• 품질경영학회지
• /
• 제51권3호
• /
• pp.363-379
• /
• 2023

Purpose: The main objective of this research is to construct an AI-based Composite Supplementary Index (ACSI) model to achieve accurate predictions of the Composite Index of Business Indicators. By incorporating various economic indicators as independent variables, the ACSI model enables the prediction and analysis of both the leading index (CLI) and coincident index (CCI). Methods: This study proposes an AI-based Composite Supplementary Index (ACSI) model that leverages diverse economic indicators as independent variables to forecast leading and coincident economic indicators. To evaluate the model's performance, advanced machine learning techniques including MLP, RNN, LSTM, and GRU were employed. Furthermore, the study explores the potential of employing deep learning models to train the weights associated with the independent variables that constitute the composite supplementary index. Results: The experimental results demonstrate the superior accuracy of the proposed composite supple- mentary index model in predicting leading and coincident economic indicators. Consequently, this model proves to be highly effective in forecasting economic cycles. Conclusion: In conclusion, the developed AI-based Composite Supplementary Index (ACSI) model successfully predicts the Composite Index of Business Indicators. Apart from its utility in management, economics, and investment domains, this model serves as a valuable indicator supporting policy-making and decision-making processes related to the economy.

• 한국초등과학교육학회지:초등과학교육
• /
• 제25권4호
• /
• pp.454-464
• /
• 2006

The purpose of this study was to develop MBL(Microcomputer Based Laboratory) programs for sixth-grade elementary students in science laboratory instructions and to ascertain the effects of this program on academic achievement and science-related affective characteristics. In laboratory instructions, using the MBL was found to be effective in improving academic achievement for elementary students, especially in the domain of knowledge. In addition, it helped students to improve science-related affective characteristics. The experimental group showed higher levels, especially in the domains of cognition and interest. When our findings were analyzed in detail, the sub-domains that showed positive effects included 'cognition of science' in the domain of cognition, and interest toward science', 'interest toward science learning', 'interest toward science related activities', and 'anxiety for science' in the domain of interest. Male students exhibited improvement in the domain of cognition while female students showed improvement in the domain of interest. In conclusion, utilizing MBL programs as an experimental measurement in the real field of elementary science education can be said to be both positive and desirable.

• Journal of Information Science Theory and Practice
• /
• 제3권1호
• /
• pp.6-23
• /
• 2015

This study develops an effective method for sentiment analysis of user-generated content on drug review websites, which has not been investigated extensively compared to other general domains, such as product reviews. A clause-level sentiment analysis algorithm is developed since each sentence can contain multiple clauses discussing multiple aspects of a drug. The method adopts a pure linguistic approach of computing the sentiment orientation (positive, negative, or neutral) of a clause from the prior sentiment scores assigned to words, taking into consideration the grammatical relations and semantic annotation (such as disorder terms) of words in the clause. Experiment results with 2,700 clauses show the effectiveness of the proposed approach, and it performed significantly better than the baseline approaches using a machine learning approach. Various challenging issues were identified and discussed through error analysis. The application of the proposed sentiment analysis approach will be useful not only for patients, but also for drug makers and clinicians to obtain valuable summaries of public opinion. Since sentiment analysis is domain specific, domain knowledge in drug reviews is incorporated into the sentiment analysis algorithm to provide more accurate analysis. In particular, MetaMap is used to map various health and medical terms (such as disease and drug names) to semantic types in the Unified Medical Language System (UMLS) Semantic Network.

• 공학교육연구
• /
• 제9권4호
• /
• pp.63-70
• /
• 2006

여러 분야에서 온라인 교육이 활성화되고 있지만, 온라인 교육의 효율성에 관해서는 많은 사람이 회의적이다. 이러닝에서는 교수자의 역할이 중요한데, "e-moderator" 라는 말이 나올 정도로 학습의 중재자로서의 역할이 강조되고 있다. 그러나 실제적으로 이러한 역할은 이러닝에서 교수자와 관리자간에 서로 책임을 전가하는 경향이 있다. 또 다른 측면에서는 오픈소스의 활용이 활성화되고 결과물을 활용하여 무료로 이러닝 환경을 구축할 수 있는데도 불구하고 국내에서의 활용 율은 상당히 낮은 실정이다. 본 논문에서는 어떻게 이러한 오픈소스 결과물을 가지고 온라인 환경을 구축하고 "e-moderator"의 역할에 충실하면서 블렌디드 러닝까지 확장하여 활용할 수 있는지를 교육 현장에서의 구현 사례를 중심으로 기술하고자 한다. Moodle을 LMS(Learning Management System)으로 사용하였으며 2006년도 2학기에 공주대학교에서 자바와 전기기기에 적용하여 수업을 진행한 내용을 반영하였다.

