Background: Imported soybeans are prone to heat damage due to high storage temperatures or poor ventilation during transportation. Heat damage directly degrades the quality of the produce and greatly reduces the edible value of soybeans. Rapid and nondestructive techniques for assessing the quality of imported soybeans are in demand. Hyperspectral imaging (HSI) technology was used to distinguish sound soybeans from heat-damaged soybeans.
Results: For testing the effectiveness of preprocessing methods in enhancing model performance, five different preprocessing methods were implemented to original spectra. To solve problems related to accuracy, efficiency, and model interpretability caused by high-dimensional HSI data, three waveband selection algorithms - dependency measure (DM-NRS), mutual information (MI-NRS) and variable precision (VP-NRS) - based on neighborhood rough set (NRS) theory were proposed to identify the waveband subsets with optimal distinguishing ability. The effectiveness of preprocessing methods and waveband selection algorithms was validated by establishing two kinds of models: extreme learning machine (ELM) and random forest (RF) models. In addition to the classification accuracy, the robustness of the waveband selection algorithms was studied. The results demonstrated that the Savitzky-Golay (SG) smoothing preprocessing method combined with the MI-NRS waveband selection algorithm and the ELM classifier achieved the best classification and robustness results. Classification accuracy reached 99.98% when using only two optimal wavebands, and reached 100% when using more than four optimal wavebands.
Conclusion: The results prove that the HSI technology is an accurate, effective, and nondestructive technique for classifying sound and heat-damaged soybeans. © 2019 Society of Chemical Industry.
Keywords: heat damage; hyperspectral imaging; identification; neighborhood rough set; soybean; waveband selection.
© 2019 Society of Chemical Industry.