Deep migration learning-based recognition of diseases and insect pests in Yunnan tea under complex environments.

BACKGROUND: The occurrence, development, and outbreak of tea diseases and pests pose a significant challenge to the quality and yield of tea, necessitating prompt identification and control measures. Given the vast array of tea diseases and pests, coupled with the intricacies of the tea planting environment, accurate and rapid diagnosis remains elusive. In addressing this issue, the present study investigates the utilization of transfer learning convolution neural networks for the identification of tea diseases and pests. Our objective is to facilitate the accurate and expeditious detection of diseases and pests affecting the Yunnan Big leaf kind of tea within its complex ecological niche. RESULTS: Initially, we gathered 1878 image data encompassing 10 prevalent types of tea diseases and pests from complex environments within tea plantations, compiling a comprehensive dataset. Additionally, we employed data augmentation techniques to enrich the sample diversity. Leveraging the ImageNet pre-trained model, we conducted a comprehensive evaluation and identified the Xception architecture as the most effective model. Notably, the integration of an attention mechanism within the Xeption model did not yield improvements in recognition performance. Subsequently, through transfer learning and the freezing core strategy, we achieved a test accuracy rate of 98.58% and a verification accuracy rate of 98.2310%. CONCLUSIONS: These outcomes signify a significant stride towards accurate and timely detection, holding promise for enhancing the sustainability and productivity of Yunnan tea. Our findings provide a theoretical foundation and technical guidance for the development of online detection technologies for tea diseases and pests in Yunnan.

Efficient Masked Autoencoders With Self-Consistency.

Inspired by the masked language modeling (MLM) in natural language processing tasks, the masked image modeling (MIM) has been recognized as a strong self-supervised pre-training method in computer vision. However, the high random mask ratio of MIM results in two serious problems: 1) the inadequate data utilization of images within each iteration brings prolonged pre-training, and 2) the high inconsistency of predictions results in unreliable generations, i.e., the prediction of the identical patch may be inconsistent in different mask rounds, leading to divergent semantics in the ultimately generated outcomes. To tackle these problems, we propose the efficient masked autoencoders with self-consistency (EMAE) to improve the pre-training efficiency and increase the consistency of MIM. In particular, we present a parallel mask strategy that divides the image into K non-overlapping parts, each of which is generated by a random mask with the same mask ratio. Then the MIM task is conducted parallelly on all parts in an iteration and the model minimizes the loss between the predictions and the masked patches. Besides, we design the self-consistency learning to further maintain the consistency of predictions of overlapping masked patches among parts. Overall, our method is able to exploit the data more efficiently and obtains reliable representations. Experiments on ImageNet show that EMAE achieves the best performance on ViT-Large with only 13% of MAE pre-training time using NVIDIA A100 GPUs. After pre-training on diverse datasets, EMAE consistently obtains state-of-the-art transfer ability on a variety of downstream tasks, such as image classification, object detection, and semantic segmentation.

Human umbilical cord mesenchymal stem cells protect MC3T3-E1 osteoblasts from dexamethasone-induced apoptosis via induction of the Nrf2-ARE signaling pathway.

