• Journal of Preventive Medicine and Public Health
• /
• v.46 no.sup1
• /
• pp.35-42
• /
• 2013

A commitment to physical activity is necessary for personal health, and is a primary goal of physical activity practitioners. Effective practitioners rely on theory and research as a guide to best practices. Thus, sound theory, which is both practical and parsimonious, is a key to effective practice. The purpose of this paper is to review the literature in search of such a theory - one that applies to and explains commitment to physical activity in the form of sport and exercise for youths and adults. The Sport Commitment Model has been commonly used to study commitment to sport and has more recently been applied to the exercise context. In this paper, research using the Sport Commitment Model is reviewed relative to its utility in both the sport and exercise contexts. Through this process, the relevance of the Investment Model for study of physical activity commitment emerged, and a more parsimonious framework for studying of commitment to physical activity is suggested. Lastly, links between the models of commitment and individuals' participation motives in physical activity are suggested and practical implications forwarded.

• Asian Oncology Nursing
• /
• v.2 no.1
• /
• pp.5-16
• /
• 2002

Purpose: This study was to develop a stress-adaptation model for family caregivers of cancer patients that could provide the basis of planning nursing intervention. Method: A hypothetical model was developed using the family adaptation model proposed by Haley et al. (1987). In the literature, the stressor was identified as patient's characteristics, caregiver's characteristics, duration of illness, and family life events. It affected stress appraisal, family resources, family coping and finally caregiver's adaptation. In this model, 18 paths were constructed. Data were collected from 241 caregivers, whose family members were in treatment between June and August 2000, at 3 university hospitals and were analyzed by SPSS and LISREL programs. Results: 1) The overall fitness indices of the hypothetical model were x 2=267.78 (P= .0), GFI= .92, AGFI= .87, NFI= .93, NNFI= .93, PNFI= .64, PGFI= .55, and RMR= .43. Ten of the eighteen paths proved to be significant. 2) To improve the model fitness, the hypothetical model was modified considering modification indices and the paths proved not significant. Final model excluded 3 paths demonstrated to be improved by x2=161.96 (P= .00), GFI= .95, AGFI= .91, NFI= .96, NNFI= .96, and RMR= .23. Twelve of fifteen paths proved to be significant. 3) Stress appraisal was influenced by disease related characteristics and duration of illness and was explained 22% of the variance. Family resources were influenced by stress appraisal and was explained 57% of variance. Family coping was influenced by disease related characteristics, caregiver's characteristics, duration of illness, family life event, and stress appraisal and was explained 57% of variance. Family caregiver adaptation was influenced by disease related characteristics, caregiver's characteristics, stress appraisal, and family coping and was explained 31% of variance. Twelve of fifteen paths were significant. Conclusion: Based on this study, to help family caregivers to adapt, individual intervention is necessary with consideration of disease related and caregiver's characteristics and duration of illness. The intervention should include efforts to raise the family resources and to identify positively the stress they encounter, and there is a need to establish an adaptation model that considers emotional aspects of family caregivers. Since there is a difference in emotional status depending on the disease stage, a study needs to be done to analyze the differences among the disease stages (diagnosis, treatment, recurrence, and terminal stages).

• Journal of Intelligence and Information Systems
• /
• v.20 no.4
• /
• pp.121-139
• /
• 2014

Predicting corporate failure has been an important topic in accounting and finance. The costs associated with bankruptcy are high, so the accuracy of bankruptcy prediction is greatly important for financial institutions. Lots of researchers have dealt with the topic associated with bankruptcy prediction in the past three decades. The current research attempts to use ensemble models for improving the performance of bankruptcy prediction. Ensemble classification is to combine individually trained classifiers in order to gain more accurate prediction than individual models. Ensemble techniques are shown to be very useful for improving the generalization ability of the classifier. Bagging is the most commonly used methods for constructing ensemble classifiers. In bagging, the different training data subsets are randomly drawn with replacement from the original training dataset. Base classifiers are trained on the different bootstrap samples. Instance selection is to select critical instances while deleting and removing irrelevant and harmful instances from the original set. Instance selection and bagging are quite well known in data mining. However, few studies have dealt with the integration of instance selection and bagging. This study proposes an improved bagging ensemble based on instance selection using genetic algorithms (GA) for improving the performance of SVM. GA is an efficient optimization procedure based on the theory of natural selection and evolution. GA uses the idea of survival of the fittest by progressively accepting better solutions to the problems. GA searches by maintaining a population of solutions from which better solutions are created rather than making incremental changes to a single solution to the problem. The initial solution population is generated randomly and evolves into the next generation by genetic operators such as selection, crossover and mutation. The solutions coded by strings are evaluated by the fitness function. The proposed model consists of two phases: GA based Instance Selection and Instance based Bagging. In the first phase, GA is used to select optimal instance subset that is used as input data of bagging model. In this study, the chromosome is encoded as a form of binary string for the instance subset. In this phase, the population size was set to 100 while maximum number of generations was set to 150. We set the crossover rate and mutation rate to 0.7 and 0.1 respectively. We used the prediction accuracy of model as the fitness function of GA. SVM model is trained on training data set using the selected instance subset. The prediction accuracy of SVM model over test data set is used as fitness value in order to avoid overfitting. In the second phase, we used the optimal instance subset selected in the first phase as input data of bagging model. We used SVM model as base classifier for bagging ensemble. The majority voting scheme was used as a combining method in this study. This study applies the proposed model to the bankruptcy prediction problem using a real data set from Korean companies. The research data used in this study contains 1832 externally non-audited firms which filed for bankruptcy (916 cases) and non-bankruptcy (916 cases). Financial ratios categorized as stability, profitability, growth, activity and cash flow were investigated through literature review and basic statistical methods and we selected 8 financial ratios as the final input variables. We separated the whole data into three subsets as training, test and validation data set. In this study, we compared the proposed model with several comparative models including the simple individual SVM model, the simple bagging model and the instance selection based SVM model. The McNemar tests were used to examine whether the proposed model significantly outperforms the other models. The experimental results show that the proposed model outperforms the other models.

