• 한국게임학회 논문지
• /
• 제16권2호
• /
• pp.27-40
• /
• 2016

스텔스 게임에서 플레이어의 행동을 예측하는 것은 게임 디자인에 있어서 핵심적인 역할을 한다. 하지만, 플레이어와 게임 환경 간의 상호작용이 실시간으로 일어난다는 점에서 이러한 예측 프로세스를 자동화하는 것은 어려운 문제이다. 본 논문은 동적 환경에서의 스텔스 움직임을 예측하기 위한 강화학습 방법을 소개하며, 이를 위해 Q-learning과 인공신경망이 통합된 형태의 모델이 액션 시뮬레이션을 위한 분류기로 활용된다. 실험 결과들은 이러한 시뮬레이션 에이전트가 동적으로 변하는 주변 상황에 민감하게 반응함을 보여주며, 따라서 게임 레벨 디자이너가 다양한 게임 요소들을 결정하는데 유용함을 보여준다.

• 정보기술응용연구
• /
• 제1권
• /
• pp.173-211
• /
• 1999

The task of classification permeates all walks of life, from business and economics to science and public policy. In this context, nonlinear techniques from artificial intelligence have often proven to be more effective than the methods of classical statistics. The objective of knowledge discovery and data mining is to support decision making through the effective use of information. The automated approach to knowledge discovery is especially useful when dealing with large data sets or complex relationships. For many applications, automated software may find subtle patterns which escape the notice of manual analysis, or whose complexity exceeds the cognitive capabilities of humans. This paper explores the utility of a collaborative learning approach involving integrated models in the preprocessing and postprocessing stages. For instance, a genetic algorithm effects feature-weight optimization in a preprocessing module. Moreover, an inductive tree, artificial neural network (ANN), and k-nearest neighbor (kNN) techniques serve as postprocessing modules. More specifically, the postprocessors act as second0order classifiers which determine the best first-order classifier on a case-by-case basis. In addition to the second-order models, a voting scheme is investigated as a simple, but efficient, postprocessing model. The first-order models consist of statistical and machine learning models such as logistic regression (logit), multivariate discriminant analysis (MDA), ANN, and kNN. The genetic algorithm, inductive decision tree, and voting scheme act as kernel modules for collaborative learning. These ideas are explored against the background of a practical application relating to financial fraud management which exemplifies a binary classification problem.

• Journal of Nutrition and Health
• /
• 제10권2호
• /
• pp.5-11
• /
• 1977

The mature human braun contains over 10 billion nerve cells (neurons), whose functions are directly related to the acquisition, transfer, processing, analysis, and utilization of all the information. There are also billions of glial cells, which serve primarily to support and to maintain the integrity of the neuron network and to synthesize an essential fatty strucfure, myelin. In the human brain DNA content therefore cell number rises rapidly until birth and then more slowly until $5{\sim}6$ months of age, when it reaches a maximum. While glial cells may be replaced, the more important nerve cell neurons can never be replaced once they are formed. Humans are born with their full complement of neurons and every neuron is as old as each individual. Thus prenatal malnutrition can seriously affect a person's entire life by severely inhibiting the production of neurons before birth.It has been demonstrated that in humans severe malnutrition during the fetal period and in infancy is associated with intellectual impairment. Severely malnourished children have brains smaller than average size and have been found to have $15{\sim}20%$ fewer brain cells than wellnourished childen. There is growing body of literature pointing to malnutrition as a cause of abnormal behavior as evidence that suggests these abnormalities may produce chromosomal damage that may persist forever. Although cognitive development in children is affected by multiple environmental factors, nutrition certainly deaerves more attention than it has received.

• 디자인학연구
• /
• 제16권2호
• /
• pp.35-48
• /
• 2003

Home networking technology connects individual home appliances through a wired or wireless network and makes possible new functions that were impossible when they were used independently. However, the new functions must not simply be confusing arrays of functions that are possible to implement, but those absolutely necessary to the users. To develop innovative information appliances with such functions, scenarios were used and played guiding roles in suggesting new product ideas, making design mockups, and producing videos to show natural situations where the products would be used in home of the future. In the phase of suggesting new product ideas, user action scenarios in the home, generated by a team consisting of experts in the fields of cognitive engineering, user interface, computer science, cultural anthropology, interaction design, and product design, helped the team identify user needs and design factors necessary to fulfill those needs and suggest new product ideas from the design factors. In the phase of making design mockups, the procedures of using the products were described in the scenario format. Based on the scenarios the s쇼les and the user interfaces of them were designed. In the phase of producing videos, the interactions between the user and the product were embodied in the course of professional writers'arranging the scenarios of using the products for the scripts of the videos. Videos were produced to show the actual situations where the design mockups would be used in home of the future and the dynamic aspects of interaction design.

• 한국항행학회논문지
• /
• 제13권5호
• /
• pp.705-713
• /
• 2009

본 논문에서는 휴머노이드 로봇의 코바 기반 비주얼 서보잉 시스템에 대해 논하고자한다. 네트워크로 연결된 휴머노이드 로봇의 효율적인 제어를 위해서 비주얼 서보잉에 필요한 각 서비스를 분산객체로 정의하고, 이를 코바 미들웨어 상에서 구현한다. 필요한 서비스로는 각 서비스를 고유한 이름으로 탐색할 수 있는 네이밍 서비스, 스테레오 카메라로부터 획득되는 영상을 제공하는데 필요한 영상 서비스 그리고 목표물을 추적하면서 3차원 위치 정보를 추출하는 비주얼 서보잉 서비스 등이 있다. 실험에서는 실시간으로 목표물인 풍선을 추적하고 일정시간 정지해 있을 경우 풍선을 터뜨리는 결과를 보인다.

