• Journal of Korea Game Society
• /
• v.14 no.4
• /
• pp.37-44
• /
• 2014

In this paper, we propose a NPC decision making model based on Prospect Theory which tries to model real-life choice, rather than optimal decision. For this purpose, we analyse the problems of reference point setting, diminishing sensitivity and loss aversion which are known as limitations of the utility theory and then apply these characteristics into the decision making in game. Dynamic Terrain Analysis is utilized to evaluate the proposed model and experimental result shows the method have effects on inducing diverse personality and emergent behavior on NPC.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2019.05a
• /
• pp.539-541
• /
• 2019

오프라인 소비자의 의사결정은 크게 라이프스타일, 동기, 개성, 학습 등 개인적인 영향요인과 문화, 기후, 가족 등 기타 상황적 요인을 포함하는 환경적 영향요인에 의해 결정된다. 이러한 요인들을 입력 값으로 하는 다양한 딥러닝 모델을 이용한 소비예측 연구들이 진행되고 있다. 딥러닝을 이용한 예측모델을 사용하기 위해서는 먼저 요인들이 의사를 결정하는데 있어 얼마나 상관관계가 있는지 파악하는 작업이 중요하다. 본 논문에서는 이를 위해 다양한 상관관계 분석모델을 이용해 소비 의사결정 요소 중 기후, 문화와 같은 상황적 요인과 소비와의 상관관계를 도출하고, 기후, 문화를 대변하는 미세먼지 데이터와, SNS 버즈량 데이터와 소비데이터를 학습하는 소비예측 LSTM모델을 제안하고자 한다.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2007.05a
• /
• pp.645-648
• /
• 2007

IT 에 대한 비즈니스 의존성이 증가하면서, 안정된 IT 서비스의 제공과 비용 효과적인 운영의 중요성이 강조되고 있다. ITIL 에서는 효율적이고 신속한 변경 처리를 위해 Service Support 영역에서 변경 관리 프로세스를 제시하고 있다. 하지만 고비용을 요하는 CAB 의 소집 여부 등 의사 결정이 변경 관리자의 자의적인 판단에 의존함으로써, 다른 비즈니스 및 안정된 IT 서비스 제공의 위험요소로 작용하고 있다. 본 논문에서는 이러한 문제점을 해결하기 위하여 요청된 변경 사안이 신중한 검토가 필요한 지 여부를 객관적으로 판단할 수 있도록, 판별분석기법을 적용한 변경 모델 결정 방법을 제안한다. 제안된 모델의 유효성을 검증하기 위해, 실제 운영에 적용된 변경 관리 모델과 제안된 모델을 이용했을 때의 결과를 비교하고 그 결과를 제시하였다. 제안된 방법은 동일한 사안에 대하여 일관성 있는 결정을 도출할 수 있어 프로세스 품질개선에 기여할 수 있으며, 궁극적으로 안정된 IT 서비스 제공에 기여하여 기업성과를 개선할 수 있을 것이다.

• The Journal of the Korea Contents Association
• /
• v.10 no.3
• /
• pp.21-31
• /
• 2010

In the architectural design technologies being changed recently, there is the study to develop the way that will enable the designers to get access logically to the processes of deciding the values of design factors which depend on the experience of the designers. This study, which is one part of those studies, has been carried out to develop the model that can decide the values logically for the design factors having the character that the design values are changed by the time variation out of design factors involved in the building energy saving design. As a result, the structure of the decision model which can decide the design values logically from the computer simulation that solve the problem by interpreting the real world as the probability distribution, has been established through this study. For the application and verification of these decision model, the case study has been carried out for the outdoor climate factors that stand for the design factors having the time variation.

• Journal of the Korean Society of Child Welfare
• /
• no.27
• /
• pp.7-35
• /
• 2008

The model of family decision-making in child protection has been widely discussed and adopted in many countries. The purpose of this study was to introduce the model and, then, investigate whether this process is applicable in child care and protection services in Korea. The main goal in the study has been to explore the philosophical and practical foundations of the family involvement approach in decision-making and describe the international applications of the model. Family group conferencing, originally developed and enacted in New Zealand, has been critically examined. The potential contributions of the study may include seeking a more effective intervention for child protection through determining whether the model is appropriate or desirable in issues of philosophy, practice and policy within the Korean culture.

