http://chineseinput.net/에서 pinyin(병음)방식으로 중국어를 변환할 수 있습니다.
변환된 중국어를 복사하여 사용하시면 됩니다.
정보통신서비스 분석을 통한 B-ISDN PLAZA 구축에 관한 연구
조용환,김태호,심영진 ( Yong Hwan Cho,Tae Ho Kim,Young Jin Shim ) 충북대학교 산업과학기술연구소 1995 산업과학기술연구 논문집 Vol.9 No.2
Abstract_Roman This paper aims at developing a scheme of demonstration to be performed at the R-ISDN Plaza which is regarded as a type of testbeds for B-ISDN service. More specifically, in the hope of providing an idea of maximizing the effectiveness of
심영진,박두환,김태우,지석준,이준탁 동아대학교 정보기술연구소 2000 情報通信硏究所論文誌 Vol.8 No.1
The stabilization control of Inverted Pendulum(IP) system is difficult because of its nonlinearity and structural unstability. Futhermore, a series of conventional techniques such as the pole placement and the optimal control based on the local linearizations have narrow stabilizable regions. At the same time, the fine tunings of their gain parameters are also troublesome. Thus, in this paper, an Evolving Neural Network Controller(ENNC) which its structure and its connection weights are optimized simultaneously by Real Variable Elitist Genetic Algorithm(RVEGA) was presented for stabilization of an IP system with nonlinearity. This proposed ENNC was described by a simple genetic chromosome. And the deletion of neuron, the determinations of input or output neuron, the deleted neuron and the activation functions types are given according to the various flag types. Therefore, the connection weights, its structure and the neuron types in the given ENNC can be optimized by the proposed evolution strategy. And the proposed ENNC was implemented successfully on the ADA-2310 data acquisition board and the P-III microprocessor in order to stabilize the nonlinear system. initial values and the external disturbances applied to pendulum. Its main hardwares were made of the ADA-2310 data acquisition board and the P-III microprocessor. Through the simulation and experimental results, we showed that the finally acquired optimal PENNC was very useful in the stabilization control of nonlinear(IP) system.
ANFIS에 의한 비선형 입·출력 관계의 퍼지구조 동정에 관한 연구
이준탁,심영진,김태우 東亞大學校 附設 情報通信硏究所 1996 情報通信硏究所論文誌 Vol.4 No.1
The characteristics of nonlinear dynamical system using fuzzy inference technique can be described by fuzzy modeling. Therefore, this paper introduce a technique for fuzzy structure identification of nonlinear input-output relationship using ANFIS (Adaptive Neuro-Fuzzy Inference System). And the simulation results of using ANFIS show its effectiveness for fuzzy structure identification of nonlinear system.
Evolving Neural Network Controller for Stabilization of Inverted Pendulum System
Shim, Young-Jin,Kim, Min-Sung,Lee, Joon-Tark 東亞大學校 大學院 2000 大學院論文集 Vol.25 No.-
도립전자 시스템은 대표적 비선형 시스템으로 특유의 구조적인 불안정성 및 비선형성으로 인해, 여러가지 제어 기법이 제안되고 있다. 그러나 이들은 파라미터의 변동에 민감하고 적절한 피드백 이득의 결정이 어려울 뿐만 아니라, 레일의 진동 및 경사 등 외란 발생 시에 안정화되지 못하는 결점을 갖고 있다. 이를 해결하고자 제안되어진 종래의 진화형 신경회로망(ENNC)은 연산량의 증대로 인한 연산 시간의 증가, 메모리 사용의 비효율성 등의 자체의 구조적인 문제점을 가지고 있다. 따라서, 본 논문에서는 도립전자 시스템의 안정화 제어를 위하여 선택, 교배, 돌연변이의 진화 연산자에 의해 일시에 최적의 구조와 결합가중치로 진화시켜 가는 새로운 형태의 ENNC를 제안하고자 한다. 또한, 시뮬레이션을 통해 다양한 초기치에 적응된 최적 구조와 결합가중치를 갖는 새로운 형태의 ENNC를 도립전자 시스템의 안정화 제어에 적용함으로써 본 논문에서 제안한 ENNC의 우수성과 강인성을 입증하고자 한다.
Vecuronium 과 Atracurium 에 의한 근이완으로부터 회복시 Neostigmine 이 TOF Ratio 에 미치는 영향
김순임,심영진,김선종,김성열,박욱 대한마취과학회 1996 Korean Journal of Anesthesiology Vol.30 No.6
Background: The train-of-four(TOF) fade known as expression of prejuntional receptor binding was useful for evaluating the residual neuromuscular blockade(NMB). The present study was undertaken to investigate the effect of the neostigmine(Neo) on TOF ratio during the recovery from vecuronium(V) or atracurium(A) induced NMB under the general anesthesia. Methods: Forty healthy adult patients were randomly divided into 4 groups as follows; spontaneous recovery from V-induced NMB(V-C group) or A-induced NMB(A-C group), reversed recovery with Neo at 20% recovery of control first twitch height(T₁) from V-induced NMB(V-R group) or A-induced NMB(A-R group). TOF ratio at 25 and 75% recovery of T₁ and recovery index(RI) defined as time from 25 to 75% recovery of T₁ were measured. Results: TOF ratios at 25 and 75% recovery of T₁ were 3.7 & 35.8%(V-C group), 8.4 & 46.9%(A-C group), 3.7 & 48.7%(V-R group) and 15.2 & 55.6%(A-R group) respectively(P$gt;0.05). RI were 19.2 min(V-C group), 19.5 min(A-C group), 3.5 min(V-R group), and 5.6 min(A-R group) respectively (P$lt;0.05). Conclusions: RI were significantly shortened in reversed recovery groups with Neo than spontaneous recovery groups (P$lt;0.05). However TOF ratio at 75% recovery of T₁ were not significantly different between spontaneous recovery and reversed recovery groups.