• Journal of Multimedia Information System
• /
• 제6권4호
• /
• pp.209-216
• /
• 2019

Over the past decade, researchers were able to solve complex medical problems as well as acquire deeper understanding of entire issue due to the availability of machine learning techniques, particularly predictive algorithms and automatic recognition of patterns in medical imaging. In this study, a technique called transfer learning has been utilized to classify Magnetic Resonance (MR) images by a pre-trained Convolutional Neural Network (CNN). Rather than training an entire model from scratch, transfer learning approach uses the CNN model by fine-tuning them, to classify MR images into Alzheimer's disease (AD), mild cognitive impairment (MCI) and normal control (NC). The performance of this method has been evaluated over Alzheimer's Disease Neuroimaging (ADNI) dataset by changing the learning rate of the model. Moreover, in this study, in order to demonstrate the transfer learning approach we utilize different pre-trained deep learning models such as GoogLeNet, VGG-16, AlexNet and ResNet-18, and compare their efficiency to classify AD. The overall classification accuracy resulted by GoogLeNet for training and testing was 99.84% and 98.25% respectively, which was exceptionally more than other models training and testing accuracies.

• 농촌계획
• /
• 제21권3호
• /
• pp.85-99
• /
• 2015

This study explores influences of the relationship between social capital and residents' perception in a collective aspects, and also explores the differences of influence between two groups in 10 rural communities. This study conducts regression analysis with residents questionnaires, and analyzes the relationship of influence among the latent factors, and differences between the two groups. As a results, associational network and social trust factors of social capital are identified as the most important factor in the quality of life and residents' attitudes. In addition, the differences in socio-cultural factor of quality of life and residents' attitude between two groups are identified by comparison with the relationship between two groups, although the explanatory power of both groups is not high. To achieve a successful rural tourism based on the result of this study, rural tourism should consider the regional and demographic characteristics, such as age, occupations and education and so on. The major contribution of this study is to confirm that the impact of social capital on the residents' perception would be different by regions in comparison with two groups, and it will be able to provide useful implication for the rural tourism development in the future.

• Journal of Information Technology Applications and Management
• /
• 제26권5호
• /
• pp.27-39
• /
• 2019

The Internet of Things (IoT) is a new paradigm that is revolutionizing computing. It is intended that all objects around us will be connected to the network, providing "anytime, anywhere" access to information. This study introduces IoT with Kolb's learning style in order to enhance the learning experience especially for inclusive education for primary and secondary schools where delivery of knowledge is not limited to physical, cognitive disabilities, human diversity with respect to ability, language, culture, gender, age and of other forms of human differences. The article also emphasizes the role of learning style as a discovery process that incorporates the characteristics of problem solving and learning. Kolb's Learning Style was chosen as it is widely used in research and in practical information systems applications. A consistent pattern of finding emerges by using a combination of Kolb's learning style and internet of things where specific individual differences, learning approach differences and IoT application differences are taken as a main research framework. Further several suggestions were made by using this combination to IoT architecture and smart environment of internet of things. Based on these suggestions, future research directions are proposed.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제9권6호
• /
• pp.2144-2159
• /
• 2015

CISCO VNI predicted an average annual growth rate of 66% for mobile video traffic between 2014 and 2019 and accordingly much academic research related to video streaming has been initiated. In video streaming, Adaptive Bitrate (ABR) is a streaming technique in which a source video is stored on a server at variable encoding rates and each streaming user requests the most appropriate video encoding rate considering their channel capacity. However, these days, ABR related studies are only focusing on real-time rate adaptation omitting energy efficiency though it is one of the most important requirement for mobile devices, which may cause dissatisfaction for streaming users. In this paper, we propose an energy efficient prefetching based dynamic adaptive streaming technique by considering the limited characteristics of the batteries used in mobile devices, in order to reduce the energy waste and provide a similar level of service in terms of the average video rate compared to the latest ABR streaming technique which does not consider the energy consumption. The simulation results is showing that our proposed scheme saves 65~68% of energy at the average global mobile download speed compared to the latest high performance ABR algorithm while providing similar rate adaptation performance.

• 농촌의학ㆍ지역보건
• /
• 제37권3호
• /
• pp.111-130
• /
• 2012

Objective: The purpose of this study was to identify and compare social capital measurement tools for the convenient use in public health studies. Method and result: This study examined and compared social capital tools developed individually by the World Bank, the OECD, the United States, United Kingdom, Canada, Australia, Ireland, and Korea. A comprehensive framework was constructed with six conceptual dimensions and sixteen indices. The six dimensions included Membership, Network, Trust, Information and communication, Social and civic participation, and Social cohesion and exclusion, which connoted the structural, cognitive, bonding, bridging, operative, and output elements. The indices of each tool were respectively matched to the indices of the comprehensive framework. The comprehensive tools were Integrated Questionnaire for the Measurement of Social Capital (SC-IQ) of the World Bank with 27 questions and the European Social Survey (ESS) of the OECD with 80 questions. Conclusion: The SC-IQ should be utilized in public health studies due to its simplicity yet comprehensiveness as a social capital tool. The ESS should also be considered as a comprehensive tool.