• 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.

• 한국콘텐츠학회논문지
• /
• 제5권5호
• /
• pp.33-42
• /
• 2005

본 논문에서는 ART 신경회로망의 성능을 개선하기 위해, 불필요한 클러스터의 생성과 변화를 억제하여 효율적인 패턴 분류가 가능하도록 하는 학습 알고리즘을 제안한다. 또한, 패턴 분류의 정확성을 향상시키기 위해 한글의 구조적 특징을 이용한 위치추출 알고리즘을 적용하였다. 제안하는 학습 알고리즘은 현재 학습되는 패턴과 최초 패턴간의 일치도를 비교한 후 리세트 시스템을 작동케 한다. 그 결과, 신경회로 망은 이미 입력되었던 패턴이 다시 입력되어도 새로운 클러스터의 생성을 방지하여 오인식율을 줄이게 된다.

• 한국전기전자재료학회:학술대회논문집
• /
• 한국전기전자재료학회 2003년도 춘계학술대회 논문집 센서 박막재료 반도체 세라믹
• /
• pp.194-199
• /
• 2003

Depth error correction effect for maladjusted stereo cameras with calibrated pixel distance parameter is presented. The proposed neural network technique is the real time computation method based theory of inter-node diffusion for searching the safety distances from the sudden appearance-objects during the work driving. The main steps of the distance computation using the theory of stereo vision like the eyes of man is following steps. One is the processing for finding the corresponding points of stereo images and the other is the interpolation processing of full image data from nonlinear image data of objects. All of them request much memory space and time. Therefore the most reliable neural-network algorithm is derived for real-time matching of objects, which is composed of a dynamic programming algorithm based on sequence matching techniques.

• 정보보호학회논문지
• /
• 제12권3호
• /
• pp.129-139
• /
• 2002

인터넷의 확장에 따라서 네트워크를 통한 침입이 증가되고 있다. 이에 따라 네트워크를 통한 침입에 대하여 즉각적으로 탐지하고 대처하는 기술이 필요하게 되었다. 본 논문은 인터넷의 특성을 악용하여 침입하는 공격들을 탐지하기 위하여 Adaptive Resonance Theory2(ART2) 이론을 이용한다. 정상적인 packet과 여러 가지 공격툴을 사용하여 생산한 인위적인 공격 패킷에 대하여 ART2를 학습한 후 실험한 결과와 기존의 방식들과 비교 분석하였다.

• 한국도로학회지:도로
• /
• 제13권1호
• /
• pp.52-61
• /
• 2011

• 한국지반공학회:학술대회논문집
• /
• 한국지반공학회 2002년도 가을 학술발표회 논문집
• /
• pp.513-520
• /
• 2002

The stability analysis of rock slope can be predicted using a suitable field data but it cannot be predicted unless suitable field data was taken. In this study, artificial neural networks theory is applied to predict plane failure that has a few data. It is well known that human brain has the advantage of handling disperse and parallel distributed data efficiently. On the basis of this fact, artificial neural networks theory was developed and has been applied to various fields of science successfully In this study, error back-propagation algorithm that is one of the teaching techniques of artificial neural networks is applied to predict plane failure. In order to verify the applicability of this model, a total of 30 field data results are used. These data are used for training the artificial neural network model and compared between the predicted and the measured. The simulation results show the potentiality of utilizing the neural networks for effective safety factor prediction of plane failure. In conclusion, the well-trained artificial neural network model could be applied to predict the plane failure stability of rock slope.

• 한국정보처리학회논문지
• /
• 제2권3호
• /
• pp.417-424
• /
• 1995

본 논문에서는 정량화(Quantification) 문제를 MFT(Mean Field Theroy)를 통해서 해결하는 기법을 제안한다. 통계학에서 중요한 문제의 하나인 정량화 문제는 주어진 공간에서 대상들간의 유사성에 따라서 최적의 상태를 갖도록 하는 문제이다. 평균장 접근 방법에 기초한 한개의 변수로 표현되는 확률적 시뮬레이티드 아닐링을 제안하고 정량화 문제를 패널티(penalty) 파라메타 항을 첨가한 비한정된 최적화 문제로 변형하 여 MFT를 적용하였다. 또한 연속변수를 갖는 신경회로망에서 실제 값을 계산하는 것 보다 평균장 접근방법으로 계산하는것이 더 빠르게 계산될 수 있음을 확인하였다. 본 논문에서 제안한 방법이 실험결과 해석적인 방법보다 좋은 정량적 결과를 보였다.

• 대한건축학회연합논문집
• /
• 제20권6호
• /
• pp.17-23
• /
• 2018

The purpose of this study is to suggest 100MPa class ultra high strength concrete mix design model applying neural network theory, in order to minimize an effort wasted by trials and errors method until now. Mix design model was applied to each of the 70 data using binary binder, ternary binder and quaternary binder. Then being repeatedly applied to back-propagation algorithm in neural network model, optimized connection weight was gained. The completed mix design model was proved, by analyzing and comparing to value predicted from mix design model and value measured from actual compressive strength test. According to the results of this study, more accurate value could be gained through the mix design model, if error rate decreases with the test condition and environment. Also if content of water and binder, slump flow, and air content of concrete apply to mix design model, more accurate and resonable mix design could be gained.

• 한국건축시공학회:학술대회논문집
• /
• 한국건축시공학회 2022년도 봄 학술논문 발표대회
• /
• pp.156-157
• /
• 2022

The purpose of this study is to propose a 40MPa mortar mixed design model that applies the neural network theory to minimize wasted effort in trial and error. A mixed design model was applied to each of the 60 data using fly ash, blast furnace slag fine powder and thickened rice husk powder. And in the neural network model, the optimized connection weight was obtained by repeatedly applying it to the MATLAB. The completed mixed design model was demonstrated by analyzing and comparing the predicted values of the mixed design model with those measured in the actual compressive strength test. As a result of the mixed design verification experiment, the error rates of the double mixed non-cement mortar using blast furnace slag fine powder and rice husk powder at a height of 40MPa were 3.24% and 3.4%. Mixed with fly ash and rice husk powder had an error rate of 3.94% and 5.8%. The error rate of the triple mixed non-cement mortar of the rice husk powder, fly ash, and blast furnace slag fine powder was 2.5% and 5.1%.

• 한국정보통신학회논문지
• /
• 제10권1호
• /
• pp.206-211
• /
• 2006

수량화 문제는 n개의 성질을 갖는 m개의 개체들을 각 개체들의 유사도(similarity)를 가장 잘 반영하도록 p차원의 공간 상에 대응시키는 문제이다. 본 논문에서는 물리학에서의 열평형 상태(thermal equilibrium state)에서 분자시스템의 해석적 근사 움직임에 대한 이론인 평균장 이론(mean field theory)에 의한 분자의 평균 변화량 계산과 어닐링(annealing) 방법에 의한 평균장 신경회로망(mean field neural network)을 수량화 문제(quantification analysis problem)의 해결에 적용하였다. 그 결과, 제안한 최적화 응용기법 이 기존의 고유치 분석방법(eigen value analysis)에 비해 비용측면에서 좀 더 최적에 가까운 해답을 찾아낼 수 있음을 확인하였다.