Abstract
Objective: To propose a new solution to overcome the two challenges of data with spikes and small sample sizes in nectarine hyperspectral measurement. Methods: Based on hyperspectral imaging technology, image processing methods were used to identify the area of nectarines in the hyperspectral image, and the spectral reflectance data of the area was calculated to form a hyperspectral curve image. For hyperspectral image data with spikes and noise, compared the effects of several data preprocessing methods, including polynomial smoothing algorithm (SG), multivariate scatter correction algorithm (MSC), standard normal variate algorithm (SNV), first-order derivative operator (D1), and second-order derivative operator (D2) on model prediction accuracy. To address the high-dimensional and small sample size characteristics of the data, the principal component analysis algorithm (PCA) was used for dimensionality reduction, followed by outlier removal using the Mahalanobis distance measure method (MD). Finally, the Kennard-Stone algorithm (KS) was used to divide the data into training and testing sets, and the partial least squares regression (PLSR) model, which performed well in the small sample scenario, was selected for estimation and analysis of nectarine water content. Results: The SG-PCA-MD-KS-PLSR model performed best for estimating nectarine water content when there were spikes and noise in the hyperspectral curve. The coefficient of determination (R2) was 0.928, and the root mean square error (RMSE) was 0.008 4 on the training set. The R2 was 0.926, and the RMSE was 0.009 2 on the testing set. In further experiments grading nectarines based on their water content, the model's predictions showed good performance. The accuracy rate of grading was 0.956 for the training set and 0.923 for the testing set. Conclusion: By using hyperspectral imaging technology and establishing the SG-PCA-MD-KS-PLSR model, non-destructive estimation of nectarine water content and grading of nectarine water content can be achieved in scenarios with small hyperspectral sample sizes and noise.
Publication Date
12-26-2023
First Page
123
Last Page
129
DOI
10.13652/j.spjx.1003.5788.2022.80560
Recommended Citation
Aidi, GAO; Fengzhang, QIAO; Wenxuan, ZHU; Xiaopin, ZHONG; and Yuanlong, DENG
(2023)
"Prediction of moisture content of hummus peach based on multi-burr hyperspectral data,"
Food and Machinery: Vol. 39:
Iss.
10, Article 19.
DOI: 10.13652/j.spjx.1003.5788.2022.80560
Available at:
https://www.ifoodmm.cn/journal/vol39/iss10/19
References
[1] 吴龙国, 何建国, 贺晓光, 等. 高光谱图像技术在水果无损检测中的研究进展[J]. 激光与红外, 2013, 43（9）: 990-996.
WU L G, HE J G, HE X G, et al. Research progress of hyperspectral imaging technology in non-destructive detection of fruit[J]. Laser & Infrared, 2013, 43（9）: 990-996.
[2] 杨昆程, 孙梅, 陈兴海. 水果成熟度的高光谱成像无损检测研究[J]. 食品科学技术学报, 2015, 33（4）: 63-67.
YANG K C, SUN M, CHEN X H. Nondestructive inspect of fruit maturity with hyperspectral imaging technology[J]. Journal of Food Science and Technology, 2015, 33（4）: 63-67.
[3] 刘燕德, 邓清. 高光谱成像技术在水果无损检测中的应用[J]. 农机化研究, 2015, 37（7）: 227-231, 235.
LIU Y D, DENG Q. Research progress of hyperspectral imaging technology in non-destructive detection of fruit[J]. Journal of Agricultural Mechanization Research, 2015, 37（7）: 227-231, 235.
[4] 廉孟茹, 张淑娟, 任锐, 等. 基于高光谱技术的鲜食水果玉米含水率无损检测[J]. 食品与机械, 2021, 37（9）: 127-132.
LIAN M R, ZHANG S J, REN R, et al. Nondestructive detection of moisture content in fresh fruit corn based on hyperspectral technology[J]. Food & Machinery, 2021, 37（9）: 127-132.
[5] 杨佳, 刘强, 赵楠, 等. 基于高光谱成像的干燥胡萝卜片水分及类胡萝卜素含量无损检测和可视化分析[J]. 食品科学, 2020, 41（12）: 285-291.
YANG J, LIU Q, ZHAO N, et al. Hyperspectral imaging for Non-destructive determination and visualization of moisture and carotenoid contents in carrot slices during drying[J]. Food Science, 2020, 41（12）: 285-291.
[6] COGDILL R P, HURBURGH C R, RIPPKE G R, et al. Single-kernel maize analysis by near-infrared hyperspectral imaging[J]. Transactions of the ASAE, 2004, 47（1）: 311.
[7] 吴静珠, 张乐, 李江波, 等. 基于高光谱与集成学习的单粒玉米种子水分检测模型[J]. 农业机械学报, 2022, 53（5）: 302-308.
WU J Z, ZHANG L, LI J B, et al. Detection model of moisture content of single maize seed based on hyperspectral image and ensemble learning[J]. Transactions of the Chinese Society for Agricultural Machinery, 2022, 53（5）: 302-308.
[8] 于一凡, 潘军, 邢立新, 等. 基于马氏距离的遥感图像高温目标识别方法研究[J]. 遥感信息, 2013, 28（5）: 90-94.
YU Y F, PAN J, XING L X, et al. Identification of high temperature Targets in remote sensing imagery based on mahalanobis distance[J]. Remote Sensing Information, 2013, 28（5）: 90-94.
[9] SAVITZKY A, GOLAY M J E. Smoothing and differentiation of data by simplified least squares procedures[J]. Analytical Chemistry, 1964, 36（8）: 1 627-1 639.
[10] 郭冰青. 反射光谱及高光谱成像结合多元分析方法快速检测肉类品质[D]. 合肥: 安徽大学, 2021: 9.
GUO B Q. Rapid detection of meat quality using reflectance spectroscopy and hyperspectral imaging with multivariate analysis methods[D]. Hefei: Anhui University, 2021: 9.
[11] 马帅帅, 于慧春, 殷勇, 等. 黄瓜水分和硬度高光谱特征波长选择与预测模型构建[J]. 食品与机械, 2021, 37（2）: 145-151.
MA S S, YU H C, YIN Y, et al. Selection of hyperspectral characteristic wavelength and construction of prediction model for cucumber hardness and moisture[J]. Food & Machinery, 2021, 37（2）: 145-151.
[12] KANDPAL L M, LOHUMI S, KIM M S, et al. Near-infrared hyperspectral imaging system coupled with multivariate methods to predict viability and vigor in muskmelon seeds[J]. Sensors and Actuators B: Chemical, 2016, 229: 534-544.