Input features and parameters optimization improved the prediction accuracy of support vector regression models based on colorimetric sensor data for detection of aflatoxin B1 in corn

A new method for quantitative detection of aflatoxin B1 (AFB1) in corn based on colorimetric sensor technology was proposed in this study. The characteristic color component combination of the colorimetric sensor was effectively mined by the SRCFS-SVR algorithm, and the PSO-SVR model based on the op...

Full description

Saved in:
Bibliographic Details
Published in:Microchemical journal Vol. 178; p. 107407
Main Authors: Liu, Tao, Jiang, Hui, Chen, Quansheng
Format: Journal Article
Language:English
Published: Elsevier B.V 01.07.2022
Subjects:
Aflatoxin B1
Characteristics of the optimization
Colorimetric sensor
Corn
Support vector machine
Corn
Aflatoxin B1
Support vector machine
Colorimetric sensor
Characteristics of the optimization
ISSN:0026-265X
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:A new method for quantitative detection of aflatoxin B1 (AFB1) in corn based on colorimetric sensor technology was proposed in this study. The characteristic color component combination of the colorimetric sensor was effectively mined by the SRCFS-SVR algorithm, and the PSO-SVR model based on the optimized characteristic combination was established to realize the high-precision detection of AFB1 in corn. This study can provide a detection method and algorithm reference for the quantitative and accurate detection of mycotoxins contamination levels during grain storage. [Display omitted] •This study proposes a method to determine the aflatoxin B1 in corn based on colorimetric sensor.•The SRCFS algorithm was used to select the sensor features.•The PSO algorithm was employed to optimize the parameters of the SVR models.•Seeking an optimal SVM model to achieve the determination of the aflatoxin B1 in corn. A new method for quantitative detection of aflatoxin B1 (AFB1) in corn based on colorimetric sensor technology was proposed in this study. First, we chose 12 kinds of color sensitive materials to make the colorimetric sensor array. The prepared colorimetric sensor array was used to collect the olfactory sensory information of corn samples with different degrees of mildew, and the information was characterized in the form of images, and using a new unsupervised feature selection with multi-subspace randomization and collaboration (SRCFS) algorithm combined with support vector machine regression (SVR) to optimize the image features of the colorimetric sensor to determine the best color components combination. The SVR model was established by using the best color components combination to achieve rapid quantitative analysis of the AFB1 in corn; in the process of SVR model calibration, optimization of SVR parameters C and g using particle swarm optimization (PSO). The research results showed that compared with the PSO-SVR model, the mean of correlation coefficient of prediction (RP) of the SRCFS-PSO-SVR model has increased from 0.97 to 0.98, and the mean of root mean square error of prediction (RMSEP) has decreased from 4.8 μg·kg−1 to 3.5 μg·kg−1; the RP of the best SRCFS-PSO-SVR model was 0.99 and the RMSEP was 2.8 μg·kg−1. The results reveal that the quantitative detection of the AFB1 in corn can be achieved by using colorimetric sensor technology combined with chemometric methods. Moreover, the SRCFS algorithm can efficiently find the feature combination of colorimetric sensor.
ISSN:0026-265X
DOI:10.1016/j.microc.2022.107407