• 한국공작기계학회:학술대회논문집
• /
• 한국공작기계학회 2001년도 춘계학술대회 논문집(한국공작기계학회)
• /
• pp.239-243
• /
• 2001

Neural networks are used in the framework of sensorbased tracking control of robot manipulators. They learn by practice movements the relationship between PSD (an analog Position Sensitive Detector) sensor readings for target positions and the joint commands to reach them. Using this configuration, the system can track or follow a moving or stationary object in real time. Furthermore, an efficient neural network architecture has been developed for real time learning. This network uses multiple sets of simple backpropagation networks one of which is selected according to which division (corresponding to a cluster of the self-organizing feature map) in data space the current input data belongs to. This lends itself to a very training and processing implementation required for real time control.

• 제어로봇시스템학회:학술대회논문집
• /
• 제어로봇시스템학회 1992년도 한국자동제어학술회의논문집(국내학술편); KOEX, Seoul; 19-21 Oct. 1992
• /
• pp.129-134
• /
• 1992

Fuzzy theory has shown good control performance for non-linear system that is difficult to be controlled by the conventional controller. Backpropagation neural network can interpolate output without the priori knowledge of its dynamics. In this paper, we proposes a Fuzzy-Neural Controller. The Fuzzy Control by deterministic rule may not be sensitive for uncertain conditions and has a disadvantage of setting the rule by repeatedly experience. To solve such problems, we construct Self organizing Fuzzy-Neural Controller which can reorganize the fuzzy rule according to the state of system. Experimental results show that proposed Fuzzy-Neural Controller has better performance than conventional controller(PID) has especially rising time and overshoot characteristics.

• 전자공학회논문지C
• /
• 제35C권5호
• /
• pp.50-58
• /
• 1998

We propose an efficient face recognition system for controllinng the access to the restricted zone using both the face region detectors based on facial symmetry and the extended self-organizing maps (ESOM) which have sensory synapses and descriptive synapses. Based on the visual cues of the facial symmetry, we apply horizontal and vertical projections on elliptic regions detected by GHT(generalized hough transform) to identify all the face regions from the complex background.And we propose an ESOM which can exploit principal components and imitate an elastic similarity matching, to authenticate faces of the enlisted member. In order to cope with changes of facial experession or glasses wearing, etc, the facial descriptions of each member at the time of authentication are simultaneously updated on the discriptive synapses online using the incremental learning of the proposed ESOM. Experimental results prove the feasibility of our approach.

• Journal of Advanced Marine Engineering and Technology
• /
• 제26권5호
• /
• pp.581-588
• /
• 2002

A fuzzy learning control algorithm is proposed in this paper. In this method, two fuzzy controllers are used as a feedback and a feedforward type. The fuzzy feedback controller can be designed using simple knowledge for the controlled system. On the other hand, the fuzzy feedforward controller has a self-organizing mechanism and therefore, it does not need any knowledge in advance. The effectiveness of the proposed algorithm is demonstrated by experiment on the position and force control problem of a parallelogram type robot manipulator with two degrees of freedom. It is shown that the rapid learning and the robustness can be achieved by adopting the proposed method.

• 한국공작기계학회:학술대회논문집
• /
• 한국공작기계학회 2000년도 추계학술대회논문집 - 한국공작기계학회
• /
• pp.108-112
• /
• 2000

Neural networks are used in the framework of sensorbased tracking control of robot manipulators. They learn by practice movements the relationship between PSD (an analog Position Sensitive Detector) sensor readings for target positions and the joint commands to reach them. Using this configuration, the system can track or follow a moving or stationary object in real time. Furthermore, an efficient neural network architecture has been developed for real time learning. This network uses multiple sets of simple backpropagation networks one of which is selected according to which division (corresponding to a cluster of the self-organizing feature map) in data space the current input data belongs to. This lends itself to a very training and processing implementation required for real time control.

• 한국지능정보시스템학회:학술대회논문집
• /
• 한국지능정보시스템학회 2004년도 추계학술대회
• /
• pp.331-339
• /
• 2004

The preferences of customers change over time. However, existing collaborative filtering (CF) systems are static, since they only incorporate information regarding whether a customer buys a product during a certain period and do not make use of the purchase sequences of customers. Therefore, the quality of the recommendations of the typical CF could be improved through the use of information on such sequences. In this paper, we propose a new methodology for enhancing the quality of CF recommendation that uses customer purchase sequences. The proposed methodology is applied to a large department store in Korea and compared to existing CF techniques. Various experiments using real-world data demonstrate that the proposed methodology provides higher quality recommendations than do typical CF techniques, with better performance, especially with regard to heavy users.

