• 한국정밀공학회지
• /
• 제28권4호
• /
• pp.391-397
• /
• 2011

Control of interior permanent magnet (IPMSM) is difficult because its nonlinearity and parameter uncertainty. In this paper, a fuzzy c-regression models clustering algorithm which is based on T-S fuzzy is used to model IPMSM with a series linear model and weight them by memberships. Lagrangian of constrained function is built for calculating clustering centers where training output data are considered. Based on these clustering centers, least square method is applied for T-S fuzzy linear model parameters. As a result, IPMSM can be modeled as T-S fuzzy model for T-S fuzzy control of them.

• Nuclear Engineering and Technology
• /
• 제52권11호
• /
• pp.2678-2685
• /
• 2020

The pipe bends and elbows in nuclear power plants (NPPs) are vulnerable to degradation mechanisms and can cause wall-thinning defects. As it is difficult to detect both the defects generated inside the wall-thinned pipes and the preliminary signs, the wall-thinning defects should be accurately estimated to maintain the integrity of NPPs. This paper proposes a deep fuzzy neural network (DFNN) method and estimates the collapse moment of wall-thinned pipe bends and elbows. The proposed model has a simplified structure in which the fuzzy neural network module is repeatedly connected, and it is optimized using the least squares method and genetic algorithm. Numerical data obtained through simulations on the pipe bends and elbows with extrados, intrados, and crown defects were applied to the DFNN model to estimate the collapse moment. The acquired databases were divided into training, optimization, and test datasets and used to train and verify the estimation model. Consequently, the relative root mean square (RMS) errors of the estimated collapse moment at all the defect locations were within 0.25% for the test data. Such a low RMS error indicates that the DFNN model is accurate in estimating the collapse moment for wall-thinned pipe bends and elbows.

• 대한전기학회:학술대회논문집
• /
• 대한전기학회 1998년도 추계학술대회 논문집 학회본부 B
• /
• pp.657-659
• /
• 1998

In order to optimize fuzzy modeling of nonlinear system, we proposed a optimal fuzzy model according to the characteristic of I/O relationship, HCM method, the genetic algorithm, and the objective function with weighting factor. A conventional fuzzy model has difficulty in definition of membership function. In order to solve its problem, the premise structure of the proposed fuzzy model is selected by both the partition of input space and the analysis of input-output relationship using the clustering algorithm. The premise parameters of the fuzzy model are optimized respectively by the genetic algorithm and the consequence parameters of the fuzzy model are identified by the standard least square method. Also, the objective function with weighting factor is proposed to achieve a balance between the performance results for the training and testing data.

• 대한전기학회:학술대회논문집
• /
• 대한전기학회 2001년도 하계학술대회 논문집 D
• /
• pp.1958-1960
• /
• 2001

In this paper, we propose the design methodology of target tracking system using the identification of TS fuzzy model based on genetic algorithm(GA) and RLS algorithm. In general, the objective of target tracking is to estimate the future trajectory of the target based on the past position of the target obtained from the sensor. In the conventional and mathematical nonlinear filtering method such as extended Kalman filter(EKF), the performance of the system may be deteriorated in highly nonlinear situation. In this paper, to resolve these problems of nonlinear filtering technique, the error of EKF by nonlinearity is compensated by identifying TS fuzzy model. In the proposed method, after composing training datum from the parameters of EKF, by identifying the premise and consequent parameters and the rule numbers of TS fuzzy model using GA, and by tuning finely the consequent parameters of TS fuzzy model using recursive least square(RLS) algorithm, the error of EKF is compensated. Finally, the proposed method is applied to three dimensional tracking problem, and the simulation results shows that the tracking performance is improved by the proposed method.

