• Information Systems Review
• /
• v.24 no.1
• /
• pp.39-57
• /
• 2022

This paper proposes the GMOPTBoost algorithm to improve the performance of the AdaBoost algorithm for bankruptcy prediction in which class imbalance problem is inherent. AdaBoost algorithm has the advantage of providing a robust learning opportunity for misclassified samples. However, there is a limitation in addressing class imbalance problem because the concept of arithmetic mean accuracy is embedded in AdaBoost algorithm. GMOPTBoost can optimize the geometric mean accuracy and effectively solve the category imbalance problem by applying Gaussian gradient descent. The samples are constructed according to the following two phases. First, five class imbalance datasets are constructed to verify the effect of the class imbalance problem on the performance of the prediction model and the performance improvement effect of GMOPTBoost. Second, class balanced data are constituted through data sampling techniques to verify the performance improvement effect of GMOPTBoost. The main results of 30 times of cross-validation analyzes are as follows. First, the class imbalance problem degrades the performance of ensembles. Second, GMOPTBoost contributes to performance improvements of AdaBoost ensembles trained on imbalanced datasets. Third, Data sampling techniques have a positive impact on performance improvement. Finally, GMOPTBoost contributes to significant performance improvement of AdaBoost ensembles trained on balanced datasets.

• Science of Emotion and Sensibility
• /
• v.8 no.2
• /
• pp.103-115
• /
• 2005

This research aimed at a clear definition of simplicity and complexity and other elements of product aesthetics and investigated the influence of simplicity/complexity on consumer preference, and balance. The research also made it an objective to find answers to underlying questions of whether there is a relationship between simplicity/complexity, and balance, and if there is, then how is the relationship? and is balance in a product's aesthetics an influential factor? does a relationship exist between consumer preference, simplicity/complexity, and balance? In conclusion, the research process categorized products into groups by use of FCB Grid, and analyze4 each group to establish a prototype which represents the group, then questionnaires where presented to consumers in order to find satisfaction to consumer preference. Also, the research proposes a verification method through design process.

• 재활복지
• /
• v.22 no.2
• /
• pp.175-212
• /
• 2018

The purpose of this study was to identify factors that affect the optimal selection of rehabilitation therapy and explore a processing model of rehabilitation decision-making for parents of children with cerebral palsy. A ground theory of Strauss and Corbin(1988)was used. Thus, collecting data was classified into open coding 140 concepts, 29 sub-categories and 8 categories. As a result of analysis, we identified that the main phenomenon was 'finding optimal therapy in trial and error' and parents experienced 6 stages including 'embarrassment', 'confusion', 'maximization', 'wandering', 'strategy', and 'balance'. Furthermore, 'rehabilitation-daily life balance' was a key category for continuation of treatment. This qualitative study discribed factors influencing determination of treatment and its continuation, and suggested a processing model of parents' decision- making for rehabilitation of their children.

• The Journal of the Korea Contents Association
• /
• v.22 no.5
• /
• pp.711-720
• /
• 2022

The aim of the present study is to test multiple mediating effects of job-efficacy and resiliance in the links between work-life balance (WLB) and deviant behavior. The date applied in empirical analysis was collected from employees working at Jeju island and 400 sets of questionnaires were spread and among collected 355 sets, 298 sets were used. Hypotheses was examined with SPSS Macro statistical package. As expected, WLB was positively related to job-efficacy and resiliance respectively and negatively associated with deviant behaivor. Moreover, mediating effects of both variables was different, in detail, job-efficacy was fully mediated in that path but not significant in case of resiliance. Findings of this study was to expand the roles of WLB from productive behaviors to counter-productive behaviors and it enables to provide a few theoretical and empirical implications.

• Annual Conference on Human and Language Technology
• /
• 2022.10a
• /
• pp.251-256
• /
• 2022

범주 불균형은 분류 모델이 다수 범주에 편향되게 학습되어 소수 범주에 대한 분류 성능을 떨어뜨리는 문제를 야기한다. 언더 샘플링 기법은 다수 범주 데이터의 수를 줄여 소수 범주와 균형을 이루게하는 대표적인 불균형 해결 방법으로, 텍스트 도메인에서의 기존 언더 샘플링 연구에서는 단어 임베딩과 랜덤 샘플링과 같은 비교적 간단한 기법만이 적용되었다. 본 논문에서는 트랜스포머 기반 문장 임베딩과 군집화 기반 샘플링 방법을 통해 텍스트 데이터의 정보 손실을 최소화하는 언더샘플링 방법을 제안한다. 제안 방법의 검증을 위해, 감성 분석 실험에서 제안 방법과 랜덤 샘플링으로 추출한 훈련 세트로 모델을 학습하고 성능을 비교 평가하였다. 제안 방법을 활용한 모델이 랜덤 샘플링을 활용한 모델에 비해 적게는 0.2%, 많게는 2.0% 높은 분류 정확도를 보였고, 이를 통해 제안하는 군집화 기반 언더 샘플링 기법의 효과를 확인하였다.

• Journal of the Korean Society for Library and Information Science
• /
• v.48 no.4
• /
• pp.297-322
• /
• 2014

The purpose of this study is to analyse the meaning and lexical morpheme of author keywords of humanities, social sciences, and art and sport in the Korea Ciation Index (KCI) and to propose a conceptual taxonomy of the author keywords. Four top-level concept categories such as 'Substance, Abstraction, General/Common, and Object' are replaced by seven more concrete categories such as 'object, action/function, property, theory/method, format/framework, general/common, and Instance'. In the middle and lower-level concept categories, the hierarchical structure is simplified and the unbalance of term distribution is reduced by creating, subdivision, integration, elimination, and movement of the categories. The result of the test based on the STNet shows that the replaced taxonomy of concept categories has the effects of making the term allocation more balanced and properties of terms more detailed.