• 한국지능정보시스템학회:학술대회논문집
• /
• 한국지능정보시스템학회 2005년도 춘계학술대회
• /
• pp.186-189
• /
• 2005

본 논문에서는 LVQ를 퍼지화한 새로운 퍼지 학습 법칙들을 제안하였다. 퍼지 LVQ 학습법칙 1은 기존의 학습률 대신에 퍼지 학습률을 사용하였는데 이는 조건 확률의 퍼지화에 기반을 두고 있다. 퍼지 LVQ 학습법칙 2는 클래스들 사이에 존재하는 입력벡터가 결정 경계선에 대한 정보를 더 가지고 있는 것을 반영한 것이다. 이 새로운 퍼지 학습 법칙들을 improved IAFC(Integrted Adaptive Fuzzy Clustering)신경회로망에 적용하였다. improved IAFC신경회로망은 ART-1 (Adaptive Resonance Theory)신경회로망과 Kohonen의 Self-Organizing Feature Map의 장점을 취합한 퍼지 신경회로망이다. 제안한 supervised IAFC 신경회로망 1과 supervised IAFC neural 신경회로망 2의 성능을 오류 역전파 신경회로망의 성능과 비교하기 위하여 iris 데이터를 사용하였는데 Supervised IAFC neural network 2가 오류 역전파 신경회로망보다 성능이 우수함을 보여주었다.

• 한국지능시스템학회논문지
• /
• 제12권3호
• /
• pp.246-254
• /
• 2002

In this paper auto-tuning scheme of PID controller based on the reference model has been studied for a Process control system by immune algorithm. Up to this time, many sophisticated tuning algorithms have been tried in order to improve the PID controller performance under such difficult conditions. Also, a number of approaches have been proposed to implement mixed control structures that combine a PID controller with fuzzy logic. However, in the actual plant, they are manually tuned through a trial and error procedure, and the derivative action is switched off. Therefore, it is difficult to tune. Since the immune system possesses a self organizing and distributed memory, it is thus adaptive to its external environment and allows a PDP (Parallel Distributed Processing) network to complete patterns against the environmental situation. Simulation results reveal that reference model basd tuning by immune network suggested in this paper is an effective approach to search for optimal or near optimal process control.

• 한국지능정보시스템학회:학술대회논문집
• /
• 한국지능정보시스템학회 2000년도 추계정기학술대회:지능형기술과 CRM
• /
• pp.479-488
• /
• 2000

다양한 재무정보를 이용하여 기업간 경쟁적 벤치마킹을 수행하는 것은 매우 어려운 작업인 동시에 분석에 상담한 시간이 소요된다. 본 연구에서는 재무정보를 이용한 기업간 경쟁적 벤치마킹을 효과적으로 수행하기 위하여 대표적인 자율신경망 모형인 자기조직화 신경망을 분석에 이용하였다. 자기조직화 신경망은 다차원적인 재무자료를 2차원 출력 공간으로 투영함으로써 결과를 시각화하는데 매우 효과적이며, 시각화된 결과는 재무적인 경쟁우위에 따라 기업을 군집화함으로써 효과적인 경쟁적 벤치마킹을 수행할 수 있도록 한다. 본 연구에서는 1998년. 1999년, 그리고 2000년 상반기까지의 국내 제조업체 재무구조 분석사례에 자기조직화 신경함을 적용하여 재무적 경쟁우위에 따른 기업들의 군집화 모형으로서의 가능성을 제시하였다.

• 한국콘텐츠학회논문지
• /
• 제10권2호
• /
• pp.462-480
• /
• 2010

특허분석은 전 세계적으로 축적된 특허 데이터베이스로부터 기업의 연구개발 전략에 필요한 지식을 추출하는 것이다. 현재까지 특허출원 결과를 분석하여 해당기술에 대한 기술동향과 전개과정을 파악하여 향후 개발될 기술에 대한 방향정립을 위하여 특허분석은 필요한 결과를 제공한다. 본 논문에서는 특허분석과 관련된 방법 및 시스템에 대한 기술 분류를 수행하고 관련된 국내특허와 미국특허, 그리고 IEEE 논문을 조사하고 분석한다. 특허분석시스템은 기술 분야의 특성상 특허출원뿐만 아니라 연구결과의 논문발표도 활발히 이루어지고 있다. 본 연구에서 선정된 검색어를 통하여 최종적으로 검색된 결과를 이용하여 기술 분류에 따른 분석을 실시한다. 유효한 전체 특허와 논문을 대상으로 특허분석시스템에 필요한 공백기술을 찾아내기 위하여 매트릭스분석을 수행한다. 현재까지 등록된 특허분석시스템에 대한 기술발전 동향을 파악하고 앞으로 필요한 특허분석시스템 관련 기술발전 방향도 제시한다. 통계적 검정과 자기조직화 지도를 이용하여 유효 특허와 논문을 정량적으로 분석하여 국내특허, 미국특허, 그리고 논문 내에서 상대적으로 개발이 취약한 기술을 찾아내고 이에 대한 개발의 필요성도 함께 제시한다.