• 한국지능시스템학회논문지
• /
• 제15권6호
• /
• pp.720-729
• /
• 2005

본 논문에서는 미지의 비선형 시스템을 제어하기 위해 웨이블릿 신경 회로망을 이용한 간접 적응 제어기를 설계한다. 제안 된 간접 적응 제어기는 웨이블릿 신경 회로망을 이용한 동정 모델과 제어기로 구성된다. 여기서 동정 모델과 제어기에 사용되는 웨이블릿 신경 회로망은 시간과 주파수에 대한 정보를 동시에 포함하는 웨이블릿의 특성을 가지고 있기 때문에 다층구조 신경회로망과 방사 기저 함수 신경회로망에 보다 더 빠른 수렴특성을 보인다. 웨이블릿 신경 회로망의 학습방법은 경사 하강법, 유전알고리듬, DNA 기법등 여러 가지가 있으나, 본 논문에서는 확장 칼만 필터를 기반으로 한 학습 방법을 제안한다. 확장 칼만 필터 학습 방법은 계산이 복잡하기는 하지만 학습되어 갱신되는 파라미터의 이전 데이터 정보를 이용하는 특성 때문에 매우 빠른 수렴 특성을 보인다. 본 논문에서는 Buffing 시스템과 1축 머니퓰레이터에 대한 컴퓨터 모치실험을 통해 제안한 확장 칼만 필터 학습 방법을 이용한 간접 적응 제어기가 일반적인 경사 하강법을 이용한 경우보다 우수함을 보인다.

• 한국정보전자통신기술학회논문지
• /
• 제6권4호
• /
• pp.243-248
• /
• 2013

In this thesis, we have designed the indirect adaptive controller using Dynamic Neural Units(DNU) for unknown nonlinear systems. Proposed indirect adaptive controller using Dynamic Neural Unit based upon the topology of a reverberating circuit in a neuronal pool of the central nervous system. In this thesis, we present a genetic DNU-control scheme for unknown nonlinear systems. Our method is different from those using supervised learning algorithms, such as the backpropagation (BP) algorithm, that needs training information in each step. The contributions of this thesis are the new approach to constructing neural network architecture and its training.

• The Korean Journal of Ecology
• /
• 제23권2호
• /
• pp.89-100
• /
• 2000

On community data. sampled in regular intervals on a long-term basis. artificial neural networks were implemented to extract information on characterizing patterns of community changes. The Adaptive Resonance Theory and Kohonen Network were both utilized in learning benthic macroinvertebrate communities in the Soktae Stream of the Suyong River collected monthly for three years. Initially, by regarding each monthly collection as a separate sample unit, communities were grouped into similar patterns after training with the networks. Subsequently, changes in communities in a sequence of samplings (e.g., two-month, four-month, etc.) were given as input to the networks. After training, it was possible to recognize new data set in line with the sampling procedure. Through the comparative study on benthic macroinvertebrates with these learning processes, patterns of community changes in chironomids diverged while those of the total benthic macro-invertebrates tended to be more stable.

• 한국방송∙미디어공학회:학술대회논문집
• /
• 한국방송∙미디어공학회 2020년도 추계학술대회
• /
• pp.234-236
• /
• 2020

Content-adaptive training and transmission of the model parameters of neural networks can boost up the SR performance with higher restoration fidelity. In this case, efficient transmission of neural network parameters are essentially needed. Thus, we propose a novel method of compressing the network model parameters based on the training of network model parameters in the sense that the residues of filter parameters and content loss are jointly minimized. So, the residues of filter parameters are only transmitted to receiver sides for different temporal portions of video under consideration. This is advantage for image restoration applications with receivers (user terminals) of low complexity. In this case, the user terminals are assumed to have a limited computation and storage resource.

• The Journal of Asian Finance, Economics and Business
• /
• 제7권2호
• /
• pp.169-180
• /
• 2020

Globalization has led to a dramatic increase in intercultural service encounters between services providers and customers from diverse cultural backgrounds. This paper explores the causal relationship between service employees‟ cultural intelligence and adaptive sales behavior in intercultural service encounters, and the mediating effect of cognitive and emotional empathy on this relationship. A quantitative survey methodology was utilized to collect data on 341 salespeople at duty-free shops located on Jeju Island, Korea. Data analysis was conducted using SPSS 18 and Amos 18. The results show that cultural intelligence has a significant impact on cognitive empathy, emotional empathy, and adaptive sales behavior. Cognitive empathy has a positive impact on adaptive sales behavior, whereas the relationship between emotional empathy and adaptive sales behavior is not significant. Additionally, cognitive empathy mediates the relationship of cultural intelligence and adaptive sales behavior. This study has useful managerial implications for employee selection, training, and development in service firms engaged in intercultural service encounters. This study extends prior research on intercultural service encounters by exploring the direct impact of cultural intelligence on intercultural adaptation and the mediating effect of empathy, suggesting the presence of a cognitive mechanism that plays a key role in the impact of cultural intelligence on adaptive sales behavior.

