Wheat Kernel Variety Identification Based on a Large Near-Infrared Spectral Dataset and a Novel Deep Learning-Based Feature Selection Method

Zhou, Lei; Zhang, Chu; Taha, Mohamed Farag; Wei, Xinhua; He, Yong; Qiu, Zhengjun; Liu, Yufei

doi:10.3389/fpls.2020.575810

Cited by 49 publications

(33 citation statements)

References 45 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…With the development and wide application of machine learning methods [ 32 , 33 ], several scientists recently interested in combining near-infrared hyperspectral imaging and deep learning methods (such as convolutional neural network (CNN), Residual Network (ResNet)) to identify crop varieties. Because of that, different varieties of crop seeds have different characters and values [ 34 – 36 ]. Zhou et al proposed a novel convolutional neural network-based feature selector (CNN-FS) for wheat variety identification with a large spectral dataset of more than 140,000 wheat kernels in 30 wheat varieties [ 34 ], and this method achieved a high accuracy (93.01%) and kept high precision (90.02%) with 60-channel features.…”

Section: Discussionmentioning

confidence: 99%

“…Because of that, different varieties of crop seeds have different characters and values [ 34 – 36 ]. Zhou et al proposed a novel convolutional neural network-based feature selector (CNN-FS) for wheat variety identification with a large spectral dataset of more than 140,000 wheat kernels in 30 wheat varieties [ 34 ], and this method achieved a high accuracy (93.01%) and kept high precision (90.02%) with 60-channel features. Although deep learning methods showed powerful prediction ability in variety identification with seed near-infrared hyperspectral images, they may not be suitable for variety identification with genotype data at the present stage since each variety (class) has only one sample in the training set.…”

Section: Discussionmentioning

confidence: 99%

See 1 more Smart Citation

Effective identification of varieties by nucleotide polymorphisms and its application for essentially derived variety identification in rice

Xiong

Song

et al. 2022

BMC Bioinformatics

View full text Add to dashboard Cite

Background Plant variety identification is the one most important of agricultural systems. Development of DNA marker profiles of released varieties to compare with candidate variety or future variety is required. However, strictly speaking, scientists did not use most existing variety identification techniques for “identification” but for “distinction of a limited number of cultivars,” of which generalization ability always not be well estimated. Because many varieties have similar genetic backgrounds, even some essentially derived varieties (EDVs) are involved, which brings difficulties for identification and breeding progress. A fast, accurate variety identification method, which also has good performance on EDV determination, needs to be developed. Results In this study, with the strategy of “Divide and Conquer,” a variety identification method Conditional Random Selection (CRS) method based on SNP of the whole genome of 3024 rice varieties was developed and be applied in essentially derived variety (EDV) identification of rice. CRS is a fast, efficient, and automated variety identification method. Meanwhile, in practical, with the optimal threshold of identity score searched in this study, the set of SNP (including 390 SNPs) showed optimal performance on EDV and non-EDV identification in two independent testing datasets. Conclusion This approach first selected a minimal set of SNPs to discriminate non-EDVs in the 3000 Rice Genome Project, then united several simplified SNP sets to improve its generalization ability for EDV and non-EDV identification in testing datasets. The results suggested that the CRS method outperformed traditional feature selection methods. Furthermore, it provides a new way to screen out core SNP loci from the whole genome for DNA fingerprinting of crop varieties and be useful for crop breeding.

show abstract

Section: Discussionmentioning

confidence: 99%

Section: Discussionmentioning

confidence: 99%

Effective identification of varieties by nucleotide polymorphisms and its application for essentially derived variety identification in rice

Xiong

Song

et al. 2022

BMC Bioinformatics

View full text Add to dashboard Cite

show abstract

“…The data set used in this study includes of 147,096 wheat kernels mean NIR spectra, measured on 30 varieties of wheat kernels, harvested in 2019 and stored under the same conditions after harvest i.e., dried and packed in woven plastic bags [22]. The wheat kernels come from the wheat plants grown in the same fields.…”

