Classification for GM and Non-GM Maize Kernels Based on NIR Spectra and Deep Learning

Abstract

The classification of GM and non-GM maize kernels is fundamental for further analysis of the gene action in maize. Therefore, a complete and novel detection scheme based on near-infrared spectra was designed to distinguish GM and non-GM maize kernels. Hyperspectral images (935–1720 nm) of 777 maize kernels from 3 kinds were captured, and the average spectra of the maize kernels were extracted for modeling analysis. The classical modeling methods based on feature engineering were first studied, and the backpropagation neural network–genetic algorithm model showed the best performance with a prediction accuracy of 0.861. Then, novel modeling methods based on deep learning were developed. To dig out the interactive information between different bands and match the application scenarios, the original spectra were transformed into two-dimensional matrices before establishing the deep learning models. A modified convolution neural network (i.e., VGG net) with dilated convolution was finally constructed to classify the maize kernels, and the prediction accuracy reached 0.961. This research provides a referential and novel way to detect GM maize kernels. Future research will improve the detection scheme for monitoring unauthorized GM organisms by introducing the visualization technology of deep learning.

Maize Kernel Quality Detection Based on Improved Lightweight YOLOv7

“…This method improves the overall crack detection and crack omission rates by 7.86% and 7.29%, respectively. Wei et al [28] developed a novel modeling approach based on deep learning based on a backpropagation neural network-genetic algorithm model. The original spectrum was converted into a two-dimensional matrix to construct an improved convolutional neural network with dilated convolution to classify the maize kernels, and the accuracy reached 96.1%.…”

Air pressure prediction model based on the fusion of laser-induced plasma images and spectra

“…[23][24][25] Wei et al constructed an improved convolutional neural network model with expanded convolutions for classifying genetically and non-genetically modied corn kernels; the predictive accuracy reached 96.1%, which was 10% higher than the classical model. 26 An attention mechanism can improve the model's focus on specic parts of the input, and so researchers oen integrate an attention module into models to improve performance. 18,27,28 Zeng et al combined the convolutional block attention module (CBAM) with the convolutional neural network (CNN) and long short-term memory (LSTM) to propose the CBAM-CNN-LSTM model for a portable LIBS system.…”