• The Journal of the Acoustical Society of Korea
• /
• 제13권1E호
• /
• pp.25-36
• /
• 1994

본 논문에서는 외부로부터 제공되는 학습데이타에 신경회로망의 자기적응화(self-adaptation)를 이룩하기 위한 접근론이 기술된다. 이러한 문제점은 신경회로망의 학습이론, 즉 현재의 학습 데이터에 적절한 신경회로망이 가중치 벡터들(weight vectors)의 개선 방법론에 기인된다. 이들에 관련된 문제점들의 이론적 검토와 아울러 신경회로망의 학습에 대한 근본적인 요소들이 재조명된다. 현재 가장 널리 이용되고 있는 후방 전달(back-propagation) 학습법과 비교함으로써, 본 연구에서 제안된 자기적응 학습법의 유용성과 우위성을 컴퓨터 모의시험 결과로 입증하게 된다.

• 한국통신학회논문지
• /
• 제36권6C호
• /
• pp.343-348
• /
• 2011

이 논문은 NFxLMS (normalized filtered-x least mean square) 적응 필터기반의 실시간 ANC (active noise control) 무선 헤드셋에 관해서 연구한다. RMS (root mean square) 지연 분포를 측정한 후 채널을 보정해서 학습시간을 줄이고, 학습 시간동안 NFxLMS 필터 계수를 갱신해서 잡음 제거 필터의 수렴속도를 개선하는 방법을 제안한다. 제안한 방법을 실제 잡음 환경에서 이용할 경우에 짧은 학습 시간과 빠른 수렴속도를 가지면서 기존 잡음 제거기와 비슷한 성능을 가지는 잡음 제거기를 구성할 수 있다.

• 한국공간정보시스템학회:학술대회논문집
• /
• 한국공간정보시스템학회 2002년도 춘계학술대회 논문집
• /
• pp.45-52
• /
• 2002

Artificial neural networks (ANN) have been successfully used for classifying remotely sensed imagery. However, ANN still is not the preferable choice for classification over the conventional classification methodology such as the maximum likelihood classifier commonly used in the industry production environment. This can be attributed to the ANN characteristic built-in stochastic process that creates difficulties in dealing with unequally represented training classes, and its training performance speed. In this paper we examined some practical aspects of training classes when using a back propagation neural network model for remotely sensed imagery. During the classification process of remotely sensed imagery, representative training patterns for each class are collected by polygons or by using a region-growing methodology over the imagery. The number of collected training patterns for each class may vary from several pixels to thousands. This unequally populated training data may cause the significant problems some neural network empirical models such as back-propagation have experienced. We investigate the effects of training over- or under- represented training patterns in classes and propose the pattern repopulation algorithm, and an adaptive alpha adjustment (AAA) algorithm to handle unequally represented classes. We also show the performance improvement when input patterns are presented in random fashion during the back-propagation training.

• International Journal of Fuzzy Logic and Intelligent Systems
• /
• 제8권1호
• /
• pp.31-36
• /
• 2008

This paper presents adaptive learning data of evolvable neural networks (ENNs) for time series prediction of nonlinear dynamic systems. ENNs are a special class of neural networks that adopt the concept of biological evolution as a mechanism of adaptation or learning. ENNs can adapt to an environment as well as changes in the enviromuent. ENNs used in this paper are L-system and DNA coding based ENNs. The ENNs adopt the evolution of simultaneous network architecture and weights using indirect encoding. In general just previous data are used for training the predictor that predicts future data. However the characteristics of data and appropriate size of learning data are usually unknown. Therefore we propose adaptive change of learning data size to predict the future data effectively. In order to verify the effectiveness of our scheme, we apply it to chaotic time series predictions of Mackey-Glass data.

• 제어로봇시스템학회:학술대회논문집
• /
• 제어로봇시스템학회 2005년도 ICCAS
• /
• pp.920-924
• /
• 2005

This paper presents adaptive learning data of evolvable neural networks (ENNs) for time series prediction of nonlinear dynamic systems. ENNs are a special class of neural networks that adopt the concept of biological evolution as a mechanism of adaptation or learning. ENNs can adapt to an environment as well as changes in the environment. ENNs used in this paper are L-system and DNA coding based ENNs. The ENNs adopt the evolution of simultaneous network architecture and weights using indirect encoding. In general just previous data are used for training the predictor that predicts future data. However the characteristics of data and appropriate size of learning data are usually unknown. Therefore we propose adaptive change of learning data size to predict the future data effectively. In order to verify the effectiveness of our scheme, we apply it to chaotic time series predictions of Mackey-Glass data.