• Journal of the Korean Institute of Intelligent Systems
• /
• v.8 no.2
• /
• pp.106-116
• /
• 1998

A position control algorithm of a flexible manipulator is studied. The proposed algorithm is based on an ACFAC(Automatic Constructed Fuzzy Adaptive Controller) system based on the neural network learning algorithms. The proposed system learns membership functions for input variables using unsupervised competitive learning algorithm and output information using supervised outstar learning algorithm. ACFAC does not need a dynamic modeling of the flexible manipulator. An ACFAC is designed that the end point of the flexible manipulator tracks the desired trajectory. The control input to the process is determined by error, velocity and variation of error. Simulation and experiment results show a robustness of ACFAC compared with the PID control and neural network algorithms.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.11 no.11
• /
• pp.4174-4181
• /
• 2010

This paper presents an adaptive scheduling algorithm for manufacturing processes with non-stationary rework probabilities. The adaptive scheduling scheme named by hybrid Q-learning algorithm is proposed in this paper making use of the non-stationary rework probability and coupling with artificial neural networks. The proposed algorithm is measured by mean tardiness and the extensive computational results show that the presented algorithm gives very efficient schedules superior to the existing dispatching algorithms.

• Annual Conference on Human and Language Technology
• /
• 2022.10a
• /
• pp.320-323
• /
• 2022

상호참조해결은 문서에서 명사, 대명사, 명사구 등의 멘션 후보를 식별하고 동일한 개체를 의미하는 멘션들을 찾아 그룹화하는 태스크이다. 딥러닝 기반의 한국어 상호참조해결 연구들에서는 BERT를 이용하여 단어의 문맥 표현을 얻은 후 멘션 탐지와 상호참조해결을 동시에 수행하는 End-to-End 모델이 주로 연구가 되었으며, 최근에는 스팬 표현을 사용하지 않고 시작과 끝 표현식을 통해 상호참조해결을 빠르게 수행하는 Start-to-End 방식의 한국어 상호참조해결 모델이 연구되었다. 최근에 한국어 상호참조해결을 위해 구축된 ETRI 데이터셋은 WIKI, QA, CONVERSATION 등 다양한 도메인으로 이루어져 있으며, 신규 도메인의 데이터가 추가될 경우 신규 데이터가 추가된 전체 학습데이터로 모델을 다시 학습해야 하며, 이때 많은 시간이 걸리는 문제가 있다. 본 논문에서는 이러한 상호참조해결 모델의 도메인 적응에 Continual learning을 적용해 각기 다른 도메인의 데이터로 모델을 학습 시킬 때 이전에 학습했던 정보를 망각하는 Catastrophic forgetting 현상을 억제할 수 있음을 보인다. 또한, Continual learning의 성능 향상을 위해 2가지 Transfer Techniques을 함께 적용한 실험을 진행한다. 실험 결과, 본 논문에서 제안한 모델이 베이스라인 모델보다 개발 셋에서 3.6%p, 테스트 셋에서 2.1%p의 성능 향상을 보였다.

• Proceedings of the Korean Institute of Communication Sciences Conference
• /
• 1990.06a
• /
• pp.671-674
• /
• 1990

• Journal of the Korea Society of Computer and Information
• /
• v.10 no.6 s.38
• /
• pp.187-194
• /
• 2005

The background subtraction method is mainly used for the real-time extraction and tracking of moving objects from image sequences. In the outdoor environment, there are many changeable environment factors such as gradually changing illumination, swaying trees and suddenly moving objects , which are to be considered for an adaptive processing. Normally, GMM(Gaussian Mixture Model) is used to subtract the background by considering adaptively the various changes in the scenes, and the adaptive GMMs improving the real-time Performance were Proposed and worked. This paper, for on-line background subtraction, employed the improved adaptive GMM, which uses the small constant for learning rate a and is not able to speedily adapt the suddenly movement of objects, So, this paper Proposed and evaluated the dynamic control method of a using the adaptive selection of the number of component distributions and the global variances of pixel values.

• Journal of KIISE:Computing Practices and Letters
• /
• v.16 no.10
• /
• pp.1000-1004
• /
• 2010

A large number of current language processing systems use a part-of-speech tagger for preprocessing. Most language processing systems required a tagger with the highest possible accuracy. Specially, the use of domain-specific advantages has become a hot issue in machine translation community to improve the translation quality. This paper addresses a method for customizing an HMM or LHMM based English tagger from general domain to specific domain. The proposed method is to semi-automatically customize the output and transition probabilities of HMM or LHMM using domain-specific raw corpus. Through the experiments customizing to Patent domain, our LHMM tagger adapted by the proposed method shows the word tagging accuracy of 98.87% and the sentence tagging accuracy of 78.5%. Also, compared with the general tagger, our tagger improved the word tagging accuracy of 2.24% (ERR: 66.4%) and the sentence tagging accuracy of 41.0% (ERR: 65.6%).

