• 전산구조공학
• /
• 제10권2호
• /
• pp.273-281
• /
• 1997

대량의 복잡한 비선형적인 관계도 단순화의 과정 없이 연관 관계를 자체 조직화 할 수 있는 인간의 뇌와 가장 유사한 병렬 연산 모델인 인공 신경 회로망을 구조 해석 분야에 도입하였다. 본 논문은 스터브 거더의 거동 예측을 위한 신경망 근사해석 모델 개발을 궁극적인 목적으로 하는 기초적 연구로서, 단순 보의 처짐 문제와 같은 정확해를 구할 수 있는 문제로부터 신경망 근사해석모델의 원형 (prototype)을 제시하고 검증하는데 목적이 있다.

• 한국감성과학회:학술대회논문집
• /
• 한국감성과학회 1998년도 추계학술발표 논문집
• /
• pp.189-194
• /
• 1998

Design factors are very important and deterministic in determining the first impression of products and environment. The final 30 number of channel button were chosen as a design factors at the Audio Unit. Then, we made the 8 types of prototype. with combining the design factors for experiment. Subjects rated the SD(Semantic Differential) evaluation sheets which have the 30 adjectives after watching each prototype. With the evaluated values, we simulated to identify the relation between the design factors and the adjectives using Neural Network. As a results, we could abstract the affective adjectives on each 8 types. Therefore, this research suggested the possibilities that we can infer the optimal design factors and types using Neural Network, if adjectives were given.

• 대한기계학회:학술대회논문집
• /
• 대한기계학회 2008년도 추계학술대회A
• /
• pp.894-899
• /
• 2008

Measured sensor datum from a quadruped robotics is commonly used for recognizing physical environment information which controls the posture of robotics. We can advance the ambulation with this sensed information and need to synthesize various sensors for obtaining accurate data, but most of these sensors are expensive and require excessive load for the operation. Those defects can be serious problem when it comes to the prototype's practicality and mass production, and maintenance of the system. This paper suggests virtual sensor technology for avoiding previous defects and presents ways to apply a theory to a walking robotics through virtual sensor information which is trained with several kinds of actual sensor information from the prototype system; the general algorithm is initially based on the neural network theory of back propagation. In specific, we verified a possibility of replacing the virtual sensor with the actual one through a reaction force measurement experiment.

• 대한전기학회:학술대회논문집
• /
• 대한전기학회 1992년도 하계학술대회 논문집 A
• /
• pp.46-48
• /
• 1992

Through the last 20 years' study, it is a well-known fact that symbolic approach has limitations in generating a new concept from given concepts. Hence, neural networks having a role of associative memory based on dynamical activation of neurons attract AI scientists' attention. In this paper, recent trials for combining neural networks and Artificial Intelligent systems are systematically reviewed and a prototype ENEDB(Experimental Neuro Expert DataBase) system built on HP9000/300 workstation is introduced to show the possibility of using the trials for real applications.

• 제어로봇시스템학회:학술대회논문집
• /
• 제어로봇시스템학회 2001년도 ICCAS
• /
• pp.43.5-43
• /
• 2001

This paper considers a new synthesis of the optimally performing brain-state-in-a-box (BSB) neural associative memory given a set of prototype patterns to be stored as asymptotically stable equilibrium points with the large and uniform size of the domain of attraction (DOA). First, we propose a new theorem that will be used to provide a guideline in design of the BSB neural associative memory. Finally, a design example is given to illustrate the proposed approach and to compare with existing synthesis methods.

• Journal of Electrical Engineering and Technology
• /
• 제12권4호
• /
• pp.1548-1555
• /
• 2017

This paper attempts to employ and investigate neural based approaches as interpolation tools for modeling of Switched Reluctance Motor (SRM) drive. Precise modeling of SRM is essential to analyse the performance of control strategies for variable speed drive application. In this work the suitability of Generalized Regression Neural Network (GRNN) and Extreme Learning Machine (ELM) in addition to conventional neural network are explored for improving the modeling accuracy of SRM. The neural structures are trained with the data obtained by modeling of SRM using Finite Element Analysis (FEA) and the trained neural network is incorporated in the model of SRM drive. The results signify the modeling accuracy with GRNN model. The closed loop drive simulation is performed in MATLAB/Simulink environment and the closeness of the results in comparison with the experimental prototype validates the modeling approach.

