• Proceedings of the KIEE Conference
• /
• 2002.07d
• /
• pp.2821-2823
• /
• 2002

In this paper we propose the Multi-FNN (Fuzzy-Neural Networks) for optimal identification modeling of complex system. The proposed Multi-FNNs is based on a concept of FNNs and exploit linear inference being treated as generic inference mechanisms. In the networks learning, backpropagation(BP) algorithm of neural networks is used to updata the parameters of the network in order to control of nonlinear process with complexity and uncertainty of data, proposed model use a HCM(Hard C-Means)clustering algorithm which carry out the input-output dat a preprocessing function and Genetic Algorithm which carry out optimization of model The HCM clustering method is utilized to determine the structure of Multi-FNNs. The parameters of Multi-FNN model such as apexes of membership function, learning rates, and momentum coefficients are adjusted using genetic algorithms. An aggregate performance index with a weighting factor is proposed in order to achieve a sound balance between approximation and generalization abilities of the model. NOx emission process data of gas turbine power plant is simulated in order to confirm the efficiency and feasibility of the proposed approach in this paper.

• Proceedings of the Korean Institute of Intelligent Systems Conference
• /
• 2000.05a
• /
• pp.47-50
• /
• 2000

In this paper, an optimal identification method using Multi-FNN(Fuzzy-Neural Network) is proposed for model ins of nonlinear complex system. In order to control of nonlinear process with complexity and uncertainty of data, proposed model use a HCM clustering algorithm which carry out the input-output data preprocessing function and Genetic Algorithm which carry out optimization of model. The proposed Multi-FNN is based on Yamakawa's FNN and it uses simplified inference as fuzzy inference method and Error Back Propagation Algorithm as learning rules. HCM clustering method which carry out the data preprocessing function for system modeling, is utilized to determine the structure of Multi-FNN by means of the divisions of input-output space. Also, the parameters of Multi-FNN model such as apexes of membership function, learning rates and momentum coefficients are adjusted using genetic algorithms. Also, a performance index with a weighting factor is presented to achieve a sound balance between approximation and generalization abilities of the model, To evaluate the performance of the proposed model, we use the time series data for gas furnace and the numerical data of nonlinear function.

• Proceedings of the Korean Vacuum Society Conference
• /
• 2000.02a
• /
• pp.63-63
• /
• 2000

Deep submicron device contact hole에서의 bottom step coverage의 향상 및 SALICIDE공정의 필요성에 의해 collimated sputtering 및 ionized sputtering 등의 다양한 증착방법이 연구되어왔다. 반도체소자의 고집적화 및 미세화에 따라서 기존의 증착방법보다 더 높은 throughput을 가진 새로운 증착방법의 필요성이 대두되고 있다. Collimated sputtering방식으로 증착한 박막의 경우에는 증착속도가 느리고 collimator의 사용기간에 따른 공정조건의 변화가 단점으로 작용하였고 새로이 ionzied sputtering방식이 개발되었다. ionzied sputtering방식은 증착되는 금속 입자를 이온화시키고 기판에 바이어스를 걸어서 증착되는 입자의 방향성 및 증착속도의 향상을 얻을 수 있었다. 하지만 고집적도가 더욱 증가함에 따라서 더 높은 박막의 증착속도, bottom step coverage의 향상, 방향성의 향상과 더불어 증착되는 입자의 이온화 율의 증가 및 기존의 증착방식에 의한 박막보다 향상된 물성을 가진 박막증착의 필요성에 의해 hollow cathode magnetron sputtering방식이 연구되었다. HCM방식으로 titanium 박막을 증착하여 collimated sputtering 및 ionize sputtering 방식으로 증착한 titanium 박막과 물성을 비교해서 증착방식에 따른 박막물성의 차이를 연구하였다. 증착전에 기판온도는 30$0^{\circ}C$를 유지하였고 base pressure는 5.0$\times$10-9torr, working pressure는 5.7m torr로 유지하였다. power는 30kW를 가하여 50nm두께의 titanium박막을 증착하였다. 증착된 박막의 미세구조는 TEM 및 XRD로 분석하였다. HCM방식으로 증착한 titanium박막은 5nm두께의 비정질 층이 관찰되었고 ionized sputtering방식으로 증착한 titatnium박막에서 나타나는 것으로 보고된 silicon (002)와 titanium (0002) eledtron diffraction spot사이의 (10-10)spot은 관찰되지 않았다. 박막은 크고 작은 grain의 연속적 분포를 가졌고 HCM방식으로 증착한 titanium박막의 in-plane grain size가 다른 증착방식으로 증착한 박막에 비해 크게 관찰됨을 Plan-view TEM 분석을 통해서 확인되었다.

