• Communications for Statistical Applications and Methods
• /
• v.21 no.4
• /
• pp.349-361
• /
• 2014

This paper compares of lasso type estimators in various high-dimensional data situations with sparse parameters. Lasso, adaptive lasso, fused lasso and elastic net as lasso type estimators and ridge estimator are compared via simulation in linear models with correlated and uncorrelated covariates and binary regression models with correlated covariates and discrete covariates. Each method is shown to have advantages with different penalty conditions according to sparsity patterns of regression parameters. We applied the lasso type methods to Arabidopsis microarray gene expression data to find the strongly significant genes to distinguish two groups.

• Journal of the Korean Statistical Society
• /
• v.31 no.1
• /
• pp.93-107
• /
• 2002

Random effects generalised linear models are useful for analysing clustered count data in which responses are usually correlated. We propose a Bayesian approach to parameter estimation and variable selection in random effects generalised linear models for count data. A simple Gibbs sampling algorithm for parameter estimation is presented and a simple and efficient variable selection is done by using the Gibbs outputs. An illustrative example is provided.

• Journal of Community Nutrition
• /
• v.4 no.3
• /
• pp.151-158
• /
• 2002

The purpose of this study was to investigate the correlations among the anthropometry, serum lipid levels and nutrient intake in Korean female university students. The subjects were 119 female students at a university located in Incheon. This study was conducted using a self-administered questionnaire. Anthropometric data were measured and blood lipid levels were analyzed. Nutrient intake collected from 3 day-recalls was analyzed by the Computer Aided Nutritional Analysis Program. The data were analyzed by SPSS 10.0 program. Average age, height and weight of the subjects were 20.9 years, 160.1cm and 54.3kg, respectively. Average serum TG (triglyceride), total cholesterol, HDL-C (high density lipoprotein-cholesterol) and LDL-C (low density lipoprotein-cholesterol) levels of the subjects were 69.47mg/dl, 146.85 mg/dl, 50.49mg/dl and 82.52mg/dl, respectively. Average AI (atherogenic index) of the subjects was 2.03, which was in the normal range based on risk values. Average intake of most nutrients except protein, vitamin B$_1$, vitamin C and phosphorus were lower than the Korean RDA. Especially calcium and iron intakes of the subjects were under 65% of the Korean RDA. Serum TG, total cholesterol and LDL-C levels were negatively correlated with DBP (diastolic blood pressure). HDL-C/LDL-C and HDL-C/total cholesterol were positively correlated with height. Age was positively correlated with phosphorus intake. DBP of the subjects was positively correlated with calcium and iron intakes. Serum TG level was positively correlated with total cholesterol, HDL-C, LDL-C and AI, while negatively correlated with HDL-C/total cholesterol. Total cholesterol level was positively correlated with HDL-C, LDL-C and AI, while negatively correlated with HDL-C/LDL-C, HDL-C/total cholesterol. HDL-C level was positively correlated with LDL-C, HDL-C/LDL-C and HDL-C/total cholesterol, while negatively correlated with AI. LDL-C level was negatively correlated with HDL-C/LDL-C and HDL-C/total cholesterol, while positively correlated with AI HDL-C/LDL-C ratio was positively correlated with HDL-C/total cholesterol and AI. HDL-C/total cholesterol was negatively correlated with AI. Fat intake was positively correlated with total cholesterol, HDL-C level, and vitamin B$_2$ intake was positively correlated with TG, HDL-C/LDL-C. Therefore, nutrition education is necessary for female university students to promote the lipid profile and to optimize the nutritional status. (J Community Nutrition 4(3) : 151∼158, 2002)

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.9 no.9
• /
• pp.3515-3538
• /
• 2015

Data accuracy can be increased by detecting and removing the incorrect data generated in wireless sensor networks. By increasing the data accuracy, network lifetime can be increased parallel. Network lifetime or operational time is the time during which WSN is able to fulfill its tasks by using microcontroller with on-chip memory radio transceivers, albeit distributed sensor nodes send summary of their data to their cluster heads, which reduce energy consumption gradually. In this paper a powerful algorithm using proactive fuzzy system is proposed and it is a mixture of fuzzy logic with comparative correlation techniques that ensure high data accuracy by detecting incorrect data in distributed wireless sensor networks. This proposed system is implemented in two phases there, the first phase creates input space partitioning by using robust fuzzy c means clustering and the second phase detects incorrect data and removes it completely. Experimental result makes transparent of combined correlated fuzzy system (CCFS) which detects faulty readings with greater accuracy (99.21%) than the existing one (98.33%) along with low false alarm rate.

