• 제어로봇시스템학회:학술대회논문집
• /
• 제어로봇시스템학회 2003년도 ICCAS
• /
• pp.2226-2229
• /
• 2003

A new method is presented to construct a classifier. This was accomplished by combining a generalized regression neural network (GRNN) and a genetic algorithm (GA). The classifier constructed in this way is referred to as a GA-GRNN. The GA played a role of controlling training factors simultaneously. In GA optimization, neuron spreads were represented in a chromosome. The proposed optimization method was applied to a data set, consisted of 4 different promoter sequences. The training and test data were composed of 115 and 58 sequence patterns, respectively. The range of neuron spreads was experimentally varied from 0.4 to 1.4 with an increment of 0.1. The GA-GRNN was compared to a conventional GRNN. The classifier performance was investigated in terms of the classification sensitivity and prediction accuracy. The GA-GRNN significantly improved the total classification sensitivity compared to the conventional GRNN. Also, the GA-GRNN demonstrated an improvement of about 10.1% in the total prediction accuracy. As a result, the proposed GA-GRNN illustrated improved classification sensitivity and prediction accuracy over the conventional GRNN.

• 대한전기학회논문지:시스템및제어부문D
• /
• 제53권7호
• /
• pp.531-535
• /
• 2004

A new method is presented to construct a classifier. This was accomplished by combining a generalized regression neural network (GRNN) and a genetic algorithm (GA). The classifier constructed in this way is referred to as a GA-GRNN. The GA played a role of controlling training factors simultaneously. The GA-GRNN was applied to classify 4 different Promoter sequences. The training and test data were composed of 115 and 58 sequence patterns, respectively. The classifier performance was investigated in terms of the classification sensitivity and prediction accuracy. Compared to conventional GRNN, GA-GRNN significantly improved the total classification sensitivity as well as the total prediction accuracy. As a result, the proposed GA-GRNN demonstrated improved classification sensitivity and prediction accuracy over the convention GRNN.

• 한국수자원학회:학술대회논문집
• /
• 한국수자원학회 2015년도 학술발표회
• /
• pp.483-486
• /
• 2015

The objective of this study is to develop generalized regression neural networks (GRNN) model for estimating daily solar radiation using limited weather variables at Champaign and Springfield stations in Illinois. The best input combinations (one, two, and three inputs) can be identified using GRNN model. From the performance evaluation and scatter diagrams of GRNN model, GRNN 3 (three input) model produces the best results for both stations. Results obtained indicate that GRNN model can successfully be used for the estimation of daily global solar radiation at Champaign and Springfield stations in Illinois. These results testify the generation capability of GRNN model and its ability to produce accurate estimates in Illinois.

• 한국지열·수열에너지학회논문집
• /
• 제16권4호
• /
• pp.16-23
• /
• 2020

In this study, the control characteristics and effects of control methods on heating performance and energy consumption for the hot water floor radiant heating control system of a residential apartment were research by experiment. As a control method, On-Off control and outdoor reset control methods with GRNN(General Regression Neural Network) and without GRNN are considered. Also, the control performances with regard to improvement of indoor thermal environment and reduction of energy consumption are compared, respectively. Experiment results show that the performance of the control method with GRNN is better than that of conventional on-off control method without GRNN in the responses of room set temperature and energy saving.

• 전자공학회논문지SC
• /
• 제41권5호
• /
• pp.57-64
• /
• 2004

한 대의 카메라와 반사각의 조절이 가능한 2개의 거울, 그리고 별도의 적외선 광원을 이용하여 자유로운 머리 움직임이 가능한 안구 응시점 추정 시스템을 제안하였다. 거울의 회전 각도는 카메라의 광축(opticai axis) 상에 안구가 올 수 있도록 공간 좌표계와 선형 방정식을 이용하여 계산하였다 제안한 시스템은 수평 방향으로 90cm 수직 방향으로 60cm 범위 내에서의 머리 움직임이 가능하였고, 응시점의 공간 해상도 각각 6°, 7°이며, 시간 해상도는 10～15 frames/sec이었다. Generalized regression neural networks(GRNN)을 기반으로 하여 2단계의 GRNN을 거치는 소위 hierarchical generalized regression neural networks(H-GRNN)을 이용하여 얻어진 인자를 모니터 좌표로 변환하였다. GRNN을 한번 사용하였을 경우 정확도가 85%이었으나 H-GRNN을 이용할 경우 약 9% 높은 94%의 정확도를 얻을 수 있었다. 그리고 입력 파라미터의 정규화를 통하여 재보정의 불편함을 제거했을 뿐만 아니라 약간의 얼굴 회전이 발생하였을 경우에도 동일한 성능을 보였다. 본 시스템은 공간 해상도는 크게 높지 않으나 자유로운 머리 움직임을 허용되므로 안정성과 피검자의 활동에 제약을 줄였다는 점에서 의의를 찾을 수 있다.