• Journal of Digital Convergence
• /
• v.11 no.9
• /
• pp.153-158
• /
• 2013

Target learning model is not recognized in this category or not classified clearly failed to determine if the vocabulary recognition is reduced. Form of classification learning model is changed or a new learning model is added to the recognition decision tree structure of the model should be changed to a structural problem. In order to solve these problems, a decision tree learning model for classification learning algorithm is proposed. Phonological phenomenon reflected sound enough to configure the database to ensure learning a decision tree learning model for classifying method was used. In this study, the indoor environment-dependent recognition and vocabulary words for the experimental results independent recognition vocabulary of the indoor environment-dependent recognition performance of 98.3% in the experiment showed, vocabulary independent recognition performance of 98.4% in the experiment shown.

• The Journal of the Korea Contents Association
• /
• v.21 no.12
• /
• pp.13-22
• /
• 2021

The clinical decision support system uses accumulated medical data to apply an AI model learned by machine learning to patient diagnosis and treatment prediction. However, the existing black box-based AI application does not provide a valid reason for the result predicted by the system, so there is a limitation in that it lacks explanation. To compensate for these problems, this paper proposes a system model that applies XAI that can be explained in the development stage of the clinical decision support system. The proposed model can supplement the limitations of the black box by additionally applying a specific XAI technology that can be explained to the existing AI model. To show the application of the proposed model, we present an example of XAI application using LIME and SHAP. Through testing, it is possible to explain how data affects the prediction results of the model from various perspectives. The proposed model has the advantage of increasing the user's trust by presenting a specific reason to the user. In addition, it is expected that the active use of XAI will overcome the limitations of the existing clinical decision support system and enable better diagnosis and decision support.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.26 no.5
• /
• pp.662-667
• /
• 2022

Semantic role labeling task(SRL) is to extract predicate and arguments such as agent, patient, place, time. In the previously SRL task studies, a pipeline method extracting linguistic features of sentence has been proposed, but in this method, errors of each extraction work in the pipeline affect semantic role labeling performance. Therefore, methods using End-to-End neural network model have recently been proposed. In this paper, we propose a neural network model using the Biaffine Average Attention model for SRL task. The proposed model consists of a structure that can focus on the entire sentence information regardless of the distance between the predicate in the sentence and the arguments, instead of LSTM model that uses the surrounding information for prediction of a specific token proposed in the previous studies. For evaluation, we used F1 scores to compare two models based BERT model that proposed in existing studies using F1 scores, and found that 76.21% performance was higher than comparison models.

• Korean Journal of Optics and Photonics
• /
• v.33 no.6
• /
• pp.324-330
• /
• 2022

We measured the Dill and Mack model parameters that determine the exposure and development characteristics of photoresists, respectively. First, photoresist samples were prepared while altering the exposure dose, and changes in transmittance were measured. Analyzing these results, the Dill model parameters A, B, and C were determined. In particular, the exact solution of the Dill model equation was used to determine the C parameter. In addition, changes in thickness were measured as a function of development time for different exposure doses, and the Mack model parameters R_min, R_max, a, and n were determined using the results. We also determined parameter values for the reduced Mack model that uses only three parameters, R_min, R_max, and n. The root mean square error between the model predictions and the measured values for the photoresist thickness was found to increase slightly compared to the case using the original Mack model with four parameters.

• Journal of the Korea Convergence Society
• /
• v.10 no.11
• /
• pp.117-124
• /
• 2019

Recently, medical IT solutions are being provided on a distributed environment basis. In Korea, the necessity of developing a clinical decision support system that can share medical information in a distributed environment has been recognized and studied. The existing clinical decision support system is being built using only medical information of its own within the hospital. This makes it difficult for existing systems to achieve good results in terms of efficiency and accuracy of decision support. In order to solve these limitations, this paper proposes a design and implementation method of clinical decision support system based on common data model in medical field. To explain the application process of the proposed model, we describe the development scenario of the clinical decision support system for the diagnosis of colorectal cancer. We also propose the essential requirements for the development of successful clinical decision support systems. Through this, it is expected that it will be possible to develop clinical decision support system that can be used in various hospitals and improve the efficiency and accuracy of the system.