Saigon University

About: Saigon University is a education organization based out in Ho Chi Minh City, Vietnam. It is known for research contribution in the topics: Vector optimization & Vietnamese. The organization has 160 authors who have published 249 publications receiving 2285 citations.

Identifying the Best Machine Learning Algorithms for Brain Tumor Segmentation, Progression Assessment, and Overall Survival Prediction in the BRATS Challenge

Abstract: Gliomas are the most common primary brain malignancies, with different degrees of aggressiveness, variable prognosis and various heterogeneous histologic sub-regions, i.e., peritumoral edematous/invaded tissue, necrotic core, active and non-enhancing core. This intrinsic heterogeneity is also portrayed in their radio-phenotype, as their sub-regions are depicted by varying intensity profiles disseminated across multi-parametric magnetic resonance imaging (mpMRI) scans, reflecting varying biological properties. Their heterogeneous shape, extent, and location are some of the factors that make these tumors difficult to resect, and in some cases inoperable. The amount of resected tumoris a factor also considered in longitudinal scans, when evaluating the apparent tumor for potential diagnosis of progression. Furthermore, there is mounting evidence that accurate segmentation of the various tumor sub-regions can offer the basis for quantitative image analysis towards prediction of patient overall survival. This study assesses thestate-of-the-art machine learning (ML) methods used for brain tumor image analysis in mpMRI scans, during the last seven instances of the International Brain Tumor Segmentation (BraTS) challenge, i.e., 2012-2018. Specifically, we focus on i) evaluating segmentations of the various glioma sub-regions in pre-operative mpMRI scans, ii) assessing potential tumor progression by virtue of longitudinal growth of tumor sub-regions, beyond use of the RECIST/RANO criteria, and iii) predicting the overall survival from pre-operative mpMRI scans of patients that underwent gross tota lresection. Finally, we investigate the challenge of identifying the best ML algorithms for each of these tasks, considering that apart from being diverse on each instance of the challenge, the multi-institutional mpMRI BraTS dataset has also been a continuously evolving/growing dataset.

Bioactive Compounds in Anti-Diabetic Plants: From Herbal Medicine to Modern Drug Discovery

Abstract: Natural products, including organisms (plants, animals, or microorganisms) have been shown to possess health benefits for animals and humans. According to the estimation of the World Health Organization, in developing countries, 80% of the population has still depended on traditional medicines or folk medicines which are mostly prepared from the plant for prevention or treatment diseases. Traditional medicine from plant extracts has proved to be more affordable, clinically effective and relatively less adverse effects than modern drugs. Literature shows that the attention on the application of phytochemical constituents of medicinal plants in the pharmaceutical industry has increased significantly. Plant-derived secondary metabolites are small molecules or macromolecules biosynthesized in plants including steroids, alkaloids, phenolic, lignans, carbohydrates and glycosides, etc. that possess a diversity of biological properties beneficial to humans, such as their antiallergic, anticancer, antimicrobial, anti-inflammatory, antidiabetic and antioxidant activities Diabetes mellitus is a chronic disease result of metabolic disorders in pancreas β-cells that have hyperglycemia. Hyperglycemia can be caused by a deficiency of insulin production by pancreatic (Type 1 diabetes mellitus) or insufficiency of insulin production in the face of insulin resistance (Type 2 diabetes mellitus). The current medications of diabetes mellitus focus on controlling and lowering blood glucose levels in the vessel to a normal level. However, most modern drugs have many side effects causing some serious medical problems during a period of treating. Therefore, traditional medicines have been used for a long time and play an important role as alternative medicines. Moreover, during the past few years, some of the new bioactive drugs isolated from plants showed antidiabetic activity with more efficacy than oral hypoglycemic agents used in clinical therapy. Traditional medicine performed a good clinical practice and is showing a bright future in the therapy of diabetes mellitus. World Health Organization has pointed out this prevention of diabetes and its complications is not only a major challenge for the future, but essential if health for all is to be attained. Therefore, this paper briefly reviews active compounds, and pharmacological effects of some popular plants which have been widely used in diabetic treatment. Morphological data from V-herb database of each species was also included for plant identification.

Twitter Sentiment Analysis Using Machine Learning Techniques

Abstract: Twitter is a microblogging site in which users can post updates (tweets) to friends (followers). It has become an immense dataset of the so-called sentiments. In this paper, we introduce an approach to selection of a new feature set based on Information Gain, Bigram, Object-oriented extraction methods in sentiment analysis on social networking side. In addition, we also proposes a sentiment analysis model based on Naive Bayes and Support Vector Machine. Its purpose is to analyze sentiment more effectively. This model proved to be highly effective and accurate on the analysis of feelings.

Functional manganese ferrite/graphene oxide nanocomposites: effects of graphene oxide on the adsorption mechanisms of organic MB dye and inorganic As(V) ions from aqueous solution

Abstract: In this study, manganese ferrite-graphene oxide (MFO-GO) nanocomposites were prepared via a co-precipitation reaction of Fe3+ and Mn2+ ions in a GO suspension. The effects of graphene oxide on the physicochemical characteristics, magnetic properties and adsorption activities of the MFO-GO nanocomposites were studied. Methylene blue (MB) and arsenic(V) were used in this study as model water pollutants. With an increase in the GO content in the range of 10 wt% to 50 wt%, the removal efficiency for both MB dye and arsenic(V) ions was improved. Our adsorption data revealed that the adsorption behavior of MB dye showed good agreement with the Langmuir isotherm model and pseudo-second-order equation, whereas the Freundlich isotherm model was more suitable for simulating the adsorption process of arsenic(V) ions on the MFO-GO nanocomposites. In addition, an important role of the GO content in the adsorption mechanisms of both MB dye and arsenic(V) ions was found, in which GO nanosheets play a key role in the mechanisms of electrostatic/ionic interactions, oxygen-containing groups and π–π conjugation in the case of the adsorption of MB dye, whereas the role of the GO content is mainly related to the mechanism of electrostatic/ionic interactions in the case of the adsorption of arsenic(V). Graphene oxide has the functions of increasing the number of active binding sites comprising oxygen-containing functional groups, reducing the agglomeration of MFO nanoparticles, increasing the number of adsorption sites, and improving the electrostatic/ionic interactions between adsorbents and adsorbates in order to enhance the adsorption performance of cationic organic dyes and/or heavy metal anions from aqueous solutions.

Nonsmooth Semi-infinite Multiobjective Optimization Problems

Abstract: We apply some advanced tools of variational analysis and generalized differentiation to establish necessary conditions for (weakly) efficient solutions of a nonsmooth semi-infinite multiobjective optimization problem (SIMOP for brevity). Sufficient conditions for (weakly) efficient solutions of a SIMOP are also provided by means of introducing the concepts of (strictly) generalized convex functions defined in terms of the limiting subdifferential of locally Lipschitz functions. In addition, we propose types of Wolfe and Mond–Weir dual problems for SIMOPs, and explore weak and strong duality relations under assumptions of (strictly) generalized convexity. Examples are also designed to analyze and illustrate the obtained results.