• 한국전산구조공학회:학술대회논문집
• /
• 한국전산구조공학회 1998년도 가을 학술발표회 논문집
• /
• pp.439-446
• /
• 1998

One of the most important roles in the nonlinear dynamic structural analysis is to select a proper ground excitation, which dominates the response of a structure. Because of the lack of recorded accelerograms in Korea, a stochastic model of ground excitation with various dynamic properties rather than recorded accelerograms is necessarily required. If all information is not available at site, the information from other sites with similar features can be used by the procedure of seismic hazard analysis. Eliopoulos and Wen identified the parameters of the ground motion model by the empirical relations or expressions developed by Trifunac and Lee. Because the relations used in the parameter identification are largely empirical, it is required to apply the artificial neural networks instead of the empirical model. Additionally, neural networks have the advantage of the empirical model that it can continuously re-train the new recorded data, so that it can adapt to the change of the enormous data. Based on the redefined traditional processes, three neural-networks-based models (FAS_NN, PSD_NN and INT_NN) are proposed to individually substitute the Fourier amplitude spectrum, the parameter identification of power spectral density function and intensity function. The paper describes the first half of the research for the development of Neural-Networks-based model for the generation of an Artificial earthquake and a Response Spectrum(NNARS).

• 한국전산구조공학회:학술대회논문집
• /
• 한국전산구조공학회 1998년도 가을 학술발표회 논문집
• /
• pp.447-454
• /
• 1998

The paper describes the second half of the research for the development of Neural-Networks-based model for the generation of an Artificial earthquake and a Response Spectrum(NNARS). Based on the redefined traditional processes related to the generation of an earthquake acceleration response spectrum and design spectrum, four neural-networks-based models are proposed to substitute the traditional processes. RS_NN tries to directly generate acceleration response spectrum with basic data that are magnitude, epicentral distance, site conditions and focal depth. The test results of RS_NN are not good because of the characteristics of white noise, which is randomly generated. ARS_NN solve this problem by the introduction of the average concept. IARS_NN has a role to inverse the ARS_NN, so that is applied to generate a ground motion accelerogram compatible with the shape of a response spectrum. Additionally, DS_NN directly produces design spectrum with basic data. As these four neural networks are simulated as a step by step, the paper describes the methods to generate a response spectrum and a design spectrum using the neural networks.

• 융합신호처리학회논문지
• /
• 제5권1호
• /
• pp.53-59
• /
• 2004

부하예측의 경우 가장 중요한 문제는 특수일의 부하를 예측하는 것이고, 따라서 본 본문은 과거 특수일 부하 데이터를 이용하여 신경회로망 모델에 의해서 특수일 피크부하를 예측하는 방법을 제시한다. 특수일 부하는 예측되었고, 예측 오차율은 광복절을 제외하고는 l∼2% 정도의 비교적 우수한 예측결과를 도출하였다. 따라서 사용한 예측 모델은 특수일의 부하에 만족스러운 정밀한 예측이 가능하고. 신경회로망은 특수일 부하 예측의 결과를 검증하기 위해 4차 직교다항식모형과 특수일 부하의 예측에효과적인 패턴 변환비를 이용한 신경회로망 모형을 구성했다. 한편, 시간별 특수일의 부하예측에도 신경회로망을 적용한 특수일 부항예측의 경우와 같은 양호한 예측결과를 보였다.

• 한국정보통신학회:학술대회논문집
• /
• 한국해양정보통신학회 1999년도 추계종합학술대회
• /
• pp.204-209
• /
• 1999

일반적으로 신경회로망은 다중분광 영상의 카테고리 분류를 위해 많이 사용되나 다중분광 영상의 경우 카테고리간 명암도차가 얼마나지 않아 오차 수렴시간이 많이 걸리고 분류성능이 떨어진다. 이와 같은 문제점을 해결하기 위해 본 논문에서는 평활화 과정, 주된 골을 찾는 과정, 그리고 향상 과정으로 구성되는 새로운 영상 향상법을 제안하고, 제안한 방법으로 향상된 다중분광 영상을 신경회로망의 입력으로 하여 카테고리 분류하였다. 제안한 방법을 LANDSAT TM 영상에 적용한 결과 신경회로망의 오차 수렴속도가 빨라졌고, 분류 성능이 향상되었음을 확인할 수 있었다.

• 전기전자학회논문지
• /
• 제22권4호
• /
• pp.1131-1139
• /
• 2018

본 논문에서는 합성곱 신경망을 이용한 유기된 물체 인식 방법을 제안한다. 유기된 물체 인식 방법은 영상 내에서 유기 물체에 대한 영역을 먼저 검출하며 검출된 영역이 있을 경우 해당 영역에 합성곱 신경망을 적용하여 어떤 물체를 나타내는지 인식하는 과정을 거친다. 실험은 쓰레기 무단투기를 검출하는 응용 시스템을 통해 진행되었다. 실험 결과, 유기 물체에 대한 영역을 효율적으로 검출하는 것을 볼 수 있었다. 검출된 영역은 합성곱 신경망으로 들어가 쓰레기인지 아닌지 분류되는 과정을 거쳤다. 이를 위해 자체적으로 수집한 쓰레기 데이터와 오픈 데이터베이스로 합성곱 신경망을 학습시켰다. 학습 결과, 학습에 포함되지 않은 테스트셋에 대해 약 97%의 정확도를 달성하였다.

