• 대한전기학회:학술대회논문집
• /
• 대한전기학회 2005년도 심포지엄 논문집 정보 및 제어부문
• /
• pp.12-14
• /
• 2005

In this paper, we propose a new architecture of Self-Organizing Fuzzy Polynomial Neural Networks(SOFPNN) by means of genetically optimized fuzzy polynomial neuron(FPN) and discuss its comprehensive design methodology involving mechanisms of genetic optimization, especially genetic algorithms(GAs). The conventional SOFPNNs hinges on an extended Group Method of Data Handling(GMDH) and exploits a fixed fuzzy inference type in each FPN of the SOFPNN as well as considers a fixed number of input nodes located in each layer. The design procedure applied in the construction of each layer of a SOFPNN deals with its structural optimization involving the selection of preferred nodes (or FPNs) with specific local characteristics (such as the number of input variables, the order of the polynomial of the consequent part of fuzzy rules, a collection of the specific subset of input variables, and the number of membership function) and addresses specific aspects of parametric optimization. Therefore, the proposed SOFPNN gives rise to a structurally optimized structure and comes with a substantial level of flexibility in comparison to the one we encounter in conventional SOFPNNs. To evaluate the performance of the genetically optimized SOFPNN, the model is experimented with using two time series data(gas furnace and chaotic time series).

• KDI Journal of Economic Policy
• /
• 제43권3호
• /
• pp.33-53
• /
• 2021

The import content of exports (ICE) is defined as the amount of foreign input embodied in one unit of export, and it has been used as a measure of the degree of integration into the global production network. In this paper, we suggest an alternative measure based on the decomposition of gross output and imports into the contributions of final demand terms. This measure considers the manner in which a country manages its domestic production base (gross output) and utilizes the foreign sector (imports) simultaneously and can thus be regarded as a more comprehensive measure than ICE. Korea's input-output tables in 1970-2018 are used in this paper. These tables were rearranged according to the same 26-industry classification so that these measures can be computed with time-series continuity and so that the results can be interpreted clearly. The results obtained in this paper are based on extended time-series data and are expected to be reliable and robust. The suggested indicators were applied to these tables, and, based on the results we conclude that the overall importance of the global economy in Korea's economic strategy has risen and that the degree of Korea's integration into the global production network increased over the entire period. This paper also shows that ICE incorrectly measures the movement of the degree of integration into the global production network in some periods.

• Journal of Power Electronics
• /
• 제19권3호
• /
• pp.665-675
• /
• 2019

Renewable energy based on photovoltaic systems is beginning to play an important role to supply power to remote areas all over the world. Owing to the lower output voltage of photovoltaic arrays, high gain DC-DC converters with a high efficiency are required in practice. This paper presents a novel interleaved DC-DC boost converter with a high voltage gain, where the input terminal is interlaced in parallel and the output terminal is staggered in series (IPOSB). The IPOSB configuration can reduce input current ripples because two inductors are interlaced in parallel. The double output capacitors are charged in staggered parallel and discharged in series for the load. Therefore, IPOSB can attain a high step-up conversion and a lower output voltage ripple. In addtion, the output voltage can be automatically divided by two capacitors, without the need for extra sharing control methods. At the same time, the voltage stress of the power devices is lowered. The inrush current problem of capacitors is restrained by the inductor when compared with high gain converters with a switching-capacitor structure. The working principle and steady-state characteristics of the converter are analyzed in detail. The correctness of the theoretical analysis is verified by experimental results.

• 한국수자원학회:학술대회논문집
• /
• 한국수자원학회 2022년도 학술발표회
• /
• pp.150-150
• /
• 2022

This study investigates the roles of decomposition methods on high accuracy in daily rainfall prediction from light gradient boosting machine (LightGBM) algorithm. Here, empirical mode decomposition (EMD) and singular spectrum analysis (SSA) methods were considered to decompose and reconstruct input time series into trend terms, fluctuating terms, and noise components. The decomposed time series from EMD and SSA methods were used as input data for LightGBM algorithm in two hybrid models, including empirical mode-based light gradient boosting machine (EMDGBM) and singular spectrum analysis-based light gradient boosting machine (SSAGBM), respectively. A total of four parameters (i.e., temperature, humidity, wind speed, and rainfall) at a daily scale from 2003 to 2017 is used as input data for daily rainfall prediction. As results from statistical performance indicators, it indicates that the SSAGBM model shows a better performance than the EMDGBM model and the original LightGBM algorithm with no decomposition methods. It represents that the accuracy of LightGBM algorithm in rainfall prediction was improved with the SSA method when using multivariate dataset.

