Fourier transform infrared spectrum pre-processing technique selection for detecting PYLCV-infected chilli plants
[Display omitted] •Pepper Yellow Leaf Curl Virus (PYLCV) can reduce the productivity of chilli plants by between 20% and 100%.•The disease exhibits the same symptoms as plants with mineral and water deficiencies so is often not correctly detected.•We propose optimized Fourier Transform Infrared Spec...
Saved in:
| Published in: | Spectrochimica acta. Part A, Molecular and biomolecular spectroscopy Vol. 278; p. 121339 |
|---|---|
| Main Authors: | , , , , , , |
| Format: | Journal Article |
| Language: | English |
| Published: |
Elsevier B.V
05-10-2022
|
| Subjects: | |
| Online Access: | Get full text |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| Summary: | [Display omitted]
•Pepper Yellow Leaf Curl Virus (PYLCV) can reduce the productivity of chilli plants by between 20% and 100%.•The disease exhibits the same symptoms as plants with mineral and water deficiencies so is often not correctly detected.•We propose optimized Fourier Transform Infrared Spectroscopy spectra pre-processing to detect PYLCV-infected chilli plants.•We choose the method from denoising, normalizing and baseline correction that delivers the highest classification accuracy.•Savitzky-Golay 1st derivative pre-processing was the best method, enabling subsequent classification accuracy of up to 100%.
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. |
|---|---|
| ISSN: | 1386-1425 |
| DOI: | 10.1016/j.saa.2022.121339 |