Objective: To investigate the protective effect human umbilical cord mesenchymal stem cells (hUC-MSCs) have on Dexamethasone (Dex)-induced apoptosis in osteogenesis via the Nrf2-ARE signaling pathway. Methods: Glucocorticoid-induced osteonecrosis of the femoral head (GC-ONFH) was developed in rats through the administration of lipopolysaccharide and methylprednisolone. The incidence of femoral head necrosis, cavity notch, apoptosis of osteoblasts, and bone density were observed by HE staining, TUNEL staining, and Micro-CT. HUC-MSCs were co-cultured with mouse pre-osteoblast MC3T3-E1. The survival rate of osteoblasts was determined by CCK8, and apoptosis and ROS levels of osteoblasts were determined by flow cytometer. The viability of antioxidant enzymes SOD, GSH-Px, and CAT was analyzed by biochemistry. Nrf2 expression levels and those of its downstream proteins and apoptosis-related proteins were analyzed by Western blotting. Results: In rats, hUC-MSCs can reduce the rates of empty bone lacuna and osteoblast apoptosis that are induced by glucocorticoids (GCs), while reducing the incidence of GC-ONFH. hUC-MSCs can significantly improve the survival rate and antioxidant SOD, GSH-Px, and CAT activity of MC3T3-E1 cells caused by Dex, and inhibit apoptosis and oxidative stress levels. In addition, hUC-MSCs can up-regulate the expression of osteoblast antioxidant protein Nrf2 and its downstream protein HO-1, NQO-1, GCLC, GCLM, and apoptosis-related protein bcl-2, while also down-regulating the expression of apoptosis-related protein bax, cleaved caspase-3, cleaved caspase-9, and cytochrome C in MC3T3-E1 cells. hUC-MSCs improve the ability of MC3T3-E1 cells to mineralize to osteogenesis. However, the promoting effects of hUC-MSCs were abolished following the blocking of the Nrf2-ARE signaling pathway for osteoblasts. Conclusion: The results reveal that hUC-MSCs can reduce Dex-induced apoptosis in osteoblasts via the Nrf2-ARE signaling pathway.

Gene Selection in a Single Cell Gene Space Based on D-S Evidence Theory.

If the samples, features and information values in a real-valued information system are cells, genes and gene expression values, respectively, then for convenience, this system is said to be a single cell gene space. In the era of big data, people are faced with high dimensional gene expression data with redundancy and noise causing its strong uncertainty. D-S evidence theory excels at tackling the problem of uncertainty, and its conditions to be met are weaker than Bayesian probability theory. Therefore, this paper studies the gene selection in a single cell gene space to remove noise and redundancy with D-S evidence theory. The distance between two cells in each gene is first defined. Then, the tolerance relation is established according to the defined distance. In addition, the belief and plausibility functions to grasp the uncertainty of a single cell gene space are introduced on the basis of the tolerance classes. Statistical analysis shows that they can effectively measure the uncertainty of a single cell gene space. Furthermore, several gene selection algorithms in a single cell gene space are presented using the proposed belief and plausibility. Finally, the performance of the proposed algorithm is compared to other algorithms on some published single-cell data sets. Experimental results and statistical tests show that the classification and clustering performance of the presented algorithm not only exceeds the other three state-of-the-art algorithms, but also its gene reduction rate is very high.

Inspired by Stenocara Beetles: From Water Collection to High-Efficiency Water-in-Oil Emulsion Separation.

Inspired by the water-collecting mechanism of the Stenocara beetle's back structure, we prepared a superhydrophilic bumps-superhydrophobic/superoleophilic stainless steel mesh (SBS-SSM) filter via a facile and environmentally friendly method. Specifically, hydrophilic silica microparticles are assembled on the as-cleaned stainless steel mesh surface, followed by further spin-coating with a fluoropolymer/SiO2 nanoparticle solution. On the special surface of SBS-SSM, attributed to the steep surface energy gradient, the superhydrophilic bumps (hydrophilic silica microparticles) are able to capture emulsified water droplets and collect water from the emulsion even when their size is smaller than the pore size of the stainless steel mesh. The oil portion of the water-in-oil emulsion therefore permeates through pores of the superhydrophobic/superoleophilic mesh coating freely and gets purified. We demonstrated an oil recovery purity up to 99.95 wt % for surfactant-stabilized water-in-oil emulsions on the biomimetic SBS-SSM filter, which is superior to that of the traditional superhydrophobic/superoleophilic stainless steel mesh (S-SSM) filter lacking the superhydrophilic bump structure. Together with a facile and environmentally friendly coating strategy, this tool shows great application potential for water-in-oil emulsion separation and oil purification.

A multi-responsive hydrogel with a triple shape memory effect based on reversible switches.

A novel multi-responsive shape memory hydrogel is described. The hydrogel shows multi-responsive shape memory performance and a programmable triple shape memory effect based on dual multi-responsive reversible switches, which will inspire the design and fabrication of novel shape memory systems.

One-pot assembly of metal/organic-acid sites on amine-functionalized ligands of MOFs for photocatalytic hydrogen peroxide splitting.

