Classification Method for Viability Screening of Naturally Aged Watermelon Seeds Using FT-NIR Spectroscopy
Classification Method for Viability Screening of Naturally Aged Watermelon Seeds Using FT-NIR Spectroscopy
复制标题
DOI：
10.3390/s19051190
复制
发表时间：
2019-03
期刊：
影响因子：
--
通讯作者：
Jannat Yasmin;Mohammed Raju Ahmed;S. Lohumi;Collins Wakholi;M. Kim;B. Cho
中科院分区：
文献类型：
--
作者：
Jannat Yasmin;Mohammed Raju Ahmed;S. Lohumi;Collins Wakholi;M. Kim;B. Cho
在播种前对储存的种子进行生活力分析非常重要，因为植物种子在长期储存时会失去其生活力。在这项研究中，傅立叶变换近红外光谱（FT-NIR）的潜力进行了研究，以区分可行的和不可行的三倍体西瓜种子的三个不同的品种储存四年（自然老化）在受控条件下。针对三倍体西瓜种子种皮较厚的特点，首次确定了FT-NIR光源的穿透深度，以保证有效采集种胚光谱。在通过进行标准发芽试验确认活力后，将收集的光谱数据分为活力组和非活力组。实验结果表明，偏最小判别分析（PLS-DA）模型对3种不同西瓜种子的混合样本具有较高的分类精度。最后，开发的模型进行了评估与外部数据集（收集在不同的时间）的100个样本随机选择的三个品种。结果产生一个很好的分类准确率为可行的（87.7%）和非可行的种子（82%），因此开发的模型可以被认为是一个“通用模型”，因为它可以应用于三个不同品种的种子和数据收集在不同的时间。
Viability analysis of stored seeds before sowing has a great importance as plant seeds lose their viability when they exposed to long term storage. In this study, the potential of Fourier transform near infrared spectroscopy (FT-NIR) was investigated to discriminate between viable and non-viable triploid watermelon seeds of three different varieties stored for four years (natural aging) in controlled conditions. Because of the thick seed-coat of triploid watermelon seeds, penetration depth of FT-NIR light source was first confirmed to ensure seed embryo spectra can be collected effectively. The collected spectral data were divided into viable and nonviable groups after the viability being confirmed by conducting a standard germination test. The obtained results showed that the developed partial least discriminant analysis (PLS-DA) model had high classification accuracy where the dataset was made after mixing three different varieties of watermelon seeds. Finally, developed model was evaluated with an external data set (collected at different time) of hundred samples selected randomly from three varieties. The results yield a good classification accuracy for both viable (87.7%) and nonviable seeds (82%), thus the developed model can be considered as a “general model” since it can be applied to three different varieties of seeds and data collected at different time.