• 한국농업기계학회:학술대회논문집
• /
• 한국농업기계학회 1993년도 Proceedings of International Conference for Agricultural Machinery and Process Engineering
• /
• pp.1273-1281
• /
• 1993

Estimation of daily and seasonal evaportranspiration is essential for water resource planning irrigation feasibility study, and real-time irrigation water management . This paper is to evaluate the applicability of neural networks to the estimation of evapotranspiration . A neural network was developed to forecast daily evapotranspiration of the rice crop. It is a three-layer network with input, hidden , and output layers. Back-propagation algorithm with delta learning rule was used to train the neural network. Training neural network wasconducted usign daily actural evapotranspiration of rice crop and daily climatic data such as mean temperature, sunshine hours, solar radiation, relative humidity , and pan evaporation . During the training, neural network parameters were calibrated. The trained network was applied to a set of field data not used in the training . The created response of the neural network was in good agreement with desired values. Evaluating the neural networ performance indicates that neural network may be applied to the estimation of evapotranspiration of the rice crop.

• 방송공학회논문지
• /
• 제26권6호
• /
• pp.748-757
• /
• 2021

본 논문은 눈 랜드마크 위치 검출과 시선 방향 벡터 추정이 하나의 딥러닝 네트워크로 통합된 시선 추정 네트워크를 제안한다. 제안하는 네트워크는 Stacked Hourglass Network를 백본(Backbone) 구조로 이용하며, 크게 랜드마크 검출기, 특징 맵 추출기, 시선 방향 추정기라는 세 개의 부분(Part)으로 구성되어 있다. 랜드마크 검출기에서는 눈 랜드마크 50개 포인트의 좌표를 추정하며, 특징 맵 추출기에서는 시선 방향 추정을 위한 눈 이미지의 특징 맵을 생성한다. 그리고 시선 방향 추정기에서는 각 출력 결과를 조합하여 최종 시선 방향 벡터를 추정한다. 제안하는 네트워크는 UnityEyes 데이터셋을 통해 생성된 가상의 합성 눈 이미지와 랜드마크 좌표 데이터를 이용하여 학습하였으며, 성능 평가는 실제 사람의 눈 이미지로 구성된 MPIIGaze 데이터셋을 이용하였다. 실험을 통해 시선 추정 오차는 3.9°의 성능을 보였으며, 네트워크의 추정 속도는 42 FPS(Frame per second)로 측정되었다.

• 제어로봇시스템학회논문지
• /
• 제21권4호
• /
• pp.378-384
• /
• 2015

Indoor localization is becoming one of the most important technologies for smart mobile applications with different requirements from conventional outdoor location estimation algorithms. Fingerprinting location estimation techniques based on neural networks have gained increasing attention from academia due to their good generalization properties. In this paper, we propose a novel location estimation algorithm based on an ensemble of multiple neural networks. The neural network ensemble has drawn much attention in various areas where one neural network fails to resolve and classify the given data due to its' inaccuracy, incompleteness, and ambiguity. To the best of our knowledge, this work is the first to enhance the location estimation accuracy in indoor wireless environments based on a neural network ensemble using fingerprinting training data. To evaluate the effectiveness of our proposed location estimation method, we conduct the numerical experiments using the TGn channel model that was developed by the 802.11n task group for evaluating high capacity WLAN technologies in indoor environments with multiple transmit and multiple receive antennas. The numerical results show that the proposed method based on the NNE technique outperforms the conventional methods and achieves very accurate estimation results even in environments with a low number of APs.

• Journal of Power Electronics
• /
• 제16권3호
• /
• pp.1131-1140
• /
• 2016

A simple design for a sliding mode observer is proposed for EV lithium battery SOC estimation in this paper. The proposed observer does not have the limiting conditions of existing observers. Compared to the design of previous sliding mode observers, the new observer does not require a solving matrix equation and it does not need many observers for all of the state components. As a result, it is simple in terms of calculations and convenient for engineering applications. The new observer is suitable for both time-variant and time-invariant models of battery SOC estimation, and the robustness of the new observer is proved by Liapunov stability theorem. Battery tests are performed with simulated FUDS cycles. The proposed observer is used for the SOC estimation on both unchanging parameter and changing parameter models. The estimation results show that the new observer is robust and that the estimation precision can be improved base on a more accurate battery model.

• 대한전기학회:학술대회논문집
• /
• 대한전기학회 2000년도 하계학술대회 논문집 A
• /
• pp.80-84
• /
• 2000

Network parameters in power systems are indispensable for all of power system engineering studies, including the power flow calculation and the state estimation. The network parameters required for the studios, in general, are estimated by using several estimation techniques, since it Is very difficult to measure. To improve the estimation accuracy of the network parameters, this paper adopt the synchronized phasor measurements which are acquired from the Phasor Measurement Unit with built-in GPS receiver. In this paper, the parameter estimation problem is formulated with over-determined nonlinear measurement equations and solved with Newton-Raphson method and pseudo-inverse. The effectiveness of the proposed parameter estimation with the synchronized phasor measurements is verified through some case studies with IEEE sample system. The results are very promising.