A one-pot organic-acid-directed post-synthetic modification allows molecular iron/citric acid complexes to be anchored into amine-functionalized MOFs by a simple and rapid liquid spraying method. Amidation between organic acid and -NH2 groups of ligands can lead to more small nanoparticles (NPs) that are well-dispersed into MOFs and exhibit high activity for photocatalytic H2O2 splitting.

An approach to fuzzy soft sets in decision making based on grey relational analysis and Dempster-Shafer theory of evidence: An application in medical diagnosis.

OBJECTIVE: The existing methods of fuzzy soft sets in decision making are mainly based on different kinds of level soft sets, and it is very difficult for decision makers to select a suitable level soft set in most instances. The goal of this paper is to present an approach to fuzzy soft sets in decision making to avoid selecting a suitable level soft set and to apply this approach to solve medical diagnosis problems. METHODS: This approach combines grey relational analysis with the Dempster-Shafer theory of evidence. It first utilizes grey relational analysis to calculate the grey mean relational degree, by which we calculate the uncertain degree of various parameters. Then, on the basis of the uncertain degree, the suitable basic probability assignment function of each independent alternative with each parameter can be obtained. Next, we apply Dempster-Shafer rule of evidence fusion to aggregate these alternatives into a collective alternative, by which these alternatives are ranked and the best alternative is obtained. Finally, we compare this approach with the mean potentiality approach. RESULTS: The results demonstrate the effectiveness and feasibility of this approach vis-a-vis the mean potentiality approach, Feng's method, Analytical Hierarchy Process and Naive Bayes' classification method because the measure of performance of this approach is the same as that of the mean potentiality approach, and the belief measure of the whole uncertainty falls from the initial mean 0.3821 to 0.0069 in an application of medical diagnosis. CONCLUSION: An approach to fuzzy soft sets in decision making by combining grey relational analysis with Dempster-Shafer theory of evidence is introduced. The advantages of this approach are discussed. A practical application to medical diagnosis problems is given.

A method for fuzzy soft sets in decision making based on grey relational analysis and d-s theory of evidence: application to medical diagnosis.

A method based on grey relational analysis and D-S theory of evidence is proposed for fuzzy soft sets in decision making. Firstly, grey relational analysis is used to calculate grey mean relational degrees and determine uncertain degrees of parameters. Then based on uncertain degrees, suitable mass functions of different independent alternatives with different parameters can be constructed. Next, D-S rule of evidence combination is applied to aggregate these alternatives into a collective alternative. Finally, these alternatives are ranked and the best alternative(s) are obtained. Moreover, the effectiveness and feasibility of this method are demonstrated by comparing with the mean potentiality approach and giving an application to medical diagnosis.

[Analysis of prevention of mother-to-child transmission of HIV (PMTCT) work in Zhumadian city, 2001 - 2009].

OBJECTIVE: To analyze the current status of maternal HIV infection, mother to child transmission, and the work accomplishments in preventing mother-to-child transmission of HIV (PMTCT). METHODS: During October, 2001 to May, 2009, HIV voluntary consultation and examination were carried out in 339 866 pregnant women in the urban areas, while 594 pregnant women who tested positive were intervened, and interventions were also conducted among 326 babies who were born to HIV positive mothers, including HIV immune body examination on the babies when they were 12 months and 18 months old. RESULTS: A total of 594 pregnant women were found HIV positive, with the positive rate of 0.17% (594/339 866). And the rate was declining year by year. The highest rate was 0.47% (37/7837) in 2002, and the lowest rate was 0.12% (86/73 343) in 2008. Of the 594 positive pregnant women, 228 (38.38%) terminated pregnancy voluntarily, 43 (7.24%) kept on pregnancy and 317 (53.37%) parturients. Of 326 babies born by the 317 parturients, 317 survived.298 received curbing intervention for mother to child transmission (PMTCT), the ratio was 94.01% (298/317). Of 224 babies who were 18 months old, 221 accepted examination, and 7 HIV positive. The maternal infant transmission rate after intervention was 3.17% (7/221). CONCLUSION: Through the prevention of mother-to-child transmission of HIV, the HIV infection status in the pregnant women can be timely observed, which can effectively decrease the level of mother-to-child transmission of HIV.