• The KIPS Transactions:PartA
• /
• v.10A no.1
• /
• pp.25-34
• /
• 2003

Parallel file system solves I/O bottleneck to store a file distributedly and read it parallel exchanging messages among computers that is connected multiple computers with high speed networks. However, they do not consider the message characteristics and performances are decreased. Accordingly, the current study proposes the Hybrid Channel model (HCM) as a message-management method, whereby the messages of a parallel file system are classified by a message characteristic between control messages and file data blocks, and the communication channel is divided into a message channel and data channel. The message channel then transfers the control messages through TCP/IP with reliability, while the data channel that is implemented by Virtual Interface Architecture (VIA) transfers the file data blocks at high speed. In tests, the proposed parallel file system that is implemented by HCM exhibited a considerably improved performance.

• International Journal of Control, Automation, and Systems
• /
• v.1 no.2
• /
• pp.194-202
• /
• 2003

In this paper, we introduce a category of Multi-FNN (Fuzzy-Neural Networks) models, analyze the underlying architectures and propose a comprehensive identification framework. The proposed Multi-FNNs dwell on a concept of fuzzy rule-based FNNs based on HCM clustering and evolutionary fuzzy granulation, and exploit linear inference being treated as a generic inference mechanism. By this nature, this FNN model is geared toward capturing relationships between information granules known as fuzzy sets. The form of the information granules themselves (in particular their distribution and a type of membership function) becomes an important design feature of the FNN model contributing to its structural as well as parametric optimization. The identification environment uses clustering techniques (Hard C - Means, HCM) and exploits genetic optimization as a vehicle of global optimization. The global optimization is augmented by more refined gradient-based learning mechanisms such as standard back-propagation. The HCM algorithm, whose role is to carry out preprocessing of the process data for system modeling, is utilized to determine the structure of Multi-FNNs. The detailed parameters of the Multi-FNN (such as apexes of membership functions, learning rates and momentum coefficients) are adjusted using genetic algorithms. An aggregate performance index with a weighting factor is proposed in order to achieve a sound balance between approximation and generalization (predictive) abilities of the model. To evaluate the performance of the proposed model, two numeric data sets are experimented with. One is the numerical data coming from a description of a certain nonlinear function and the other is NOx emission process data from a gas turbine power plant.

• Journal of Power Electronics
• /
• v.18 no.1
• /
• pp.234-250
• /
• 2018

This paper presents a new load sharing control for use between paralleled three-phase inverters in an islanded microgrid based on the online line impedance estimation by the use of a Kalman filter. In this study, the mismatch of power sharing when the line impedance changes due to temperature, frequency, significant differences in line parameters and the requirements of the Plug-and-Play mode for inverters connected to a microgrid has been solved. In addition, this paper also presents a new droop control method working with the line impedance that is different from the traditional droop algorithm when the line impedance is assumed to be pure resistance or pure inductance. In this paper, the line impedance estimation for parallel inverters uses the minimum square method combined with a Kalman filter. In addition, the secondary control loops are designed to restore the voltage amplitude and frequency of a microgrid by using a combined nominal value SOGI-PLL with a generalized integral block and phase lock loop to monitor the exact voltage magnitude and frequency phase at the PCC. A control model has been simulated in Matlab/Simulink with three voltage source inverters connected in parallel for different ratios of power sharing. The simulation results demonstrate the accuracy of the proposed control method.

