• Genomics & Informatics
• /
• 제18권1호
• /
• pp.2.1-2.11
• /
• 2020

In this paper, we propose a new approach to detecting outliers in a set of segmented genomes of the flu virus, a data set with a heterogeneous set of sequences. The approach has the following computational phases: feature extraction, which is a mapping into feature space, alignment-free distance measure to measure the distance between any two segmented genomes, and a mapping into distance space to analyze a quantum of distance values. The approach is implemented using supervised and unsupervised learning modes. The experiments show robustness in detecting outliers of the segmented genome of the flu virus.

• 천문학회보
• /
• 제43권1호
• /
• pp.40.3-40.3
• /
• 2018

We present results from our two experiments of using machine learning algorithms in processing and analyzing the KMTNet imaging data. First, density estimation and clustering methods find meaningful structures in the metric space of imaging quality measurements described by photometric quantities. Second, we also develop a method to separate out light curves of reliable microlensing event candidates from spurious events, estimating reliability scores of the candidates.

• 한국실내디자인학회논문집
• /
• 제24권3호
• /
• pp.48-58
• /
• 2015

This study is to conclude a direction for Information Commons, which supports the university library in a new role. The study explains perspectives on the changing role of the university library by examining the approaches, histories, and theories practiced by various researchers on Information Commons. The study aims to discover ways of improving the library space that are dedicated to technology using Information Commons, it also examines ways of creating a unified "library space" that will support learning and access to knowledge and information. The features of Cultural Commons include making improvements to technology-centered space, and providing support to research, freedom of speech, creative approach, public freedom and collaboration, and interaction. The functions of Cultural Commons within the university library are listed: First, it supports programs that will transform the library into a social hub within the university. The space specifically blurs the boundary between the library building and its surroundings, and unifies these spaces to enhance its catalytic role in aiding social interactions and human-centered approach. Second, it supports active participation through cultural programs and provides a fluid and interactive space with virtual resources. Third, it enhances user experience to supports behaviors and activities that involve fixtures and equipment in the space to promote learning. The study notes that, with the emergence of these characteristics, the university library is changing by implementing Cultural Commons for on-campus social space and new learning. Accordingly, this implementation is expected to enhance active acceptance of the library space in the future.

• Journal of Information Processing Systems
• /
• 제8권3호
• /
• pp.409-420
• /
• 2012

The decision-making by agents in games is commonly based on reinforcement learning. To improve the quality of agents, it is necessary to solve the problems of the time and state space that are required for learning. Such problems can be solved by Macro-Actions, which are defined and executed by a sequence of primitive actions. In this line of research, the learning time is reduced by cutting down the number of policy decisions by agents. Macro-Actions were originally defined as combinations of the same primitive actions. Based on studies that showed the generation of Macro-Actions by learning, Macro-Actions are now thought to consist of diverse kinds of primitive actions. However an enormous amount of learning time and state space are required to generate Macro-Actions. To resolve these issues, we can apply insights from studies on the learning of tasks through Programming by Demonstration (PbD) to generate Macro-Actions that reduce the learning time and state space. In this paper, we propose a method to define and execute Macro-Actions. Macro-Actions are learned from a human subject via PbD and a policy is learned by reinforcement learning. In an experiment, the proposed method was applied to a car simulation to verify the scalability of the proposed method. Data was collected from the driving control of a human subject, and then the Macro-Actions that are required for running a car were generated. Furthermore, the policy that is necessary for driving on a track was learned. The acquisition of Macro-Actions by PbD reduced the driving time by about 16% compared to the case in which Macro-Actions were directly defined by a human subject. In addition, the learning time was also reduced by a faster convergence of the optimum policies.

• 대한지구과학교육학회지
• /
• 제15권1호
• /
• pp.27-46
• /
• 2022

이 연구는 초등 및 중등 지구과학 예비교사들을 대상으로 생소한 경험 공간(Novelty Space)에 대한 인식 조사를 목적으로 하였다. 이를 위해 A 교육대학교의 초등 예비교사 38명과 B 대학교 지구과학교육과에 재학 중인 31명의 중등 지구과학 예비교사들이 설문에 참여하였다. 또한 연구 참여자 중 추가적인 면담 참여에 동의한 초등 예비교사 3명과 중등 지구과학 예비교사 9명, 총 12명을 대상으로 비대면 면담을 실시하였다. 생소한 경험 공간에 대한 요소를 사전 지식(인지), 사전야외학습 경험(심리), 야외조사지역과의 친숙도(지리)에 덧붙여, 사회적인(social) 요소과 기술적인(technical) 요소를 추가하였다. 초등과 중등, 학년를 기준으로 분류하였을 때 생소한 경험 공간의 요소에 대해 인지적 영역, 심리적 영역, 지리적 영역, 사회적 영역에서 통계적으로 유의미한 차이를 보였다. 통계적인 차이는 야외학습과 관련된 경험이나 자본이 중등 지구과학 예비교사들이 초등 예비교사들보다 더 많은 것으로부터 비롯되었을지도 모른다고 해석하였다. 반-구조화된 면담에서 초등 예비교사 및 중등 지구과학 예비교사 모두 가상야외지질학습의 가치나 필요성을 강조하였으며 특히 기술적인 영역에서의 역량을 강조하였다. 이 연구는 초등 및 중등 지구과학 예비교사들을 대상으로 야외지질학습을 실행하기 위한 생소한 경험 공간에 대해 현재의 교육 맥락적인 상황을 고려하여 새롭게 정의할 필요성을 제안할 뿐만 아니라 생소한 경험 공간 요소들을 구체화하였다는 점에서 학술적인 의의를 갖는다.

