Single-Kernel FT-NIR Spectroscopy for Detecting Supersweet Corn (Zea mays L. Saccharata Sturt) Seed Viability with Multivariate Data Analysis

Abstract

The viability and vigor of crop seeds are crucial indicators for evaluating seed quality, and high-quality seeds can increase agricultural yield. The conventional methods for assessing seed viability are time consuming, destructive, and labor intensive. Therefore, a rapid and nondestructive technique for testing seed viability has great potential benefits for agriculture. In this study, single-kernel Fourier transform near-infrared (FT-NIR) spectroscopy with a wavelength range of 1000–2500 nm was used to distinguish viable and nonviable supersweet corn seeds. Various preprocessing algorithms coupled with partial least squares discriminant analysis (PLS-DA) were implemented to test the performance of classification models. The FT-NIR spectroscopy technique successfully differentiated viable seeds from seeds that were nonviable due to overheating or artificial aging. Correct classification rates for both heat-damaged kernels and artificially aged kernels reached 98.0%. The comprehensive model could also attain an accuracy of 98.7% when combining heat-damaged samples and artificially aged samples into one category. Overall, the FT-NIR technique with multivariate data analysis methods showed great potential capacity in rapidly and nondestructively detecting seed viability in supersweet corn.

Single-Kernel FT-NIR Spectroscopy for Detecting Maturity of Cucumber Seeds Using a Multiclass Hierarchical Classification Strategy

“…The NIR reflectance spectra were calculated as log (1/R), where R represents the reflectance. A schematic diagram of the SK-NIRS can be found in previous work [20]. Averaged spectra from 16 successive scans of each individual seed were obtained for further analysis.…”

“…It is widely known that near infrared spectral patterns, especially in the wavelength ranges of 1600-1800 nm and 2100-2200 nm, contain information about cis-unsaturation as well as about the carbon chain itself according to many reports [17][18][19]. Previous work has shown that the SK-NIRS approach coupled with chemometrics can be used to identify differences in viability in corn seeds [20]. Since the maturation stage of seeds at harvest can vary over a long time period, i.e., from 30 days after pollination (DAP) to 50 DAP, the differentiation of maturation stage results in different classes.…”

Analysis of Operational Mechanized Technologies of Seed Separation Under Artificial Forest Restoration

“…Цвет является довольно устойчивым генетически и наиболее простым в измерении биофизическими мето-дами феномаркером для контроля качества семян. Оптическая технология сепарации семян, согласно обширным исследованиям [25,28,31,32,33,34,36,38,39,40,42,43,44,45,46,47,49], способна определять происхождение и жизнеспособность репродуктивного материала. При необходимости нетрудно реализовать и классификацию семян по количественному признаку, и элиминирование примесей.…”

Identification of heat damage in imported soybeans based on hyperspectral imaging technology

“…The general steps involved in classifying sound and heat‐damaged soybeans using HSI technology are image processing, spectral preprocessing, waveband selection, and classification model building . The goal of spectral preprocessing is to correct unwanted systematic sample‐to‐sample variation, such as kernel shape and kernel surface roughness, and to weaken the impact of length change of light scattering and light path . Hidden information can be enlarged and unwanted information can be removed by spectral preprocessing.…”