Scholarlink

<p>This study employed near-infrared hyperspectral imaging technology (858–1700 nm) for the non-destructive detection of SSC and maturity in 480 kiwifruits during postharvest storage at room temperature (20 ± 1 °C) over a period of 0–14 days. The effectiveness of six spectral preprocessing methods was comprehensively evaluated: multiplicative scatter correction (MSC), standard normal variate (SNV), Savitzky-Golay smoothing (SG), MSC + SNV, MSC + SG, and SNV + SG. Additionally, the performance of three characteristic wavelength selection algorithms was compared: competitive adaptive reweighted sampling (CARS), successive projections algorithm (SPA), and uninformative variable elimination (UVE). Subsequently, four prediction models were constructed and compared: partial least squares regression (PLSR), back propagation neural network (BP), linear regression (LR), and least squares support vector machine (LSSVM). The results demonstrated that the MSC + SG + CARS + LSSVM model yielded optimal performance, with correlation coefficients Rc = 0.881 and Rp = 0.927, root mean square errors RMSEC = 0.590°Brix and RMSEP = 0.597°Brix, and ratio of performance to deviation (RPD) = 2.61. Additionally, genetic algorithm-optimized backpropagation neural network (GA-BP) and radial basis function neural network (RBF) models were developed for storage days discrimination, yielding accuracies of 95.15% and 93.75%, respectively. The results demonstrate that near-infrared hyperspectral imaging technology can effectively assess the internal quality and post-harvest storage days of kiwifruit stored under room temperature (20 ± 1 °C) conditions. This technology facilitates the determination of the optimal transportation window during storage and holds significant potential for quality monitoring and maturity classification in the kiwifruit industry.</p> Graphical Abstract <p></p>

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

Non-Destructive Prediction of SSC and Storage Days Classification of Kiwifruit During Postharvest Storage Using Near-Infrared Hyperspectral Imaging

  • 期刊论文

  • 发表日期：

    2026年4月16日

查看全文
  • Yunfei Li,
  • Yinhu Qiao,
  • Renshan Zhu,
  • Jue Wang,
  • Zhicheng Sun,
  • Sai Yang,
  • Zhiyun Ai,
  • Shuqiang Song

摘要

This study employed near-infrared hyperspectral imaging technology (858–1700 nm) for the non-destructive detection of SSC and maturity in 480 kiwifruits during postharvest storage at room temperature (20 ± 1 °C) over a period of 0–14 days. The effectiveness of six spectral preprocessing methods was comprehensively evaluated: multiplicative scatter correction (MSC), standard normal variate (SNV), Savitzky-Golay smoothing (SG), MSC + SNV, MSC + SG, and SNV + SG. Additionally, the performance of three characteristic wavelength selection algorithms was compared: competitive adaptive reweighted sampling (CARS), successive projections algorithm (SPA), and uninformative variable elimination (UVE). Subsequently, four prediction models were constructed and compared: partial least squares regression (PLSR), back propagation neural network (BP), linear regression (LR), and least squares support vector machine (LSSVM). The results demonstrated that the MSC + SG + CARS + LSSVM model yielded optimal performance, with correlation coefficients Rc = 0.881 and Rp = 0.927, root mean square errors RMSEC = 0.590°Brix and RMSEP = 0.597°Brix, and ratio of performance to deviation (RPD) = 2.61. Additionally, genetic algorithm-optimized backpropagation neural network (GA-BP) and radial basis function neural network (RBF) models were developed for storage days discrimination, yielding accuracies of 95.15% and 93.75%, respectively. The results demonstrate that near-infrared hyperspectral imaging technology can effectively assess the internal quality and post-harvest storage days of kiwifruit stored under room temperature (20 ± 1 °C) conditions. This technology facilitates the determination of the optimal transportation window during storage and holds significant potential for quality monitoring and maturity classification in the kiwifruit industry.

Graphical Abstract