Identification of Five Similar Cinnamomum Wood Species Using Portable Near-Infrared Spectroscopy

The feasibility of using a portable near-infrared (NIR) spectrometer combined with partial least squares for discrimination analysis (PLS-DA) to identify five similar Cinnamomum wood species was investigated. To improve model reliability and identification accuracy, the effects three main spectra preprocessing methods their combinations were examined. Then, performance created by collected before after specimen surface sanding compared. In PLS-DA based on preprocessed standard normal variate (SNV) first derivative combined, accuracy above 95%, compared results demonstrated natural change influences NIR performance. It shown that device can be used rapidly accurately species.