• The KIPS Transactions:PartD
• /
• v.12D no.6 s.102
• /
• pp.829-836
• /
• 2005

The way to assign a splitting criterion for correct object classification is the main issue in all decisions trees. This paper describes new splitting rules for classification in order to find an optimal split point. Unlike the current splitting rules that are provided by searching all threshold values, this paper proposes the splitting rules that we based on the probabilities of pre assigned intervals. Our methodology provides that user can control the accuracy of tree by adjusting the number of intervals. In addition, we applied the proposed splitting rules to a set of image data that was retrieved by parameterized feature extraction to recognize image objects.

• Journal of Korean Academy of Nursing
• /
• v.44 no.6
• /
• pp.630-638
• /
• 2014

Purpose: The purpose of this study was to develop a scale to evaluate stress in elderly patients with coronary artery diseases (CAD) and to examine validity and reliability of the scale. Methods: The development process for the preliminary scale included construction of a conceptual framework and initial items, verification of content analysis, sentence correction, and pilot study. This study was conducted using a questionnaire survey with one-to-one interviews during January and February, 2012. Participants were 240 elderly patients with CAD. Data were analyzed using item analysis, factor analysis, criterion related validity, and internal consistency. Results: The developed scale consisted of 32 items and 6 factors - aging and disease (7 items), family relations (5 items), anxiety and withdrawal (9 items), management of daily living (3 items), compliance of medical regimen (4 items), poverty and finance (4 items), and explained 68.5% of total variance. The scale had significantly positive correlation with the Korean Perceived Stress Scale (KPSS). Cronbach's alpha was .96, and Guttman split half coefficient was .91. Conclusion: Results indicate that the Stress Scale for Elderly Patients with CAD has validity and reliability, and is a suitable scale in health care settings to assess stress in elderly patients with CAD.

• Journal of Power System Engineering
• /
• v.6 no.3
• /
• pp.57-63
• /
• 2002

This paper describes the acoustic analysis of mid duty truck. The focus of the analysis is on structure borne engine noise with major contributions of 2nd order. It has been previously recognized that the noise contribution of each transfer path of structure borne noise can be varied with the charateristics of each mounts and vibro acoustic sensitivity of car body. The structure of car body will be split up into three major sub components, which are modeled separately, the engine, the frame and the cab. The acoustic performance is evaluated on three levels: engine to frame transfer, frame to cab transfer, and panel contribution from cab to driver. In order to perform these analyses, analytical models are created for the engine, frame, cab and acoustic cavity. The models are linked through a coupled fluid structure calculation, and through FRF Based Substructuring for the structural couplings. Based on the structural coupling calculations, a transfer path analysis is performed to identify the most important transfer paths. These paths are then the focussing points for applying modifications to the structure or the mount system. Finally, a number of modification are proposed and their effect is quantified.

• Child Health Nursing Research
• /
• v.21 no.2
• /
• pp.131-140
• /
• 2015

Purpose: The purpose of this study was to develop an instrument that evaluated QUality Of care Through patients' Eyes for hospitalized child (QUOTE-Child), and examine the validity and reliability. Methods: Preliminary items were reviewed through expert content validity and face validity. To test the validity and reliability of the instrument, the data were collected from 221 care givers of hospitalized children. Data were analyzed using exploratory factor analysis, Pearson correlation coefficient, Cronbach's alpha and Spearman-Brown coefficient. Results: Factor analysis yielded 19 items in four factors including 1) respect, 2) explanation, 3) kindness, and 4) skillfulness, with a cumulative explanatory variance of 70.68%. For criterion-related validity, a significant positive relationship was found between quality of care and pediatric family satisfaction. For internal consistency reliability, the Cronbach's ${\alpha}$ was .93 (importance) and .95 (performance) for the overall instrument. The half split reliabilities were .86, .95 (importance) and .92, .97 (performance). The Cronbach's ${\alpha}$ of 110 data was .92 (importance) and .94 (performance). Conclusion: Researchers and practitioners can use this instrument to systematically assess quality of care for hospitalized children and identify areas of support for hospitalized children and their family.