• Imaging Science in Dentistry
• /
• 제49권1호
• /
• pp.19-26
• /
• 2019

Purpose: It has been proposed that using new prediction methods, such as neural networks based on dental data, could improve age estimation. This study aimed to assess the possibility of exploiting neural networks for estimating age by means of the pulp-to-tooth ratio in canines as a non-destructive, non-expensive, and accurate method. In addition, the predictive performance of neural networks was compared with that of a linear regression model. Materials and Methods: Three hundred subjects whose age ranged from 14 to 60 years and were well distributed among various age groups were included in the study. Two statistical software programs, SPSS 21 (IBM Corp., Armonk, NY, USA) and R, were used for statistical analyses. Results: The results indicated that the neural network model generally performed better than the regression model for estimation of age with pulp-to-tooth ratio data. The prediction errors of the developed neural network model were acceptable, with a root mean square error (RMSE) of 4.40 years and a mean absolute error (MAE) of 4.12 years for the unseen dataset. The prediction errors of the regression model were higher than those of the neural network, with an RMSE of 10.26 years and a MAE of 8.17 years for the test dataset. Conclusion: The neural network method showed relatively acceptable performance, with an MAE of 4.12 years. The application of neural networks creates new opportunities to obtain more accurate estimations of age in forensic research.

• 전기학회논문지P
• /
• 제53권4호
• /
• pp.195-200
• /
• 2004

Many kinds of speed sensorless control system of induction motor had been developed. But it is difficult to implement at the real system because of complex algorithm and equations. This paper investigates a novel speed sensorless control of induction motor using neural networks. The proposed control strategy is based on neural networks using stator current and output of neural model based on state observer. The errors between the stator current and the output of neural model are back-propagated to adjust the rotor speed, so that adaptive state variable will coincide with the desired state variable. This algorithm may overcome several shortages of conventional model, such as integrator problems, small EMF at low speed and relatively large sensitivity of stator resistance variation. Also, this paper presents a newly developed optimal equation about the momentum constant and the learning rate. The proposed algorithms are verified through simulation.

• 제어로봇시스템학회:학술대회논문집
• /
• 제어로봇시스템학회 2005년도 ICCAS
• /
• pp.1474-1477
• /
• 2005

This paper is proposed maximum torque per ampere of induction motor using fuzzy-neural networks controller. Operation of maximum torque per ampere is achieved when, at a given torque and speed, the slip frequency is adjusted to that so that the stator current amplitude is minimized. This paper introduces a induction motor drive system with fuzzy-neural networks controller. A neural network-based architecture is described for fuzzy logic control. The characteristic rule and their membership function of fuzzy system are represented as the processing nodes in the neural network structure. This paper is proposed the analysis as well as the simulation results to verify the effectiveness of the new method.

• 전자공학회논문지B
• /
• 제31B권5호
• /
• pp.123-133
• /
• 1994

This paper presents an output arbitrator for input buffering ATM (Asynchronous Transfer Mode) switches using neural networks. To avoid blocking in ATM switches with blocking characteristics, it is required to buffer ATM cells in input buffer and to schedule them. The N$\times$N request matrix is divided into N/16 submatrices in order to get rid of internal blocking systematically in scheduling phase. The submatrices are grouped into N/4 groups, and the cells in each group are switched alternatively. As the window size of input buffer is increases, the number of input cells switched in a time slot approaches to N. The selection of nonblocking cells to be switched is done by neural network modules. N/4 neural network modules are operated simultaneously. Fast selection can be achieved by massive parallelism of neural networks. The neural networks have 4N neurons and 14N connection. The proposed method is implemented in C language, and the simulation result confirms the feasibility of this method.

• 대한전기학회:학술대회논문집
• /
• 대한전기학회 1999년도 하계학술대회 논문집 C
• /
• pp.1522-1522
• /
• 1999

This paper proposes the methods of short-term load forecasting using Kohonen neural networks and back-propagation neural networks. Historical load data is divided into 5 patterns for the each seasonal data using Kohonen neural networks and using these results, load forecasting neural network is used for next day hourly load forecasting. Normal days and holidays are forecasted. For load forecasting in summer, max-, and min-temperature data are included in neural networks for a better forecasting accuracy. To show the possibility of the proposed method, it was tested with hourly load data of Korea Electric Power Corporation. (1993-1997)