Title
Different Algorithms For Detection Of Malondialdehyde Content In Eggplant Leaves Stressed By Grey Mold Based On Hyperspectral Imaging Technique
Abstract
The feasibility of using hyperspectral imaging (HSI) technique to measure malondialdehyde (MDA) content in eggplant leaves stressed by grey mold was evaluated in this paper. Hyperspectral images of infected and healthy eggplant leaves were obtained in the spectral region of 380 to 1030nm, and their spectral reflectance of region of interest (ROI) was extracted by Environment for Visualizing Images (ENVI 4.7) software. Several pre-processing methods were adopted and partial least squares (PLS) models were established to estimate MDA content in eggplant leaves. In order to reduce high dimensionality of spectral data, competitive adaptive re-weighted sampling (CARS) and latent variables (LV) were carried out to identify the most effective wavebands. The result showed that PLS model based on baseline pre-processing had a good performance for prediction set. On the basis of the effective wavelengths suggested by CARS and LV, PLS and multiple linear regression (MLR) models were established, respectively. Among these models, LV-MLR performed best with the highest value of correlation coefficient (r) and lowest value of root mean square error of prediction (RMSEP) for prediction set. The overall results demonstrated the potentiality of HSI technique as an objective and non-destructive method to detect MDA content in eggplant leaves stressed by grey mold.
Year
DOI
Venue
2015
10.1080/10798587.2015.1015773
INTELLIGENT AUTOMATION AND SOFT COMPUTING
Keywords
Field
DocType
Eggplant, Competitive adaptive reweighted sampling (CARS), Hyperspectral imaging (HSI), Malondialdehyde (MDA), Multiple linear regression (MLR), Latent variables (LV)
Mold,Computer science,Partial least squares regression,Spectral data,Artificial intelligence,Linear regression,Computer vision,Pattern recognition,Hyperspectral imaging,Sampling (statistics),Region of interest,Reflectivity,Machine learning
Journal
Volume
Issue
ISSN
21
3
1079-8587
Citations 
PageRank 
References 
2
0.46
8
Authors
4
Name
Order
Citations
PageRank
Chuanqi Xie120.46
Hailong Wang220.46
Yongni Shao362.21
Yong He44415.57