• 대한전기학회:학술대회논문집
• /
• 대한전기학회 2007년도 제38회 하계학술대회
• /
• pp.1805-1806
• /
• 2007

Silicon nitride (SiN) 박막을 플라즈마 응용화학기상법을 이용하여 증착하였다. SiN박막의 전하밀도는 일반화된 회귀 신경망 (GRNN)을 이용하여 모델링하였다. PECVD 공정은 Box Wilson 실험계획표를 이용하여 수행하였다. GRNN 모델의 예측수행은 유전자 알고리즘 (GA)을 이용하여 최적화하였다. 최적화한 GA-GRNN 모델은 종래의 GRNN 모델과 비교하여, 약55%정도의 예측성능의 향상을 보였다.

• Journal of Electrical Engineering and Technology
• /
• 제10권1호
• /
• pp.188-194
• /
• 2015

This paper proposes a generalized regression neural network (GRNN) based algorithm for data interpolation and design optimization of brushless dc (BLDC) motor. The procedure makes use of magnet length, stator slot opening and air gap length as design variables. Cogging torque and average torque are treated as performance indices. The optimal design necessitates mitigating the cogging torque and maximizing the average torque by varying design variables. The data set for interpolation and ensuing design optimisation using GRNN is obtained by modeling a standard BLDC motor using finite element analysis (FEA) tool MagNet 7.1.1. The performance indices of the standard motor obtained using FEA are validated with an experimental model and an analytical method. The optimal design is authenticated using particle swarm optimization (PSO) algorithm and the performance indices of the optimal design obtained using GRNN is validated using FEA. The results indicate the suitability of GRNN as an interpolation and design optimization tool for a BLDC motor.

• 한국전자통신학회논문지
• /
• 제5권3호
• /
• pp.256-261
• /
• 2010

본 연구에서는 신경회로망의 일종인 GRNN을 이용하여 동영상 대역분할 부호화에 적용하고자 하는 새로운 비선형 움직임 예측기를 제안하였다. 제안된 비선형 예측기의 성능은 가장 일반적으로 많이 사용되는 블록매칭 알고리즘과 비교하였다. 결과적으로 제안된 비선형 움직임 예측기는 블록매칭 알고리즘보다 2-3dB 성능이 우수함을 알 수 있었다. 특히, 제안된 예측기는 클러스터링 과정과 잡음 신호를 둔화시키는 기능이 있어서 원영상의 에지를 잘 보존하는 장점이 있음을 알 수 있다. 이러한 결과는 인간의 시각적 특성에 중요하며 동영상의 대역분할 부호화에서도 우수한 특성을 나타낸다.

• Structural Engineering and Mechanics
• /
• 제71권6호
• /
• pp.739-749
• /
• 2019

This article deals with the application of reliability analysis for determining the safety of simply supported beam under the uniformly distributed load. The uncertainties of the existing methods were taken into account and hence reliability analysis has been adopted. To accomplish this aim, Generalized Regression Neural Network (GRNN), Extreme Learning Machine (ELM) and Gaussian Process Regression (GPR) models are developed. Reliability analysis is the probabilistic style to determine the possibility of failure free operation of a structure. The application of probabilistic mathematics into the quantitative aspects of a structure and improve the qualitative aspects of a structure. In order to construct the GRNN, ELM and GPR models, the dataset contains Modulus of Elasticity (E), Load intensity (w) and performance function (${\delta}$) in which E and w are inputs and ${\delta}$ is the output. The achievement of the developed models was weighed by various statistical parameters; one among the most primitive parameter is Coefficient of Determination ($R^2$) which has 0.998 for training and 0.989 for testing. The GRNN outperforms the other ELM and GPR models. Other different statistical computations have been carried out, which speaks out the errors and prediction performance in order to justify the capability of the developed models.

• 한국지능시스템학회:학술대회논문집
• /
• 한국퍼지및지능시스템학회 2003년도 ISIS 2003
• /
• pp.595-598
• /
• 2003

A new classifier is constructed by using a generalized regression neural network (GRNN) in conjunction with a random generator (RC). The RG played a role of generating a number of sets of random spreads given a range for gaussian functions in the pattern layer, The range experimentally varied from 0.4 to 1.4. The DNA sequences consisted 4 types of promoters. The performance of classifier is examined in terms of total classification sensitivity (TCS), and individual classification sensitivity (ICS). for comparisons, another GRNN classifier was constructed and optimized in conventional way. Compared GRNN, the RG-GRNN demonstrated much improved TCS along with better ICS on average.