• International Journal of Fuzzy Logic and Intelligent Systems
• /
• 제16권4호
• /
• pp.270-275
• /
• 2016

We present an approach for acceleration actor-critic algorithm for reinforcement learning with continuous action space. Actor-critic algorithm has already proved its robustness to the infinitely large action spaces in various high dimensional environments. Despite that success, the main problem of the actor-critic algorithm remains the same-speed of convergence to the optimal policy. In high dimensional state and action space, a searching for the correct action in each state takes enormously long time. Therefore, in this paper we suggest a search accelerating function that allows to leverage speed of algorithm convergence and reach optimal policy faster. In our method, we assume that actions may have their own distribution of preference, that independent on the state. Since in the beginning of learning agent act randomly in the environment, it would be more efficient if actions were taken according to the some heuristic function. We demonstrate that heuristically-accelerated actor-critic algorithm learns optimal policy faster, using Educational Process Mining dataset with records of students' course learning process and their grades.

• 한국전자파학회논문지
• /
• 제27권5호
• /
• pp.407-415
• /
• 2016

무선 통신의 최근 동향을 살펴보면 에너지 효율적 전송의 중요성이 강조되고 있다. 본 논문은 multiple-input multiple-output orthogonal frequency division multiplexing(MIMO-OFDM) 무선 시스템에서 에너지 효율성을 최대화하기 위해 기계학습 기술을 사용하는 적응형 전송을 고려한다. MIMO-OFDM 시스템의 채널 상태를 효과적으로 나타내기 위한 two- dimensional capacity(2D-CAP) feature space와 classification 기술을 통해 에너지 효율적인 적응형 전송을 수행하는 machine-learning-based bit and power adaptation(ML-BPA) 알고리즘을 제안한다. 모의 실험 결과를 통해 2D-CAP이 본 논문이 고려하는 무선 채널 상태를 정확하게 나타내며, 이를 통해 적응형 전송의 성능을 향상시킴을 확인하였다. 또한, ordered postprocessing signal-to-noise ratio(ordSNR)를 포함한 다른 feature space들과 직접적인 비교를 통해 2D-CAP이 전송 성능이나 복잡도 측면에서 뚜렷한 이득을 가짐을 확인하였다.

• 우주기술과 응용
• /
• 제1권1호
• /
• pp.49-63
• /
• 2021

태양계 천체 탐사는 다양한 탑재체를 통해 이루어지고 있고, 그에 따라 많은 연구 결과들이 나오고 있다. 우리는 태양계 천체 연구의 한 방법으로 딥러닝 적용을 시도해 보았다. 지구 관측 위성 자료와 다르게 태양계 천체 자료들은 천체들에 따라 탐사선에 따라 각 탐사선의 탑재체에 따라 그 자료의 형태가 매우 다르다. 그래서 학습시킨 모델로 다양한 자료에 적용이 어려울 수 있지만 사람에 의한 오류를 줄이거나, 놓치는 부분들을 보완해 줄 수 있을 것이라고 기대한다. 우리는 달 표면의 크레이터를 탐지하는 모델을 구현해 보았다. Lunar Reconnaissance Orbiter Camera (LROC) 영상과 제공하는 shapefile을 입력값으로 하여 모델을 만들었고, 이를 달 표면 영상에 적용하여 보았다. 결과가 만족스럽지는 못했지만 이후 이미지 전처리와 모델 수정 작업을 통해 최종적으로는 ShadowCam에 의해 획득되는 달의 영구음영지역 영상에 적용할 예정이다. 이 외에도 달 표면과 비슷한 형태를 가진 세레스와 수성에 적용을 시도하여 딥러닝이 태양계 천체 연구에 또 다른 방법임을 시사하고자 한다.

• 한국멀티미디어학회논문지
• /
• 제21권5호
• /
• pp.626-637
• /
• 2018

Human exchanges information not only through words, but also through body gesture or hand gesture. And they can be used to build effective interfaces in mobile, virtual reality, and augmented reality. The past 2D gesture recognition research had information loss caused by projecting 3D information in 2D. Since the recognition of the gesture in 3D is higher than 2D space in terms of recognition range, the complexity of gesture recognition increases. In this paper, we proposed a real-time gesture recognition deep learning model and application in 3D space using deep learning technique. First, in order to recognize the gesture in the 3D space, the data collection is performed using the unity game engine to construct and acquire data. Second, input vector normalization for learning 3D gesture recognition model is processed based on deep learning. Thirdly, the SELU(Scaled Exponential Linear Unit) function is applied to the neural network's active function for faster learning and better recognition performance. The proposed system is expected to be applicable to various fields such as rehabilitation cares, game applications, and virtual reality.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제16권3호
• /
• pp.792-812
• /
• 2022

Multi-agent systems often need to achieve the goal of learning more effectively for a task through coordination. Although the introduction of deep learning has addressed the state space problems, multi-agent learning remains infeasible because of the joint action spaces. Large-scale joint action spaces can be sparse according to implicit or explicit coordination structure, which can ensure reasonable coordination action through the coordination structure. In general, the multi-agent system is dynamic, which makes the relations among agents and the coordination structure are dynamic. Therefore, the explicit coordination structure can better represent the coordinative relationship among agents and achieve better coordination between agents. Inspired by the maximization of social group utility, we dynamically construct a factor graph as an explicit coordination structure to express the coordinative relationship according to the utility among agents and estimate the joint action values based on the local utility transfer among factor graphs. We present the application of such techniques in the scenario of multiple intelligent vehicle systems, where state space and action space are a problem and have too many interactions among agents. The results on the multiple intelligent vehicle systems demonstrate the efficiency and effectiveness of our proposed methods.