• KIPS Transactions on Software and Data Engineering
• /
• v.10 no.9
• /
• pp.367-374
• /
• 2021

Stock price prediction is a subject of research in various fields such as economy, statistics, computer engineering, etc. In recent years, researches on predicting the movement of stock prices by learning artificial intelligence models from various indicators such as basic indicators and technical indicators have become active. This study proposes a deep learning model that predicts the ups and downs of KOSPI from overseas indices such as S&P500, past KOSPI indices, and trading trends by KOSPI investors. The proposed model extracts a latent variable using a stacked auto-encoder to predict stock price fluctuations, and predicts the fluctuation of the closing price compared to the market price of the day by learning an LSTM suitable for learning time series data from the extracted latent variable to decide to buy or sell based on the value. As a result of comparing the returns and prediction accuracy of the proposed model and the comparative models, the proposed model showed better performance than the comparative models.

• Communications for Statistical Applications and Methods
• /
• v.24 no.2
• /
• 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
• /
• v.7 no.10
• /
• 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.

• Korean Journal of Childcare and Education
• /
• v.12 no.6
• /
• 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.

• Korean Journal of Organic Agriculture
• /
• v.27 no.3
• /
• 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.

• Journal of Fisheries and Marine Sciences Education
• /
• v.24 no.5
• /
• 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
• /
• v.10 no.2
• /
• 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.

• Journal of the Korea Computer Graphics Society
• /
• v.27 no.5
• /
• pp.33-43
• /
• 2021

In this paper, we propose a framework that transfers the information of style motions to content motions based on a variational autoencoder network combined with a style encoding in the latent space. Because we transfer a style to a content motion that is sampled from a variational autoencoder, we can increase the diversity of existing motion data. In addition, we can improve the unnatural motions caused by decoding a new latent variable from style transfer. That improvement was achieved by additionally using the velocity information of motions when generating next frames.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2024.05a
• /
• pp.611-614
• /
• 2024

최근 많은 분야에서 인공지능을 사용한 산업이 각광을 받고 있고 그중 챗-GPT 로 인하여 챗봇에 관한 관심도가 높아져 관련 연구가 많이 진행되고 있다. 특히 질문에 대한 답변을 생성해주는 분야에 대한 연구가 많이 이루어지고 있는데, 질문-답변의 데이터 셋에 대한 학습 방식보다는 질문-답변-배경지식으로 이루어진 데이터 셋에 대한 학습 방식이 많이 연구가 되고 있다. 그러다 보니 배경지식을 어떤 방식으로 모델에게 이해를 해줄 지가 모델 성능에 큰 부분 차지한다. 그리고 최근 연구에 따르면 이러한 배경지식 정보를 이해시키기 위해 잠재 변수 모델링 기법을 활용하는 것이 높은 성능을 갖는다고 하고 트랜스포머 기반 모델 중 생성 문제에서 강점을 보이는 BART(Bidirectional Auto-Regressive Transformer)[1]도 주로 활용된다고 한다. 본 논문에서는 BART 모델에 잠재 변수 모델링 기법 중 잠재 변수를 어텐션에 곱하는 방식을 이용한 모델을 통해 답변 생성 문제에 관한 해결법을 제시하고 그에 대한 결과로 배경지식 정보를 담은 답변을 보인다. 생성된 답변에 대한 평가는 기존에 사용되는 BLEU 방식과 배경지식을 고려한 방식의 BLEU 로 평가한다.

• KIPS Transactions on Software and Data Engineering
• /
• v.11 no.8
• /
• pp.331-338
• /
• 2022

Successor representation (SR) is a model of human reinforcement learning (RL) mimicking the underlying mechanism of hippocampal cells constructing cognitive maps. SR utilizes these learned features to adaptively respond to the frequent reward changes. In this paper, we evaluated the performance of SR under the context where changes in latent variables of environments trigger the reward structure changes. For a benchmark test, we adopted SR-Dyna, an integration of SR into goal-driven Dyna RL algorithm in the 2-stage Markov Decision Task (MDT) in which we can intentionally manipulate the latent variables - state transition uncertainty and goal-condition. To precisely investigate the characteristics of SR, we conducted the experiments while controlling each latent variable that affects the changes in reward structure. Evaluation results showed that SR-Dyna could learn to respond to the reward changes in relation to the changes in latent variables, but could not learn rapidly in that situation. This brings about the necessity to build more robust RL models that can rapidly learn to respond to the frequent changes in the environment in which latent variables and reward structure change at the same time.