• 대한전기학회:학술대회논문집
• /
• 대한전기학회 2000년도 하계학술대회 논문집 D
• /
• pp.2374-2376
• /
• 2000

In this paper, we propose an indirect vector control method using Adaptive Neuro-Fuzzy Inference System (ANFIS) parameter estimator. It estimates the rotor time constant when the indirect vector control of induction motor is applied. We use the stator current error that is difference between the current command and estimated current calculated from terminal voltage and current. And two induced current estimate equations are used in training ANFIS.The estimator is trained by the hybrid learning algorithm. Simulation results shows good performance under load disturbance and motor parameter variations.

• 상하수도학회지
• /
• 제23권2호
• /
• pp.241-249
• /
• 2009

It is well known that the trend of water demand in large-size water supply systems has been suddenly changed, and many expansions of water supply facilities become unnecessary. To be cost-effective, thus, politicians as well as many professionals lay stress on the adaptive management of water supply facilities. Failure in adapting to the new trend of demand is sure to be the most critical reason of unnecessary expansions. Hence, we try to develop the model and modeling procedure that do not depend on the old data of demand, and provide engineers with the fast learning process. To forecast water demand of Seoul, the Bayesian parameter estimation was applied, which is a representative method for statistical pattern recognition. It results that we can get a useful time-series model after observing water demand during 6 years, although trend of water demand were suddenly changed.

• 전기전자학회논문지
• /
• 제24권4호
• /
• pp.969-974
• /
• 2020

Research into hyper parameter optimization (HPO) has recently revived with interest in models containing many hyper parameters, such as deep neural networks. In this paper, we introduce the most widely used HPO methods, such as grid search, random search, and Bayesian optimization, and investigate their characteristics through experiments. The MNIST data set is used to compare results in experiments to find the best method that can be used to achieve higher accuracy in a relatively short time simulation. The learning rate and weight decay have been chosen for this experiment because these are the commonly used parameters in this kind of experiment.

• Journal of the Korean Data and Information Science Society
• /
• 제16권4호
• /
• pp.815-821
• /
• 2005

Among the various artificial neural networks the backpropagation network (BPN) has become a standard one. One of the components in a neural network is an activating function or a transfer function of which a representative function is a sigmoid. We have discovered that by updating the slope parameter of a sigmoid function simultaneous with the weights could improve performance of a BPN.

• 한국지능시스템학회:학술대회논문집
• /
• 한국퍼지및지능시스템학회 2001년도 춘계학술대회 학술발표 논문집
• /
• pp.101-104
• /
• 2001

This paper deals with the speed-up of interval regression neural network. We propose an improved method of adjusting the parameter alpha used in the interval regression neural network to improve the learning speed and regression performance. Finally, we provide numerical examples to evaluate the performance of the proposed method.

• 대한원격탐사학회지
• /
• 제34권5호
• /
• pp.811-827
• /
• 2018

본 연구의 목적은 다중시기 원격탐사 자료를 이용한 작물분류에서 기계학습 알고리즘과 딥러닝 알고리즘의 비교에 있다. 이를 위해 전라남도 해남군과 미국 Illinois 주의 작물 재배지를 대상으로 기계학습 알고리즘과 딥러닝 알고리즘에 대해 (1) 하이퍼파라미터와 (2) 훈련자료의 크기에 따른 영향을 비교 분석하였다. 비교 실험에는 기계학습 알고리즘으로 support vector machine(SVM)을 적용하고 딥러닝 알고리즘으로 convolutional neural network(CNN)를 적용하였다. 특히 CNN에서 2차원의 공간정보를 고려하는 2D-CNN과 시간차원을 확장한 구조의 3D-CNN을 적용하였다. 비교 실험 결과, 다양한 하이퍼파라미터를 고려해야 하는 CNN의 경우 SVM과 다르게 두 지역에서 정의된 하이퍼파라미터 값이 유사한 것으로 나타났다. 이러한 결과를 바탕으로 모델 최적화에 많은 시간이 소요되지만 최적화된 CNN 모델을 다른 지역으로 확장할 수 있는 전이학습의 적용 가능성이 높을 것으로 판단된다. 다음 훈련자료 크기에 따른 비교 실험 결과, SVM 보다 CNN에서 훈련자료 크기의 영향이 큰 것으로 나타났는데 특히 다양한 공간특성을 갖는 Illinois 주에서 이러한 경향이 두드러지게 나타났다. 또한 Illinois 주에서 3D-CNN의 분류 성능이 저하되는 것으로 나타났는데, 이는 모델 복잡도가 증가하면서 과적합의 영향이 발생한 것으로 판단된다. 즉 모델의 훈련 정확도는 높지만 다양한 공간특성이나 입력 자료의 잡음 효과 등으로 오히려 분류 성능이 저하된 것으로 나타났다. 이러한 결과는 대상 지역의 공간특성을 고려해 적절한 분류 알고리즘을 선택해야 하는 것을 의미한다. 또한 CNN에서 특히, 3D-CNN에서 일정 수준의 분류 성능을 담보하기 위해 다량의 훈련자료 수집이 필요하다는 것을 의미한다.

