This research underscores the importance of enhancing the early detection of diabetic retinopathy and glaucoma, two prominent culprits behind vision loss. Typically, retinal diseases lurk without symptoms until they inflict severe vision impairment, underscoring the critical need for early identification. The research is centered on the potential of leveraging fundus images, which offer invaluable insights by analyzing various attributes of retinal blood vessels, such as their length, width, tortuosity, and branching patterns. The conventional practice of manually segmenting retinal vessels by medical professionals is both intricate and time-consuming, demanding specialized expertise. This approach, reliant on pathologists, grapples with limitations related to scalability and accessibility. To surmount these challenges, the research introduces an automated solution employing computer vision. It conducts an evaluation of diverse retinal vessel segmentation and classification methods, including machine learning, filtering-based, and model-based techniques. Robust performance assessments, involving metrics like the true positive rate, true negative rate, and accuracy, facilitate a comprehensive comparison of these methodologies. The ultimate goal of this research is to create more efficient and accessible diagnostic tools, consequently enhancing the early detection of eye diseases through automated retinal vessel segmentation and classification. This endeavor combines the capabilities of computer vision and deep learning to pioneer new benchmarks in the realm of biomedical imaging, thereby addressing the pressing issues surrounding eye disease diagnosis.

Atomic interaction between mediator protein of human prostate cancer (PHPC) and Fe/C720 Buckyballs-Statin is important for medical science. For the first time, we use molecular dynamics (MD) approach based on Newton’s formalism to describe the destruction of PHPC via Fe/C720 Buckyballs-Statin with atomic accuracy. In this work, the atomic interaction of PHPC and Fe/C720 Buckyballs-Statin introduced via equilibrium molecular dynamics approach. In this method, each PHPC and Fe/C720 Buckyballs-Statin is defined by C, H, Cl, N, O, P, S, and Fe elements and contrived by universal force field (UFF) and DREIDING force-field to introduce their time evolution. The results of our studies regarding the dynamical behavior of these atom-base compounds have been reported by calculating the Potential energy, center of mass (COM) position, diffusion ratio and volume of defined systems. The estimated values for these quantities show the attraction force between Buckyball-based structure and protein sample, which COM distance of these samples changes from 10.27 Å to 2.96 Å after 10 ns. Physically, these interactions causing the destruction of the PHPC. Numerically, the volume of this biostructure enlarged from 665,276 Å3 to 737,143 Å3 by MD time passing. This finding reported for the first time which can be considered by the pharmaceutical industry. Simulations indicated the volume of the PHPC increases by Fe/C720 Buckyballs-Statin diffusion into this compound. By enlarging this quantity (diffusion coefficient), the atomic stability of PHPC decreases and protein destruction procedure fulfilled.

Retinal disorders, such as diabetic retinopathy, glaucoma, macular edema, and vein occlusions, are significant contributors to global vision impairment. These conditions frequently remain symptomless until patients suffer severe vision deterioration, underscoring the critical importance of early diagnosis. Fundus images serve as a valuable resource for identifying the initial indicators of these ailments, particularly by examining various characteristics of retinal blood vessels, such as their length, width, tortuosity, and branching patterns. Traditionally, healthcare practitioners often rely on manual retinal vessel segmentation, a process that is both time-consuming and intricate, demanding specialized expertise. However, this approach poses a notable challenge since its precision and consistency heavily rely on the availability of highly skilled professionals. To surmount these challenges, there is an urgent demand for an automatic and efficient method for retinal vessel segmentation and classification employing computer vision techniques, which form the foundation of biomedical imaging. Numerous researchers have put forth techniques for blood vessel segmentation, broadly categorized into machine learning, filtering-based, and model-based methods. Machine learning methods categorize pixels as either vessels or non-vessels, employing classifiers trained on hand-annotated images. Subsequently, these techniques extract features using 7D feature vectors and apply neural network classification. Additional post-processing steps are used to bridge gaps and eliminate isolated pixels. On the other hand, filtering-based approaches employ morphological operators within morphological image processing, capitalizing on predefined shapes to filter out objects from the background. However, this technique often treats larger blood vessels as cohesive structures. Model-based methods leverage vessel models to identify retinal blood vessels, but they are sensitive to parameter selection, necessitating careful choices to simultaneously detect thin and large vessels effectively. Our proposed research endeavors to conduct a thorough and empirical evaluation of the effectiveness of automated segmentation and classification techniques for identifying eye-related diseases, particularly diabetic retinopathy and glaucoma. This evaluation will involve various retinal image datasets, including DRIVE, REVIEW, STARE, HRF, and DRION. The methodologies under consideration encompass machine learning, filtering-based, and model-based approaches, with performance assessment based on a range of metrics, including true positive rate (TPR), true negative rate (TNR), positive predictive value (PPV), negative predictive value (NPV), false discovery rate (FDR), Matthews's correlation coefficient (MCC), and accuracy (ACC). The primary objective of this research is to scrutinize, assess, and compare the design and performance of different segmentation and classification techniques, encompassing both supervised and unsupervised learning methods. To attain this objective, we will refine existing techniques and develop new ones, ensuring a more streamlined and computationally efficient approach.

