• 정보처리학회논문지:소프트웨어 및 데이터공학
• /
• 제10권9호
• /
• pp.367-374
• /
• 2021

주가 예측은 경제, 통계, 컴퓨터 공학 등 여러 분야에서 연구되는 주제이며, 특히 최근에는 기본적 지표나 기술적 지표 등 다양한 지표로부터 인공지능 모델을 학습하여 주가의 변동을 예측하는 연구들이 활발해 지고 있다. 본 연구에서는 S&P500 등의 해외지수, 과거 KOSPI 지수, 그리고 KOSPI 투자자별 매매 동향으로부터 KOSPI의 등락을 예측하는 딥러닝 모델을 제안한다. 제안 모델은 주가 등락 예측을 위하여 비지도 학습 방법인 적층 오토인코더를 이용하여 잠재변수를 추출하고, 추출된 잠재변수로부터 시계열 데이터 학습에 적합한 LSTM 모델로 학습하여 당일 시가 대비 종가의 등락을 예측하며, 예측된 값을 기반으로 매수 또는 매도를 결정한다. 본 연구에서 제안하는 모델과 비교 모델들의 수익률 및 예측 정확도를 비교한 결과 제안 모델이 비교 모델들 보다 우수한 성능을 보였다.

• Communications for Statistical Applications and Methods
• /
• 제24권2호
• /
• pp.143-154
• /
• 2017

A variable selection method based on probabilistic principal component analysis (PCA) using penalized likelihood method is proposed. The proposed method is a two-step variable reduction method. The first step is based on the probabilistic principal component idea to identify principle components. The penalty function is used to identify important variables in each component. We then build a model on the original data space instead of building on the rotated data space through latent variables (principal components) because the proposed method achieves the goal of dimension reduction through identifying important observed variables. Consequently, the proposed method is of more practical use. The proposed estimators perform as the oracle procedure and are root-n consistent with a proper choice of regularization parameters. The proposed method can be successfully applied to high-dimensional PCA problems with a relatively large portion of irrelevant variables included in the data set. It is straightforward to extend our likelihood method in handling problems with missing observations using EM algorithms. Further, it could be effectively applied in cases where some data vectors exhibit one or more missing values at random.

• The Journal of Asian Finance, Economics and Business
• /
• 제7권10호
• /
• pp.999-1006
• /
• 2020

This study provides an understanding of the role of job satisfaction as a mediator of compensation and workplace environments for the organizational commitment of employees in the public sector. This study used a structural model using path analysis. The population and sample in this study were all employees at the Population and Civil Registry Office of one of the districts in Indonesia. The sampling technique used was total sampling, due to the considerably smaller amount of the sample size. This study found that compensation and workplace environment could explain job satisfaction variables with a 93.8% confidence level and simultaneously compensation, workplace environment, and job satisfaction that could explain organizational commitment with a variable of 97.4%. This findings also shows that the manifest bonus variable on the latent compensation variable is one of the main indicators that needs to improve to increase job satisfaction and organizational commitment. One of the important things which needs to be done is to increase compensation. The first thing which needs to be done is to increase the bonus. Furthermore, to improve the quality of the workplace environment, facilities, and infrastructure such as stable internet connections, computer specifications are the important criteria that must be met.

• 한국보육지원학회지
• /
• 제12권6호
• /
• pp.79-102
• /
• 2016

The purpose of this study was to identify school adjustment groups by applying a Latent Profile Analysis(LPA) and to investigate the effects of children's emotional problems and study habits on determining the membership of these groups. LPA and multiple logistic regression were conducted using the data of 2,200 third-graders from the Korean Children and Youth Panel Study. The results are listed as follows. First, four school adjustment groups were identified: adjustment, approach to adjustment, maladjustment risk, and maladjustment group. Second, accomplishment value and mastery goal orientation were relatively strong predictors of membership of the school adjustment groups. Time management was also a significant variable that predicted the membership of maladjustment or the maladjustment-risk group. Third, attention problems and depression were the most consistent predictors of membership of maladjustment or the maladjustment-risk group. Physical symptoms and social withdrawal were also significant. Based on the results, implications for intervention to promote early school adjustment were discussed.