• 한국지능시스템학회논문지
• /
• 제25권1호
• /
• pp.15-21
• /
• 2015

커널에 대한 모수의 조절은 서포트 벡터 기계의 일반화 능력에 영향을 준다. 이와 같이 모수들의 적절한 값을 결정하는 것은 종종 어려운 작업이 된다. 서포트 벡터 회귀에서 이와 같은 모수들의 값을 결정하기 위한 부담은 앙상블 학습을 사용함으로써 감소시킬 수 있다. 그러나 대용량의 자료에 대한 문제에 직접적으로 적용하기에는 일반적으로 시간 소모적인 방법이다. 본 논문에서 서포트 벡터 회귀의 모수 조절에 대한 부담을 감소하기 위하여 원래 자료집합을 유한개의 부분집합으로 분해하는 방법을 제안하였다. 제안하는 방법은 대용량의 자료들인 경우와 특히 불균등 자료 집합에서 효율적임을 보일 것이다.

• 로봇학회논문지
• /
• 제15권4호
• /
• pp.385-391
• /
• 2020

As deep learning technology has been developed and applied to various fields, it is gradually changing from an existing single image based application to a video based application having a time base in order to recognize human behavior. However, unlike 2D CNN in a single image, 3D CNN in a video has a very high amount of computation and parameter increase due to the addition of a time axis, so improving accuracy in action recognition technology is more difficult than in a single image. To solve this problem, we investigate and analyze various techniques to improve performance in 3D CNN-based image recognition without additional training time and parameter increase. We propose a time base ensemble using the time axis that exists only in the videos and an ensemble in the input frame. We have achieved an accuracy improvement of up to 7.1% compared to the existing performance with a combination of techniques. It also revealed the trade-off relationship between computational and accuracy.

• 제어로봇시스템학회논문지
• /
• 제16권12호
• /
• pp.1220-1225
• /
• 2010

This paper proposes a novel active noise control (ANC) approach that uses an IIR filter and neural network techniques to effectively reduce interior noise. We construct a multiple-channel IIR filter module which is a linearly augmented framework with a generic IIR model to generate a primary control signal. A three-layer perceptron neural network is employed for establishing a secondary-path model to represent air channels among noise fields. Since the IIR module and neural network are connected in series, the output of an IIR filter is transferred forward to the neural model to generate a final ANC signal. A gradient descent optimization based learning algorithm is analytically derived for the optimal selection of the ANC parameter vectors. Moreover, re-estimation of partial parameter vectors in the ANC system is proposed for online learning. Lastly, we present the results of a numerical study to test our ANC methodology with realistic interior noise measurement obtained from Korean railway trains.

• 한국수자원학회:학술대회논문집
• /
• 한국수자원학회 2020년도 학술발표회
• /
• pp.170-170
• /
• 2020

Due to the development of technologies, complex computation of huge data set is possible with a prevalent personal computer. Therefore, machine learning methods have been widely applied in the hydrologic field such as regression-based regional frequency analysis (RFA). The main purpose of this study is to compare two frameworks of RFA based on the artificial neural network (ANN) models: quantile regression technique (QRT-ANN) and parameter regression technique (PRT-ANN). As an output layer of the ANN model, the QRT-ANN predicts quantiles for various return periods whereas the PRT-ANN provides prediction of three parameters for the generalized extreme value distribution. Rainfall gauging sites where record length is more than 20 years were selected and their annual maximum rainfalls and various hydro-meteorological variables were used as an input layer of the ANN model. While employing the ANN model, 70% and 30% of gauging sites were used as training set and testing set, respectively. For each technique, ANN model structure such as number of hidden layers and nodes was determined by a leave-one-out validation with calculating root mean square error (RMSE). To assess the performances of two frameworks, RMSEs of quantile predicted by the QRT-ANN are compared to those of the PRT-ANN.