• 한국통신학회논문지
• /
• 제32권9C호
• /
• pp.861-866
• /
• 2007

본 논문은 가우시안 확률분포함수 (Gaussian Probability Distribution Function) 데이터 군집화를 위해 중심신경망 (Centroid Neural Network, CNN)에 Bhattacharyya 커널을 적용한 군집화 알고리즘 (Bhattacharyya Kernel based CNN, BK-CNN)을 제안한다. 제안된 BK-CNN은 무감독 알고리즘인 중심신경망을 기반으로 하고 있으며, 커널 방법을 이용하여 데이터를 특징공간에서 투영한다. 입력공간의 비선형 문제를 선형적으로 해결하기 위해 제안한 커널 방법인데, 확률분포 사이의 거리측정을 위해 Bhattacharyya 거리를 이용한 커널방법을 사용하였다. 제안된 BK-CNN을 영상데이터 분류의 문제에 적용했을 때, 제안된 BK-CNN 알고리즘이 Bhattacharyya 커널을 적용한 k-means, 자기조직지도(Self-Organizing Map)와 중심 신경망등의 기존 알고리즘보다 1.7% - 4.3%의 평균 분류정확도 향상을 가져옴을 확인할 수 있었다.

• 전자공학회논문지CI
• /
• 제46권6호
• /
• pp.44-55
• /
• 2009

최근 활발히 연구가 진행 중인 마이크로어레이로부터 얻어지는 유전자 발현 데이터를 이용한 질병 진단은, 데이터를 직접적으로 분석하기 힘들기 때문에 일반적으로 기계 학습 알고리즘을 사용하여 이루어져왔다. 그러나 유전자 발현 데이터를 분석함에 있어서 유전자들 간의 상호작용을 고려하는 분석이 필요하다는 최근의 연구 결과들은 기존 기계 학습 알고리즘들을 이용한 분석에 한계가 있음을 의미한다고 볼 수 있다. 본 논문에서는 특징들 사이의 고차원 상관관계를 고려 가능한 하이퍼네트워크 모델을 이용하여 유전자 발현 데이터의 분류를 수행하고 기존의 기계 학습 알고리즘들과 분류 성능을 비교한다. 또한 기존 하이퍼네트워크 모델의 단점을 개선 한 모델을 제안하고, 이를 병렬 프로세서 상에서 구현하여 처리 성능을 비교한다. 실험 결과 제안 된 모델은 기존의 기계 학습 방법들과의 비교에서도 경쟁력 있는 분류 성능을 보여주었고, 기존 하이퍼네트워크 모델 보다 안정적이고 향상된 분류 성능을 보여주었다. 또한 이를 병렬 프로세서 상에서 구현 할 경우 처리 성능을 극대화 할 수 있음을 보였다.

• Journal of Power Electronics
• /
• 제17권2호
• /
• pp.346-357
• /
• 2017

The Modular Multilevel Converter (MMC) is particularly attractive for medium and high power applications such as High-Voltage Direct Current (HVDC) systems. In order to reach a high voltage, the number of cascaded submodules (SMs) is generally very large. Thus, in the applications with hundreds or even thousands of SMs such as MMC-HVDCs, the sorting algorithm of the conventional voltage balancing strategy is extremely slow. This complicates the controller design and increases the hardware cost tremendously. This paper presents a Two-Way Merge Sort (TWMS) strategy based on the prediction of the capacitor voltages under ideal conditions. It also proposes an innovative Insertion Sort Correction for the TWMS (ISC-TWMS) to solve issues in practical engineering under non-ideal conditions. The proposed sorting methods are combined with the features of the MMC-HVDC control strategy, which significantly accelerates the sorting process and reduces the implementation efforts. In comparison with the commonly used quicksort algorithm, it saves at least two-thirds of the sorting execution time in one arm with 100 SMs, and saves more with a higher number of SMs. A 501-level MMC-HVDC simulation model in PSCAD/EMTDC has been built to verify the validity of the proposed strategies. The fast speed and high efficiency of the algorithms are demonstrated by experiments with a DSP controller (TMS320F28335).

• 조명전기설비학회논문지
• /
• 제14권1호
• /
• pp.94-101
• /
• 2000

본 논문에서는 서브밴드 기법을 이용한 다중채널 능동소음제어 알고리즘을 제안하였다. 제안된 서브밴드 제어 기법은 3차원 폐공간에서의 능동소음제어서 가장 문제가 되는 계산량을 줄이고 성능올 향상시키기 위한 방법으로, 소음신호를 여러 개의 주파수 밴드로 분할하여 병렬 처리함으로서 원하는 주파수 범위의 소음을 효과적으로 제거할 수 있어 기존의 알고리즘 보다 낮은 차수의 적웅필터를 사용할 수 있다. 적용필터 알고리즘으로 서브밴드로 나펀 기준입력 대신에 오차신호를 perfiltering하는 adjoint LMS 알고리즘을 적용하여 전체적인 계산량의 감소를 이룰 수 있었으며, 성능 향상올 위하여 기존의 하이브리드 제어기법을 변형하여 전향제어기와 궤환제어기의 특성을 가중적으로 갖는 하이브리드 제어기법올 광대역 소음제어 시스템에 적용하여 우수한 소음제거특성과 시스템의 높은 안정성올 얻었다. 제안된 알고리즘의 성능을 평가하기 위해서 컴퓨터 시뮬레이션을 통해 기존의 알고리즘과 비교하였다.

