• 전자공학회논문지B
• /
• 제28B권10호
• /
• pp.831-841
• /
• 1991

A combined model of probabilistic and MLP(multi layer perceptron) model is proposed for the pattern classification of EMG( electromyogram) signals. The MLP model has a problem of not guaranteeing the global minima of error and different quality of approximations to Bayesian probabilities. The probabilistic model is, however, closely related to the estimation error of model parameters and the fidelity of assumptions. A proper combination of these will reduce the effects of the problems and be robust to input variations. Proposed model is able to get the MAP(maximum a posteriori probability) in the probabilistic model by estimating a priori probability distribution using the MLP model adaptively. This method minimize the error probability of the probabilistic model as long as the realization of the MLP model is optimal, and this is a good combination of the probabilistic model and the MLP model for the usage of MLP model reliability. Simulation results show the benefit of the proposed model compared to use the Mlp and the probabilistic model seperately and the average calculation time fro classification is about 50ms in the case of combined motion using an IBM PC 25 MHz 386model.

• 대한기계학회논문집A
• /
• 제36권4호
• /
• pp.379-386
• /
• 2012

본 논문의 주 목적은 확률변수의 잔차를 이용하여 제안된 확률론적 피로균열전파모델들을 평가하고 Mg-Al-Zn 합금의 확률론적 피로거동을 묘사하기에 적합한 모델을 제시하는 것이다. 제안된 모델은 '확률론적 Paris-Erdogan 모델', '확률론적 Walker 모델', '확률론적 Forman 모델'과 '확률론적 수정 Forman 모델'이다. 이 모델들은 실험적 피로균열전파모델인 Paris-Erdogan 모델, Walker 모델, Forman 모델과 수정 Forman 모델에 확률변수를 도입하여 준비하였다. Mg-Al-Zn 합금의 피로균열전파거동을 묘사하기에 적합한 모델은 일반적으로 '확률론적 Paris-Erdogan 모델'과 '확률론적 Walker 모델'임을 밝혔으며, 시편두께 9.45mm 에서는 '확률론적 Forman 모델'이 적합하였다.

• 한국농공학회논문집
• /
• 제56권1호
• /
• pp.11-20
• /
• 2014

Many classification studies for the community of densely-connected nodes are limited to the comprehensive analysis for detecting the communities in probabilistic networks with nodes and edge of the probabilistic distribution because of the difficulties of the probabilistic operation. This study aims to use convolution method for operating nodes and edge of probabilistic distribution. For the probabilistic hierarchy network with nodes and edges of the probabilistic distribution, the model of this study detects the communities of nodes to make the new probabilistic distribution with two distribution. The results of our model was verified through comparing with Monte-carlo Simulation and other community-detecting methods.

• Geomechanics and Engineering
• /
• 제18권6호
• /
• pp.595-603
• /
• 2019

A modified model combining Kriging and Monte Carlo method (MC) is proposed for probabilistic estimation of tunnel face stability in this paper. In the model, a novel uniform design is adopted to train the Kriging, instead of the existing active learning function. It has advantage of avoiding addition of new training points iteratively, and greatly saves the computational time in model training. The kinematic approach of limit analysis is employed to define the deterministic computational model of face failure, in which the Hoek-Brown failure criterion is introduced to account for the nonlinear behaviors of rock mass. The trained Kriging is used as a surrogate model to perform MC with dramatic reduction of calls to actual limit state function. The parameters in Hoek-Brown failure criterion are considered as random variables in the analysis. The failure probability is estimated by direct MC to test the accuracy and efficiency of the proposed probabilistic model. The influences of uncertainty level, correlation relationship and distribution type of random variables are further discussed using the proposed approach. In summary, the probabilistic model is an accurate and economical alternative to perform probabilistic stability analysis of tunnel face excavated in spatially random Hoek- Brown media.

• 대한의용생체공학회:학술대회논문집
• /
• 대한의용생체공학회 1991년도 춘계학술대회
• /
• pp.65-70
• /
• 1991

A hybrid model which uses a probabilistic model and a MLP(multi layer perceptron) model for pattern recognition of EMG(electromyogram) signals is proposed in this paper. MLP model has problems which do not guarantee global minima of error due to learning method and have different approximation grade to bayesian probabilities due to different amounts and quality of training data, the number of hidden layers and hidden nodes, etc. Especially in the case of new test data which exclude design samples, the latter problem produces quite different results. The error probability of probabilistic model is closely related to the estimation error of the parameters used in the model and fidelity of assumtion. Generally, it is impossible to introduce the bayesian classifier to the probabilistic model of EMG signals because of unknown priori probabilities and is estimated by MLE(maximum likelihood estimate). In this paper we propose the method which get the MAP(maximum a posteriori probability) in the probabilistic model by estimating the priori probability distribution which minimize the error probability using the MLP. This method minimize the error probability of the probabilistic model as long as the realization of the MLP is optimal and approximate the minimum of error probability of each class of both models selectively. Alocating the reference coordinate of EMG signal to the outside of the body make it easy to suit to the applications which it is difficult to define and seperate using internal body coordinate. Simulation results show the benefit of the proposed model compared to use the MLP and the probabilistic model seperately.

