Abstract

Near-infrared (NIR) hyperspectroscopy becomes an emerging nondestructive sensing technology for inspection of crop seeds. A large spectral dataset of more than 140,000 wheat kernels in 30 varieties was prepared for classification. Feature selection is a critical segment in large spectral data analysis. A novel convolutional neural network-based feature selector (CNN-FS) was proposed to screen out deeply target-related spectral channels. A convolutional neural network with attention (CNN-ATT) framework was designed for one-dimension data classification. Popular machine learning models including support vector machine (SVM) and partial least square discrimination analysis were used as the benchmark classifiers. Features selected by conventional feature selection algorithms were considered for comparison. Results showed that the designed CNN-ATT produced a higher performance than the compared classifier. The proposed CNN-FS found a subset of features, which made a better representation of raw dataset than conventional selectors did. The CNN-ATT achieved an accuracy of 93.01% using the full spectra and keep its high precision (90.20%) by training on the 60-channel features obtained via the CNN-FS method. The proposed methods have great potential for handling the analyzing tasks on other large spectral datasets. The proposed feature selection structure can be extended to design other new model-based selectors. The combination of NIR hyperspectroscopic technology and the proposed models has great potential for automatic nondestructive classification of single wheat kernels.

Highlights

  • Wheat is one of the most important agricultural products

  • A convolutional neural network (CNN) classifier with attention mechanism was designed for wheat kernel identification

  • The convolutional neural network with attention (CNN-ATT) method produced a higher precision than that realized by partial least squares discrimination analysis (PLSDA) and Radial basis function support vector machine classifier (RBF-SVC)

Read more

Summary

Introduction

Wheat is one of the most important agricultural products. Various varieties of wheat are cultivated to adapt to different planting environments and to improve the yield and quality. Mass spectrometry-based methods have been widely accepted for inspection of wheat quality owing to their high sensitivity (Koistinen and Hanhineva, 2017). They are destructive methods, and expensive instrument is required. Hyperspectral imaging (HSI) is an emerging tool with the advantages of collecting spectral and spatial information simultaneously. It allows a user to collect data of many samples by scanning a single HSI image. It is very suitable for analyzing large quantities of crop kernels (Feng et al, 2019)

Objectives
Methods
Results
Discussion
Conclusion
Full Text
Paper version not known

Talk to us

Join us for a 30 min session where you can share your feedback and ask us any queries you have

Schedule a call