• 대한원격탐사학회지
• /
• 제33권4호
• /
• pp.401-410
• /
• 2017

Estimation of snow depth using optical image is conducted by using correlation with Snow Cover Fraction (SCF). Various algorithms have been proposed for the estimation of snow cover fraction based on Normalized Difference Snow Index (NDSI). In this study we tested linear, quadratic, and exponential equations for the generation of snow cover fraction maps using data from the Moderate Resolution Imaging Spectroradiometer (MODIS) Aqua satellite in order to evaluate their applicability to the complex terrain of South Korea and to search for improvements to the estimation of snow depth on this landscape. The results were validated by comparison with in-situ snowfall data from weather stations, with Root Mean Square Error (RMSE) calculated as 3.43, 2.37, and 3.99 cm for the linear, quadratic, and exponential approaches, respectively. Although quadratic results showed the best RMSE, this was due to the limitations of the data used in the study; there are few number of in-situ data recorded on the station at the time of image acquisition and even the data is mostly recorded on low snowfall. So, we conclude that linear-based algorithms are better suited for use in South Korea. However, in the case of using the linear equation, the SCF with a negative value can be calculated, so it should be corrected. Since the coefficients of the equation are not optimized for this area, further regression analysis is needed. In addition, if more variables such as Normalized Difference Vegetation Index (NDVI), land cover, etc. are considered, it could be possible that estimation of national-scale snow depth with higher accuracy.

• Journal of Power Electronics
• /
• 제13권1호
• /
• pp.139-160
• /
• 2013

In this paper, an intelligent robust control system (IRCS) for precision tracking control of permanent-magnet synchronous motor (PMSM) servo drives is proposed. The IRCS comprises a recurrent wavelet-based interval type-2 fuzzy-neural-network controller (RWIT2FNNC), an RWIT2FNN estimator (RWIT2FNNE) and a compensated controller. The RWIT2FNNC combines the merits of a self-constructing interval type-2 fuzzy logic system, a recurrent neural network and a wavelet neural network. Moreover, it performs the structure and parameter-learning concurrently. The RWIT2FNNC is used as the main tracking controller to mimic the ideal control law (ICL) while the RWIT2FNNE is developed to approximate an unknown dynamic function including the lumped parameter uncertainty. Furthermore, the compensated controller is designed to achieve $L_2$ tracking performance with a desired attenuation level and to deal with uncertainties including approximation errors, optimal parameter vectors and higher order terms in the Taylor series. Moreover, the adaptive learning algorithms for the compensated controller and the RWIT2FNNE are derived by using the Lyapunov stability theorem to train the parameters of the RWIT2FNNE online. A computer simulation and an experimental system are developed to validate the effectiveness of the proposed IRCS. All of the control algorithms are implemented on a TMS320C31 DSP-based control computer. The simulation and experimental results confirm that the IRCS grants robust performance and precise response regardless of load disturbances and PMSM parameters uncertainties.

• 제어로봇시스템학회논문지
• /
• 제8권2호
• /
• pp.126-135
• /
• 2002

The study is concerned with an approach to the design of new architectures of fuzzy neural networks and the discussion of comprehensive design methodology supporting their development. We propose an Adaptive Fuzzy Polynomial Neural Networks(APFNN) based on Fuzzy Neural Networks(FNN) and Self-organizing Networks(SON) for model identification of complex and nonlinear systems. The proposed AFPNN is generated from the mutually combined structure of both FNN and SON. The one and the other are considered as the premise and the consequence part of AFPNN, respectively. As the premise structure of AFPNN, FNN uses both the simplified fuzzy inference and error back-propagation teaming rule. The parameters of FNN are refined(optimized) using genetic algorithms(GAs). As the consequence structure of AFPNN, SON is realized by a polynomial type of mapping(linear, quadratic and modified quadratic) between input and output variables. In this study, we introduce two kinds of AFPNN architectures, namely the basic and the modified one. The basic and the modified architectures depend on the number of input variables and the order of polynomial in each layer of consequence structure. Owing to the specific features of two combined architectures, it is possible to consider the nonlinear characteristics of process system and to obtain the better output performance with superb predictive ability. The availability and feasibility of the AFPNN are discussed and illustrated with the aid of two representative numerical examples. The results show that the proposed AFPNN can produce the model with higher accuracy and predictive ability than any other method presented previously.

