Fine-grained image classification methods often suffer from the challenge that the subordinate categories within an entry-level category can only be distinguished by subtle differences. Crop disease classification is affected by various visual interferences, including uneven illumination, dew, and equipment jitter. It demands an effective algorithm to accurately discriminate one category from the others. Thus, the representational ability of algorithm needs to be strengthened to learn a robust domain-specific discrimination through an effective way. To address this challenge, a unified convolutional neural network (CNN) denoting the matrix-based convolutional neural network (M-bCNN) was proposed. Its hallmark is the convolutional kernel matrix, whose convolutional layers are arranged parallelly in the form of a matrix, and integrated with DropConnect, exponential linear unit, local response normalization, and so on to defeat over-fitting and vanishing gradient. With a tolerable addition of parameters, it can effectively increase the data streams, neurons, and link channels of the model compared with the commonly used plain networks. Therefore, it will create more non-linear mappings and will enhance the representational ability with a tolerable growth of parameters. The images of winter wheat leaf diseases were utilized as experimental samples for their strong similarities among sub-categories. A total of 16 652 images containing eight categories were collected from Shandong Province, China, and were augmented into 83 260 images. The M-bCNN delivered significant improvements and achieved an average validation accuracy of 96.5% and a testing accuracy of 90.1%; this outperformed AlexNet and VGG-16. The M-bCNN demonstrated accuracy gains with a convolutional kernel matrix in fine-grained image classification. INDEX TERMS Convolutional neural network, fine-grained image classification, deep learning, convolutional kernel matrix, wheat leaf diseases.
Previous studies have demonstrated that the p.Lys232Ala substitution in the acylCoA: diacylglycerol acyltransferase (DGAT1) gene and the p.Phe279Tyr mutation in the growth hormone receptor (GHR) gene are the causative quantitative trait loci underlying milk yield and composition on BTA14 and BTA20 respectively. To examine their applications in the genetic improvement of Chinese dairy cattle productivity, we herein investigated the effects of the DGAT1 p.Lys232Ala and GHR p.Phe279Tyr mutations on milk, fat and protein yield, as well as fat and protein percentage in the milk of 1222 Holstein cows. Genotyping was performed using PCR-RFLP for DGAT1 or primer-introduced restriction analysis (PCR-PIRA) for GHR. With a mixed animal model, the significant associations of the DGAT1 p.Lys232Ala substitution with 305-day milk, fat and protein yield were identified (P = 0.0001). The DGAT1 allele that encode lysine at position 232 was associated with increased 305-day milk fat yield, but with decreased 305-day milk and protein yield, whereas the GHR p.Phe279Tyr mutation was found to be significantly associated with protein percentage (P = 0.0014). The allele substitution effect of p.279Phe by p.279Tyr may lead to a significant increase in protein percentage. Our findings indicate that DGAT1 p.232Ala and GHR p.279Phe could be used to increase milk yield and protein yield of Chinese Holstein cows.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.