A classification method for soybean leaf diseases based on an improved ConvNeXt model.

Deep learning technologies have enabled the development of a variety of deep learning models that can be used to detect plant leaf diseases. However, their use in the identification of soybean leaf diseases is currently limited and mostly based on machine learning methods. In this investigation an enhanced deep learning network model was developed to recognize soybean leaf diseases more accurately. The improved network model consists of three parts: feature extraction, attention calculation, and classification. The dataset used was first diversified through data augmentation operations such as random masking to enhance network robustness. An attention module was then used to generate feature maps at various depths. This increased the network's focus on discriminative features, reduced background noise, and enabled the use of the LeakyReLu activation function in the attention module to prevent situations in which neurons fail to learn when the input is negative. Finally, the extracted features were then integrated using a fully connected layer, and the predicted disease category inferred to improve the classification accuracy of soybean leaf diseases. The average recognition accuracy of the improved network model for soybean leaf diseases was 85.42% both higher than the six deep learning comparison models (ConvNeXt (66.41%), ResNet50 (72.22%), Swin Transformer (77.00%), MobileNetV3 (67.27%), ShuffleNetV2 (59.89%), and SqueezeNet (72.92%)), thus proving the effectiveness of the improved method.The model proposed in this paper was also tested on the grapevine leaf dataset, and the performance ability of the improved network model remained due to other common network models, and overall the proposed network model was very effective in leaf disease identification.

Gut microbiota, host lipid metabolism and regulation mechanism of high-fat diet induced mice following different probiotics-fermented wheat bran intervention.

Wheat bran (WB) was fermented by Lactobacillus rhamnosus, Lactobacillus plantarum, Lactobacillus brevis (LAB-FWB), respectively, and their corresponding mechanism of obesity alleviation via gut microbiota and lipid metabolism was investigated. Results indicated LAB-FWB reduced body weight and serum glucose, followed by an improved lipid profile in obese mice compared with WB. All LAB-FWB interventions led to an enriched steroid hormone biosynthesis. LGG-WB significantly up-regulated genes in arachidonic acid metabolism, bile secretion and linoleic acid metabolism. While LB-WB down-regulated genes in PPAR signaling pathway and LP-WB up-regulated genes in linoleic acid metabolism, indicate their different regulation patterns. Furthermore, LAB-FWB reduced Firmicutes/Bacteroidetes ratio and returned HFD-dependent bacteria Colidextribacter and Erysipelatoclostridium to be normalized. Interestingly, LAB-FWB significantly enriched lipid-related pathways, benefiting xanthohumol, prostaglandin F2alpha, LPI 18:2 and lipoamide biosynthesis in lipid metabolic pathway, but not found in WB group. Among them, treatment with LGG-WB exerted the greatest function on alleviating obesity syndromes.

Gut microbiota derived structural changes of phenolic compounds from colored rice and its corresponding fermentation property.

The influence of phenolic compound extracts from three colored rice cultivars on the gut microbiota was investigated. The results revealed that protocatechuic acid, chlorogenic acid, caffeic acid and p-coumaric acid were the major metabolites after gut microbiota fermentation. The presence of phenolic compounds led to a significantly decreased ratio of Firmicutes and Bacteroidetes, while the abundance of Proteobacteria decreased. At the genus level, phenolic compounds promoted an increase of Prevotella, Megamonas and Bifidobacterium, while the abundance of Bacteroides and Escherichia-Shigella was inhibited. The concentration of ferulic acid and syringic acid was positively correlated with Bifidobacterium, while Megamonas was positively correlated with catechin and caffeic acid. The abundance of Escherichia-Shigella and Citrobacter was found to be significantly negatively correlated with chlorogenic acid. More importantly, this study revealed that the presence of phenolic compounds generated more propionate, followed by acetate, but not butyrate after gut microbiota fermentation.

Starch acylation of different short-chain fatty acids and its corresponding influence on gut microbiome and diabetic indexes.

This study investigated correlations between gut microbiota and type 2 diabetic (T2D) indexes using either native resistant starch (RS, from high amylose maize starch, HAMS) or acylated starch via short-chain fatty acids (SCFAs) acylation. Compared to HAMS, consumption of acylated starch achieved a greater impact on the improvement of T2D indexes in term of body weight loss, fasting blood glucose, serum insulin level and amino acid metabolism. Intervention with acylated starches alleviated metabolism disorders and modified the gut microbiota. This study found all the acylated starch significantly enhanced the growth of SCFAs-producing bacteria compared to its native HAMS, and this change was highly consistent with their corresponding SCFAs concentration both in serum and fecal samples. This is the first reported to reveal that propionylated HAMS promoted the abundance of Bifidobacterium, while acetylated and butylated HAMS benefited the enrichment of Coprococcus, Butyricimonas and Blautia, which may indicate their different intervention pathway.