• 제어로봇시스템학회:학술대회논문집
• /
• 제어로봇시스템학회 2000년도 제15차 학술회의논문집
• /
• pp.19-19
• /
• 2000

This paper introduces a new scheme for neural network classifier which can describe the shape of patterns in clustered group by using a self-organizing teeming algorithm. The prototype based neural network classifier can not describe the shape of group and it has low classification performance when the data groups are complex. To improve above-mentioned problem, new neural scheme is introduced. This proposed neural network algorithm can be regarded as the extension of self-organizing feature map which can describe The experimental results shows that the proposed algorithm can describe the shape of pattern successfully.

• 제어로봇시스템학회:학술대회논문집
• /
• 제어로봇시스템학회 2004년도 ICCAS
• /
• pp.2037-2040
• /
• 2004

In this paper we introduce a new prototype based classifiers for overlapping data, where training pattern can be overlap on the feature space. The proposed classifier is based on the prototype from neural network classifier (NNC)[1] for overlap data. The method automatically chooses the initial center and two radiuses for each class. The center is used as a mean representative of training data for each class. The unclassified pattern is classified by measure distance from the class center. If the distance is in the lower (shorter radius) the unknown pattern has the high percentage of being in this class. If the distance is between the lower and upper (further radius), the pattern has the probability of being in this class or others. But if the distance is outside the upper, the pattern is not in this class. We borrow the words upper and lower from the rough set to represent the region of certainty [3]. The training algorithm to find number of cluster and their parameters (center, lower, upper) is presented. The clustering result is tested using patterns from Thai handwritten letter and the clustering result is very similar to human eyes clustering.

• 한국통신학회논문지
• /
• 제29권12A호
• /
• pp.1333-1339
• /
• 2004

IS-95와 IMT-2000 시스템에서 사용되고 있는 여러 종류의 길쌈 부호기를 부호율 1/2, 구속장 3인 길쌈 부호기로 한정하여, neural network의 LVQ(Learning Vector Quantization)과 PVSL(Prototype Vector Selecting Logic)을 적용하여 비터비 복호기에서 사용되는 PM(Path Metric)과 BM(Branch Metric) 메모리 수와 산술$.$비교 연산량을 줄임으로써 시스템의 단순화와 순방향 복호를 가능하게 한다. 구속장의 확장성 여부와 관계없이 간단한 응용으로 기존의비터비 복호기에 적용할 수 있는 새로운 비터비 복호기의 구조와 적용 알고리즘을 제시하고, 제시된 비터비 복호기의 합리성을 VHDL 시뮬레이션으로 검증 후, 기존의 복호기와의 성능을 비교 분석한다.

• 대한전자공학회논문지TE
• /
• 제37권3호
• /
• pp.114-122
• /
• 2000

본 논문에서는 기존의 Fuzzy C-Means, Nearest Neighborring Classification, FMMCNN, Fuzzy -ART등에서 사용하였던 정형에 근거한 분류에서 유기될 수 있던 판단 오류를 최소화하기 위해 단 한가지의 형태적 특징을 갖고 있는 정형에 의존하지 않고 분류를 수행하는 방법을 제안하고i파 한다. 이를 위해 본 논문에서는 주어진 학습 데이터로 학습하는 과정에서 볼록 다면체를 적응적으로 생성하고 다면체의 구조를 수정하는 퍼지 신경회로망을 설계하였다. 따라서, 본 방법은 순차적으로 입력되는 데이터를 분류하여 패턴 유형들을 생성하는 기능을 갖게된다. 본 방법의 유용성을 증명하기 위해, Hyperbox를 정형으로 하는 FMMCNN과의 다양한 시뮬레이션 비교를 수행하였다.