• Current Optics and Photonics
• /
• 제3권2호
• /
• pp.150-153
• /
• 2019

Larynx cancer is a potentially terminal and severe type of neck and head cancer in which malignant cells start to grow and spread upwards in the larynx, or voice box. Smoking tobacco, drinking hot beverages and drinking alcohol are the main risk factors for these tumors. In this study, we aimed to develop a precise, accurate and rapid chemometrics assisted Raman spectroscopy method for diagnosis of larynx cancer in deparaffinized tissue samples. In the proposed method, samples were deparaffinized and 20 microns of each tissue were located on a coverslip. Both healthy (n = 13) and cancerous tissues (n = 13) were exposed to a Raman laser (785 nm) and excitations were recorded between wavenumbers of $50{\sim}1500cm^{-1}$. An Orthogonal Partial Least Square algorithm was applied to evaluate the Raman spectrum obtained. Sensitivity and specificity of the proposed method is high enough with the aid of Principal Component Analysis (PCA) to test the whole model. Healthy and cancerous tissues were accurately and precisely clustered. A rapid, easy and precise diagnosis algorithm was developed for larynx cancer. By this method, some useful data about differences in biomolecules of each group (phospholipids, amides, tyrosine, phenylalanine collagen etc.) was also obtained from the spectra. It is claimed that the optimized method has a great potential for clustering and separating tumor tissues from healthy ones. This novel, rapid, precise and objective diagnosis method may be an alternative for the conventional methods in literature for diagnosis of larynx cancer.

• Computers and Concrete
• /
• 제33권1호
• /
• pp.55-75
• /
• 2024

The present study introduces an optimum performance soft computing model for predicting the compressive strength of high-performance concrete (HPC) by comparing models based on conventional (kernel-based, covariance function-based, and tree-based), advanced machine (least square support vector machine-LSSVM and minimax probability machine regressor-MPMR), and deep (artificial neural network-ANN) learning approaches using a common database for the first time. A compressive strength database, having results of 1030 concrete samples, has been compiled from the literature and preprocessed. For the purpose of training, testing, and validation of soft computing models, 803, 101, and 101 data points have been selected arbitrarily from preprocessed data points, i.e., 1005. Thirteen performance metrics, including three new metrics, i.e., a20-index, index of agreement, and index of scatter, have been implemented for each model. The performance comparison reveals that the SVM (kernel-based), ET (tree-based), MPMR (advanced), and ANN (deep) models have achieved higher performance in predicting the compressive strength of HPC. From the overall analysis of performance, accuracy, Taylor plot, accuracy metric, regression error characteristics curve, Anderson-Darling, Wilcoxon, Uncertainty, and reliability, it has been observed that model CS4 based on the ensemble tree has been recognized as an optimum performance model with higher performance, i.e., a correlation coefficient of 0.9352, root mean square error of 5.76 MPa, and mean absolute error of 4.1069 MPa. The present study also reveals that multicollinearity affects the prediction accuracy of Gaussian process regression, decision tree, multilinear regression, and adaptive boosting regressor models, novel research in compressive strength prediction of HPC. The cosine sensitivity analysis reveals that the prediction of compressive strength of HPC is highly affected by cement content, fine aggregate, coarse aggregate, and water content.

• 대한전자공학회논문지TC
• /
• 제43권11호
• /
• pp.141-148
• /
• 2006

본 논문은 OFDMA 기반의 Wibro 중계국에서 발생되는 루프 간섭 신호의 제거와 위상 보상을 위한 적응 등화기를 사용하여 성능을 개선하기 위한 것이다. Wibro 중계국은 기지국의 통신 가능 영역 확장 및 Throughput 개선을 위하여 사용되는데 송신기와 수신기가 인접해 있으므로 이들간에 루프 간섭의 문제가 성능을 결정하는 중요한 요인이 된다. 논문에서는 먼저 OFDMA 신호를 기저 대역에서 발생시킨 후 Training 시간동안 전송되는 파일롯 톤을 2 가지 삽입 방식으로 조합하여 전송하였다. 또한 부가 잡음 및 루프 간섭 신호에 의한 페이딩파를 발생시켜 수신 신호를 얻은 후 LS (Least Square) 알고리즘을 적용한 채널 추정을 이용을 하여 간섭 신호가 제거된 수신 신호를 복원한 후 적응 등화기를 통과시켜 위상을 보상하였다. 중계기의 성능을 채널 추정 결과, 간섭 제거 후와 등화 출력 신호의 성상도 (Constellation) 및 SNR 변화에 따른 BER 특성 분석을 통하여 개선되었음을 컴퓨터 시뮬레이션을 통해 확인할 수 있었다.

