• The Journal of the Korea Contents Association
• /
• v.9 no.10
• /
• pp.51-58
• /
• 2009

Reinforcement learning is a sub area of machine learning concerned with how an agent ought to take actions in an environment so as to maximize some notion of long-term reward. In the case of multi-agent, especially, which state space and action space gets very enormous in compared to single agent, so it needs to take most effective measure available select the action strategy for effective reinforcement learning. This paper proposes a multi-agent reinforcement learning model based on fuzzy inference system in order to improve learning collect speed and select an effective action in multi-agent. This paper verifies an effective action select strategy through evaluation tests based on Robocup Keepaway which is one of useful test-beds for multi-agent. Our proposed model can apply to evaluate efficiency of the various intelligent multi-agents and also can apply to strategy and tactics of robot soccer system.

• Journal of the Korea Convergence Society
• /
• v.12 no.9
• /
• pp.21-30
• /
• 2021

Unlike behaviors that are generally known, information regarding unspecific behaviors is insufficient. For an education or guidance regarding the unspecific behaviors, collection and management of data regarding the unspecific behaviors of special-needs students are needed. In this paper, a consultation management model based on behavior classification of special-needs students using machine learning is proposed. It collects data by photographing the behavior of special students in real time, analyzes the behavior pattern, composes a data set, and trains it in the suggestion system. It is possible to improve the accuracy by comparing the behavior of special students photographed later into the suggestion system and analyzing the results by comparing it with the existing data again. The test has been performed by arbitrarily applying unspecific behaviors that are not stored in the database, and the forecast model has accurately classified and grouped the input data. Also, it has been verified that it is possible to accurately distinguish and classify the behaviors through the feature data of the behaviors even if there are some errors in the input process.

• Korean Journal of Remote Sensing
• /
• v.35 no.2
• /
• pp.279-288
• /
• 2019

We evaluated the land cover classification performance of SegNet, which features semantic segmentation of aerial imagery. We selected four semantic classes, i.e., urban, farmland, forest, and water areas, and created 2,000 datasets using aerial images and land cover maps. The datasets were divided at a 8:2 ratio into training (1,600) and validation datasets (400); we evaluated validation accuracy after tuning the hyperparameters. SegNet performance was optimal at a batch size of five with 100,000 iterations. When 200 test datasets were subjected to semantic segmentation using the trained SegNet model, the accuracies were farmland 87.89%, forest 87.18%, water 83.66%, and urban regions 82.67%; the overall accuracy was 85.48%. Thus, deep learning-based semantic segmentation can be used to classify land cover.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.9 no.5
• /
• pp.1296-1303
• /
• 2008

Recently, the university environment has been changed faster than before. It has based on university environment and IT infrastructure. Especially, most of local university has devised development plan such as improving the image and competitive power of campus. Digital, Electronic and Mobile Campus has increased the importance as people realize that the use of technology can improve the learning process. U-Campus of latest IT Technology need a service environment of which the practical use is possible through IT analysis of the members. For example u-campus setup of mobile offers the convenience to the members. We expected thing to use much, even though actual condition investigation about IT environment of the user is insufficient. The inconvenience of mobile could not be activated to the service for proactive use. The importance became the result about u-campus service setup of a company and university center. This service environment cannot offer specific information of center members for which the service implements. In this paper, we studied about members centralized u-campus model through u-recruit, campus information mobile service on university.

• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.22 no.5
• /
• pp.171-176
• /
• 2022

With the recent development of deep learning technology, the areas of recommendation systems have also diversified. This paper studied algorithms to improve the learning rate and studied the significance results according to words through comparison with the performance characteristics of the Word2Vec model. The problem recommendation algorithm was implemented with the values expressed through the reflection of meaning and similarity test between texts, which are characteristics of the Word2Vec model. Through Word2Vec's learning results, problem recommendations were conducted using text similarity values, and problems with high similarity can be recommended. In the experimental process, it was seen that the accuracy decreased with the quantitative amount of data, and it was confirmed that the larger the amount of data in the data set, the higher the accuracy.

• The Journal of the Acoustical Society of Korea
• /
• v.29 no.1
• /
• pp.82-90
• /
• 2010

This paper proposes an efficient method to enhance the quality of synthesized speech in HMM based speech synthesis system. The proposed method trains spectral parameters and excitation signals using Gaussian mixture model, and estimates appropriate excitation signals from spectral parameters during the synthesis stage. Both WB-PESQ and MUSHRA results show that the proposed method provides better speech quality than conventional HMM based speech synthesis system.

