• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2021.05a
• /
• pp.240-243
• /
• 2021

Recently, there have been research results of applying Big data and AI technologies to the evaluation and individual learning for education. It is information technology innovations that collect dynamic and complex data, including student personal records, physiological data, learning logs and activities, learning outcomes and outcomes from social media, MOOCs, intelligent tutoring systems, LMSs, sensors, and mobile devices. In addition, e-learning was generated a large amount of learning data in the COVID-19 environment. It is expected that learning analysis and AI technology will be applied to extract meaningful patterns and discover knowledge from this data. On the learner's perspective, it is necessary to identify student learning and emotional behavior patterns and profiles, improve evaluation and evaluation methods, predict individual student learning outcomes or dropout, and research on adaptive systems for personalized support. This study aims to contribute to research in the field of education by researching and classifying machine learning technologies used in anomaly detection and recommendation systems for educational data.

• Journal of The Korean Association For Science Education
• /
• v.32 no.4
• /
• pp.570-585
• /
• 2012

The Korean national curriculum for secondary school emphasizes scientific problem solving. In line with the national curriculum, many educational studies have been conducted in relation to science education. The objects of these studies were well-defined and well-structured problems. The studies were criticized for overlooking ill-defined and ill-structured problems. Some research has dealt with problem finding in ill-structured problems, which is related to creativity. There is a need for a study of scientific problem finding process in an ill-structured problem situation, because this study will help teachers wanting to teach scientific problem-finding in an ill-structured problem situation. The objective of this study was to conduct an empirical study on the scientific problem finding process in an ill-structured problem situation. One task of scientific problem finding in an ill-structured problem situation was assigned to 92 university students; thereafter, 32 of them participated in the research through interviews. Results indicated that the scientific problem finding process depended on initial clues and tentative solutions. Initial clues were affected by students' experiences, such as major classes, films, and novels. Tentative solutions were influenced by background knowledge of the tasks. Students screened information browsed on the Internet. They applied some standards for selection, particularly emphasized reliability standards, which are supposed to be studied in other contexts. All the students used assumptions to make their problems appear probable, which could be a useful tool to articulate.

• 한국HCI학회:학술대회논문집
• /
• 2008.02b
• /
• pp.507-512
• /
• 2008

This study investigated the navigation ability of patients with MCI in Virtual Environments(VE) and on the visual functioning. The participants consisted of elderly adults with/without MCI. Neuropsychological tests(RCFT, BVRT, TMT, and Digit Span), the Groton Maze Learning Test(12trials), and the VE navigation learning task(6 trials) were performed. As a result, there were significant group differences for the RCFT and BVRT, but not for the GMLT. For the VE task, there was a significant difference between the MCI and normal group and no interactions between the groups and trials were found. The VE task was correlated with The RCFT, the BVRT, and the GMLT and omnibus the RCFT and the BVRT accounted for 45% of VE performances. Thus, we concluded that patients with MCI are inferior to VE navigation and visual retention/memory play a role in navigation abilities.

• Journal of the Korea Institute of Information Security & Cryptology
• /
• v.28 no.6
• /
• pp.1463-1474
• /
• 2018

Fuzzing is one of the software testing techniques that find security flaws by inputting invalid values or arbitrary values into the program and various methods have been suggested to increase the efficiency of such fuzzing. In this paper, focusing on the existence of field with high relevance to coverage and software crash, we propose a new method for intensively fuzzing corresponding field part while performing field based fuzzing. In this case, we use a deep learning model called Variational Autoencoder(VAE) to learn the statistical characteristic of input values measured in high coverage and it showed that the coverage of the regenerated files are uniformly higher than that of simple variation. It also showed that new crash could be found by learning the statistical characteristic of the files in which the crash occurred and applying the dropout during the regeneration. Experimental results showed that the coverage is about 10% higher than the files in the queue of the AFL fuzzing tool and in the Hwpviewer binary, we found two new crashes using two crashes that found at the initial fuzzing phase.

• Design Convergence Study
• /
• v.18 no.4
• /
• pp.1-15
• /
• 2019

As the game industry is steadily becoming the spotlight industry, the importance of user experience design in game industry is increasing. This study tried to approach game from the viewpoint of user experience design and aimed to analyze the onboarding process focusing on user accessibility and retention in an online game. First, through literature review, onboarding process was devided into three stages. Then each stages were analyzed into experience design, game design elements to derive the key UX factors. Second, based on the UX elements, the game experience and cognitive element analysis frame was presented. With this frame, five domestic online games were qualitatively analyzed and cognitive elements of each game's onboarding process were derived. Key cognitive factors in each stages were, selective attention in the discovery stage, working memory and active learning in the learning stage, and participation and motivation in the immersion stage. Finally, improvement direction were presented, focusing on the key cognitive factors. These studies highlight the importance of the user entry process in online games and suggests improvements to lower entry barriers.