• Proceedings of the Korean Society for Technology of Plasticity Conference
• /
• 1997.03a
• /
• pp.155-158
• /
• 1997

The investigation deals with of a intermediate process condition hving a bolt-shaped final product where it is required to extend tool-life in forging. In this study, optimization of the design variables is conducted by a genetic algorithm, where the fitness values are evaluated on the basis of FEM analysis model. The approach is applied to the determination of the intermediate process conditions which are optimal with regard to minimization of peak die pressure.

• Proceedings of the Korean Society for Technology of Plasticity Conference
• /
• 1997.10a
• /
• pp.153-157
• /
• 1997

The investigation deals with the process design in cold rolling mill of electric plant. In this study, multiple objective optimization is conducted by a genetic algorithm, where the fitness values are evaluated on the basis of one - dimensional model of flat rolling. The approach is applied to the determination of the process conditions which are optimal with regard to minimization of roll power and maximization of productivity.

• Korean Journal of Biological Psychiatry
• /
• v.26 no.2
• /
• pp.33-38
• /
• 2019

Psychiatric disorder as dysfunctional behavioural syndrome is a paradoxical phenomenon that is difficult to explain evolutionarily because moderate prevalence rate, high heritability and relatively low fitness are shown. Several evolutionary genetic models have been proposed to address this paradox. In this paper, I explain each model by dividing it into selective neutrality, mutation-selection balance, and balancing selection hypothesis, and discuss the advantages and disadvantages of them. In addition, the feasibility of niche specialization and frequency dependent selection as the plausible explanation about the central paradox is briefly discussed.

• Journal of Digital Convergence
• /
• v.6 no.2
• /
• pp.41-53
• /
• 2008

This research is to redefine the concept of Good School and to validate an effective Good Secondary School Scale in Kyung-gi Province and Seoul. As statistical methods, SPSS 13.0 and AMOS 5.0 were used. Item Analysis and Exploratory Factor Analysis(EFA) were conducted to test the reliability of items and the factor structure. And Confirmatory Factor Analysis(CFA) was conducted to test the validity and fitness of the Good School Scale. The outcomes are as follows: First, six factors(school environment, curriculum, teacher, school-based management system, director) will increase the good schooling effectiveness. Second, As a result of Confirmatory Factor Analysis(CFA), the goodness of fit indices(GFI AGFI, CFI, RMSEA) demonstrate statistically significance and fitness of the model. The final Good School Scale supports 6 Good School Factors obtained in main test. Therefore, we can say that this scale can be used as a valid instrument to measure a real Good Schooling Effectiveness at the secondary school situation in Korea.

• Korean Journal of Artificial Intelligence
• /
• v.5 no.1
• /
• pp.18-28
• /
• 2017

Recently, there are many companies that use systems based on artificial intelligence. The accuracy of artificial intelligence depends on the amount of learning data and the appropriate algorithm. However, it is not easy to obtain learning data with a large number of entity. Less data set have large generalization errors due to overfitting. In order to minimize this generalization error, this study proposed DGA which can expect relatively high accuracy even though data with a less data set is applied to machine learning based genetic algorithm to deep learning based dropout. The idea of this paper is to determine the active state of the nodes. Using Gradient about loss function, A new fitness function is defined. Proposed Algorithm DGA is supplementing stochastic inconsistency about Dropout. Also DGA solved problem by the complexity of the fitness function and expression range of the model about Genetic Algorithm As a result of experiments using MNIST data proposed algorithm accuracy is 75.3%. Using only Dropout algorithm accuracy is 41.4%. It is shown that DGA is better than using only dropout.

• Journal of Convergence for Information Technology
• /
• v.8 no.1
• /
• pp.95-103
• /
• 2018

This study set out to evaluate the fitness of shelter locations by taking into consideration service zones according to walking speed, the changing population between day and night, and walking routes. Walking speed was defined as 1.6 m/s, 2 m/s based on the cases of previous studies. The changing population between day and night was estimated with the dasymetric mapping technique. Shelter service zones according to walking speed and routes were analyzed with the network of the location allocation model. The findings show some shelters had limits with their capacity according to the changing floating population and walking speed in time and space and raise a need to appoint additional shelters.

• International Journal of Advanced Culture Technology
• /
• v.5 no.2
• /
• pp.74-81
• /
• 2017

Recently, there are many companies that use systems based on artificial intelligence. The accuracy of artificial intelligence depends on the amount of learning data and the appropriate algorithm. However, it is not easy to obtain learning data with a large number of entity. Less data set have large generalization errors due to overfitting. In order to minimize this generalization error, this study proposed DGA(Dropout Genetic Algorithm) which can expect relatively high accuracy even though data with a less data set is applied to machine learning based genetic algorithm to deep learning based dropout. The idea of this paper is to determine the active state of the nodes. Using Gradient about loss function, A new fitness function is defined. Proposed Algorithm DGA is supplementing stochastic inconsistency about Dropout. Also DGA solved problem by the complexity of the fitness function and expression range of the model about Genetic Algorithm As a result of experiments using MNIST data proposed algorithm accuracy is 75.3%. Using only Dropout algorithm accuracy is 41.4%. It is shown that DGA is better than using only dropout.