Bayesian model selection for generalized linear models using non-local priors

Shi, Guiling,Lim, Chae Young,Maiti, Tapabrata Elsevier 2019 Computational statistics & data analysis Vol.133 No.-

<P><B>Abstract</B></P> <P>Variable selection is currently an important research topic under both frequentist and Bayesian framework. While most developments in Bayesian model selection literature are based on a local prior on regression parameters, a nonlocal prior for model selection can be also used. In this article, we extend nonlocal prior approach to logistic regression and to generalized linear models. Laplace approximation is used in implementation to avoid integration in the likelihood. A convergence rate is derived under some regularity conditions. The selection based on a nonlocal prior eliminates unnecessary variables and recommends a simple model. The method is validated by simulation study and illustrated by a real data example.</P>

Model selection using mass-nonlocal prior

Shi, Guiling,Lim, Chae Young,Maiti, Tapabrata Elsevier 2019 STATISTICS & PROBABILITY LETTERS - Vol.147 No.-

<P><B>Abstract</B></P> <P>Bayesian variable selection is an active research area. The paper proposes a variable selection technique by taking advantages of two distinctive approaches of Bayesian variable selection, namely spike and slab prior and nonlocal prior. Contrary to the local priors, nonlocal priors put zero mass at null values of the parameters. The proposed method uses posterior median as the parameter estimates and asymptotic consistency is established. The Bayesian implementation is proposed via Gibbs sampling. The full conditional distributions are provided. Extensive numerical study indicates superiority of the proposed procedure compared to its competitors. Most importantly, the procedure works well in low signal situation which is not the case in general.</P>

Nature of Controlling Stake, R&D Investment and Corporate Performance-Based on Empirical Data of Listed Companies in China

Zhang Guiling 보안공학연구지원센터 2016 International Journal of u- and e- Service, Scienc Vol.9 No.2

This article makes an empirical analysis on influence of R&D investment on corporate performance under different nature of controlling stake by applying multivariate regression analysis and ordinary least square and taking China A-share listed companies as samples. The study finds that for the whole sample enterprises and non-state-controlled enterprises, current and last R&D investment have significant positive influence on corporate performance; for state-controlled enterprises, current and last R&D investment have positive influence on corporate performance but not significant.

Study on Influencing Factors for Investment Strategy of Chinese Cultural Industry

Zhang Guiling 보안공학연구지원센터 2016 International Journal of u- and e- Service, Scienc Vol.9 No.10

This paper analyzes relations of influence of the four factors, including corporate external financing capacity, governance mechanism, systems and talents environment, on longsighted investment strategy for cultural industry using the least square method of regression analysis by data samples. The study finds enhancing corporate external financing capacity, improving its governance mechanism, optimizing its systems and talents environment for a competitive promotion and a strategic investment transformation from shortsighted to longsighted for culture industry.

Exponential stability of a class of impulsive stochastic delay partial differential equations driven by a fractional Brownian motion

Dingshi Li,Guiling Chen 제어·로봇·시스템학회 2017 International Journal of Control, Automation, and Vol.15 No.4

Several new criteria on exponential stability of a class of impulsive stochastic delay partial differentialequations with a fractional Brownian motion are presented by employing the variation of parameters formulaand using an inequality technique. The criteria we provided in this paper do not assume the condition that thecorresponding continuous stochastic system is stable, so this criteria can be applied to stabilize unstable systems. Moreover, the exponential convergence rate is estimated. Some examples are given to illustrate our main results.

An Efficient Model Based on Smoothed ℓ₀ Norm for Sparse Signal Reconstruction

( Yangyang Li ),( Guiling Sun ),( Zhouzhou Li ),( Tianyu Geng ) 한국인터넷정보학회 2019 KSII Transactions on Internet and Information Syst Vol.13 No.4

Compressed sensing (CS) is a new theory. With regard to the sparse signal, an exact reconstruction can be obtained with sufficient CS measurements. Nevertheless, in practical applications, the transform coefficients of many signals usually have weak sparsity and suffer from a variety of noise disturbances. What's worse, most existing classical algorithms are not able to effectively solve this issue. So we proposed an efficient algorithm based on smoothed ℓ₀ norm for sparse signal reconstruction. The direct ℓ₀ norm problem is NP hard, but it is unrealistic to directly solve the ℓ₀ norm problem for the reconstruction of the sparse signal. To select a suitable sequence of smoothed function and solve the ℓ₀ norm optimization problem effectively, we come up with a generalized approximate function model as the objective function to calculate the original signal. The proposed model preserves sharper edges, which is better than any other existing norm based algorithm. As a result, following this model, extensive simulations show that the proposed algorithm is superior to the similar algorithms used for solving the same problem.

