Aarhus University Seal

A chemometric method for the viability analysis of spinach seeds by near infrared spectroscopy with variable selection using successive projections algorithm

Research output: Contribution to journal/Conference contribution in journal/Contribution to newspaperJournal articleResearchpeer-review

This paper proposes a chemometric method for evaluating the viability of spinach seeds using near infrared (NIR) spectroscopy and successive projections algorithms (SPA). An essential step of the procedure is to apply the SPA to optimize the choice of variables for multivariate classification. Variable selection using SPA has been described as an optimization problem in which a cost function is minimized. Selecting the correct variables makes the chemometric models more complete, precise, accurate, and less complex. The NIR spectra were processed using the Savitzky-Golay and multiplicative scatter correction techniques. After that, the best wavelength subset was selected using SPA. Different classification techniques are then applied to the dimension-reduced data to determine the seeds’ viability. The results show that the proposed method is less complex compared to existing canonical variance methods (1.7% miscalculation error in the proposed way) and is also easier to implement.

Original languageEnglish
JournalJournal of Near Infrared Spectroscopy
Pages (from-to)24-32
Number of pages9
Publication statusPublished - Feb 2023

    Research areas

  • seed quality assessment, near infrared spectroscopy, chemometrics, variable selection for data classification, successive projections algorithm

See relations at Aarhus University Citationformats

ID: 301320251