• Child Health Nursing Research
• /
• v.25 no.2
• /
• pp.85-94
• /
• 2019

Purpose: This study presents methodological research that aimed to verify the content validity, construct validity, reliability, and criterion-related validity of the Child Abuse Potential Inventory (CAPI), originally developed by Milner and then translated into Korean by Ahn. Methods: Data used in this study were collected from 209 mothers of infants, toddlers, and children of preschool age in D metropolitan city. The collected data were analyzed using SPSS version 24. Results: The Korean version of the Child Abuse Potential Inventory (K-CAPI) was developed by condensing 44 of the original 77 CAPI items. Four factors of K-CAPI were extracted using principal component analysis. These 4 factors-distress; problems with child, self, family, and others; unhappiness; rigidity-accounted for 54.01% of variance. The Cronbach's ${\alpha}$ was .96, the Guttman split-half coefficient was .88, and test-retest reliability was r=.86 (p<.001). Conclusion: The results of this study established the reliability and validity of the K-CAPI and found it to be an appropriate tool to evaluate mothers' potential to abuse their children.

• 한국노년학
• /
• v.41 no.1
• /
• pp.149-168
• /
• 2021

This study was to develop the Medication Adherence Scale in Elderly (MAS-E) with chronic disease and verify its reliability and validity. The MAS-E was developed in 5 steps: Configuration of conceptual frame by content analysis, preliminary items, pilot study, reliability and validity test, and development of final MAS-E with chronic disease. The questionnaires were collected from 345 adults with one-to-one interviews. Verification of its reliability and validity was divided into two phases. Reliability was tested using Cronbach's alpha, split-halves reliability, and test-retest. For validity tests, item analysis, factor analysis, total score-factor score correlation analysis, and criterion related validity were used. The developed scale consisted of 18 items and 4 factors - remember of taking medication (2 items), expectations for drug effects (5 items), practice taking medication according to instructions (8 items), communicating with health professionals (3 items), and explained 69.7% of total variance. The scale had significantly positive correlation (r = .72, p <.001) with the Morisky Medication Adherence Scale (MMAS-8). Cronbach's alpha was .91, Guttman split half coefficient was .80, and test-retest reliability was .912. Finding suggest that the MAS-E is a suitable scale to assess the status of medication adherence in elderly with chronic disease.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.12 no.4
• /
• pp.772-780
• /
• 2008

K-means is one of the simplest unsupervised learning algorithms that solve the clustering problem. However K-means suffers the basic shortcoming: the number of clusters k has to be known in advance. In this paper, we propose extensions of X-means, which can estimate the number of clusters using Bayesian information criterion(BIC). We introduce two different versions of algorithm: modified X-means(MX-means) and generalized X-means(GX-means), which employ one full covariance matrix for one cluster and so can estimate the number of clusters efficiently without severe over-fitting which X-means suffers due to its spherical cluster assumption. The algorithms start with one cluster and try to split a cluster iteratively to maximize the BIC score. The former uses K-means algorithm to find a set of optimal clusters with current k, which makes it simple and fast. However it generates wrongly estimated centers when the clusters are overlapped. The latter uses EM algorithm to estimate the parameters and generates more stable clusters even when the clusters are overlapped. Experiments with synthetic data show that the purposed methods can provide a robust estimate of the number of clusters and cluster parameters compared to other existing top-down algorithms.