• Journal of Science Education
• /
• v.37 no.1
• /
• pp.23-39
• /
• 2013

Science teachers' perception on their preparation program can help in conceptualizing how science teachers could be prepared. Based on this premise, this study aims to investigate preservice and inservice science teachers' perception on their teacher preparation programs with a focus on the coherence and balance of program. For this purpose, 20 preservice and 39 inservice science teachers were participated. Selection form and open-ended form questionnaires were developed to survey science teachers' perception on their program. The results of study are as follows: Firstly, participating preservice and inservice science teachers perceived the coherence of their program as moderate. The most and least coherent category of program was 'planning & preparation' and 'professional responsibilities' respectively. Inservice teachers perceived the program less coherent than preservice teachers in all four categories. Secondly, participating preservice and inservice science teachers perceived that practical elements were deficient compare to theoretical elements in light of balance of the program. Lastly, participating preservice and inservice science teachers perceived that current science teacher preparation program was biased to test-driven curriculum, and four domains of the program (subject matter knowledge, pedagogical content knowledge, general pedagogical knowledge, and teaching practicum) need to be more strongly connected to secondary school context. Alternative ways to be more coherent and balanced science teacher preparation program were also discussed based on the research.

• Information Systems Review
• /
• v.24 no.4
• /
• pp.23-40
• /
• 2022

Although Support Vector Machine(SVM) has been used in various fields such as bankruptcy prediction model, the hyperplane learned by SVM in class imbalance problem can be severely skewed toward minority class and has a negative impact on performance because the area of majority class is expanded while the area of minority class is invaded. This study proposed optimized uneven margin SVM(OPT-UMSVM) combining threshold moving or post scaling method with UMSVM to cope with the limitation of the traditional even margin SVM(EMSVM) in class imbalance problem. OPT-UMSVM readjusted the skewed hyperplane to the majority class and had better generation ability than EMSVM improving the sensitivity of minority class and calculating the optimized performance. To validate OPT-UMSVM, 10-fold cross validations were performed on five sub-datasets with different imbalance ratio values. Empirical results showed two main findings. First, UMSVM had a weak effect on improving the performance of EMSVM in balanced datasets, but it greatly outperformed EMSVM in severely imbalanced datasets. Second, compared to EMSVM and conventional UMSVM, OPT-UMSVM had better performance in both balanced and imbalanced datasets and showed a significant difference performance especially in severely imbalanced datasets.

• The Journal of Korean society of community based occupational therapy
• /
• v.9 no.2
• /
• pp.43-58
• /
• 2019

Objective : The purpose of this study was to develop an assessment tool to measure Korean occupational balance. Methods : From March 2017 to July 2019, preliminary questionnaire was prepared through analysis of previous research and expert focus meeting, and preliminary questions were selected through the Delphi survey. In order to verify the validity of the items, Rash analysis was conducted to analyze the persons and items fitness, the distribution of item difficulty, separation reliability, and the appropriateness of the rating scale. Results : Among 141 subjects, 9 (6.38%) in time use and 11 (7.80%) in the occupation area were inappropriate subjects. As a result of analyzing the appropriateness of the items except for the inappropriate subjects, the 3 items were judged as ineligible items, but 1 item of the occupation characteristics was finally deleted based on the theoretical and clinical grounds. In the analysis of the scale, 4 points were more appropriate than the 5 point scale, and the separation reliability was .86~.94. Finally, 3 categories (time use, occupation area, occupation characteristics) and 18 items were selected. Conclusion : The occupational balance assessment tool was selected three categories and 18 questions finally, three categories and 18 questions, and was developed on a four-point Likert scale. Further research needs to prove the concurrent validity of the K-OBA and to analyze the factors that influence the occupational balance.

• Communications of Mathematical Education
• /
• v.38 no.2
• /
• pp.167-186
• /
• 2024

Since the 5th mathematics curriculum, the goals of mathematics education have been presented in three categories: cognitive, process, and affective goals. In the 2022 revised mathematics curriculum, the content system was also presented as knowledge-understanding, process-skill, and value-attitude. Therefore, in order to present lesson goals to students, it is necessary to present all three aspects that are the goals of mathematics education. Currently, the lesson titles presented in mathematics textbooks are directly linked to lesson goals and are the first source of information for students during class. Accordingly, this study analyzed how the three categories of lesson titles and content system presented in the 2015 revised 1st and 2nd grade mathematics textbook are connected. As a result, most lesson titles presented two of the three categories, but the reflected elements showed a tendency to focus on the categories of knowledge-understanding and process-skill. Some cases of lesson titles reflected content elements of the value-attitude category, but this showed significant differences depending on the mathematics content area. Considering the goals of mathematics lessons, it will be necessary to look at ways to present lesson titles that reflect the content elements of the value-attitude categories and also explore ways to present them in a balanced way. In particular, considering the fact that students can accurately understand the goals of the knowledge-understanding categories even without presenting them, descriptions that specifically reflect the content elements of the process-skill and value-attitude categories seem necessary. Through this, we attempted to suggest the method of presenting the lesson titles needed when developing the 2022 revised mathematics textbook and help present effective lesson goals using this.