• Industrial Engineering and Management Systems
• /
• 제16권1호
• /
• pp.64-79
• /
• 2017

Identifying disease genes from human genome is a critical task in biomedical research. Important biological features to distinguish the disease genes from the non-disease genes have been mainly selected based on traditional feature selection approaches. However, the traditional feature selection approaches unnecessarily consider many unimportant biological features. As a result, although some of the existing classification techniques have been applied to disease gene identification, the prediction performance was not satisfactory. A small set of the most important biological features can enhance the accuracy of disease gene identification, as well as provide potentially useful knowledge for biologists or clinicians, who can further investigate the selected biological features as well as the potential disease genes. In this paper, we propose a new stepwise random forests (SRF) approach for biological feature selection and disease gene identification. The SRF approach consists of two stages. In the first stage, only important biological features are iteratively selected in a forward selection manner based on one-dimensional random forest regression, where the updated residual vector is considered as the current response vector. We can then determine a small set of important biological features. In the second stage, random forests classification with regard to the selected biological features is applied to identify disease genes. Our extensive experiments show that the proposed SRF approach outperforms the existing feature selection and classification techniques in terms of biological feature selection and disease gene identification.

• 한국의류학회지
• /
• 제26권1호
• /
• pp.15-26
• /
• 2002

The purpose of this study was to classier the somatotype of late middle-aged women and to analyze the characteristics of each somatotype. The subjects were 337 late middle-aged women and their age range os from 45 to 59 fears old. Data were collected through anthropometry and photometry and analyzed by factor analysis, cluster analysis and discriminant analysis. The results were as follows; 1. The result of factor analysis indicated that 9 factors were extracted through factor analysis and those factors comprised 83.56 percent of total valiance. 2. Using factor scores, cluster analysis was carried out and the subject were classified into 4 cluster. Each cluster was classified as their body front and side view contour. Type 1 is tall, slim, and lower balk is flat on the side. Type 2 is standard and lean-back type on the side. Type 3 is standard height and weight, H type in front, and belly-protruded on the side. Type 4 is short, fat, and the side is hip-protruded. 3. According to the stepwise discriminant analysis, the 9 important items in classifying the somatotype of the late middle-aged women are as follows ; lower back tilt angle, hip depth(back) -back waist depth(back), bust depth(fore) - anterior waist depth(fore), jugular fossa point(fore), upper back tilt angle, burst breadth -waist breadth, right shoulder tilt, height of shoulder - height of anterior waist, abdomen breath. The correct classification rate for these items is as exact as 84.62%.

• Clinical and Experimental Pediatrics
• /
• 제53권6호
• /
• pp.680-687
• /
• 2010

Patients with congenital heart diseases (CHD) are confronted with early- and late-onset complications, such as conduction disorders, arrhythmias, myocardial dysfunction, altered coronary flow, and ischemia, throughout their lifetime despite successful hemodynamic and/or anatomical correction. Rhythm disturbance is a well-known and increasingly frequent cause of morbidity and mortality in patients with CHD. Predisposing factors to rhythm disturbances include underlying cardiac defects, hemodynamic changes as part of the natural history, surgical repair and related scarring, and residual hemodynamic abnormalities. Acquired factors such as aging, hypertension, diabetes, obesity, and others may also contribute to arrhythmogenesis in CHD. The first step in evaluating arrhythmias in CHD is to understand the complex anatomy and to find predisposing factors and hemodynamic abnormalities. A practical stepwise approach can lead to diagnosis and prompt appropriate interventions. Electrophysiological assessment and management should be done with integrated care of the underlying heart defects and hemodynamic abnormalities. Catheter ablation and arrhythmia surgery have been increasingly applied, showing increasing success rates with technological advancement despite complicated arrhythmia circuits in complex anatomy and the difficulty of access. Correction of residual hemodynamic abnormalities may be critical in the treatment of arrhythmia in patients with CHD.

• 산경연구논집
• /
• 제9권2호
• /
• pp.17-26
• /
• 2018

Purpose - The purpose of this study is to provide a formalized process of decision making for companies or organizations that need to make various decisions in the age of uncertainty. Therefore, this study aimed to proposes a strategic decision-making approach citing the relatively easily accessible using IPA(important-performance analysis) and SWOT/AHP analysis. Research design, data, and methodology - To be specific, the first step is to derive necessary attributes and conduct IPA. The second step is to subdivide the IPA results into internal strength and weakness factors and the external opportunity and threat factors, hierarchize those factors, and weight them accordingly. The third step is to build a causality model to propose a method of supporting a rational decision making. Results - The foregoing approach seems to facilitate the diversification of decision-making strategies by helping businesses or organizations to measure and analyze the attributes needed for certain decisions. Additionally, the perceived importance and satisfaction (or achievement) usage of those derived attributes can be used as the reference data for SWOT/AHP analysis. Conclusions - The proposed stepwise approach is applicable to businesses or organizations in need of making stepwise decisions in line with their retained competencies in comparison to conventional or intuitive decision-making practices.

• 한국생활과학회지
• /
• 제16권6호
• /
• pp.1131-1140
• /
• 2007

The purpose of this study is to investigate the effect of parenting behavior and parent-child communication on internet use among school-aged children. The subjects were 215 children whose grade are 3rd and 5th selected from an elementary school in Incheon. The statistics used for this data were t-test, one-way ANOVA(Duncan's test), and stepwise regression. The findings from the present study suggested that academic achievement and birth order turned out to be significant variables on children's internet use, except for sex and grade. Results of the stepwise regression analyses that the etiologic model of this study was more proper, and parenting behavior is more effective variable than parent-child communication in predicting internet use among school-aged children. Implications based on this study are as follows; In order to decrease the degree of school-aged children's internet use, parents should do less permissive parenting behavior and problematic communication with their children.

