• International Journal of Fuzzy Logic and Intelligent Systems
• /
• 제8권1호
• /
• pp.31-36
• /
• 2008

This paper presents adaptive learning data of evolvable neural networks (ENNs) for time series prediction of nonlinear dynamic systems. ENNs are a special class of neural networks that adopt the concept of biological evolution as a mechanism of adaptation or learning. ENNs can adapt to an environment as well as changes in the enviromuent. ENNs used in this paper are L-system and DNA coding based ENNs. The ENNs adopt the evolution of simultaneous network architecture and weights using indirect encoding. In general just previous data are used for training the predictor that predicts future data. However the characteristics of data and appropriate size of learning data are usually unknown. Therefore we propose adaptive change of learning data size to predict the future data effectively. In order to verify the effectiveness of our scheme, we apply it to chaotic time series predictions of Mackey-Glass data.

• 제어로봇시스템학회:학술대회논문집
• /
• 제어로봇시스템학회 2005년도 ICCAS
• /
• pp.920-924
• /
• 2005

This paper presents adaptive learning data of evolvable neural networks (ENNs) for time series prediction of nonlinear dynamic systems. ENNs are a special class of neural networks that adopt the concept of biological evolution as a mechanism of adaptation or learning. ENNs can adapt to an environment as well as changes in the environment. ENNs used in this paper are L-system and DNA coding based ENNs. The ENNs adopt the evolution of simultaneous network architecture and weights using indirect encoding. In general just previous data are used for training the predictor that predicts future data. However the characteristics of data and appropriate size of learning data are usually unknown. Therefore we propose adaptive change of learning data size to predict the future data effectively. In order to verify the effectiveness of our scheme, we apply it to chaotic time series predictions of Mackey-Glass data.

• 한국정보디스플레이학회:학술대회논문집
• /
• 한국정보디스플레이학회 2009년도 9th International Meeting on Information Display
• /
• pp.1099-1102
• /
• 2009

Conventional stereoscopic (3D) displays using binocular parallax generate unnatural conflicts between convergence and accommodation. Those conflicts can affect the ability to fuse binocular images and may cause visual fatigue. This study examined time-series changes in visual fatigue and depth sensation while viewing stereoscopic images with changing parallax. We examined the physiological changes, including the subjective symptoms of visual fatigue, when viewing five parallax conditions. The time-series results suggest that 2D and 3D images produce significantly different types of visual fatigue over the range of binocular disparity.

• 한국콘크리트학회:학술대회논문집
• /
• 한국콘크리트학회 1999년도 봄 학술발표회 논문집(I)
• /
• pp.487-492
• /
• 1999

The purpose of this study to find the mixture of concrete for Top-Down method. Throughout test of elapsed time change and L-type flow, it was proposed basic performance and level of top-down method concrete. When change as to elapsed time is considered, so series of F10 added 10% S.P satisfied slump and demanded flow (60$\pm$5cm), and L-type slump, L-type flow satisfied liquidity, it can be considered basic mixture of designed actual frame later.

• 대한원격탐사학회:학술대회논문집
• /
• 대한원격탐사학회 2006년도 Proceedings of ISRS 2006 PORSEC Volume II
• /
• pp.635-638
• /
• 2006

Regression of conventional prediction techniques in data mining uses the model which is generated from the training step. This model is applied to new input data without any change. If this model is applied directly to time series, the rate of prediction accuracy will be decreased. This paper proposes an incremental regression for time series prediction like typhoon track prediction. This technique considers the characteristic of time series which may be changed over time. It is composed of two steps. The first step executes a fractional process for applying input data to the regression model. The second step updates the model by using its information as new data. Additionally, the model is maintained by only recent data in a queue. This approach has the following two advantages. It maintains the minimum information of the model by using a matrix, so space complexity is reduced. Moreover, it prevents the increment of error rate by updating the model over time. Accuracy rate of the proposed method is measured by RME(Relative Mean Error) and RMSE(Root Mean Square Error). The results of typhoon track prediction experiment are performed by the proposed technique IMLR(Incremental Multiple Linear Regression) is more efficient than those of MLR(Multiple Linear Regression) and SVR(Support Vector Regression).

• 환경영향평가
• /
• 제12권1호
• /
• pp.45-54
• /
• 2003

The purpose of this paper is to examine the trend on the change of the cherry blossom flowering time due to the temperature change by selecting regions that have long periods of cherry blossom flowering time data as cases. With the flowering time data, the distribution of cherry blossom flowering time, time series change and change rate of cherry blossom flowering time were analyzed. Also, the correlation between the cherry blossom flowering time and the temperature was analyzed. The flowering of cherry blossom is earlier in metropolitan areas, and in the east coastal region than the west coastal region. The trend on the change of the cherry blossom flowering time is very similar to change the temperature. The change rate of the cherry blossom flowering time is rising up in the whole regions under study, and is relatively high in metropolitan areas. Especially, the cherry blossom flowering time festinated greatly in Pohang that is one of the heavily industrialized cities. From the analysis of correlation analysis between cherry blossom flowering time and temperature elements, the cherry blossom flowering time is highly related with mean temperature of March, which the month is just before the beginning of flowering.