• 한국정보시스템학회지:정보시스템연구
• /
• 제29권1호
• /
• pp.241-265
• /
• 2020

Purpose Various machine learning techniques are used to implement for predicting corporate credit. However, previous research doesn't utilize time series input features and has a limited prediction timing. Furthermore, in the case of corporate bond credit rating forecast, corporate sample is limited because only large companies are selected for corporate bond credit rating. To address limitations of prior research, this study attempts to implement a predictive model with more sample companies, which can adjust the forecasting point at the present time by using the credit score information and corporate information in time series. Design/methodology/approach To implement this forecasting model, this study uses the sample of 2,191 companies with KIS credit scores for 18 years from 2000 to 2017. For improving the performance of the predictive model, various financial and non-financial features are applied as input variables in a time series through a sliding window technique. In addition, this research also tests various machine learning techniques that were traditionally used to increase the validity of analysis results, and the deep learning technique that is being actively researched of late. Findings RNN-based stateful LSTM model shows good performance in credit rating prediction. By extending the forecasting time point, we find how the performance of the predictive model changes over time and evaluate the feature groups in the short and long terms. In comparison with other studies, the results of 5 classification prediction through label reclassification show good performance relatively. In addition, about 90% accuracy is found in the bad credit forecasts.

• 한국정보통신학회:학술대회논문집
• /
• 한국해양정보통신학회 2000년도 추계종합학술대회
• /
• pp.190-195
• /
• 2000

본 논문에서는 IMT-2000(International Mobile Telecommunication-2000) 휴대용 단말기 수신 주파수인 2.13 - 2.16 GHz 대역의 저잡음 중폭기(LNA ; Low Noise Amplifier)를 직렬 피드백과 저항결합 회로룰 이용하여 설계.구현하였다. 소스 리드에에 부가된 직렬 피드백은 중폭기의 저잡음 특성을 유지하면서 동시에 입력 반사계수를 작게 하고, 또한 대역내의 안정성을 향상시키는 역할을 하였다. 사용된 저항 결합회로는 저주파 영역의 신호를 정합 회로내의 저항을 통해 소모시킴으로써 저잡음 중폭기의 설계시 입력단 정함에 용이하였다. 저잡음 중폭기의 설계.제작에서 저잡음 증폭단에는 HP사의 GaAs FET인 ATF-10136을, 이득 증폭단에는 Mini-Circuit사의 내부 정합된 MMIC인 VNA-25를 사용하였다. 전원회로는 자기 바이어스(Self-bias) 회로를 사용하였고, 유전율 3.5인 테프론 기판 상에 장착하였다. 이렇게 제작된 저잡음 증폭기는 대역 내에서 30 dB 이상의 이득과 0.7 dB 이하의 잡음지수, $P_{ldB}$ 17 dB 이상, 그리고 입.출력 정재파비가 1.5 이하인 특성을 나타내었다.다.

• KIEE International Transaction on Electrical Machinery and Energy Conversion Systems
• /
• 제5B권3호
• /
• pp.277-282
• /
• 2005

This paper describes a step-down AC voltage regulator using an AC chopper and auxiliary transformer, which is a series connected to the main input. The detail design of the AC regulator, logic and PWM pattern of the AC chopper is described and the three-phase AC regulator using two single­phase AC choppers with a three transformer configuration is proposed for three-phase application. The proposed three-phase system has the advantages of lower system cost due to reduced switch number and gate driver circuit as well as advantages of decreased size and weight because it uses a series compensated scheme. The proposed AC regulator has many benefits such as fast voltage control, high efficiency and simple control logic. Experimental results indicate that it can be used as a step-down AC voltage regulator for power saving purposes very efficiently.

• 대한전기학회:학술대회논문집
• /
• 대한전기학회 2003년도 추계학술대회 논문집 전기기기 및 에너지변환시스템부문
• /
• pp.181-183
• /
• 2003

In this paper, phase controlled series resonant converter(PCSRC) system for control power supply in base station is suggested. PCSRC system is robust to load variations because it is POSR(parallel output series resonant) type. And it provides stable output voltage by changing phase angle of MOSFET switches to input voltage variations. Firstly, operation analysis about suggested series resonant converter system was carried. Then Computer simulations using PSIM were carried to prove characteristics of suggested system.

• Journal of Electrical Engineering and Technology
• /
• 제11권1호
• /
• pp.100-108
• /
• 2016

This paper presents a simple high efficiency full-bridge DC-DC converter using a series resonant capacitor. The proposed converter achieves the zero voltage switching of the primary switches under a wide range of load conditions and reduces the high circulating current in the freewheeling mode using the leakage resonant inductance and the series resonant capacitor. Thus, the proposed converter overcomes the drawbacks of the conventional full-bridge DC-DC converter and improves its overall system efficiency. Its structure is simplified by using the leakage inductance of the transformer as the resonant inductance and omitting the DC output filter inductance. Also it can operate over a wide range of input voltages. In this paper, the operational principle, analysis and design example are described in detail. Finally, the experimental results from a 650W (24V/27A) prototype are demonstrated to confirm the operation, validity and features of the proposed converter.

• 대한전기학회:학술대회논문집
• /
• 대한전기학회 2000년도 추계학술대회 논문집 학회본부 D
• /
• pp.666-668
• /
• 2000

In this paper, a fuzzy prediction method is proposed for time series data having uncertainty and non-stationary characteristics. Conventional methods, which use past data directly in prediction procedure, cannot properly handle non-stationary data whose long-term mean is floating. To cope with this problem, a data preprocessing technique utilizing the differences of original time series data is suggested. The difference sets are established from data. And the optimal difference set is selected for input of fuzzy predictor. The proposed method based the Takigi-Sugeno-Kang(TSK or TS) fuzzy rule. Computer simulations show improved results for various time series.