• 한국경영과학회지
• /
• 제39권3호
• /
• pp.51-61
• /
• 2014

In this paper, we deal with developing a cost estimation relationships (CER) for Korean maneuverable weapons systems using historical production cost. To develop the CER, we collected the historical data of the production cost of four tanks and five armored vehicles. We also analyzed the Required Operational Capability (ROC) of the weapons systems and chose cost drivers that can compare operational capabilities of the weapons systems We used Forward selection, Backward selection, Stepwise Regression and $R^2$ selection as the cost drivers which have the greatest influence with the dependent variables. And we used Principle Component Regression, Robust Regression and Weighted Regression to deal with multicollinearity and outlier among the data to develop a more appropriate CER. As a result, we were able to develop a production cost CER for Korean maneuverable weapons systems that have the lowest cost errors. Thus, this research is meaningful in terms of developing a CER based on Korean original cost data without foreign data and these methods will contribute to developing a Korean cost analysis program in the future.

• 대한수학회논문집
• /
• 제31권2호
• /
• pp.395-414
• /
• 2016

In this work, we study on subdivision schemes reproducing polynomials and build a symmetric subdivision scheme reproducing polynomials of a certain predetermined degree, which is a slight variant of the family of Deslauries-Dubic interpolatory ones. Related to polynomial reproduction, a necessary and sufficient condition for a subdivision scheme to reproduce polynomials of degree L was recently established under the assumption of non-singularity of subdivision schemes. In case of stepwise polynomial reproduction, we give a characterization for a subdivision scheme to reproduce stepwise all polynomials of degree ${\leq}L$ without the assumption of non-singularity. This characterization shows that we can investigate the polynomial reproduction property only by checking the odd and even masks of the subdivision scheme. The minimal-support condition being relaxed, we present explicitly a general formula for the mask of (2n + 4)-point symmetric subdivision scheme with two parameters that reproduces all polynomials of degree ${\leq}2n+1$. The uniqueness of such a symmetric subdivision scheme is proved, provided the two parameters are given arbitrarily. By varying the values of the parameters, this scheme is shown to become various other well known subdivision schemes, ranging from interpolatory to approximating.

• 지식경영연구
• /
• 제13권5호
• /
• pp.43-64
• /
• 2012

Emerging technologies have significant implications in establishing competitive advantages and are characterized by continuous rapid development. Efficient benchmarking is more and more important in the development of emerging technologies. Similar input level and importance are two necessary criteria need to be considered for emerging technology's benchmarking. In this study, we proposed a sequential use of self-organizing map(SOM), data envelopment analysis(DEA) and analytical hierarchy process(AHP) method for the stepwise benchmarking of emerging technology. The proposed method uses two-level SOM to cluster the emerging technologies with similar required input levels together, then, in each cluster, uses DEA-BCC model to evaluate the efficiencies of the emerging technologies and do tier analysis to form tiers. On each tier, AHP rating method is used to calculate each emerging technology's importance priority. The optimal benchmarking path of each cluster is established by connecting the emerging technologies with the highest importance priority. In order to validate the proposed method, we apply it to a case of biotechnology. The result shows the proposed method can overcome difficulties in benchmarking, select suitable benchmarking targets and make the benchmarking process more efficient and reasonable.

• 한국운동역학회지
• /
• 제30권1호
• /
• pp.83-91
• /
• 2020

Objective: The study aimed to develop a functional performance index that evaluates the functional performance of Parkinson's patients, i.e., to integrate biomechanical measurements of walking, balance, muscle strength and tremor, and to use multiple linear regression with stepwise methods to identify the most suitable predictors for the progression of disease. Method: A total of 60 subjects were tested for sub-variables of four factors: walking, balance, isometric strength and hand tremors. Potential independet variables were extracted through correlation analysis of the sub-variables and dependent variables, Hoehn & Yahr scale. And then, a stepwise multiple regression analysis using the potential independent variables was performed to identify predictor of Hoehn & Yahr scale. Results: First, the results of the study showed that physical composition and gait had a relatively more correlated with the progression of the disease, compared to balance and hand tremor. Second, Parkinson's functional performance is characterized by dynamic pattern of walking, such as foot clearance and turning angle (TA) of walking, and a high-explained regression model is completed. Conclusion: The study emphasized the importance of walking variables and body composition in minor pathological features compared to Parkinson's patient's balancing ability and hand tremor. Specifically, it revealed that dynamic walking patterns functionally characterize patients. The results are worth considering when assessing functional performance related to the progression of the disease at the site.

• 동서간호학연구지
• /
• 제23권2호
• /
• pp.142-149
• /
• 2017

Purpose: The purpose of this study was to investigate factors affecting trait anger level in undergraduate students. Methods: The participants consisted of 315 undergraduate students at the universities in the P and D cities. Data were collected with a structured questionnaire and analyzed using descriptive analysis, t-test, ANOVA, Pearson correlation coefficients, and multiple stepwise regression with the SPSS/Win 20.0 program. Results: The low trait anger group showed lower levels of anger-out, anger-in and depression compared to the high trait anger group. The anger-control and positive thinking were higher in the low trait anger group than that of high trait anger group. The result of multiple stepwise regression showed that both depression and anger-out were predictors in trait anger in the both groups. In the low trait anger group, anger-control, anger-in, depression, and anger-out were significant factors of trait anger, which accounted for 31% of the total variance. High trait anger level was affected by depression, anger-out and positive thinking, which explained 40% of trait anger. Conclusion: The results of this study suggest that anger management program for undergraduate students should consider trait anger level as well as approaches with customized strategies according to trait anger level.