• Proceedings of the Korean Society for Cognitive Science Conference
• /
• 2005.05a
• /
• pp.244-253
• /
• 2005

사람에게 행동의 개인차가 있듯이 rat이나 mouse에 있어서도 행동의 차이를 발견할 수 있다. Rat의 행동성향에 따른 (1)학습 및 기억 능력의 차이, (2)기억과 해마의 관계, (3)치매유발단백질의 하나로 알려진 아밀로이드 베타($A{\beta}$ )및 수종의 항 치매 약물효과를 알아보는 것이 본 실험의 목적이다. Rat의 행동관찰을 통해 두 가지 행동패턴을 관찰할 수 있었는데, 이러한 rat의 행동 특성은 심리학자 Jung이 심리유형으로 설명하고 있는 extraversion, introversion의 행동성향과 유사할 것이라는 가정 하에 실험을 계획, 실시하였다. Rat에 water maze test를 실시하여 공간 기억의 단기, 장기 기억을 분석하였는데 그 결과 두 가지 행동 성향을 가진 rat은 서로 다른 학습 및 기억 능력의 특성을 보였다. 즉, extraversion은 단기 기억의 향상을 보인 반면에, introversion은 장기 기억의 향상을 보였다. Rat을 대상으로 water maze test 외에 Y-maze, passive avoidance test를 실시하여 공간 기억(spatial memory), 작동 기억(working memory), passive avoidance memory, 그리고 단기, 장기 기억의 관계를 종합적으로 분석해 보았다. 그 결과 두 가지 행동성향에 따라 서로 영향을 미치는 기억의 종류 및 관계에 차이가 있음을 발견할 수 있었다. 또한 두 가지 행동성향을 가진 rat에 약물을 투여했을 때, 서로 다른 약물 효과를 보였으며, $A{\beta}$ 를 주입했을 때, 기억(memory) 및 해마(hippocampus) 세포 사멸(cell death)에 서로 상반된 결과를 보여주었다. 이러한 연구 결과는 개체의 행동성향에 따라 학습 및 기억의 효과가 다를 수 있음을 보여주는 결과라 할 수 있고, 개인의 적성과 소질의 인식 및 개발의 중요성에 시사하는 바가 크다. 또한 개개인의 행동과 학습 및 기억 능력의 차이를 두뇌과학적으로 이해하여, 두뇌의 장점은 살리고 단점을 보완할 수 있는 이론적 토대를 세우는데 이러한 동물실험이 그 기초를 제공해 줄 수 있을 것이다. 또한 행동성향 및 기억의 종류에 따른 약물효과의 차이는 기억과 관련된 질병인 알츠하이머 환자에 있어 개개인에게 맞는 적절한 특징적인 치료약물이 존재할 것이라는 가능성을 제공해줄 뿐만 아니라 학습과 기억력 증진 효과를 기대해 볼 수 있을 것이라고 생각된다.

• Korean Journal of Childcare and Education
• /
• v.8 no.1
• /
• pp.145-167
• /
• 2012

The objective of this study is to investigate the meaning of pre-service educare teachers' experience about child safety management classes based on Problem Based Learning (PBL). The participants in this study were thirty five sophomores majoring in Social Welfare, and fifteen weeks of data were collected. The participants were given five problems that were related with real situations. During the given period, they made documents from reflective journals, group or individual interviews, and online community resources. Analyzing the documents sheds light on the meaning of the pre-service educare teachers' experience. The results are as follows: First, pre-service educare teachers found themselves recovering confidence, earning recognitions from others, and pursuing their study. Second, they showed continuous conflicts not only with the PBL approach but also with themselves and group members. Finally, they experienced mutual help and interactions among the group members thorough their cooperative learning and they realized the meaning of cooperative learning by means of comparisons and references between the groups. In conclusion, this study confirms the applicability of PBL to the educare teacher training courses and points out specific ways to alleviate the conflicts in applying PBL to class needs in future studies.

