• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.25 no.3B
• /
• pp.570-576
• /
• 2000

This paper proposed LQ-Servo PI controller by considering LQ-Servo structure as PI controller with a partial state feedback and concerns about the development of the flexible design algorithm by introducing weights to the design parameters of the previous LQ-Servo design method. the propose algorithm improves the matchings of the maximum and minimum singular values at high and low frequencies of the design loop transfer function as well as its loop shaping for performance.

• Proceedings of the Korean Information Science Society Conference
• /
• 2005.07b
• /
• pp.691-693
• /
• 2005

본 연구에서는 FMM 신경망의 학습 알고리즘에서 하이퍼박스 확장과정에 수반되는 중첩현상을 분석하고, 이에 대한 축소 과정의 특성과 이를 보완하기 위한 새로운 활성화 함수에 관하여 고찰한다. 하이퍼박스 중첩 영역에 속하는 패턴 데이터는 그 분류 결과가 왜곡될 수 있다. 왜냐하면 학습과정에서 하이퍼박스상의 특징범위는 특징값의 빈도요소를 고려하지 않음으로 인하여 극소수의 비정상적 데이터에 관해서도 동일 수준으로 민감하게 확장되기 때문이다. 본 논문에서는 특징집합에서 가중치와 빈도요소를 반영하는 모델로서 이러한 중첩현상의 영향을 개선하는 방법론을 소개한다. 제안된 이론은 단순화된 패턴집합에 대하여 그 유용성을 이론적으로 고찰하며, 실제 패턴분류 문제에 적용하여 실험적으로 평가한다.

• Journal of the Korean Society for Precision Engineering
• /
• v.21 no.9
• /
• pp.149-157
• /
• 2004

This paper presents a new method for hi-objective optimization. Ordinary weighted sum method is easy to implement, but it has two significant drawbacks: (1) the solution distribution by the weighted sum method is not uniform, and (2) the method cannot determine any solutions that reside in non-convex regions of a Pareto front. The proposed adaptive weighted sum method does not solve a multiobjective optimization in a predetermined way, but it focuses on the regions that need more refinement by imposing additional inequality constraints. It is demonstrated that the adaptive weighted sum method produces uniformly distributed solutions and finds solutions on non-convex regions. Two numerical examples and a simple structural problem are presented to verify the performance of the proposed method.

• Journal of the Korea Society of Computer and Information
• /
• v.7 no.1
• /
• pp.1-7
• /
• 2002

Component-based software development(CBSD) is gaining popularity Effective search and retrieval of desired components, which are stored in a component repository, is a very important issue in CBSD. In this paper. a new weighted synaptic connectivity matrix is proposed to find more appropriate components. An algorithm is proposed for effective search with NOT operator and a proof for the algorithm is Presented . A new procedure to calculate the output vector for a logically combined query is also presented.

• Journal of the Korean Society for Aeronautical & Space Sciences
• /
• v.32 no.4
• /
• pp.24-33
• /
• 2004

In this paper, the helicopter flight control system using online adaptive neural networks which have the universal function approximation property is considered. It is not compensation for modeling errors but approximation two functions required for feedback linearization control action from input/output of the system. To guarantee the tracking performance and the stability of the closed loop system replaced two nonlinear functions by two neural networks, weight update laws are provided by Lyapunov function and the simulation results in low speed flight mode verified the performance of the control system with the neural networks.

• Journal of the Korean Society for Aeronautical & Space Sciences
• /
• v.31 no.6
• /
• pp.61-71
• /
• 2003

In the study of control technique for a turbojet engine model, the Takagi-Sugeno fuzzy logic controller has been designed based on the model identification by the well designed PI controlled system through T-S neuro-fuzzy inference system. To enhance this designed controller, those procedures are proposed that certainty factors are adopted to each rule of objective groups which are classified by the fuzzy C-Means algorithm and the satisfaction degrees are matched to meet the objectives. This proposed technique shows its feasibility by upgrading performances of the previously well-designed T-S fuzzy controller.

• Journal of the Institute of Electronics Engineers of Korea CI
• /
• v.41 no.3
• /
• pp.27-36
• /
• 2004

Detection and recognition of human faces in images can be considered as an important aspect for applications that involve interaction between human and computer. In this paper, we propose a face recognition method using eigenfaces and fuzzy neural networks. The Principal Components Analysis (PCA) is one of the most successful technique that have been used to recognize faces in images. In this technique the eigenvectors (eigenfaces) and eigenvalues of an image is extracted from a covariance matrix which is constructed form image database. Face recognition is Performed by projecting an unknown image into the subspace spanned by the eigenfaces and by comparing its position in the face space with the positions of known indivisuals. Based on this technique, we propose a new algorithm for face recognition consisting of 5 steps including preprocessing, eigenfaces generation, design of fuzzy membership function, training of neural network, and recognition. First, each face image in the face database is preprocessed and eigenfaces are created. Fuzzy membership degrees are assigned to 135 eigenface weights, and these membership degrees are then inputted to a neural network to be trained. After training, the output value of the neural network is intupreted as the degree of face closeness to each face in the training database.