• Journal of Veterinary Clinics
• /
• v.31 no.2
• /
• pp.85-89
• /
• 2014

Arterial thromboembolism (ATE) is a common and fatal complication of hypertrophic cardiomyopathy (HCM) in cats. Therefore in this study, we evaluated the hypercoagulability (using plasma concentration of D-dimer) in HCM cats with different stage of heart failure and left atrial enlargement and also investigated the any correlation with echocardiographic indices (including left free wall thickness at diastole, interventricular septal thickness at diastole, LA to Ao ratio, heart failure stage, existence of systolic anterior motion of mitral valve). The median plasma D-dimer concentration in this study population was $0.51{\pm}0.70$ (range 0 to 2.50) ug/mL in the control group, $1.47{\pm}1.29$ (range 0.3 to 5.79) ug/mL in the HCM group, $1.48{\pm}1.65$ (range 0.3 to 5.79) ug/mL in the ISACHC I group, $1.62{\pm}0.4$ (range 1.31 to 2.07) ug/mL in the ISACHC II group, $1.36{\pm}0.91$ (range 0.3 to 2.31) ug/mL in the ISACHC III group, $1.90{\pm}1.60$ (range 0.3 to 5.79) ug/mL in the cat with LA dilation, $1.72{\pm}0.72$ (range 0.6 to 2.31) ug/mL in cats with SEC-T, $1.19{\pm}0.70$ (range 0.3 to 2.31) ug/mL in the cats with SAM, and $1.63{\pm}0.80$ (range 0.6 to 2.31) ug/mL in the cats with ATE. Our study found the median and mean concentration of plasma D-dimer was higher in cat with HCM, ATE, SECT and SAM and clearly provides evidence of hypercoagulability in cats with HCM, although the severity was not correlated to the dilation of LA and the presence of heart failure. This is the first study evaluating the hypercoagulability in cats with HCM in Korea.

• Proceedings of the KIEE Conference
• /
• 2005.05a
• /
• pp.9-11
• /
• 2005

We propose a optimal identification of information granulation(IG)-based fuzzy model to carry out the model identification of complex and nonlinear systems. To optimally identity we use genetic algorithm (GAs) sand Hard C-Means (HCM) clustering. An initial structure of fuzzy model is identified by determining the number of input, the selected input variables, the number of membership function, and the conclusion inference type by means of GAs. Granulation of information data with the aid of Hard C-Means(HCM) clustering algorithm help determine the initial parameters of fuzzy model such as the initial apexes of the membership functions and the initial values of polynomial functions being used in the premise and consequence part of the fuzzy rules. And the initial parameters are tuned effectively with the aid of the genetic algorithms(GAs) and the least square method. Numerical example is included to evaluate the performance of the proposed model.

• Proceedings of the KIEE Conference
• /
• 2005.10b
• /
• pp.146-148
• /
• 2005

In this paper, we propose a genetically optimized identification of information granulation(IG)-based fuzzy model. To optimally design the IG-based fuzzy model we exploit a hybrid identification through genetic alrogithms(GAs) and Hard C-Means (HCM) clustering. An initial structure of fuzzy model is identified by determining the number of input, the seleced input variables, the number of membership function, and the conclusion inference type by means of GAs. Granulation of information data with the aid of Hard C-Means(HCM) clustering algorithm help determine the initial paramters of fuzzy model such as the initial apexes of the membership functions and the initial values of polyminial functions being used in the premise and consequence part of the fuzzy rules. And the inital parameters are tuned effectively with the aid of the genetic algorithms and the least square method. And also, we exploite consecutive identification of fuzzy model in case of identification of structure and parameters. Numerical example is included to evaluate the performance of the proposed model.

• International journal of advanced smart convergence
• /
• v.1 no.2
• /
• pp.30-33
• /
• 2012

This paper propose a new design of fuzzy neural networks based on hard partition to generate the rules of the networks. For this we use hard c-means (HCM) clustering algorithm. The premise part of the rules of the proposed networks is realized with the aid of the hard partition of input space generated by HCM clustering algorithm. The consequence part of the rule is represented by polynomial functions. And the coefficients of the polynomial functions are learned by BP algorithm. The number of the hard partition of input space equals the number of clusters and the individual partitioned spaces indicate the rules of the networks. Due to these characteristics, we may alleviate the problem of the curse of dimensionality. The proposed networks are evaluated with the use of numerical experimentation.