• International journal of advanced smart convergence
• /
• 제9권2호
• /
• pp.203-211
• /
• 2020

This study proposes a method for estimating gender and age that is robust to various external environment changes by applying deep learning-based learning. To improve the accuracy of the proposed algorithm, an improved CNN network structure and learning method are described, and the performance of the algorithm is also evaluated. In this study, in order to improve the learning method based on CNN composed of 6 layers of hidden layers, a network using GoogLeNet's inception module was constructed. As a result of the experiment, the age estimation accuracy of 5,328 images for the performance test of the age estimation method is about 85%, and the gender estimation accuracy is about 98%. It is expected that real-time age recognition will be possible beyond feature extraction of face images if studies on the construction of a larger data set, pre-processing methods, and various network structures and activation functions have been made to classify the age classes that are further subdivided according to age.

• 한국국방경영분석학회지
• /
• 제32권1호
• /
• pp.133-158
• /
• 2006

정보통신 기술의 급속한 발달은 군의 전장 환경에도 커다란 변화를 가져오고 있다. 특히, 멀티미디어 정보를 이용하여 다양한 대용량의 정보유통 서비스 수요가 급증할 것으로 예상된다. 이와 같은 사용자의 요구사항을 충족하기 위해서는 국방정보통신망의 업그레이드는 불가피하다. 네트워크의 용량을 증가시키기 위해서는 예산 투자가 당연하다. 하지만 데이터 트래픽의 양을 과학적인 방법으로 측정하는 기법이 없는 것이 현실이다. 본 논문은 미래 군 전술종합정보통신 체계에서 요구되는 정보유통소요량에 대하여 네트워크 시뮬레이션 기법을 적용한 툴(Tool) 기반의 과학적이고 신뢰성 있는 정보유통소요량을 분석 및 예측 할 수 있는 기법을 제시하고자 한다.

• 디지털산업정보학회논문지
• /
• 제19권1호
• /
• pp.109-118
• /
• 2023

Data-based analysis methods have become used more for estimating or predicting housing prices, and neural network models and decision trees in the field of big data are also widely used more and more. Neural network models are often evaluated to be superior to existing statistical models in terms of estimation or prediction accuracy. However, there is ambiguity in determining the input feature of the input layer of the neural network model, that is, the type and number of input features, and decision trees are sometimes used to overcome these disadvantages. In this paper, we evaluate the existing methods of using decision trees and propose the method of using decision trees to prioritize input feature selection in neural network models. This can be a complementary or combined analysis method of the neural network model and decision tree, and the validity was confirmed by applying the proposed method to house price estimation. Through several comparisons, it has been summarized that the selection of appropriate input characteristics according to priority can increase the estimation power of the model.

• ETRI Journal
• /
• 제15권2호
• /
• pp.35-51
• /
• 1993

This paper presents function approximation based on nonparametric estimation. As an estimation model of function approximation, a three layered network composed of input, hidden and output layers is considered. The input and output layers have linear activation units while the hidden layer has nonlinear activation units or kernel functions which have the characteristics of bounds and locality. Using this type of network, a many-to-one function is synthesized over the domain of the input space by a number of kernel functions. In this network, we have to estimate the necessary number of kernel functions as well as the parameters associated with kernel functions. For this purpose, a new method of parameter estimation in which linear learning rule is applied between hidden and output layers while nonlinear (piecewise-linear) learning rule is applied between input and hidden layers, is considered. The linear learning rule updates the output weights between hidden and output layers based on the Linear Minimization of Mean Square Error (LMMSE) sense in the space of kernel functions while the nonlinear learning rule updates the parameters of kernel functions based on the gradient of the actual output of network with respect to the parameters (especially, the shape) of kernel functions. This approach of parameter adaptation provides near optimal values of the parameters associated with kernel functions in the sense of minimizing mean square error. As a result, the suggested nonparametric estimation provides an efficient way of function approximation from the view point of the number of kernel functions as well as learning speed.

• 한국습지학회지
• /
• 제5권1호
• /
• pp.15-27
• /
• 2003

The fractal study in river basin has been performed for the sinuosity of an individual stream and bifurcation of the stream network. The previous studies has suggested many methods or equations for the fractal dimension estimation in a river network. This study used those many equations for the estimation of fractal dimensions on the streams such as Bokha, Gonjiam, and Pocheon streams. The estimated dimensions are in the range of 1 to 1.359 for the individual stream and 1.634 to 2 for the stream network. The most of equations were suggested based on the assumption of self-similarity of a river basin for the individual stream and stream network. However, the real river basin could be characterized by self-affinity rather than self-similarity. Even though we estimate the dimensions by using many equations, we could not recommend which one is better equation for the estimation of fractal dimension. This might be from the self-similarity assumption of equations. Therefore, the assumption and research work of self-affinity will be needed for the appropriate estimation of fractal dimension in river basin.