A Rapid and Highly Efficient Method for the Identification of Soybean Seed Varieties: Hyperspectral Images Combined with Transfer Learning

Zhu, Shaolong; Zhang, Jinyu; Chao, Maoni; Xu, Xiaoxin; Song, Puwen; Zhang, Jinlong; Huang, Zhongwen

doi:10.3390/molecules25010152

Cited by 52 publications

(26 citation statements)

References 52 publications

(49 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Quercetin, rich in the stems and leaves of buckwheat, sea buckthorn, hawthorn, and onion, exists mostly in the form of glycosides, such as rutin and hyperoside, and can be extracted by alkaline extraction and acid precipitation [ 28 , 29 ]. The formula of quercetin is shown in Fig.…”

Section: Flavonoids For the Treatment Of Diabetic Nephropathymentioning

confidence: 99%

Flavonoids on diabetic nephropathy: advances and therapeutic opportunities

Xiaolin

et al. 2021

Chin Med

View full text Add to dashboard Cite

With the advances in biomedical technologies, natural products have attracted substantial public attention in the area of drug discovery. Flavonoids are a class of active natural products with a wide range of pharmacological effects that are used for the treatment of several diseases, in particular chronic metabolic diseases. Diabetic nephropathy is a complication of diabetes with a particularly complicated pathological mechanism that affects at least 30% of diabetic patients and represents a great burden on public health. A large number of studies have shown that flavonoids can alleviate diabetic nephropathy. This review systematically summarizes the use of common flavonoids for the treatment of diabetic nephropathy. We found that flavonoids play a therapeutic role in diabetic nephropathy mainly by regulating oxidative stress and inflammation. Nrf-2/GSH, ROS production, HO-1, TGF-β1 and AGEs/RAGE are involved in the process of oxidative stress regulation. Quercetin, apigenin, baicalin, luteolin, hesperidin, genistein, proanthocyanidin and eriodictyol were found to be capable of alleviating oxidative stress related to the aforementioned factors. Regarding inflammatory responses, IL-1, IL-6β, TNF-α, SIRT1, NF-κB, and TGF-β1/smad are thought to be essential. Quercetin, kaempferol, myricetin, rutin, genistein, proanthocyanidin and eriodictyol were confirmed to influence the above targets. As a result, flavonoids promote podocyte autophagy and inhibit the overactivity of RAAS by suppressing the upstream oxidative stress and inflammatory pathways, ultimately alleviating DN. The above results indicate that flavonoids are promising drugs for the treatment of diabetic nephropathy. However, due to deficiencies in the effect of flavonoids on metabolic processes and their lack of structural stability in the body, further research is required to address these issues.

show abstract

Section: Flavonoids For the Treatment Of Diabetic Nephropathymentioning

confidence: 99%

Flavonoids on diabetic nephropathy: advances and therapeutic opportunities

Xiaolin

et al. 2021

Chin Med

View full text Add to dashboard Cite

show abstract

“…The model learned rich feature representations for a wide variety of images [78-80]. In order to contribute to the solution of many problems, the AlexNet pretrained model has been used in many scientific studies [81-83].…”

Section: Architecture Of the 2d-cnn Modelmentioning

confidence: 99%

Detection of Epileptic Seizure Using Pretrained Deep Convolutional Neural Network and Transfer Learning

2020

View full text Add to dashboard Cite

Introduction: The diagnosis of epilepsy takes a certain process, depending entirely on the attending physician. However, the human factor may cause erroneous diagnosis in the analysis of the EEG signal. In the past 2 decades, many advanced signal processing and machine learning methods have been developed for the detection of epileptic seizures. However, many of these methods require large data sets and complex operations. Methods: In this study, an end-to-end machine learning model is presented for detection of epileptic seizure using the pretrained deep two-dimensional convolutional neural network (CNN) and the concept of transfer learning. The EEG signal is converted directly into visual data with a spectrogram and used directly as input data. Results: The authors analyzed the results of the training of the proposed pretrained AlexNet CNN model. Both binary and ternary classifications were performed without any extra procedure such as feature extraction. By performing data set creation from short-term spectrogram graphic images, the authors were able to achieve 100% accuracy for binary classification for epileptic seizure detection and 100% for ternary classification. Discussion/Conclusion: The proposed automatic identification and classification model can help in the early diagnosis of epilepsy, thus providing the opportunity for effective early treatment.

show abstract

“…In 2015, Yang et al used a support vector machine (SVM) to identify waxy corn seeds, achieving the highest identification accuracy of 98.2% [ 27 ]. In 2020, Zhu et al used a convolutional neural network to identify hyperspectral images of six types of soybean seeds with an average recognition rate of 91% [ 28 ]. The identification methods of rice can be broadly classified into two categories.…”

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

A Rapid and Highly Efficient Method for the Identification of Soybean Seed Varieties: Hyperspectral Images Combined with Transfer Learning

Cited by 52 publications

References 52 publications

Flavonoids on diabetic nephropathy: advances and therapeutic opportunities

Flavonoids on diabetic nephropathy: advances and therapeutic opportunities

Detection of Epileptic Seizure Using Pretrained Deep Convolutional Neural Network and Transfer Learning

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

Contact Info

Product

Resources

About