• 한국지능시스템학회논문지
• /
• 제19권4호
• /
• pp.574-579
• /
• 2009

복잡한 비선형 회귀문제들에서 최적의 신경망을 구축하기 위해서는 구조의 선정 및 노이즈에 의한 과잉학습(overtraining)등에 따른 많은 문제들이 있다. 본 논문에서는 flexible incremental 알고리즘을 이용하여 단계적으로 최적의 신경망을 구축하는 방법을 제안한다. Flexible incremental 알고리즘은 예측 잔류오차를 최소화하기 위해 단계적으로 추가되어지는 은닉노드 개수를 검증데이터를 이용하여 신축성 있게 조절하고, 빠른 학습을 위하여 ELM (Extreme Learning Machine)을 이용한다. 제안된 방법은 신경망의 구축과정에서 사용자의 어떠한 관여 없이도 빠른 학습과 적은 수의 은닉노드들에 의한 범용 근사화 (universal approximation)가 가능한 신경망의 구축이 가능한 장점을 가지고 있다. 다양한 종류의 벤치마크 데이터들을 이용한 실험 결과를 통하여 제안된 방법이 실제 회귀문제들에서 우수한 성능을 가짐을 확인하였다.

• 대한간호학회지
• /
• 제34권3호
• /
• pp.576-585
• /
• 2004

Purpose: The purpose of this study was to identify the relationship between eating disorders, physical symptoms, depression and health locus of control. Method: The research design was a descriptive study done by using a constructive self-report questionnaire. A total of 464 elementary school girls were measured. The instrument was a constructive questionnaire that consisted 136 items. The subjects were divided into 4 groups according to the Body Mass Index (BMI). Data analysis was done by SPSS/WIN Programs using frequency, percentage, mean, SD, ANOVA, Pearson correlation coefficient, and stepwise multiple regression. Result: The score of eating disorders differed significantly by BMI : the score was highest in the group of obese students(F=4.208, P=.015). Stepwise multiple regression analysis revealed that the most powerful predictor of eating disorders was BMI. Conclusion: These results indicate that Korean elementary school girls need more education and counseling on diet. Also, we should take systematic efforts to reestablish the social standard of beauty to promote normal growth development.

• 간호행정학회지
• /
• 제11권1호
• /
• pp.45-58
• /
• 2005

Purpose: The purpose of this study was to identify the relationship among self-leadership, job satisfaction, and perceived outcome in nurses. Method: The subjects of study were nurses as a population who were working for the 2 of university hospitals which have over 500 beds in Kyong Ki Province as well as who have been working for over 6 months. The data was collected by questionnaires from 217 nurses and analyzed using descriptive statistics, pearson correlation coefficient, and multiple regression on SPSS 10. 0 version. Results: The degree of Self-leadership was 3.38 out of 5 as a mean point. There was a significant difference in self-leadership according to age, level of education, working department, and position. There was a significant positive correlation between self-relationship and job satisfaction, self-relationship and perceived outcome, and job satisfaction and perceived outcome. The stepwise multiple regression analysis revealed that the most powerful predictor of job satisfaction and perceived outcome was constructive thinking. Conclusion: In conclusion, the result was obtained that self-leadership is much correlated with job-satisfaction of nurse and outcome of nursing practice. Therefore, as a way to promote efficiency of nursing organization, the constant study about self-leadership with the various aspects is needed focusing on self-management and inner motivation as a new leadership paradigm.