• Proceedings of the IEEK Conference
• /
• 2003.11a
• /
• pp.397-400
• /
• 2003

본 연구에서는 KM-Net(Hidden Markov Network)을 다양한 태스크에의 적용과 화자의 특성을 효과적으로 나타내기 위해 HM-Net 음성인식 시스템에 MLLR(Maximum Likelihood Linear Regression) 적응방법을 도입하였으며, HM-Net 학습 알고리즘을 개량하여 회귀클래스 생성방법을 제안한다. 제안방법은 PDT-SSS(Phonetic Decision Tree-based Successive State Splitting) 알고리즘의 문맥방향 상태분할에 의한 상태레벨 공유를 이용한 방법으로 새로운 화자로부터 문맥정보와 적응화 데이터의 발성 양에 의존하여 결정된 많은 적응 파라미터들을(평균, 분산) 자유롭게 제어할 수 있게 된다. 제안방법의 유효성을 확인하기 위해 국어공학센터(KLE) 452 음성 데이터와 항공편 예약관련 연속음성을 대상으로 인식실험을 수행한 결과, 전체적으로 음소인식의 경우 평균 34-37％, 단어인식의 경우 평균 9％, 연속음성인식의 경우 평균 7-8％의 인식성능 향상을 각각 보였다. 또한 적응화 데이터의 양에 따른 인식성능 비교에서, 제안방법을 적용한 인식 시스템이 적응 데이터의 양이 적은 경우에도 향상된 인식률을 보였으며. 잡음을 부가한 음성에 대한 적응화 실험에서도 향상된 인식성능을 보여 MLLR 적응방법의 특성을 만족하였다. 따라서 MLLR 적응방법을 도입한 HM-Net 음성인식 시스템에 제안한 회귀클래스 생성방법이 유효함을 확인한 수 있었다.

• Korean Journal of Cognitive Science
• /
• v.26 no.4
• /
• pp.377-392
• /
• 2015

Korean semantic role labeling (SRL) is usually performed by a machine learning and requires a lot of corpus. However, the Korean PropBank used in Korean SRL system is less than PropBank. It leads to a low performance. Therefore, we expand the annotated corpus and verb frames for Korean SRL system to expand the Korean PropBank corpus. Most of the SRL system have a domain-dependent performance so, the performance may decrease if domain was changed. In this paper, we use the domain adaptation technique to reduce decreasing performance with the existing corpus and the small size of new domain corpus. We apply the domain adaptation technique to Structural SVM and Deep Neural Network. The experimental result show the effectiveness of the domain adaptation technique.

• The KIPS Transactions:PartB
• /
• v.10B no.4
• /
• pp.397-402
• /
• 2003

This paper proposes an efficient fixed-point (FP) algorithm for improving performances of the independent component analysis (ICA) based on neural networks. The proposed algorithm is the FP algorithm based on Newton method for ICA using the adaptive learning parameters. The purpose of this algorithm is to improve the separation speed and performance by using the learning parameters in Newton method, which is based on the first order differential computation of entropy optimization function. The learning rate and the moment are adaptively adjusted according to an updating state of inverse mixing matrix. The proposed algorithm has been applied to the fingerprints and the images generated by random mixing matrix in the 8 fingerprints of 256${\times}$256-pixel and the 10 images of 512$\times$512-pixel, respectively. The simulation results show that the proposed algorithm has the separation speed and performance better than those using the conventional FP algorithm based on Newton method. Especially, the proposed algorithm gives relatively larger improvement degree as the problem size increases.

• Journal of Korea Multimedia Society
• /
• v.11 no.8
• /
• pp.1129-1137
• /
• 2008

E-learning as a new education trend is being applied not only to cyber school but also various education fields such as employee training for companies or interactive learning for consumers. Users of the E-learning can take online tests individually anywhere, to evaluate their achievement level. Because users who are taking the online tests may show their own IDs or passwords to others, the possibility of cheating is very high. Therefore, it is very important to authenticate the users. In this paper, we propose an adaptive-keyboard authentication method which depends on user behavior patterns through the use of IDs and passwords. This method does not need any additional devices or special effort. An adaptive method to update patterns in which IDs and passwords are entered was previously suggested and this new method has proved to be better than previous methods through simulations and implementation.