• 지능정보연구
• /
• 제4권1호
• /
• pp.133-147
• /
• 1998

Recently, many researchers have been involved in finding deterministic equations which can accurately predict future event, based on chaotic theory, or fractal theory. The theory says that some events which seem very random but internally deterministic can be accurately predicted by fractal equations. In contrast to the conventional methods, such as AR model, MA, model, or ARIMA model, the fractal equation attempts to discover a deterministic order inherent in time series data set. In discovering deterministic order, researchers have found that neural networks are much more effective than the conventional statistical models. Even though prediction accuracy of the network can be different depending on the topological structure and modification of the algorithms, many researchers asserted that the neural network systems outperforms other systems, because of non-linear behaviour of the network models, mechanisms of massive parallel processing, generalization capability based on adaptive learning. However, recent survey shows that prediction accuracy of the forecasting models can be determined by the model structure and data structures. In the experiments based on actual economic data sets, it was found that the prediction accuracy of the neural network model is similar to the performance level of the conventional forecasting model. Especially, for the data set which is deterministically chaotic, the AR model, a conventional statistical model, was not significantly different from the MLP model, a neural network model. This result shows that the forecasting model. This result shows that the forecasting model a, pp.opriate to a prediction task should be selected based on characteristics of the time series data set. Analysis of the characteristics of the data set was performed by fractal analysis, measurement of Hurst index, and measurement of Lyapunov exponents. As a conclusion, a significant difference was not found in forecasting future events for the time series data which is deterministically chaotic, between a conventional forecasting model and a typical neural network model.

• 지능정보연구
• /
• 제14권3호
• /
• pp.25-39
• /
• 2008

본 연구는 인공신경망을 이용하여 대대급 방어 작전에서 임의시점에서의 작전지속능력을 예측하는 데 있다. 전투결과에 대한 수학적 모델링은 이를 위한 많은 요인들이 가지는 시?공간적 가변성으로 인해 전투력을 평가하는데 많은 문제점이 있었다. 따라서 이번 연구에서는 대대 전투지휘훈련간 각 부대의 생존률을 전방향 다층 신경망(Feed-Forward Multilayer Perceptrons, MLP)과 일반 회귀신경망(General Regression Neural Network, GRNN)모형에 적용하여 임무달성 여부를 예측하였다. 실험 결과 매개변수들의 비선형적인 관계에도 불구하고 각각 82.62%, 85.48%의 적중률을 보여 일반회귀신경망 모형이 지휘관이 상황을 인식하고 예비대 투입 우선순위 선정 등 실시간 지휘결심을 하는데 도움을 줄 수 있는 방법임을 보여준다.

• 한국조경학회지
• /
• 제30권3호
• /
• pp.73-85
• /
• 2002

The purpose of this study was to develop prediction models for plant species abundance by stream restoration. Generally the stream plant is affected by stream gemophology. So in this study, the relationship between the vegetation abundance and stream gemophology was developed by multiple regression analysis. The stream characteristics utilized in this study were longitudinal slope, transectional slope, micro-landforms through the longitudinal direction, riparian width and geometric mean diameter and biggest diameter of bed material, and cumulated coarse and fine sand weight portion. The Pyungchang River with mountainous watershed and the Kyungan stream and the Bokha stream in the agricultural region were selected and vegetation species abundance and stream characteristics were documented from the site at 2~3km intervals from the upper stream to the lower. The Models for predicting the vegetation abundance were developed by multiple regression analysis using SPSS statistics package. The linear relationship between the dependant(species abundance) and independant(stream characteristics) variables was tested by a graphical method. Longitudinal and transectional slope had a nonlinear relationship with species abundance. In the next step, the independance between the independant variables was tested and the correlation between independant and dependant variables was tested by the Pearson bivariate correlation test. The selected independant variables were transectional slope, riparian width, and cumulated fine sand weight portion. From the multiple regression analysis, the $R^2$for the Pyungchang river, Kyungan stream, Bokga stream were 0.651, 0.512 and 0.240 respectively. The natural stream configuration in the Pyungchang river had the best result and the lower $R^2$for Kyunan and Bokha stream were due to human impact which disturbed the natural ecosystem. The lowest $R^2$for the Bokha stream was due to the shifting sandy bed. If the stream bed is fugitive, the prediction model may not be valid. Using the multiple regression models, the vegetation abundance could be predicted with stream characteristics such as, transection slope, riaparian width, cumulated fine sand weigth portion, after stream restoration.

