• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.24 no.2
• /
• pp.204-211
• /
• 2020

In this paper, we propose an optimal deep learning network architecture for main object location detection through weak supervised learning. The proposed network adds convolution blocks for improving the localization accuracy of the main object through weakly-supervised learning. The additional deep learning network consists of five additional blocks that add a composite product layer based on VGG-16. And the proposed network was trained by the method of weakly-supervised learning that does not require real location information for objects. In addition, Grad-CAM to compensate for the weakness of GAP in CAM, which is one of weak supervised learning methods, was used. The proposed network was tested through the CUB-200-2011 data set, we could obtain 50.13% in top-1 localization error. Also, the proposed network shows higher accuracy in detecting the main object than the existing method.

• Proceedings of the Korean Society of Broadcast Engineers Conference
• /
• 2017.06a
• /
• pp.147-148
• /
• 2017

본 논문에서는 간단한 사용자 입력과 다중 랜덤 워크(multiple random walker) 기법을 기반으로 동영상 내의 주요 객체를 분할하는 알고리즘을 제안한다. 우선 동영상의 첫 프레임에서 점 형태의 사용자의 입력을 받아 대략적인 객체와 배경의 위치를 얻고, Lab 색상의 측지거리를 이용하여 객체와 배경의 중요도 지도를 얻는다. 다음으로 영상을 슈퍼 픽셀 단위로 분할하고, 다중 랜덤 워크 기법을 적용하여 객체 분할을 수행한다. 랜덤 워크 기법 적용 시, 중요도 지도를 각 랜덤 워커의 초기 분포로 설정하고, 노드간 색상과 움직임 차이를 이용하여 전이 행렬을 계산한다. 마지막으로 결과를 정련한 뒤, 다음 프레임으로 분할 결과를 전파하여 시간적 일관성을 유지한다. 실험을 통하여 제안 기법이 기존 기법에 비하여 우수한 객체 분할 성능을 보임을 확인한다.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2024.05a
• /
• pp.254-257
• /
• 2024

5G 통신과 인공지능 기술이 발전하고, 사물인터넷 기기의 수가 증가함에 따라 종래의 정보보호체계를 우회하는 지능적인 사이버 공격이 증가하고 있다. 그러나, 종래의 기계학습 기반 멀웨어 탐지 방식은 이미 알려진 멀웨어만 탐지할 수 있으며, 새로운 멀웨어는 탐지가 어렵거나, 기존의 알려진 멀웨어로 잘못 분류되는 문제가 있다. 본 연구에서는 비지도학습을 사용하여 알려지지 않은 멀웨어를 탐지하고, 새롭게 탐지된 멀웨어를 새로운 라벨로 분류하여 재학습하는 준지도 학습 기반의 멀웨어 탐지 기법을 제안한다. 다양한 데이터 환경에서 알려지지 않은 멀웨어 데이터가 탐지 모델로 입력될 때 제안한 방식의 성능을 평가했다. 실험 결과에 따르면 제안한 준지도 학습 기반의 멀웨어 탐지 방법은 종래의 방식 대비 정확도를 약 16% 개선했다.

• The Journal of the Acoustical Society of Korea
• /
• v.13 no.6
• /
• pp.83-90
• /
• 1994

In this paper, we propose a new learning algorithm, ASOFM(Adaptive Self Organizing Feature Map), to solve the defects of Kohonen's Self Organiaing Feature Map. Kohonen's algorithm is sometimes stranded on local minima for the initial weights. The proposed algorithm uses an object function which can evaluate the state of network in learning and adjusts the learning rate adaptively according to the evaluation of the object function. As a result, it is always guaranteed that the state of network is converged to the global minimum value and it has a capacity of generalized learning by adaptively. It is reduce that the learning time of our algorithm is about $30\%$ of Kohonen's.

• Journal of The Korean Association For Science Education
• /
• v.35 no.4
• /
• pp.573-584
• /
• 2015

Inquiry has been consistently emphasized in science education as a crucial element for learning. Although many researchers came to agree on the importance of scientific inquiry, authentic inquiry activities are hard to be actualized in an educational context. Therefore it is required to critically examine what teachers have difficulty in teaching inquiry. In this article, we looked into inquiry-based science activities in a small group setting where pre-service science teachers faced dilemmas between cognition and practice of inquiry. A case study was conducted on eight undergraduate students who are majoring in science education. The participants attended a weekly science program for middle school students in low SES as teaching assistants and mentors, and took full care of his/her mentees during open-inquiry activities. The results were drawn by analyzing participants' personal and group interviews, participant observations, self-reports, and others. The pre-service teachers viewed the knowledge and procedure of science as an essential factor in inquiry activities along with student's spontaneous attitude. However, in the process of performing inquiry, they faced several dilemmas between ideal cognition and real activities. The aspects of dilemmas could be summarized in three pairs of opposing concepts: 'diverging inquiry or converging science', 'interest-centered inquiry or learning-centered inquiry', and 'student as the subject or student with the insufficient expertise.' We discussed ways of resolving dilemmas and alternative perspectives on scientific inquiry.