• 한국유기농업학회지
• /
• 제27권3호
• /
• pp.247-269
• /
• 2019

Although food related lifestyle has been widely discussed over the last ten years, the majority of research on food related lifestyle has been only conducted in terms of a variable-centered approach. But, recently there is a growing body of research on food related lifestyle profiles over the last three years from the view of a person-centered approach. This study conducted both a cluster analysis and a latent profile analysis (LPA) to identify the patterns of potential food related lifestyle customer profiles based on the five components on the sample of customer, who bought organic products (n=509). The results of each statistical analysis showed both quantitatively and qualitatively different types of food related lifestyle customer profiles even though there were similar types of profiles identified in common between these two analyses. These various profiles were then compared with customer's level of buying behaviors (e.g., buying attitude and buying intentions). Results showed that food related lifestyle profiles with respect to the high level of interesting in dietary life in terms of health and safety are associated with the higher level of buying behaviors. Based on the results, implications for food related lifestyle literature, practices and future research are discussed.

• 수산해양교육연구
• /
• 제24권5호
• /
• pp.616-626
• /
• 2012

The purpose of this study is to verify career maturity, achievement goal, learning attitude and academic achievement relation with subjects-related career education of middle school students. To achieve these aims, this study used SELS(Seoul education longitudinal study) of Seoul Education Research & Information Institute. Also, analysis as well as descriptive statistics calculation on average, deviation, skewness and kurtosis of variable factor and calculated characteristic item and degree of reliability(Cronbach ${\alpha}$). For goodness of fit test, this study used TLI(Tucker-Lewis index) and RMSEA(Root mean square error of approximation). To achieve the ultimate objects, this study used LMA(latent mean analysis) for analysis of difference career maturity, achievement goal, learning attitude and academic achievement relation with subjects-related career education in middle school students. The results are as follows. First, experience relation with subjects-related career education were influenced on career maturity with career cognition. Second, experience relation with subjects-related career education were influenced on achievement goal, learning attitude, and larger than career maturity and academic achievement. Third, experience relation with subjects-related career education were influenced on middle school students more than inexperienced relation with subjects-related career education.

• Asian Journal for Public Opinion Research
• /
• 제10권2호
• /
• pp.123-146
• /
• 2022

This study aims to identify the effect of the relationship between human resources management (HRM) and total quality management (TQM) on improving employee performance. Several previous qualitative studies have stated that TQM and HRM are separate methods. This article describes a new method using a quantitative approach. This research is needed to fill the gap in the literature by empirically analyzing the relationship between HRM, TQM practices, and organizational performance. Data was collected quantitatively from 100 employees in Indonesia through questionnaires and online survey methods. The data collected were analyzed using structural equation modeling (SEM) with the Lisrel 8.5 system. TQM-oriented HRM is operationalized as a second-order latent variable measured by four factors (training, empowerment, teamwork, compensation). The findings support the validity of the TQM-oriented HRM model as a hierarchical, second-order latent construct and show a strong relationship with employee performance. The results of this study are different from previous studies, which showed that TQM and HRM are separate methods. The results of our research provide an academic and practical overview that TQM-oriented HRM can be used to help organizations build platforms for human resources policies aimed at improving employee performance.

• 한국컴퓨터그래픽스학회논문지
• /
• 제27권5호
• /
• pp.33-43
• /
• 2021

본 논문에서는 변형 자동 인코더 네트워크(variational autoencoder network)의 잠재 공간 내에 스타일 자동 인코더 네트워크를 적용하여 컨텐츠 캐릭터의 모션에 스타일 캐릭터 모션의 스타일 정보를 이전하는 프레임워크를 제안한다. 이 프레임워크를 사용하면 기존의 변형 자동 인코더를 통해 얻은 모션의 다양성을 스타일 캐릭터 모션의 스타일 정보를 이전하여 증가시킬 수 있다. 또한 입력 데이터 및 출력 데이터에 모션의 속도 정보를 포함시켜 이전 프레임의 모션에 속도를 적분하여 모션을 계산함으로써, 변형 자동 인코더로 인한 샘플링과 잠재 공간 내에서 스타일 정보가 이전된 새로운 잠재 변수의 디코더 네트워크를 통한 확장으로 발생할 수 있는 부자연스러운 동작을 개선할 수 있다.