• 전기학회논문지
• /
• 제60권1호
• /
• pp.184-192
• /
• 2011

In this study, we introduce a identification methodology for FCM-based fuzzy model. The two underlying design mechanisms of such networks involve Fuzzy C-Means (FCM) clustering method and Particle Swarm Optimization(PSO). The proposed algorithm is based on FCM clustering method for efficient processing of data and the optimization of model was carried out using PSO. The premise part of fuzzy rules does not construct as any fixed membership functions such as triangular, gaussian, ellipsoidal because we build up the premise part of fuzzy rules using FCM. As a result, the proposed model can lead to the compact architecture of network. In this study, as the consequence part of fuzzy rules, we are able to use four types of polynomials such as simplified, linear, quadratic, modified quadratic. In addition, a Weighted Least Square Estimation to estimate the coefficients of polynomials, which are the consequent parts of fuzzy model, can decouple each fuzzy rule from the other fuzzy rules. Therefore, a local learning capability and an interpretability of the proposed fuzzy model are improved. Also, the parameters of the proposed fuzzy model such as a fuzzification coefficient of FCM clustering, the number of clusters of FCM clustering, and the polynomial type of the consequent part of fuzzy rules are adjusted using PSO. The proposed model is illustrated with the use of Automobile Miles per Gallon(MPG) and Boston housing called Machine Learning dataset. A comparative analysis reveals that the proposed FCM-based fuzzy model exhibits higher accuracy and superb predictive capability in comparison to some previous models available in the literature.

• 한국정보전자통신기술학회논문지
• /
• 제8권6호
• /
• pp.483-490
• /
• 2015

소프트웨어의 디버깅과정에서 오류 발생의 시간을 기반으로 하는 많은 소프트웨어 신뢰성 모델이 제안되어 왔다. 무한고장 모형과 비동질적인 포아송 과정에 의존한 소프트웨어 신뢰성 모형을 이용하면 모수 추정이 가능하다. 소프트웨어를 시장에 인도하는 결정을 내리기 위해서는 조건부 고장률이 중요한 변수가 된다. 무한 고장 모형은 실제 상황에서 다양한 분야에 사용된다. 특성화 문제, 특이점의 감지, 선형 추정, 시스템의 안정성 연구, 수명을 테스트, 생존 분석, 데이터 압축 및 기타 여러 분야에서의 사용이 점점 많아지고 있다. 통계적 공정 관리 (SPC)는 소프트웨어 고장의 예측을 모니터링 함으로써 소프트웨어 신뢰성의 향상에 크게 기여 할 수 있다. 컨트롤 차트는 널리 소프트웨어 산업의 소프트웨어 공정 관리에 사용되는 도구이다. 본 논문에서 NHPP에 근원을 둔 로그 포아송 실행시간 모형, 즉,Musa-Okumo 모형과 파우어 로우(Power-law) 모형의 평균값 함수를 이용한 통계적 공정관리 차트를 이용한 제어 메커니즘을 제안하였다.

• 산업공학
• /
• 제20권1호
• /
• pp.1-10
• /
• 2007

The main purpose of this research is to find out whether curriculums of industrial engineering (IE) departments meet the demand of IE graduates working in various fields. The research was conducted as an online questionnaire survey selecting IE Graduates working in industries as practising engineers. 1,324 participants were validated among 1,477 participants. 13 fields were selected and used in the survey. Those were; 1) Mathematical statistics, 2) Computer, 3) Purchase, 4) Production system, 5) Logistics, 6) Marketing, 7) Monetary, 8) Experiment methods, 9) Operations Research (OR), 10) Human Factors, 11) Quality, 12) Engineering management, and 13) Information systems. Using the 5-scale Likert rating, each education subject was assessed both in terms of its usefulness in practices and the amount it being taught in school. As a result, courses such as motion/time study, linear programming that IE has traditionally focused showed less usefulness in practices while it is taught in relatively large amount in schools. However, courses such as 6 sigma, CRM which are closely related to industrial practices showed high usefulness in practices compared with low degree of teaching in school. This was the first ever large scalesurvey conducted for IE graduates in Korea. The result of survey displayed many helpful information on current status and future direction of IE education in Korea.