• Clinical and Experimental Reproductive Medicine
• /
• v.48 no.2
• /
• pp.163-173
• /
• 2021

Objective: This study aimed to characterize a validated model for predicting oocyte retrieval in controlled ovarian stimulation (COS) and to construct model-based nomograms for assistance in clinical decision-making regarding the gonadotropin protocol and dose. Methods: This observational, retrospective, cohort study included 636 women with primary unexplained infertility and a normal menstrual cycle who were attempting assisted reproductive therapy for the first time. The enrolled women were split into an index group (n=497) for model building and a validation group (n=139). The primary outcome was absolute oocyte count. The dose-response relationship was tested using modified Poisson, negative binomial, hybrid Poisson-E_max, and linear models. The validation group was similarly analyzed, and its results were compared to that of the index group. Results: The Poisson model with the log-link function demonstrated superior predictive performance and precision (Akaike information criterion, 2,704; λ=8.27; relative standard error (λ)=2.02%). The covariate analysis included women's age (p<0.001), antral follicle count (p<0.001), basal follicle-stimulating hormone level (p<0.001), gonadotropin dose (p=0.042), and protocol type (p=0.002 and p<0.001 for short and antagonist protocols, respectively). The estimates from 500 bootstrap samples were close to those of the original model. The validation group showed model assessment metrics comparable to the index model. Based on the fitted model, a static nomogram was built to improve visualization. In addition, a dynamic electronic tool was created for convenience of use. Conclusion: Based on our validated model, nomograms were constructed to help clinicians individualize the stimulation protocol and gonadotropin doses in COS cycles.

• Child Health Nursing Research
• /
• v.19 no.1
• /
• pp.29-38
• /
• 2013

Purpose: This study was done to develop a cell phone addiction scale for Korean parents of young children, and to evaluate the reliability and validity of the developed scale. Methods: The scale was developed through construction of a conceptual framework, generation of initial items, verification of content validity, selection of secondary items, preliminary study, and extraction of final items. Participants were 465 parents and 178 children. Data were analyzed using item analysis, factor analysis, criterion related validity, internal consistency, and split-half reliability. Results: Twenty items were categorized into three factors explaining 60.3% of total variance. Factors were named as withdrawal - 4 items, loss of control - 9 items, and persistence - 7 items. Scores for the scale were significantly correlated with self-control, impulsiveness, cell phone use, and cell phone addiction of children as measured by a scale for Korean children. Cronbach's alpha coefficient for the 20 items was .94, and Guttman coefficient was .87. Scale scores identified children as high risk users, at risk users, or average users by standard scores. Conclusion: The results suggest that the cell phone addiction scale for Korean parents is a reliable and valid instrument to measure cell phone addiction in young children.

• The Korean Journal of Elementary Counseling
• /
• v.9 no.1
• /
• pp.41-58
• /
• 2010

The purpose of this study was to invent anger-inducing automatic thoughts examination for elementary school children based on its investigation for Korean one. I made the anger-inducing Automatic Thoughts Questionnaire(I, II) and made an examination of the contents of the automatic thoughts with it. Based on it, with preliminary questionnaire 90, I did principal component analysis varimax rotation and then final anger-inducting automatic thoughts examination of 40 question in 2 primary factor construction was consisted. I made 300 students carry out it to know its reliability, propriety and made 100 students carry it out at 2-week intervals test-retest. I divided them in three groups as low, middle and high according to its soore regarding anger-inducting automatic thoughts, I confirmed the variation of each group in positive thoughts, self-esteem, life satisfaction, anger, the result is same as follows; First, the content of Anger-inducting Automatic thoughts for elementary school students is revealed as unreasonableness(56.4%), retailation and passive, active offense(16.3%), blame and contempt(11.9%), injured pride and refusal(9.2%), absurd(3.9%), abandonment and avoidance(2.1%), self-abasement in turn. Second, said inventory is consist of 2 notion; first(20 questions) is blame, retaliation and second(20 questions) is injustice. Inner-item consistency of total 40 question is .97, Split-half reliability is .93, Test-retest reliability is .86. Third, criterion validity is revealed fine by reviewing the correlation between existing index related to the inventory of Anger-inducting Automatic thoughts of the elementary school students. Moreover, to find out discriminant validity, I divided three classes(low, middle, high) according to the score of said thoughts. As a result, there is certain variations when I confirmed variations in groups by reviewing the self-esteem, positive way of thinking, life satisfaction, anger.