• Proceedings of the Korean Society of Broadcast Engineers Conference
• /
• 2010.07a
• /
• pp.216-219
• /
• 2010

최근 기존의 지상파 DMB와 역호환성을 유지하면서 전송속도를 증대시켜, 비디오 서비스의 품질을 증대시키거나, 다른 서비스들을 추가로 제공할 수 있는 새로운 이동멀티미디어 방송을 위한 전송기술이 개발되었으며, '고전송율 지상파 디지털멀티미디어방송(AT-DMB)' 이라 명명되었다. 현재 고전송율 지상파 디지털멀티미디어방송의 상용화 서비스를 위한 필트 테스트가 진행 중이며, 이를 이용한 신규서비스 개발이 추진되고 있다. 본 논문은 고전송율 지상파 디지털멀티미디어방송 시스템을 이용하여 제공할 수 있는 모바일 멀티미디어 서비스들을 제안한다. 이를 위해 고전송율 지상파 디지털멀티미디어방송의 전송 특성을 분석하였으며, 이를 이용해 제공될 수 있는 모바일 멀티미디어 서비스 모델들을 포함한다.

• Proceedings of the Korea Multimedia Society Conference
• /
• 2002.05d
• /
• pp.574-578
• /
• 2002

층 단위로 가공하는 RP(Rapid Prototype) 시스템에서 가공되는 물체의 표면에서는 계단형의 윤곽이 나타난다. 이러한 문제점을 보완하기 위해 경사절단 방법으로 3D 모델을 가공하여 기존의 가공방법에 의해 발생하는 계단형 윤곽 모습과 표면 왜곡 둥의 문제를 보완할 수 있다. 최적의 경사선분의 집합을 구하기 위해 경사절단 선분의 길이와 중간층 점의 거리를 정의하여 이를 최소화하는 에너지 함수를 구현한다. 그러나 이 방법은 경사절단 선분이 에너지가 작아지는 방향으로만 움직이기 때문에 레이어의 윤곽이 복잡한 경우 최적의 위치가 아닌 다른 위치에서 더 이상 움직이지 않는 국부적 최적해(Local Minima)가 발생할 수 있다. 본 논문에서는 국부적 최적해를 벗어나기 위해 경사절단 선분 추출 알고리즘에 시뮬레이티드 어니얼링(Simulated Annealing) 방법을 적용하였다. 제안된 방법으로 테스트한 결과 복잡한 레이어 윤곽에서 생길 수 있는 국부적 최적해가 어느 정도 해결되었다.

• Annual Conference on Human and Language Technology
• /
• 2018.10a
• /
• pp.605-607
• /
• 2018

본 논문에서는 음절 임베딩과 양방향 LSTM-CRF 모델을 이용한 한국어 문장 자동 띄어쓰기 시스템을 제안한다. 문장에 대한 자질 벡터 표현을 위해 문장을 구성하는 음절을 Unigram 및 Bigram으로 나누어 각 음절을 연속적인 벡터 공간에 표현하고, 양방향 LSTM을 이용하여 현재 자질에 양방향 자질들과 의존성을 부여한 새로운 자질 벡터를 생성한다. 이 새로운 자질 벡터는 전방향 신경망과 선형체인(Linear-Chain) CRF를 이용하여 최적의 띄어쓰기 태그 열을 예측하고, 생성된 띄어쓰기 태그를 기반으로 문장 자동 띄어쓰기를 수행하였다. 문장 13,500개와 277,718개 어절로 이루어진 학습 데이터 집합과 문장 1,500개와 31,107개 어절로 이루어진 테스트 집합의 학습 및 평가 결과는 97.337%의 음절 띄어쓰기 태그 분류 정확도를 보였다.

• Proceedings of the KIEE Conference
• /
• 2015.07a
• /
• pp.157-158
• /
• 2015

본 논문은 직렬 보상 커패시터 사용으로 인해 발생될 수 있는 SSR(Subsynchronous Resonance) 현상을 해석하기 위한 도구로서 EMTDC의 활용에 관해 다루고 있다. EMTDC를 이용한 순시치 기반의 계통 해석은 주파수 스캔이나 Eigenvalue 계산법의 한계를 보완할 수 있다. EMTDC 기반 해석의 효용성을 검증하기 위해 IEEE 2nd Benchmark 모델을 PSCAD/EMTDC로 구현하였고, 시뮬레이션을 통해 유도 발전기 효과와 비틀림 상호작용 및 축 토크 증폭 현상을 검증했다. 또한, SSR의 억제 수단으로 SVC와 보조제어기를 발전기단에 투입하였고, 그 억제 효과를 시뮬레이션으로 검증하였다.