Longfei Han

Learn More
AIMS To develop a risk assessment model for persons at risk from type 2 diabetes in Chinese. MATERIALS AND METHODS The model was generated from the cross-sectional data of 16246 persons aged from 20 years old and over. C4.5 algorithm and multivariate logistic regression were used for variable selection. Relative risk value combined with expert decision(More)
Diabetes mellitus is a chronic disease and a worldwide public health challenge. It has been shown that 50-80% proportion of T2DM is undiagnosed. In this paper, support vector machines are utilized to screen diabetes, and an ensemble learning module is added, which turns the “black box” of SVM decisions into comprehensible and transparent(More)
Sulfated polysaccharide (UFP(31)) extracted from the marine algae Ulva fasciata (UFP) was a heteropolysaccharide, and consisted of rhamnose, xylose, and glucose in a ratio of 1:0.46:0.27 with a (1 → 4)-linked glycosyl backbone. The rheology of UFP(31) solution has been investigated by steady shear and small amplitude oscillatory experiments. The effects of(More)
The aim of this study is to quantitatively analyze the influence of risk factors on the blood glucose level, and to provide theory basis for understanding the characteristics of blood glucose change and confirming the intervention index for type 2 diabetes. The quantitative method is proposed to analyze the influence of risk factors on blood glucose using(More)
Stream structure is usually dominated by various human activities over a short term. An analysis of variation in stream structure from 1979 to 2009 in the Qinhuai River Basin, China, was performed based on remote sensing images and topographic maps by using ArcGIS. A series of river parameters derived from river geomorphology are listed to describe the(More)
Further understanding the mechanisms of landscape-water interactions is of great importance to water quality management in the Xitiaoxi catchment. Pearson's correlation analysis, stepwise multiple regression and redundancy analysis were adopted in this study to investigate the relation between water quality and landscape at the sub-catchment and 200 m(More)
A simulation based computational method was conducted to reflect the effect of intervention for those at high risk of type 2 diabetes. Hierarchy Support Vector Machines (H-SVMs) were used to classify high risk. The proportion transitioning from the high risk state to moderate state, low state or the normal state was calculated. When Body Mass Index (BMI)(More)
Mixture of regressions (MoR) is the wellestablished and effective approach to model discontinuous and heterogeneous data in regression problems. Existing MoR approaches assume smooth joint distribution for its good anlaytic properties. However, such assumption makes existing MoR very sensitive to intra-component outliers (the noisy training data residing in(More)
Having a system to stratify individuals according to risk is key to clinical disease prevention. This allows individuals identified at different risk tiers to benefit from further investigation and intervention. But the same risk score estimated for two different persons does not mean they need the same further investigation or represent the similarity(More)
Water quality in wetlands plays a huge role in maintaining the health of the wetland ecosystem. Water quality should be controlled by an appropriate water allocation policy for the protection of the wetlands. In this paper, models of rainfall/runoff, non-point source pollution load, water quantity/quality, and dynamic pollutant-carrying capacity were(More)