• Journal of Korean Academy of Nursing
• /
• v.25 no.2
• /
• pp.259-278
• /
• 1995

This study was done to investigate levels of physical fitness, self efficacy(SE), instrumental activities of daily living(IADL), and quality of life (QL), and their relationships among the elderly Data were collected from 47 noninstitutionalized elderly dwell-ing in their own homes and 43 institutionalized elderly living in homes for older people. The ages of the subjects were 65 years and over. The data were col lected from January 20th to February 20th, 1995. Physical fitness was measured with T.K. K dyna mometer, grip dynamometer, stop watch, and Purdue pegboard. Structured questionnaires developed by Kim by Lawton & Brody, and by Ro were adopted to measure SE, IADL, and QL, respectively. The data were analyzed using t-test, ANOVA, and Pearson correlation coefficients. The results were as follows : 1. The noninstitutionalized elderly had higher scores in such measures of physical fitness as body weight, skinfold thickness, flexibility and coordination as compared to the institutionalized elderly. 2. On the following measures of physical fitness, men showed higher levels than women ; in height when standing, height when sitting, body weight, and muscle strength. Women had more trunk flexibility than men. 3. Muscle strength was positively correlated with height when standing, height when sitting, and body weight. The following measures of physical fitness, muscle strength, flexibility and coordi nation, were negatively correlated with "up and go”. 4. The noninstitutionalized elderly had higher scores in SE(t=2.28, p<0.05), IADL(t=2.24, p<0.05), and QL(t=2.41, p<0.05) as compared to the institutionalized elderly. 5. SE was positively correlated with both IADL(r=0.41, p<0.001) and QL(r=0.54, p<0.001), and the latter two variables were a positively correlated (r=0.30, p<0.001). 6. SE was positively correlated with the physical fitness measures of height when standing, body weight, strength of leg muscles, strength of back muscles, grip strength, and level of touching the floor, but negatively correlated with "up and go”. 7. Positive correlations were revealed between IADL and the physical fitness measures of height, strength of leg muscles, level of trunk muscle extension, level of touching the floor, and coordination. The IADL was negatively correlated with “up and go”. 8. QL was positively correlated with body weight (r=0.28, p<0.01) and skinfold thickness (r=0.26, p<0.05). 9. Age was negatively correlated with the physical fitness measures of height when standing, height when sitting, “up and go”, strength of leg muscles, strength of back muscles, grip strength, level of trunk muscle extension, and coordination. 10. Age was also negatively correlated with SE (r=-0.24, p<0.05) and IADL(r=-0.22, p<0.05). The above results suggest that caring elderly in their own homes were more effective and that nursing interventions to enhance physical fitness, SE, IADL, and QL especially for the institutionalized elderly are stressed.

• 제어로봇시스템학회:학술대회논문집
• /
• 2001.10a
• /
• pp.102.1-102
• /
• 2001

In this work, extensions to partial least squares (PLS) for wastewater treatment (WWT) process monitoring are discussed. Conventional data gathered by monitoring WWT systems are usually time varying, high dimensional, correlated and nonlinear, PLS has been shown to be an efficient approach in modeling and monitoring high dimensional and correlated data. To represent dynamic and nonlinear features of the data several kinds of dynamic nonlinear PLS (DNLPLS) models have been proposed. However, the complexity and ambiguity of the models make them unsuitable for WWT monitoring, Recently, dynamic fuzzy PLS (DFPLS) was proposed ...