• 영재교육연구
• /
• 제24권5호
• /
• pp.851-876
• /
• 2014

이 논문은 학습장애영재 모델(Song & Porath, 2011)의 실증적 검증 차원으로, 읽기, 쓰기, 수학에서 학습장애가 없는 영재와 학습장애영재가 보이는 영역적 사고를 조사하였다. 두 그룹의 영재들로부터 인터뷰 자료를 수집하였고 분야적 사고 측면에서 분석하였다. 그 결과 영재는 읽기, 쓰기, 수학에서 비교적 균형 잡힌 영역적 사고를 나타낸 반면 학습장애영재는 특정 분야에서 약한 영역적 사고를 보였다. 뿐만 아니라 오직 학습장애영재만이 읽기, 쓰기, 수학의 각각의 분야 내에서 서로 상반된 태도를 보였는데 그들은 같은 분야 내에서 긍정과 부정의 감정을 동시에 드러냈다. 이 논문은 학습장애영재 모델에서 제시하고 있는 인지 메커니즘을 통해 두 영재집단의 차이점들을 설명하고 영재 선발과 교육에 대한 새로운 접근 방법을 제안하고 있다.

• 한국콘텐츠학회논문지
• /
• 제15권8호
• /
• pp.625-641
• /
• 2015

감성이 기억 및 학습과 밀접하게 관련되어 있다는 최근의 연구결과와 학습의 정의적 측면에 관한 교육계의 높은 관심에도 불구하고 학습자의 감성에 기반한 교수방법이나 학습환경에 대한 체계적인 연구가 부족하다. 면대면 강의와 온라인 학습에서 감성의 역할을 이해하고 긍정적 감성을 촉진하기 위한 노력이 점차 증가하고 있으나, 학습자의 감성을 타당하고 신뢰롭게 측정하는 것은 여전히 도전적인 과제로 남아있다. 감성을 고려한 교육을 실천하기 위해서는 학습자의 기억에 의존한 자기보고식 감성측정도구의 제한점을 보완하는 것이 필요하다. 본 연구는 최근 교육학과 인접학문 영역에서 사용되고 있는 감성측정도구를 자기보고, 생리적 신호, 행동적 반응의 측면에서 조사하고 그 도구들이 교수학습 상황에서 어떻게 활용될 수 있는지를 논의하였다. 특히, 실시간으로 학습자의 감성을 편리하게 수집하여 분석할 수 있는 첨단 테크놀로지의 교육적 활용방안을 조사하였다. 이 연구는 향후 실제적인 교수학습 상황에서 감성의 역할을 규명하고 학습자의 감성 변화를 고려한 적응적 학습환경을 설계하는 데 크게 기여할 것이다.

• 한국정보과학회논문지:소프트웨어및응용
• /
• 제37권2호
• /
• pp.120-128
• /
• 2010

하이퍼네트워크는 하이퍼그래프의 일반화된 모델로 학습과정에 있어 진화적 개념을 도입한 확률 그래프 기반의 기계학습 알고리즘으로서 최근 들어 여러 다양한 분야에 응용되고 있다. 그러나 하이퍼네트워크 모델은 데이터와 모델을 구성하는 하이퍼에지 간의 동등비교를 기반으로 하는 학습과정의 특성상 데이터를 구성하는 인자들이 범주형인 경우에만 학습 및 모델링이 가능하고 실수 값으로 표현된 데이터를 학습하기 위해서는 이산화 등의 전처리가 선행되어야 한다는 한계점이 있다. 하지만 데이터 전처리에 있어 이산화 하는 과정은 필연적으로 정보손실이 발생할 수밖에 없기 때문에 이는 분류 예측 모델의 성능 저하를 유발하는 원인이 될 수 있다. 이러한 기존 하이퍼네트워크 모델의 한계점을 극복하기 위해 본 연구에서는 별도의 데이터 전처리 과정을 거치지 않고 실수 인자로 구성된 데이터의 패턴 학습이 가능한 개선된 하이퍼네트워크 모델을 제안한다. 여러 실험 결과를 통해 제안한 하이퍼네트워크 모델은 기존 하이퍼네트워크 모델에 비해 실수형 데이터에 대한 학습 및 분류 결과 성능이 향상되었을 뿐 아니라, 다른 여러기계학습 방법들에 비해서도 경쟁력 있는 성능이 나타남을 확인하였다.