• Annual Conference on Human and Language Technology
• /
• 2020.10a
• /
• pp.591-594
• /
• 2020

담화에서 의미를 전달하는 데 문제가 없을 경우에는 문장성분을 생략하여 표현한다. 생략된 문장성분을 무형대용어(zero anaphora)라고 한다. 무형대용어를 복원하기 위해서는 무형대용어 탐지와 무형대용어 해결이 필요하다. 무형대용어 탐지란 문장 내에서 생략된 필수성분을 찾는 것이고, 무형대용어 해결이란 무형대용어에 알맞은 문장성분을 찾아내는 것이다. 본 논문에서는 담화에서의 무형대용어 탐지 및 해결을 위한 말뭉치 생성 방법을 제안한다. 먼저 기존의 세종 구어 말뭉치에서 어휘지도를 이용하여 무형대용어를 복원한다. 이를 위해 본 논문에서는 동형이의어 부착과 어휘지도를 이용해서 무형대용어를 복원하고 복원된 무형대용어에 대한 오류를 수정하고 그 선행어(antecedent)를 수동으로 결정함으로써 무형대용어 해결 말뭉치를 생성한다. 총 58,896 문장에서 126,720개의 무형대용어를 복원하였으며, 약 90%의 정확률을 보였다. 앞으로 심층학습 등의 방법을 활용하여 성능을 개선할 계획이다.

• Journal of the Korean association of regional geographers
• /
• v.17 no.4
• /
• pp.381-394
• /
• 2011

In Korea, the number of foreigners reached about 1,260,000. So we are now living in a multicultural society. There are more than 36,000 multicultural students in kindergarten, elementary, middle, and high school(2010's standards). In other words, Still more multicultural students are expected to increase in the future. As a matter of fact, one of the biggest problems which mixed couples and immigrants from other countries have had is most concerned about possible bias and discrimination of their children. Study has shown that multicultural students are alienated from the others at school, because of their skin colours, the pronunciation they speak Korean, and maladjustment in their school life. Actually, multi-cultural education program should be applied to the first grade in elementary school. Besides, teachers have to direct multicultural and general students with integrated education. Study also found that it is necessary to use more visuals and pictures as the main multi-cultural education. And books and CDs should be used as guide materials. It's desirable that the appropriate time to teach relate to lesson.

• Proceedings of the Korean Information Science Society Conference
• /
• 2001.10b
• /
• pp.316-318
• /
• 2001

본 논문에서는 자기조직화 형상지도(Self-organizing Feature Maps)를 사용하여 움직이는 물체에 대해 움직임의 특성을 자동으로 분석하였다. Kohonen Network는 자기조직을 형성하는 unsupervised learning 알고리즘으로서, 이 논문에서는 생태계에서의 데이터를 Patternizing하고, Clustering 하는데 사용한다. 본 논문에서 Kohonen 신경망의 학습에 사용한 데이터는 CCD 카메라로 물고기의 움직임을 추적한 좌표 데이터이며, diazinon 0.1 ppm을 처리한 물고기 점 데이터와 처리하지 않은 점 데이터를 각각 낮.밤 약 10시간동안 수집하여, \circled1처리전 낮 데이터 \circled2처리전 밤 데이터 \circled3처리전 낮 데이터 \circled4처리후 밤 데이터 각각 4개의 group으로 분류한 후, Kohonen Network을 사용하여 물고기의 행동 차이를 분석하였다.

• The Journal of the Korea Contents Association
• /
• v.18 no.2
• /
• pp.427-437
• /
• 2018

This study explored the effectiveness of the online English learning program contents for elementary school students. The study used the online English learning program served by Gyeonggi province office of education. 107 students attending P elementary school in K city volunteered for the program. After studying English via the website for almost one year, they were asked to respond the questionnaires related to the contents of the online English program. Since the research investigated that the relations of students' grades, the time for the study, their diagnostic test scores, and the effectiveness of the contents, the survey responses were analyzed with Spearman correlation. As a result, older students thought that the type of problem-solving, the type of performing a task, WBI (Web Based Instruction) were not efficacious. Also, these types of online English program were chosen as ineffective from the students at the higher level. Whereas the type of private lesson, the lessons based on a story, and the type of animation were preferred to the students who spent longer time on the website. This highlights the need to consider the students' characteristics such as students' grades, the time for the study, and their English level when developing the contents of the online English learning program.

• Journal of the Korean Society for information Management
• /
• v.22 no.2 s.56
• /
• pp.125-145
• /
• 2005

This paper presents a semantic vector space retrieval model incorporating a word sense disambiguation algorithm in an attempt to improve retrieval effectiveness. Nine Korean homonyms are selected for the sense disambiguation and retrieval experiments. The total of approximately 120,000 news articles comprise the raw test collection and 18 queries including homonyms as query words are used for the retrieval experiments. A Naive Bayes classifier and EM algorithm representing supervised and unsupervised learning algorithms respectively are used for the disambiguation process. The Naive Bayes classifier achieved $92\%$ disambiguation accuracy. while the clustering performance of the EM algorithm is $67\%$ on the average. The retrieval effectiveness of the semantic vector space model incorporating the Naive Bayes classifier showed $39.6\%$ precision achieving about $7.4\%$ improvement. However, the retrieval effectiveness of the EM algorithm-based semantic retrieval is $3\%$ lower than the baseline retrieval without disambiguation. It is worth noting that the performances of disambiguation and retrieval depend on the distribution patterns of homonyms to be disambiguated as well as the characteristics of queries.