• 정보처리학회논문지:소프트웨어 및 데이터공학
• /
• 제11권8호
• /
• pp.331-338
• /
• 2022

차기 상태 천이 표상(Successor representation, SR) 기반 강화학습 알고리즘은 두뇌에서 발현되는 신경과학적 기전을 바탕으로 발전해온 강화학습 모델이다. 해마에서 형성되는 인지맵 기반의 환경 구조 정보를 활용하여, 변화하는 환경에서도 빠르고 유연하게 학습하고 의사결정 가능한 자연 지능 모사형 강화학습 방법으로, 불확실한 보상 구조 변화에 대해 빠르게 학습하고 적응하는 강인한 성능을 보이는 것으로 잘 알려져 있다. 본 논문에서는 표면적인 보상 구조가 변화하는 환경뿐만 아니라, 상태 천이 확률과 같은 환경 구조 내 잠재 변수가 보상 구조 변화를 유발하는 상황에서도 SR-기반 강화학습 알고리즘이 강인하게 반응하고 학습할 수 있는지 확인하고자 한다. 성능 확인을 위해, 상태 천이에 대한 불확실성과 이로 인한 보상 구조 변화가 동시에 나타나는 2단계 마르코프 의사결정 환경에서, 목적 기반 강화학습 알고리즘에 SR을 융합한 SR-다이나 강화학습 에이전트 시뮬레이션을 수행하였다. 더불어, SR의 특성을 보다 잘 관찰하기 위해 환경을 변화시키는 잠재 변수들을 순차적으로 제어하면서 기존의 환경과 비교하여 추가적인 실험을 실시하였다. 실험 결과, SR-다이나는 환경 내 상태 천이 확률 변화에 따른 보상 변화를 제한적으로 학습하는 행동을 보였다. 다만 기존 환경에서의 실험 결과와 비교했을 때, SR-다이나는 잠재 변수 변화로 인한 보상 구조 변화를 빠르게 학습하지는 못하는 것으로 확인 되었다. 본 결과를 통해 환경 구조가 빠르게 변화하는 환경에서도 강인하게 동작할 수 있는 SR-기반 강화학습 에이전트 설계를 기대한다.

• 한국사회복지학
• /
• 제64권1호
• /
• pp.101-124
• /
• 2012

본 연구에서는 중노년층의 본인의 노화에 대한 태도에 관한 종단적 변화와 이에 영향을 미치는 요인을 알아보기 위해 "고령화와 한국노인의 삶의 질에 관한 연구"의 3개년도 자료를 잠재성장모델로 분석하였다. 분석결과, 중노년층의 본인의 노화에 대한 태도는 시간이 지남에 따라 부정적으로 변화하는 것으로 나타났다. 또한 고연령집단일수록, 무배우일수록, 농촌지역 거주자일수록, 교육수준이 낮을수록, 사회활동의 수가 적을수록, 주관적 경제상태에 여유가 없을수록, 주관적 건강상태가 나쁠수록 중노년층의 본인의 노화에 대한 초기 태도는 부정적인 것으로 나타났다. 중노년층의 본인의 노화에 대한 태도의 종단적 변화는 거주지역, 교육수학기간, 주관적 경제상태, 주관적 건강상태에 따라 다른 것으로 나타났다. 연구결과를 토대로 중노년층이 본인의 노화에 대한 부정적인 태도를 줄이기 위해 필요한 정책적, 실천적 시사점에 대해 논의하였다.