Determination of Chlorophyll and Hardness in Cucumbers by Raman Spectroscopy with Successive Projections Algorithm (SPA) – Extreme Learning Machine (ELM)

Abstract

The chlorophyll content and hardness are critical indicators for evaluating vegetable quality. To overcome the drawbacks of traditional detection methods, Raman spectroscopy was investigated for the determination of chlorophyll content and hardness in cucumbers. Cucumbers at different storage periods were analyzed and a successive projections algorithm – extreme learning machine (SPA-ELM) method was employed to establish a model for chlorophyll content and hardness. The Raman spectra were preprocessed to reduce noise and minimize the background fluorescence. Subsequently, SPA was used to select characteristic wavelengths for chlorophyll content and hardness using 19 and 26 characteristic wavelengths, respectively. ELM was employed to establish a model based on the selected characteristic wavelengths. The predicted results by ELM were compared with those obtained using partial least squares (PLS) and support vector machine (SVM). The results showed that the best accuracy was obtained using the SPA-ELM algorithm. The coefficients of determination (R²) of SPA-ELM model for chlorophyll content and hardness were 0.9569 and 0.9659. The root mean square error (RMSE) values were 0.0038 and 0.3570, respectively. A good correlation coefficient and small RMSE value were obtained, indicating the results to be highly accurate and reliable. Raman spectroscopy combined with SPA-ELM method was shown to rapidly and accurately evaluate the chlorophyll content and hardness of cucumbers.

Keywords:

• chlorophyll content
• cucumber
• hardness
• Raman spectroscopy
• successive projections algorithm – extreme learning machine (SPA-ELM)

Disclosure statement

The authors have no conflicts of interest to declare related to the content of this work.

Additional information

Funding

This work was supported by the Henan Provincial Science and Technology Research Project by grant number 212102110262 and the Henan Provincial Science and Technology Research Project by grant number 212102110077.