• 한국분무공학회지
• /
• 제27권2호
• /
• pp.57-65
• /
• 2022

The purpose of this study is to use machine learning to build a model capable of predicting the flash boiling spray characteristics. In this study, the flash boiling spray was visualized using Shadowgraph visualization technology, and then the spray image was processed with MATLAB to obtain quantitative data of spray characteristics. The experimental conditions were used as input, and the spray characteristics were used as output to train the machine learning model. For the machine learning model, the XGB (extreme gradient boosting) algorithm was used. Finally, the performance of machine learning model was evaluated using R² and RMSE (root mean square error). In order to have enough data to train the machine learning model, this study used 12 injectors with different design parameters, and set various fuel temperatures and ambient pressures, resulting in about 12,000 data. By comparing the performance of the model with different amounts of training data, it was found that the number of training data must reach at least 7,000 before the model can show optimal performance. The model showed different prediction performances for different spray characteristics. Compared with the upstream spray angle and the downstream spray angle, the model had the best prediction performance for the spray tip penetration. In addition, the prediction performance of the model showed a relatively poor trend in the initial stage of injection and the final stage of injection. The model performance is expired to be further enhanced by optimizing the hyper-parameters input into the model.

• 한국컴퓨터정보학회논문지
• /
• 제26권4호
• /
• pp.1-9
• /
• 2021

본 연구에서는 민감 정보가 포함된 경우의 서포트 벡터 머신 (SVM) 학습 알고리즘을 제안한다. 기계 학습 모형들이 실세계의 자동화된 의사 결정을 가능하게 하였지만 규제들은 프라이버시 보호를 위해서 민감 정보들의 활용을 제한하고 있다. 특히 인종, 성별, 장애 여부와 같은 법적으로 보호되는 정보들의 프라이버시 보호는 필수이다. 본 연구에서는 완전 동형암호를 활용하여 부분적인 민감 정보가 포함된 경우에 최소 제곱 SVM (LSSVM) 모형을 효율적으로 학습할 수 있는 방법을 제안한다. 본 프레임워크에서는 데이터 소유주가 민감하지 않은 정보와 민감한 정보 모두를 가지고 있고, 이를 기계학습 서비스 제공자에게 제공할 때에 민감 정보만 암호화해서 제공하는 것을 가정한다. 결과적으로 데이터 소유자는 민감 정보를 노출시키지 않으면서도 암호화된 상태로 모형의 학습 정보를 얻을 수 있다. 모형을 실제 활용할 경우에는 모든 정보를 암호화하여 안전하게 예측 결과를 제공할 수 있도록 한다. 실제 데이터에 대한 실험을 통해 본 알고리즘이 동형암호로 구현될 경우에 원래의 LSSVM 모형과 비슷한 성능을 가질 수 있음을 확인해 볼 수 있었다. 또한, 개선된 효율적인 알고리즘에 대한 실험은 적은 성능 저하로 큰 연산 효율성을 달성할 가능성을 입증하였다.

• 디지털콘텐츠학회 논문지
• /
• 제18권1호
• /
• pp.159-165
• /
• 2017

태블릿 캡슐의 품질 검사를 자동으로 해내기 위해서는 효율적인 이미지 처리기법, 적절한 임계치 설정, 에지 검출 그리고 세그멘테이션 방법 등이 필요하다. 그리고 기 존재하는 태블릿 캡슐의 품질 자동 검사 장비는 매우 고가이므로 품질 검사의 용이성을 높이기 위해서 저가의 하드웨어 시스템이 도입 되어야하다. 본 연구에서는 저가 카메라 모듈을 사용하여 이미지를 취득하고 전최소자승법 커브 피팅, 에지기반 이미지 세그멘테이션 방법을 사용하여 태블릿 캡슐의 함몰을 검사한다. 제안한 방법의 성능을 보이기 위해서 주요 분류 알고리즘인 PCA, ICA, SVM 방법을 사용하여 캡슐이미지 영역 데이터세트와 커브 피팅 에지 데이터세트에 대하여 훈련시간, 테스트시간 그리고 분류 정확도를 구하였다.