• 한국산업정보학회논문지
• /
• 제9권1호
• /
• pp.36-42
• /
• 2004

본 논문은 벡터모델과 확률모델의 성능 비교에 관한 연구이다. 벡터모델로써는 잠재적 의미를 적용한 검색 결과를 찾기 위해 사용되는 LSI 모델을 이용하였다. 확률모델로써는 현재 상용화 단계에 있는 콘도르 정보검색 시스템을 적용하였다. 각 모델 시스템의 검색 성능 비교를 위한 실험은 사용자가 입력한 원래 질의어에 관한 검색 결과를 바탕으로 성능을 비교한 후에, 사전적 의미를 적용한 확장 질의어에 대한 검색 결과를 추가하여 비교하였다. 본 연구에서는 입력된 질의어와 관련된 용어를 추가하여 검색하였을 경우, 확률모델에 비해 벡터모델에서 성능이 대부분의 질의어에 대해서 향상됨을 보인다.

• 한국농공학회지
• /
• 제38권2호
• /
• pp.108-122
• /
• 1996

This study was to introduced estimation model for optimum probabilistic rainfall intensity on hydrological area. Originally, probabilistic rainfall intensity formula have been characterized different coefficient of formula and model following watersheds. But recently in korea rainfall intensity formula does not use unionize applyment standard between administration and district. And mingle use planning formula with not assumption model. Following the number of year hydrological duration adjust areal index. But, with adjusting formula applyment was without systematic conduct. This study perceive the point as following : 1) Use method of excess probability of Iwai to calculate survey rainfall intensity value. 2) And, use method of least squares to calculate areal coefficient for a unit of 157 rain gauge station. And, use areal coefficient was introduced new probabilistic rainfall intensity formula for each rain gauge station. 3) And, use new probabilistic rainfall intensity formula to adjust a unit of fourteen duration-a unit of fifteen year probabilistic rainfall intensity. 4) The above survey value compared with adjustment value. And use three theory of error(absolute mean error, squares mean error, relative error ratio) to choice optimum probabilistic rainfall intensity formula for a unit of 157 rain gauge station.

• 대한기계학회논문집A
• /
• 제39권1호
• /
• pp.63-69
• /
• 2015

본 논문의 주 목적은 최대하중조건을 변화시키면서 확률변수의 잔차를 이용하여 확률론적 피로균열전파모델들을 평가하고, Mg-Al-Zn 합금의 피로균열성장거동의 변동성을 묘사하기에 적합한 확률론적 모델을 제시하는 것이다. 평가에 사용된 모델은 피로균열성장의 변동성을 나타내기 위하여 실험적 피로균열전파모델인 Paris-Erdogan 모델, Walker 모델, Forman 모델과 수정 Forman 모델에 확률변수를 도입한 모델이다. 최대하중조건에 따른 Mg-Al-Zn 합금의 피로균열전파거동의 확률적 변동성을 묘사하기에 적합한 모델은 '확률론적 Paris-Erdogan 모델'과 '확률론적 Walker 모델'임을 밝혔으며, 최대하중조건이 피로균열성장의 확률적 변동성에 미치는 영향 또한 고찰하였다.

• 대한전기학회논문지:전력기술부문A
• /
• 제50권9호
• /
• pp.431-439
• /
• 2001

This Paper illustrates a new numerical analysis method using a nodal effective load model for nodal probabilistic production cost simulation of the load point in a composite power system. The new effective load model includes capacities and uncertainties of generators as well as transmission lines. The CMELDC(composite power system effective load duration curve) based on the new effective load model at HLll(Hierarchical Level H) has been developed also. The CMELDC can be obtained from convolution integral processing of the outage capacity probabilistic distribution function of the fictitious generator and the original load duration curve given at the load point. It is expected that the new model for the CMELDC proposed in this study will provide some solutions to many problems based on nodal and decentralized operation and control of an electric power systems under competition environment in future. The CMELDC based on the new model at HLll will extend the application areas of nodal probabilistic production cost simulation, outage cost assessment and reliability evaluation etc. at load points. The characteristics and effectiveness of this new model are illustrated by a case study of MRBTS(Modified Roy Billinton Test System).

• Communications for Statistical Applications and Methods
• /
• 제24권1호
• /
• pp.67-80
• /
• 2017

Over the last few decades, ensemble forecasts based on global climate models have become an important part of climate forecast due to the ability to reduce uncertainty in prediction. Moreover in ensemble forecast, assessing the prediction uncertainty is as important as estimating the optimal weights, and this is achieved through a probabilistic forecast which is based on the predictive distribution of future climate. The Bayesian model averaging has received much attention as a tool of probabilistic forecasting due to its simplicity and superior prediction. In this paper, we propose a new Bayesian model averaging method for probabilistic ensemble forecasting. The proposed method combines a deterministic ensemble forecast based on a multivariate regression approach with Bayesian model averaging. We demonstrate that the proposed method is better in prediction than the standard Bayesian model averaging approach by analyzing monthly average precipitations and temperatures for ten cities in Korea.