Real-time Evaluation Mechanism Based on Double Evidence Classification of User Behavior

Jiale Zhang,Guiling Zhang,Xiufang Zhang 보안공학연구지원센터 2016 International Journal of Security and Its Applicat Vol.10 No.12

With the development of trusted network, the research of trusted evaluation mechanism of user behavior is a hotpot in the network security. In order to solve the problems of subjectivity, limitations and static in traditional trusted network user behavior evaluation models, we have to find a real-time and dynamic evaluation method for user behavior. In this paper, the authors construct a real-time evaluation mechanism based on double evidence classification of user behavior (DEC-UB). The evaluation mechanism includes the process classification and characteristic classification of user behavior evidence, which makes the user behavior evidence of any time can be directly involved in the trust evaluation, and the evaluation result is more comprehensive and accurate. Simulation experiments have evaluated the three kinds of user behaviors based on the DEC-UB, and compared them with the other two kinds of trust evaluation methods of user behavior, the results show that the proposed methods can evaluate the user's behavior comprehensively, accurately and dynamically in complex network environments, and the results are more realistic.

Fecal Microbiota Transplantation (FMT) Alleviates Experimental Colitis in Mice by Gut Microbiota Regulation

Zhang Wanying,Zou Guiling,Li Bin,Du Xuefei,Sun Zhe,Sun Yu,Jiang Xiaofeng 한국미생물·생명공학회 2020 Journal of microbiology and biotechnology Vol.30 No.8

Inflammatory bowel disease (IBD) is an increasing global burden and a predisposing factor to colorectal cancer. Although a number of treatment options are available, the side effects could be considerable. Studies on fecal microbiota transplantation (FMT) as an IBD intervention protocol require further validation as the underlying mechanisms for its attenuating effects remain unclear. This study aims to demonstrate the ameliorative role of FMT in an ulcerative colitis (UC) model induced by dextran sulfate sodium (DSS) and elucidate its relative mechanisms in a mouse model. It was shown that FMT intervention decreased disease activity index (DAI) levels and increased the body weight, colon weight and colon length of experimental animals. It also alleviated histopathological changes, reduced key cytokine expression and oxidative status in the colon. A down-regulated expression level of genes associated with NF-κB signaling pathway was also observed. The results of 16S rRNA gene sequencing showed that FMT intervention restored the gut microbiota to the pattern of the control group by increasing the relative abundance of Firmicutes and decreasing the abundances of Bacteroidetes and Proteobacteria. The relative abundances of the genera Lactobacillus, Butyricicoccus, Lachnoclostridium, Olsenella and Odoribacter were upregulated but Helicobacter, Bacteroides and Clostridium were reduced after FMT administration. Furthermore, FMT administration elevated the concentrations of SCFAs in the colon. In conclusion, FMT intervention could be suitable for UC control, but further validations via clinical trials are recommended.

Seismological Evidence for North-east Strike Large Active Structure in the Yellow Sea

Zhao, Genmo,Diao, Guiling,Wang, Junguo,Yang, Gangsheng 한국지진연구소 1996 SAFE Vol.2 No.1

The Yellow Sea which is situated between the Chinese continent and the Korean peninsula is a typical marginal sea basin, the submarine structure of which is covered with very thick Cenozoic deposit and sea water Liu, 1992). The method of judging tectonic activity based on the microdynamic observation of tectonic deformation is very difficult to be used here. Although the submarine heat flow can be used as the significant basis for studying the submarine structure, yet the water in the Yellow Sea is rather shallow, the variation in water temperature produces a great impact on the measurement of heat flow and convincible data of which are very difficult to be obtained. Therefore, as far as the entire Yellow Sea is concerned, especially for the area fat away from the seacoast, the studies of the tectonic activity as seldom reported. However, the method of analyzing tectonic activity based on the data of seismic wave from the depth of the earth has been paid move and more attentions nowadays, With the seismic data in China, the characteristics of the earthquakes in the Yellow Sea have already been described, but the description was limited only to the flank along the Chinese continent (Liu et al., 1994), as to the other flank along the Korean peninsula, not much is known. Recently, we have systematically collected the seismic data from China, D. P. R. Korea and R. 0. Korea to compile the earthquake cataloger for the Yellow Sea and the surrounding regions, as result, it is possible to make a complete analysis of seismic activity in the Yellow Sea area now.

Southern Identification and Homology Analysis of the Resistance Gene Analog in Cucumis sativus L

Guohua Ding,Zhiwei Qin,Xiuyan Zhou,Guiling Wang 한국원예학회 2006 한국원예학회 기타간행물 Vol.- No.-