National Chung Hsing University

About: National Chung Hsing University is a education organization based out in Taichung, Taiwan. It is known for research contribution in the topics: Catalysis & Thin film. The organization has 19443 authors who have published 24060 publications receiving 540154 citations. The organization is also known as: NCHU.

Fuzzy System Learned Through Fuzzy Clustering and Support Vector Machine for Human Skin Color Segmentation

Abstract: This paper proposes a Fuzzy System learned through Fuzzy Clustering and Support Vector Machine (FS-FCSVM). The FS-FCSVM is a fuzzy system constructed by fuzzy if-then rules with fuzzy singletons in the consequence. The structure of FS-FCSVM is constructed by fuzzy clustering on the input data, which helps to reduce the number of rules. Parameters in FS-FCSVM are learned through a support vector machine (SVM) for the purpose of achieving higher generalization ability. In contrast to nonlinear kernel-based SVM or some other fuzzy systems with a support vector learning mechanism, both the number of parameters/rules in FS-FCSVM and the computation time are much smaller. FS-FCSVM is applied to skin color segmentation. For color information representation, different types of features based on scaled hue and saturation color space are used. Comparisons with a fuzzy neural network, the Gaussian kernel SVM, and mixture of Gaussian classifiers are performed to show the advantage of FS-FCSVM.

Hydroxychloroquine reduces risk of incident diabetes mellitus in lupus patients in a dose-dependent manner: a population-based cohort study

Abstract: OBJECTIVE SLE is associated with increased risk of diabetes mellitus. Treatment for SLE requires high-dose glucocorticoids that may worsen glucose homoeostasis. HCQ can reduce diabetes risk in RA. This study aimed to investigate the association of HCQ use and diabetes mellitus risk in SLE patients. METHODS This nationwide, population-based cohort study was conducted using the Taiwan National Health Insurance Research Database. In the period 2001-10, 8628 newly diagnosed SLE patients were identified after excluding those with a previous diagnosis of RA, psoriasis or diabetes mellitus. Incidence of diabetes mellitus was identified as a new diagnostic code using a diabetes mellitus-specific medication. RESULTS Two hundred and twenty-one newly diagnosed diabetes mellitus patients were identified among SLE patients (6795 had taken HCQ and 1833 had never taken HCQ), with an average follow-up period of 5.6 years. Compared with patients without HCQ treatment, the hazard ratio (HR) of diabetes mellitus in patients taking HCQ at a cumulative dose ≥129 g was reduced [HR 0.26 (95% CI 0.18, 0.37), P < 0.001]. Daily glucocorticoid ≥10 mg prednisolone-equivalent dose was associated with increased risk of developing diabetes mellitus [HR 2.47 (95% CI 1.44, 4.23), P = 0.001], which was minimized by concomitant HCQ use at a cumulative dose ≥129 g. CONCLUSION In SLE patients, the use of HCQ is associated with reduced risk of incident diabetes mellitus in a dose-dependent manner. High-dose glucocorticoids increase the risk of diabetes, which can be decreased by concomitant HCQ use.

Roles of insulin-like growth factor II in cardiomyoblast apoptosis and in hypertensive rat heart with abdominal aorta ligation

Abstract: Although IGF-II activating the IGF-II receptor signaling pathway has been found to stimulate cardiomyocyte hypertrophy, the role of IGF-II in cardiac cell apoptosis remains unclear. This study aime...

Automated diagnosis of sewer pipe defects based on machine learning approaches

Abstract: In sewage rehabilitation planning, closed circuit television (CCTV) systems are the widely used inspection tools in assessing sewage structural conditions for non man entry pipes. Currently, the assessment of sewage structural conditions by manually interpretation on CCTV images seems inefficient, especially for several thousands of frames in one inspection plan. Also, the assessment work significantly involves engineers' eye sight and professional experience. With a purpose of assisting general staffs in diagnosing pipe defects on CCTV inspection images, a diagnostic system by applying machine learning approaches is proposed in this paper. This research was first to use image process techniques, including wavelet transform and computation of co-occurrence matrices, for describing the textures of the pipe defects. Then, three neural network approaches, back-propagation neural network (BPN), radial basis network (RBN), and support vector machine (SVM), were adopted to classify pipe defect patterns, and their performances were compared and discussed. The diagnostic system of pipe defects was applied to a sewer system in the 9th district, Taichung City which is the largest city in middle Taiwan. The result shows that the diagnosis accuracy of 60% derived by SVM is the best and also better than the diagnosis accuracy of 57.4% derived by a Bayesian classifier.