|YASMIN, JANNAT - Chungnam National University
|AHMED, MOHAMMED - Chungnam National University
|LOHUMI, SANTOSH - Chungnam National University
|WAKHOLI, COLIN - Chungnam National University
|CHO, BYOUNG-KWAN - Chungnam National University
Submitted to: Sensors
Publication Type: Peer Reviewed Journal
Publication Acceptance Date: 3/5/2019
Publication Date: 3/8/2019
Citation: Yasmin, J., Ahmed, M., Lohumi, S., Wakholi, C., Kim, M.S., Cho, B. 2019. Classification method for viability screening of naturally aged watermelon seeds using FT-NIR spectroscopy. Sensors. 19(5):1190. https://doi.org/10.3390/s19051190.
Interpretive Summary: VViability analysis of stored seeds before sowing is of great importance because plant seeds can lose viability during long term storage. A spectroscopic method was developed for discriminating between viable and nonviable watermelon seeds that had been stored for four years (natural aging) in controlled conditions. Spectral data for three different varieties of triploid watermelon seeds were first acquired, and then each seed’s spectral measurement was assigned to either the viable or non-viable group based on the results of standard germination tests performed after the spectral data acquisition. A classification model was developed to assess seed viability and then tested on one hundred sample seeds randomly selected from the three varieties, with the classification results exhibiting relatively high classification accuracies for both viable (87.7%) and nonviable seeds (82%). The method developed in this research can benefit the produce seed industry and produce growers by providing a rapid and nondestructive technique to determine the viability of seeds.
Technical Abstract: 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 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.