Section: Data Setmentioning

confidence: 99%

“…The second approach involves the use of Convolutional Neural Networks (CNNs) architectures for joint feature extraction and predictive modelling [17,21]. The application of DL for spectral classification is also increasing and DL has already shown to outperform traditional chemometric methods such as PLS-DA and ML methods such as SVM [22,23].…”

Section: Introductionmentioning

confidence: 99%

An automated deep learning pipeline based on advanced optimisations for leveraging spectral classification modelling

Passos

Mishra

2021

Chemometrics and Intelligent Laboratory Systems

View full text Add to dashboard Cite

In deep learning (DL) modelling for spectral data, a major challenge is related to the choice of DL network architecture and the selection of the best hyperparameters. Often, slight changes to the neural architecture or its hyperparameter can have a direct influence on the model's performance, making its robustness questionable. To deal with it, this study presents an automated deep learning modelling based on advanced optimisation techniques involving Hyperband and Bayesian optimisation, to automatically find optimal neural architecture and its hyperparameters to reach robust DL models. The optimisation requires a base neural architecture to be initialized, however, later it automatically adjusts the neural architecture and the hyperparameters to reach the optimal model. Furthermore, to support the interpretation of the DL models, a wavelength weighing schema based on gradient-weighted class activation mapping (Grad-CAM) was implemented. The potential of the approach was showed on a real case of wheat variety classification with near-infrared spectral data. The performance of the classification was compared with that previously reported on the same dataset with different DL and chemometric approaches. The results showed that with the proposed approach a classification accuracy of 94.9% was reached, which was better than the best reported accuracy on the same data set i.e., 93%. Furthermore, the better performance was obtained with a simpler neural architecture compared to what was used in earlier studies. The automated deep learning based on advanced optimisation can support DL modelling of spectral data.

show abstract

“…Recently, nondestructive testing methods based on optical technology, such as infrared spectroscopy technology [ 4 , 5 ], machine vision, and hyperspectral technology [ 6 , 7 , 8 , 9 , 10 , 11 , 12 , 13 ], have received significant attention. Infrared spectroscopy technology identifies the spectral features of seeds [ 14 ] and analyses their internal chemical compositions (such as protein and starch) to classify them. However, this technology can only acquire a small area of spectral information from the seed samples at a time, and many repetitive measurements in different places are needed to represent the entire scenario of adulteration [ 15 ].…”

Section: Introductionmentioning

confidence: 99%

Rice Seed Purity Identification Technology Using Hyperspectral Image with LASSO Logistic Regression Model

Liu

Zeng

Guiju

et al. 2021

Sensors

View full text Add to dashboard Cite

Hyperspectral technology is used to obtain spectral and spatial information of samples simultaneously and demonstrates significant potential for use in seed purity identification. However, it has certain limitations, such as high acquisition cost and massive redundant information. This study integrates the advantages of the sparse feature of the least absolute shrinkage and selection operator (LASSO) algorithm and the classification feature of the logistic regression model (LRM). We propose a hyperspectral rice seed purity identification method based on the LASSO logistic regression model (LLRM). The feasibility of using LLRM for the selection of feature wavelength bands and seed purity identification are discussed using four types of rice seeds as research objects. The results of 13 different adulteration cases revealed that the value of the regularisation parameter was different in each case. The recognition accuracy of LLRM and average recognition accuracy were 91.67–100% and 98.47%, respectively. Furthermore, the recognition accuracy of full-band LRM was 71.60–100%. However, the average recognition accuracy was merely 89.63%. These results indicate that LLRM can select the feature wavelength bands stably and improve the recognition accuracy of rice seeds, demonstrating the feasibility of developing a hyperspectral technology with LLRM for seed purity identification.

show abstract

Wheat Kernel Variety Identification Based on a Large Near-Infrared Spectral Dataset and a Novel Deep Learning-Based Feature Selection Method

Cited by 49 publications

References 45 publications

Effective identification of varieties by nucleotide polymorphisms and its application for essentially derived variety identification in rice

Effective identification of varieties by nucleotide polymorphisms and its application for essentially derived variety identification in rice

An automated deep learning pipeline based on advanced optimisations for leveraging spectral classification modelling

Rice Seed Purity Identification Technology Using Hyperspectral Image with LASSO Logistic Regression Model

Contact Info

Product

Resources

About