Recently, visible/near-infrared (Vis/NIR) spectroscopy has been used in the agricultural field, especially in the food industry, for monitoring food quality, postharvest handling of products, and identification of contamination on animal feeds, as well as prediction of a variety of fruits or vegetables. In this study, six products of the cucurbitaceous commodity, including zucchini, bitter gourd, ridge gourd, melon, chayote, and cucumber, were classified using Vis/NIR spectral data. After testing spectral data as feature, we also extracted statistical features and tested them with k-nearest neighbor, Bayes, decision tree, and support vector machines classifiers. We obtained a classification accuracy rate of 99 on the test data by applying standard normal variate technique as a preprocessing stage. The results showed that cucurbitaceous commodity could be successfully classified using Vis/NIR spectra data.
展开▼
机译：最近，可见光/近红外 （Vis/NIR） 光谱已用于农业领域，尤其是食品工业，用于监测食品质量、产品收获后处理、动物饲料污染识别以及各种水果或蔬菜的预测。本研究采用可见光/近红外光谱数据对西葫芦、苦瓜、脊葫芦、甜瓜、佛手瓜、黄瓜等6种葫芦类产品进行分类。在测试光谱数据作为特征后，我们还提取了统计特征，并使用 k 最近邻、贝叶斯、决策树和支持向量机分类器对其进行了测试。我们采用标准正态变异技术作为预处理阶段，在测试数据上获得了99%的分类准确率。结果表明，利用Vis/NIR光谱数据可以成功地对葫芦科商品进行分类。
展开▼
