Search

Pre-processing is a crucial step in analyzing spectra from Fourier transform infrared (FTIR) spectroscopy because it can reduce unwanted noise and enhance system performance. Here, we present the results of pre-processing technique optimization to facilitate the detection of pepper yellow leaf curl virus (PYLCV)-infected chilli plants using FTIR spectroscopy. Optimization of a range of pre-processing techniques was undertaken, namely baseline correction, normalization (standard normal variate, vector, and min–max), and de-noising (Savitzky-Golay (SG) smoothing, 1st and 2 derivatives). The pre-processing was applied to the mid-infrared spectral range (4000 – 400 cm−1) and the biofingerprint region (1800 – 900 cm−1) then the discrete wavelet transform (DWT) was used for dimension reduction. The pre-processed data were then used as an input for classification using a multilayer perceptron neural network, a support vector machine, and linear discriminant analysis. The pre-processing method with the highest classification model accuracy was selected for the further use in the processing. It was seen that only the SG 1st derivative method applied to both wavenumber ranges could produce 100% accuracy. This result was supported by principal component analysis clustering. Thus, we have demonstrated that by using the right pre-processing technique, classification success can be increased, and the process simplified by optimization and minimization of the technique used.

Pepper yellow leaf curl virus (PYLCV) is a threat to chili plants and can significantly reduce yields. This study aimed as a pilot project to detect PYLCV by analyzing compounds emitted by chili plants using gas chromatography-mass spectrometry (GC-MS). The samples investigated in this research were PYLCV-infected and PYLCV-undetected chili plants taken from commercial chili fields. The infection status was validated by using a polymerase chain reaction (PCR) test. A headspace technique was used to extract the volatile organic compounds emitted by plants. The analysis of GC-MS results began with pre-processing, analyzing sample compound variability with a boxplot analysis, and sample classification by using a multivariate technique. Unsupervised multivariate technique principal component analysis (PCA) was performed to discover whether GC-MS could identify PYLCV-infected or not. The results showed that PYLCV-infected and PYLCV-undetected chili plants could be differentiated, with a total percent variance of the first three principal components reaching 91.32%, and successfully discriminated between PYLCV-infected and PYLCV-undetected chili plants. However, more comprehensive studies are needed to find the potential biomarkers of the infected plants.