• Journal of The Korean Association For Science Education
• /
• v.33 no.7
• /
• pp.1385-1402
• /
• 2013

This study analyzes pre-service teachers' PCK dealing with visualization of the contents related to boiling point elevation and teaching methods in mock-lessons. As a result of analyzing pre-service teachers' knowledge based on PCK factors, most of the pre-service teachers accentuated on understanding boiling point elevation conceptually, whereas some of the others inclined to make students understand boiling point elevation in a scientific way, let the kids use numerical formulas to describe the concept, and motivate them to learn through the examples in real life. The pre-service teachers represented majority of the important facts of boiling point elevation as the knowledge required to understand things conceptually. However, they did not focus on improving the scientific thinking and inquiring levels of the students. Also, the pre-service teachers tended to teach at the level and order of the textbook. In some other cases, they considered the vocabularies and materials in the textbook (which could have been highlighted in the editing sequence) as the main topic to learn, or regarded the goal as giving students the ability to solve exercises in the textbook. It turned out that the pre-service teachers had a low level of knowledge of their students. It is recommended that they should make use of the materials given (such as data related to the misconception of students) during the training session. The knowledge of teaching and evaluating students was described superficially by the pre-service teachers; they merely mentioned the applications of models, such as the cyclic model and discovery learning, rather than thinking of a method related to the goals, or listed general assessment methods.

• Journal of The Korean Association of Information Education
• /
• v.16 no.4
• /
• pp.451-462
• /
• 2012

In this study, our primary areas of mathematical shapes as a way to solve the problem of sixth grade math and geometry around the area in addition to the real world, the virtual objects to explore on their own learning, heuristic principles and learning concepts are developed. To this end, second-class sixth grade in Seoul class M is selected and the area of Augmented Reality class shapes students' academic achievement sure to affect how much agreed. experimental study was developed and then applied to the actual class content across pre and post implementation evaluation, and subsequent academic achievement levels were compared and analyzed. As a result, learners in the experimental group and control group than the class of interested students and class satisfaction, a statistically higher achievement. Learning on augmented reality, which shapes have the gumption to participate in classes, and concepts related to shape the formation and indicates that academic achievement is related.

• Proceedings of the Korean Society for Bioinformatics Conference
• /
• 2001.10a
• /
• pp.165-196
• /
• 2001

DNA chip 또는 microarray는 다수의 유전자 또는 유전자 조각을 (보통 수천내지 수만 개)칩상에 고정시켜 놓고 DNA hybridization 반응을 이용하여 유전자들의 발현 양상을 분석할 수 있는 기술이다. 이러한 high-throughput기술은 예전에는 생각하지 못했던 여러가지 분자생물학의 문제에 대한 해답을 제시해 줄 수 있을 뿐 만 아니라, 분자수준에서의 질병 진단, 신약 개발, 환경 오염 문제의 해결 등 그 응용 가능성이 무한하다. 이 기술의 실용적인 적용을 위해서는 DNA chip을 제작하기 위한 하드웨어/웻웨어 기술 외에도 이러한 데이터로부터 최대한 유용하고 새로운 지식을 창출하기 위한 bioinformatics 기술이 핵심이라고 할 수 있다. 유전자 발현 패턴을 데이터마이닝하는 문제는 크게 clustering, classification, dependency analysis로 구분할 수 있으며 이러한 기술은 통계학과인공지능 기계학습에 기반을 두고 있다. 주로 사용된 기법으로는 principal component analysis, hierarchical clustering, k-means, self-organizing maps, decision trees, multilayer perceptron neural networks, association rules 등이다. 본 세미나에서는 이러한 기본적인 기계학습 기술 외에 최근에 연구되고 있는 새로운 학습 기술로서 probabilistic graphical model (PGM)을 소개하고 이를 DNA chip 데이터 분석에 응용하는 연구를 살펴본다. PGM은 인공신경망, 그래프 이론, 확률 이론이 결합되어 형성된 기계학습 모델로서 인간 두뇌의 기억과 학습 기작에 기반을 두고 있으며 다른 기계학습 모델과의 큰 차이점 중의 하나는 generative model이라는 것이다. 즉 일단 모델이 만들어지면 이것으로부터 새로운 데이터를 생성할 수 있는 능력이 있어서, 만들어진 모델을 검증하고 이로부터 새로운 사실을 추론해 낼 수 있어 biological data mining 문제에서와 같이 새로운 지식을 발견하는 exploratory analysis에 적합하다. 또한probabilistic graphical model은 기존의 신경망 모델과는 달리 deterministic한의사결정이 아니라 확률에 기반한 soft inference를 하고 학습된 모델로부터 관련된 요인들간의 인과관계(causal relationship) 또는 상호의존관계(dependency)를 분석하기에 적합한 장점이 있다. 군체적인 PGM 모델의 예로서, Bayesian network, nonnegative matrix factorization (NMF), generative topographic mapping (GTM)의 구조와 학습 및 추론알고리즘을소개하고 이를 DNA칩 데이터 분석 평가 대회인 CAMDA-2000과 CAMDA-2001에서 사용된cancer diagnosis 문제와 gene-drug dependency analysis 문제에 적용한 결과를 살펴본다.