• The Korean Journal of Applied Statistics
• /
• v.33 no.5
• /
• pp.615-625
• /
• 2020

The document-term frequency matrix is a term extracted from documents in which the group information exists in text mining. In this study, we generated the document-term frequency matrix for document classification according to research field. We applied the traditional term weighting function term frequency-inverse document frequency (TF-IDF) to the generated document-term frequency matrix. In addition, we applied term frequency-inverse gravity moment (TF-IGM). We also generated a document-keyword weighted matrix by extracting keywords to improve the document classification accuracy. Based on the keywords matrix extracted, we classify documents using a deep neural network. In order to find the optimal model in the deep neural network, the accuracy of document classification was verified by changing the number of hidden layers and hidden nodes. Consequently, the model with eight hidden layers showed the highest accuracy and all TF-IGM document classification accuracy (according to parameter changes) were higher than TF-IDF. In addition, the deep neural network was confirmed to have better accuracy than the support vector machine. Therefore, we propose a method to apply TF-IGM and a deep neural network in the document classification.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.11 no.11
• /
• pp.2158-2165
• /
• 2007

In this paper, a Modified Fuzzy C-Means algorithm with Gaussian Weights(MFCM_GW) is presented for nonlinear blind channel equalization. The proposed algorithm searches the optimal channel output states of a nonlinear channel from the received symbols, based on the Bayesian likelihood fitness function and Gaussian weighted partition matrix instead of a conventional Euclidean distance measure. Next, the desired channel states of a nonlinear channel are constructed with the elements of estimated channel output states, and placed at the center of a Radial Basis Function(RBF) equalizer to reconstruct transmitted symbols. In the simulations, binary signals are generated at random with Gaussian noise. The performance of the proposed method is compared with those of a simplex genetic algorithm(GA), a hybrid genetic algorithm(GA merged with simulated annealing(SA): GASA), and a previously developed version of MFCM. It is shown that a relatively high accuracy and fast search speed has been achieved.

• Proceedings of the Korea Water Resources Association Conference
• /
• 2023.05a
• /
• pp.112-112
• /
• 2023

발전용댐의 댐 유입량 예측 및 운영을 위해서 (주)한국수력원자력에서는 수자원통합 운영시스템(Water resources Integrated System, WIOS)을 운영 중에 있다. 해당 시스템에서는 댐 유입량을 예측하기 위해서 기상청 수치예보모델 중 하나인 국지예보모델(Local Data Assimilation and Prediction System, LDAPS)의 예측강우를 수문모형의 입력자료로 활용하고 있으며, 레이더 기반의 초단시간 강우예측 기법을 자체 개발 중에 있다. 기상청 국지예보모델은 강우의 on/off에 대한 정확도는 90%를 상회할 만큼 높으나 정량적인 강우량의 정확도는 매우 낮고, 레이더 기반의 초단시간 예측 강우는 선행 1~2시간 예측에서는 정량적 정확도는 높으나, 그 이후 예측성능이 급격히 떨어지는 경향을 보인다. 따라서 댐 유입량의 정량적 예측 정확도를 확보하기 위해 초단시간 모델과 국지예보모델의 강우예측 결과를 병합(blending)하는 기법을 적용하여 초기 6시간 동안의 예측 성능을 향상시켜야 한다. 본 연구에서는 선행시간 0~6시간에 대해서 병합하는 기법들을 적용하고 평가하고자 한다. 기본적으로 병합은 초단시간 예측강우와 수치예보자료 간 가중치를 통해 수행된다. 일반적으로 초기 1시간 선행시간에서 레이더 기반 예측강우는 완벽한 예측자료(외삽 관측자료의 가중치는 1.0)로 가정하며, tanh 함수를 이용하여 선행시간의 증가에 따라 가중치를 감소시키면서, 6시간 선행시간에서는 수치예보 예측강우가 완벽한 예측자료라고 가정한다. 본 연구에서는 일반적인 병합 방법 외에 병합된 예측강우에 과거 관측강우와 예측강우의 평균편이를 적용하여 보정하는 방법, 사례별 변동성이 큰 병합된 예측강우 특성을 고려하여 병합 가중치를 신뢰도에 따라 가변시키는 방법을 적용하여 평가한다. 이를 통해 댐 유입량 예측에 최적이 되는 병합기법을 선정하고자 한다.