• 지역사회간호학회지
• /
• 제13권4호
• /
• pp.595-607
• /
• 2002

The objectives of this study were to identify the phenomena of school health nursing at schools in Korea and to contribute to building a school health domain of International Classification for Nursing Practice. A retrospective method was used in this study to develop ICNP during the period from July to October 200l. The procedure of the study involved choosing nursing phenomena using preliminary terms from the reports on the field of school health nursing practice documented by nursing students in 10 different nursing colleges. The detail procedures of the study were as follows. 1) Choosing nursing phenomena by using preliminary terms 2) Choosing the characteristics of school health nursing practice from the selected nursing phenomena 3) In order to make a consensus regarding the appropriate characteristics of phenomena. 15 study group members re-categorized the nursing phenomena through 5 times of cyber meetings and 3 times of formal meetings. 4) To verify each characteristic, 5 community nursing faculties and 25 school health nurses participated in the procedure to give scores on nursing characteristics. 5) Classification of the definite nursing phenomena and characteristics. Following the 5 step procedures, school health nursing phenomena were categorized into human and environmental domains. Human domains were classified into human behavioral and functional domains. Environmental domains were classified into physical and psychosocial domains. The essential characteristics of each phenomena were selected when it obtains the mean score of 3.0 or over at the related characteristics. The human behavioral domain consisted of 7 phenomena including risk for spinal disorder, inadequate dietary habit, inadequate weight control, smoking and substance abuse, inadequate stress management, inadequate sex related coping strategies and inadequate accident management. The human functional domain consisted of 6 phenomena including inadequate eye care and visual management, risk for respiratory disorder, inadequate dental health care, inappropriate infectious disease control, risk for gastrointestinal disorder, and lack of sexual identity. The physical environmental domain consisted of 6 phenomena including risk for incident at inside classroom, risk for incident at outside classroom, risk for incident around school, risk for exposure to hazardous facilities around school. inadequate garbage and disposal management, and inadequate physical environment for learning. The psychosocial domain included impaired social interaction at school. Each phenomenon was composed of 2 to 8 characteristics and all phenomena will include a total number of 85 characteristics. The phenomena of school health nursing in Korea partially confirmed school health architecture of ICNP. Further study on verification of school health nursing phenomena in Korea needs to be done to support the findings of this study through review of literature on nursing classifications or field studies.

• Journal of the Korean Academy of Child and Adolescent Psychiatry
• /
• 제28권4호
• /
• pp.235-243
• /
• 2017

Objectives: This study aimed to evaluate the mental health status of the children of psychiatric patients in order to plan for the resources that may be necessary to help these children achieve their full potential. Methods: Forty-eight children (age 9-18) whose parents were registered in 5 community mental health centers located in Seoul were recruited. Tests assessing 3 psychological domains were conducted: 1) cognition: Korean version of Learning Disability Evaluation Scale, Comprehensive Attention Test, 2) parent reported emotion and behavior: Korean Child Behavior Checklist, Korean attention-deficit hyperactivity disorder Rating Scale, and 3) self-reported emotion and behavior: Korean Beck's Depression Inventory-II/Children's Depression Inventory-II, Korean Youth Self Report). We defined the children as having a high risk of developing mental health problems if their test scores were over the cut-off levels in 2 or more of the 3 domains assessed. Results: Twelve (25%) children were classified as having a high risk of developing mental health issues. 20 (41.6%) children scored above the cut-off in only one of the domains. Conclusion: Our results suggest that the children of psychiatric patients might be vulnerable to mental illness and need early prevention or interven-tions for the sake of their mental health.

• 아동학회지
• /
• 제14권2호
• /
• pp.79-94
• /
• 1993

The purpose of this study was (1) to investigate whether linguistic contrast helps children map a new word into a specific semantic domain when a new word is introduced, (2) to examine the existence of a hierarchy of domains into which children will place a new word, (3) to examine whether children's existing lexicons affect how children map a new word. A total of 320 children from 3 to 6 years of age were drawn from Pusan, Korea. The children were divided into one of four age groups. There were 80 children in each age group. In each group, children were randomly assigned to one of four groups; the linguistic contrast group exposed to color, the linguistic contrast group exposed to shape, a label group and control group. All of the children were tested for production and comprehension of the new word. The results of this study were as follows; (1) The linguistic contrast helped children learn the meanings of a new word. Especially, children age 4 or more showed a significant effect for linguistic contrast; however, it was not sufficient to teach 3-year-old the correct, referent of a term. (2) There was a hierarchy of domains into which children mapped a new word. There was no significant effect for domains into which 3-year-old children mapped the new word, but from 4 years of age children showed a preference for assuming a new word refered to an object's shape rather than its color. (3) Children's existing lexicon had no effect, on how children comprehend a new word.