• Journal of Power Electronics
• /
• 제16권3호
• /
• pp.1209-1217
• /
• 2016

This paper presents a novel charge pump scheme that combines the advantages of Fibonacci and Dickson charge pumps to obtain 30 V voltage for display driver integrated circuit application. This design only requires four external capacitors, which is suitable for a small-package application, such as smart card displays. High-amplitude (<6.6 V) clocks are produced to enhance the gate drive of a Dickson charge pump and improve the system's current drivability by using a voltage-doubler charge pump with a pulse skip regulator. This regulation engages many middle-voltage devices, and approximately 30% of chip size is saved. Further optimization of flying capacitors tends to decrease the total chip size by 2.1%. A precise and simple model for a one-stage Fibonacci charge pump with current load is also proposed for further efficiency optimization. In a practical design, its voltage error is within 0.12% for 1 mA of current load, and it maintains a 2.83% error even for 10 mA of current load. This charge pump is fabricated through a 0.11 μm 1.5 V/6 V/32 V process, and two regulators, namely, a pulse skip one and a linear one, are operated to maintain the output of the charge pump at 30 V. The performances of the two regulators in terms of ripple, efficiency, line regulation, and load regulation are investigated.

• 전력전자학회논문지
• /
• 제15권3호
• /
• pp.167-178
• /
• 2010

영구자석 동기전동기에서 고정자 권선의 단락으로 인해 발생하는 권선 고장을 동작 중 실시간으로 검출할 수 있는 고장 진단 기법을 제시한다. 제안된 기법은 고조파 분석을 통해 q축 전류의 2차 고조파를 관찰함으로서 이루어지며 고장이 없는 정상 조건에서의 고조파 데이터와 비교를 통해서 고장을 판별한다. 임의의 정상 동작 조건에서의 고조파 데이터는 선형 보간법과 몇 개의 사전 측정된 고조파 데이터를 통해서 구해진다. 제안된 고장 검출 기법의 타당성을 입증하기 위해 내부 고정자의 권선 단락이 가능한 전동기가 제작되었으며 전체 구동 시스템과 고조파 분석 알고리즘 및 고장 검출 알고리즘이 DSP TMS320F28335에 의해 구현되어 실험이 수행된다. 제안된 방법은 부가적인 진단 장비를 필요로 하지 않으며 정상 상태 조건만 만족된다면 동작 중 실시간으로 고장을 검출할 수 있다.

• 한국통신학회논문지
• /
• 제29권4A호
• /
• pp.458-465
• /
• 2004

본 논문에서는 CMOS 공정을 사용하여 선형적으로 제어가 가능한 П모델 감쇄기를 구현하였고, 브릿지 T모델을 사용한 감쇄기를 제안하였다. CMOS 공정으로 코어의 수동소자를 트랜지스터로 구현하여 기존의 수동소자나 능동소자를 사용하는데 따른 문제점을 개선하였으며 GaAs MESFET공정의 문제점인 높은 비용 또한 해결하였다. П모델 감쇄기는 2-poly 4-metal 0.35$\mu\textrm{m}$ CMOS 공정을 사용하여 구현하였으며 기존의 수백 MHz의 동작 주파수범위를 DC-l㎓ 대역으로 향상시켰다. 또한 700$\mu\textrm{m}$${\times}$300$\mu\textrm{m}$ 로 면적을 줄였으며 일정한 주파수에서 감쇄 값과 제어 전압 사이의 선형적인 관계를 개선하였다. 제안된 브릿지 T모델 감쇄기는 П모델에서 동작주파수를 제한하던 매칭 특성을 향상시킴으로써 동작 주파수 템위를 DC-2㎓ 대역으로 넓혔다.

• 한국통신학회논문지
• /
• 제36권5C호
• /
• pp.302-308
• /
• 2011

본 논문에서는 시변 다중 입출력 (multiple-input multiple-output) 방송(broadcast) 채널에서 피드백 양자화와 지연을 고려한 협력 빔형성 (coordinated beamforming: CBF) 시스템을 제안한다. 다중 데이터 스트림을 전송하는 CBF 시스템에 피드백 양자화 기법을 적용하고, 구현 복잡도와 피드백 오버헤드 측면에서 효율적인 CBF 시스템을 제시한다. 또한, 실제적인 무선통신 환경에서 발생하는 피드백 지연에 의한 오류를 최소화하기 위하여 사용자 단말에 선형 채널 예측기를 적용한다. 선형 예측기로 Wiener 필터를 이용하여 피드백 지연시간 후의 미래 채널을 예측하교 이를 토대로 피드백 정보를 생성함으로써 지연된 피드백 정보를 이용하는 CBF 시스템의 성능을 향상시킨다. 모의실험을 통해 다양한 도플러 (Doppler) 주파수의 MIMO 방송 채널에서 양자화와 Wiener 필터를 적용한 CBF 시스템의 향상된 심볼 오율과 합 전송률 성능을 확인한다.