• 전기학회논문지
• /
• 제60권4호
• /
• pp.862-870
• /
• 2011

In this paper, we introduce a new topology of Radial Basis Function-based Polynomial Neural Networks (RPNN) that is based on a genetically optimized multi-layer perceptron with Radial Polynomial Neurons (RPNs). This study offers a comprehensive design methodology involving mechanisms of optimization algorithms, especially Fuzzy C-Means (FCM) clustering method and Particle Swarm Optimization (PSO) algorithms. In contrast to the typical architectures encountered in Polynomial Neural Networks (PNNs), our main objective is to develop a design strategy of RPNNs as follows : (a) The architecture of the proposed network consists of Radial Polynomial Neurons (RPNs). In here, the RPN is fully reflective of the structure encountered in numeric data which are granulated with the aid of Fuzzy C-Means (FCM) clustering method. The RPN dwells on the concepts of a collection of radial basis function and the function-based nonlinear (polynomial) processing. (b) The PSO-based design procedure being applied at each layer of RPNN leads to the selection of preferred nodes of the network (RPNs) whose local characteristics (such as the number of input variables, a collection of the specific subset of input variables, the order of the polynomial, and the number of clusters as well as a fuzzification coefficient in the FCM clustering) can be easily adjusted. The performance of the RPNN is quantified through the experimentation where we use a number of modeling benchmarks - NOx emission process data of gas turbine power plant and learning machine data(Automobile Miles Per Gallon Data) already experimented with in fuzzy or neurofuzzy modeling. A comparative analysis reveals that the proposed RPNN exhibits higher accuracy and superb predictive capability in comparison to some previous models available in the literature.

• 대한원격탐사학회:학술대회논문집
• /
• 대한원격탐사학회 2002년도 Proceedings of International Symposium on Remote Sensing
• /
• pp.708-708
• /
• 2002

Recent developments in sensor technologies have provided remotely sensed data with very high spatial resolution. In order to fully utilize the potential of high resolution images, new image classification strategies are necessary. Unfortunately, the high resolution images increase the spectral within-field variability, and the classification accuracy of traditional methods based on pixel-based classification algorithms such as Maximum-Likelihood method may be decreased (Schiewe 2001). Recent development in Object Oriented Classification based on image segmentation algorithms can be used for the classification of forest patches on rugged terrain of Korea. The objectives of this paper are as follows. First, to compare the pros and cons of image classification methods based on pixel-based and object oriented classification algorithm for the forest patch classification. Landsat ETM＋ data and IKONOS data will be used for the classification. Second, to investigate ways to increase classification accuracy of forest patches. Supplemental data such as DTM and Forest Type Map of 1:25,000 scale are used for topographic correction and image segmentation. Third, to propose the best classification strategy for forest patch classification in terms of accuracy and data requirement. The research site for this paper is Namhansansung Provincial Park located at the eastern suburb of Seoul Metropolitan City for its diverse forest patch types and data availability. Both Landsat ETM＋ and IKONOS data are used for the classification. Preliminary results can be summarized as follows. First, topographic correction of reflectance is essential for the classification of forest patches on rugged terrain. Second, object oriented classification of IKONOS data enables higher classification accuracy compared to Landsat ETM＋ and pixel-based classification. Third, multi-stage segmentation is very useful to investigate landscape ecological aspect of forest communities of Korea.

• 한국항행학회논문지
• /
• 제24권4호
• /
• pp.291-298
• /
• 2020

본 연구는 입자 무리 최적화 (PSO; particle swarm optimization) 알고리즘을 이용하여 기존의 MPPT 알고리즘보다 신속하게 MPP를 추적할 수 있는 모델을 제안하였다. 제안 모델은 PSO 알고리즘에서 gbest 및 pbest의 가속 상수를 높게 설정하여 신속하게 MPP 지점을 추적하고 이로 인한 전력 불안정 문제점을 제거하였다. 또한, 일사량의 급격한 변화에 따른 태양광 패널의 전력 변화를 감지하여 알고리즘을 다시 실행하였다. 실험결과, 일사량이 691.5W/m2에 대해서 MPPT 시간이 0.03초와 전력이 131.65로서 기존의 P&O와 INC 알고리즘보다 높은 전력과 빠른 속도로 MPP를 추적하였으며, 일사량 변화에 따라 신속하게 MPP를 추적하였다. 제안 모델은 태양광 패널이 병렬로 연결되어 있는 태양광 발전소에서 부분적인 음영에 의해 전력량의 변화를 감지하였을 경우에도 적용할 수 있다. 본 연구는 MPPT 알고리즘을 개선하기 위해 MFO (moth flame optimization) 및 WOA (whale optimization algorithm)와 같은 최적화 알고리즘에 대한 비교 연구가 필요하다.