• 대한원격탐사학회지
• /
• 제36권6_1호
• /
• pp.1379-1391
• /
• 2020

농업에서의 무인기는 촬영 영역은 작지만, 위성이 가지지 못하는 초고해상도의 영상 수집이 가능하며, 작물의 생물계절에 맞는 영상을 적시에 획득 할 수 있어 들녘단위 농경지의 모니터링에 유용하게 사용될 수 있다. 하지만 무인기의 경우 위성과 달리 다양한 카메라와 촬영 환경에 따른 다중시기 영상을 활용하기 때문에 시계열 영상 활용을 위해서는 정규화 된 영상자료를 활용하는 것이 필수적으로 요구된다. 본 연구는 무인기 다중분광 영상의 농업 모니터링 시계열 활용을 위해 촬영 환경에 따른 무인기 반사율 및 식생지수의 변동성을 분석하였다. 촬영 고도, 촬영 방향, 촬영시간, 운량과 같은 환경요인에 따른 반사율 변동성은 8%에서 11%로 매우 크게 나타났으나, 식생지수의 변동성은 1% ~ 5%로 안정적인 것을 확인 할 수 있었다. 이러한 현상은 무인기 다중분광센서의 특성과 후처리 프로그램의 정규화 등 다양한 원인이 존재하는 것으로 판단된다. 따라서 무인기 영상의 시계열 활용을 위해서는 식생지수와 같은 밴드비율함수를 활용하는 것이 권장되며 촬영 시 가능한 동일한 촬영시간, 촬영 고도, 촬영 방향을 설정하여 시계열 영상의 변동성을 최소화하는 것이 권장된다.

• 대한전기학회논문지
• /
• 제41권3호
• /
• pp.237-243
• /
• 1992

The large value of the snubber capacitor is needed to protect the devices in high voltage converters using series connected power semiconductors. But that results in more losses and longer commutation time. So, new technique of series connection is required, which can minimize the value of snubber capacitor and also promote the reliability of high voltage converters. We study on the switching characteristics of series connected power semiconductors and then propose a novel switching algorithm for series-connection which is able to implement not only the dynamic voltage balancing in spite of the differerce of switching characteristics, but the minimization of the value of snubber capacitor, through the change of the value of snubber capacitor by Miller effect. Finally, we illustrate the validity of this synchronization by computer simulation and experimental results.

• 디지털콘텐츠학회 논문지
• /
• 제19권9호
• /
• pp.1727-1737
• /
• 2018

본 논문에서는 토지피복도에서 공간구조를 검출하고 시계열 공간구조 변화를 검출하는 시스템을 제안한다. 서로 다른 시간의 토지피복도에서 패치를 검출하고 패치의 측정요소를 계산하여 공간구조 패턴을 분석한다. 검출된 시계열 패치에 대해 패치 매핑을 이용하여 유지, 생성, 소멸, 분할, 병합, 혼합적 변환 등의 변화 유형을 결정한다. 또한, 시계열 토지피복도의 패치 기반 공간구조 패턴을 이진으로 저장하여 변화를 추출하였다. 본 논문에서는 제안하는 토지피복도 공간구조 변화검출 시스템을 통해 해당 지역(도시)의 난개발 현상을 진단하고, 향후 도시공간구조의 재구축을 위한 계획수립에 근거 자료로 활용될 수 있음을 보여주고 있다.

• Wind and Structures
• /
• 제26권3호
• /
• pp.129-146
• /
• 2018

Extreme wind speed analysis has been carried out conventionally by assuming the extreme series data is stationary. However, time-varying trends of the extreme wind speed series could be detected at many surface meteorological stations in China. Two main reasons, exposure change and climate change, were provided to explain the temporal trends of daily maximum wind speed and annual maximum wind speed series data, recorded at Hangzhou (China) meteorological station. After making a correction on wind speed series for time varying exposure, it is necessary to perform non-stationary statistical modeling on the corrected extreme wind speed data series in addition to the classical extreme value analysis. The generalized extreme value (GEV) distribution with time-dependent location and scale parameters was selected as a non-stationary model to describe the corrected extreme wind speed series. The obtained non-stationary extreme value models were then used to estimate the non-stationary extreme wind speed quantiles with various mean recurrence intervals (MRIs) considering changing climate, and compared to the corresponding stationary ones with various MRIs for the Hangzhou area in China. The results indicate that the non-stationary property or dependence of extreme wind speed data should be carefully evaluated and reflected in the determination of design wind speeds.