representation with stacked sparse auto-encoder and convolutional neural network for hyperspectral imaging-based detection of cucumber defects[J].Transactions of the ASABE,2018,61(2):425-436.