The goal of the project is to investigate and discover tree species abundant in the Mekong Delta Vietnam, and find out species to develop land in southern coastal of Vietnam and based on research to applicated for food and medicinal on part of forest trees. Mekong Delta a amount of alluvium sediments flows from upstream China to Vietnam by the river branches, then get out the Sea. This sediments accumulated gradually elevation the new land. The coastal where mangrove forests with a rich ecosystem of plants and animals. Over time, these forests change, with different plant species succeeding each other. This aims of this study to finding plant species, classification of forest types based on ecological regions, assessement the biodiversity of tree species, and compare the abundance communities, measuring the growth of the forest in these regions. In 2023, a comprehensive survey was conducted by using a systematic approach. Research content and methods. The content is to investigate the situation of woody plant species in mangrove forests in sub-regions with different ecological characteristics. The number of survey plots have done depend on the density of the forest, Base on the width of the forest range, the number of survey plots in sub region set up from 10 to 15 plots. In total, 68 plots have done established in the erea, the area of plot is 100 square meters (10 m x 10 m). Using the statistical software in forestry to survey and analysis data. The results of research is to find the number of species in each ecological region and growth situation, in which the important thing is to evaluate the adaptation of species in each sub-region to propose wich species to choose as the main species in aforestation the fastest land on sea. The result provided a complete picture of the tree species composition, distribution, and community structure characteristics in each ecological sub-region. The result of survey showed in the sub-region one is seven species. In the sub region two is eleven species. In the sub region three is eight species. In the region four is ten species. The total species of the mangrove forest in the Western Mekong Delta have 16 species from 11 plant families have been identified. Among these species have 6 dominant species include Avicennia oficinali),Avicennia alba, Rhizophora apiculata, Excoecaria agallocha, Someratia caseolaris, and Bruguiera yipamoriza. From the investigation have been found two species grow on the best on new land were Avicennia officinalis and Avicennia alba this findings show they can develope on the original new land for the shore of the Western Mekong Delta. The survey results also calculated the average of the height, diameter (D1.3), canopy, health of the nature mangrove tree for each sub region and total region. From these results showed the division of foresty structure, the structure of height, diameter (D1.3), canopy, heathy of the sub region and total region in the Western Mekong Delta. Suggestions after discovering during the investigation that there are Avicennia officinalis and Avicennia alba are two species that can implement development plants to expand natural land by planting on suitable sea surface areas for Mekong Delta of Vietnam. In addition, referring to research documents on these adapted species can exploit food and medicinal herbs in discovering the level biodiversity distribution abundance of these species. This finding can help Vietnam by mearsures using the species Aviecennia be discovered will promote sea reclamation faster instead of letting the natural law of sea reclamation follow.

By carrying out a laboratory experiment, the influence of priming methods, including ZnSO4, BSN, and hydropriming was evaluated on the seed germination of hybrid AS71 corn. Then, the main and interaction effects of the priming methods, planting dates, and weed interference levels were surveyed on the vegetative growth traits, yield, and yield components of corn in a field experiment. Based on the lab experiment, although the maximum germination percentage (100%) was observed in the treated plots by hydropriming 22 h after treatment (HAT), the greatest seedling vigor index (122.99) was recorded with treated seeds by ZnSO4 (0.03 mg L–1) at 8 HAT. The greatest emergence index was observed in the treated plots by hydropriming on both planting dates of June 1 and 11. The interaction of planting dates and weed interference levels revealed that the highest emergence index (14%–17%) occurred in the weed-free plots on both planting dates. BSN recorded the greatest corn 1000-grain weight that was significantly higher than the control plots by 28%. Furthermore, BSN enhanced the corn grain yield compared with the control plots by 63% and 24.9% on the planting dates of June 1 and 11, respectively. BSN, as a nutri-priming approach, by displaying the highest positive effects in boosting the corn grain yield in both weedy and weed-free plots as well as both planting dates, could be a recommendable option for growers to improve the crop yield production.