• Korean Journal of Human Ecology
• /
• v.13 no.6
• /
• pp.861-874
• /
• 2004

The goal of this study is to investigate the relationship between maternal rearing behavior characteristics and elementary school children's Internet use, and to utilize the results as the basic data to develop a program, in which parents learn how to educate their children for better use of the Internet. The subjects were 713 children whose grade are in fourth through sixth in an elementary school. Data were obtained with questionnaires. The instruments employed were Children's Internet Use and Addiction, and maternal rearing behavior characteristics-Rational Guidance, Affection, Authoritarian Control, Overprotection, Achievement Encouragement, and Active Involvement-Scales. The data were analyzed with the SPSS program. They were analyzed by Frequency, Percentage, ANOVA, Duncan's test, and Pearson correlation. The results of this study are as follows: First, 30.2% of the subjects has used Internet for more than three years. 55.6% of the subjects spend less than an hour per day in using the Internet. The two major types of Internet use were playing games(49.9%) and sending e-mails(25.4%). The main reason for playing Internet games was escape from stress(34.7%). 34.5% of the subjects also said that their parents usually encourage them to use the Internet. Second, maternal affection, authoritarian control, and active involvement were significantly different in the types of Internet use. Maternal authoritarian control and overprotection were significantly different in the reasons of doing Internet game. The rational guidance and active involvement of mothers were correlated negatively with children's Internet using time, but their authoritarian control and overprotection were correlated positively with children's Internet using time. Maternal overprotection was correlated positively with parents' encouragement level in the Internet use. Third, the rational guidance, affection, and active involvement of mothers were correlated negatively with children's Internet addiction. In the other hand, maternal authoritarian control and overprotection were correlated positively with children's Internet addiction. Lastly, children's Internet addiction was significantly different by the types of Internet Use and the reasons for doing internet game. Children's Internet using time was correlated positively with children's Internet addiction.

• International Journal of Computer Science & Network Security
• /
• v.22 no.4
• /
• pp.340-350
• /
• 2022

The big data term refers to the great volume of data and complicated data structure with difficulties in collecting, storing, processing, and analyzing these data. Big data analytics refers to the operation of disclosing hidden patterns through big data. This information and data set cloud to be useful and provide advanced services. However, analyzing and processing this information could cause revealing and disclosing some sensitive and personal information when the information is contained in applications that are correlated to users such as location-based services, but concerns are diminished if the applications are correlated to general information such as scientific results. In this work, a survey has been done over security and privacy challenges and approaches in big data. The challenges included here are in each of the following areas: privacy, access control, encryption, and authentication in big data. Likewise, the approaches presented here are privacy-preserving approaches in big data, access control approaches in big data, encryption approaches in big data, and authentication approaches in big data.

• Communications for Statistical Applications and Methods
• /
• v.18 no.6
• /
• pp.751-759
• /
• 2011

The method of generalized estimating equations(GEE) is widely used in the analysis of a correlated dataset that consists of repeatedly observed responses within subjects. The GEE uses a quasi-likelihood equations to find the parameter estimates without assuming a specific distribution for the correlated responses. In this paper we study the importance of specifying the working correlation structure appropriately in fitting GEE for correlated counts data. We investigate the empirical coverages of confidence intervals for the regression coefficients according to four kinds of working correlations where one structure should be specified by the users. The confidence intervals are computed based on the asymptotic normality and the sandwich variance estimator.

• Journal of Korean Academy of Nursing Administration
• /
• v.7 no.3
• /
• pp.487-495
• /
• 2001

Purpose : In this study, task performance and job satisfaction of nurses in non-life insurance companies were examined to improve the personnel management in their companies. Method : Data collection was done with 119 nurses in non-life insurance companies in October and November, 1999. Data analyses were performed using SPSS Win 8.0 package. Result: The Results were as follows: 1. The tasks most commonly performed by nurses were 'medical fee inspection', 'education for staves', 'management of the injured', 'management of injury and disablement'. 2. The mean score of total job satisfaction was 3.2(interaction. 3.8; professional status, 3.6; autonomy, 3.4; task requirements, 3.1; administration, 2.8; pay and advancement, 2.6). 3. Task performance was significantly correlated with job satisfaction total score(r=0.478, p<.01). The item, 'executing statistical works and data analyses related with injury and disablement', was highly correlated with job satisfaction total score(r=0.418, p<.01). 4. The amount of task performance was significantly correlated with educational background and position. The job satisfaction level significantly correlated with personal experience and position. Conclusion : To improve the work efficiency and job satisfaction in the companies, it is necessary to set the bounds of task performance and to enlarge the promotion opportunities to higher positions.