• 한국경영과학회:학술대회논문집
• /
• 한국경영과학회 1995년도 추계학술대회발표논문집; 서울대학교, 서울; 30 Sep. 1995
• /
• pp.325-333
• /
• 1995

Back-propagation is the most widely used algorithm for supervised learning in multi-layer feed-forward networks. However, back-propagation is very slow in convergence. In this paper, a new weight initialization method, called rough map initialization, in multi-layer perceptrons is proposed. To overcome the long convergence time, possibly due to the random initialization of the weights of the existing multi-layer perceptrons, the rough map initialization method initialize weights by utilizing relationship of input-output features with singular value decomposition technique. The results of this initialization procedure are compared to random initialization procedure in encoder problems and xor problems.

• 한국정보디스플레이학회:학술대회논문집
• /
• 한국정보디스플레이학회 2003년도 International Meeting on Information Display
• /
• pp.122-125
• /
• 2003

We describe a new method to initialize the raster and convergence of a flat intelligent tracking (F!T) tube. By splitting up the initialization algorithm into three parts, it can comply with the variety of boundary conditions that are stated for a consumer product. Experiments on raster initialization have shown that the new algorithm speeds up the initialization by one order of magnitude.

• Journal of Electrical Engineering and Technology
• /
• 제11권6호
• /
• pp.1846-1856
• /
• 2016

This study proposes a novel feature point initialization method in order to improve the accuracy of feature point positions by fusing a vision sensor and a lidar. The initialization is a process that determines three dimensional positions of feature points through two dimensional image data, which has a direct influence on performance of a 6-DoF bearing-only SLAM. Prior to the initialization, an extrinsic calibration method which estimates rotational and translational relationships between a vision sensor and lidar using multiple calibration tools was employed, then the feature point initialization method based on the estimated extrinsic calibration parameters was presented. In this process, in order to improve performance of the accuracy of the initialized feature points, an iterative automatic scaling parameter tuning technique was presented. The validity of the proposed feature point initialization method was verified in a 6-DoF bearing-only SLAM framework through an indoor and outdoor tests that compare estimation performance with the previous initialization method.

• 대기
• /
• 제22권1호
• /
• pp.117-128
• /
• 2012

Does snow depth initialization have a quantitative impact on sub-seasonal to seasonal prediction skill? To answer this question, a snow depth initialization technique for seasonal forecast system has been implemented and the impact of the initialization on the seasonal forecast of surface air temperature during the wintertime is examined. Since the snow depth observation can not be directly used in the model simulation due to the large systematic bias and much smaller model variability, an anomaly rescaling method to the snow depth initialization is applied. Snow depth in the model is initialized by adding a rescaled snow depth observation anomaly to the model snow depth climatology. A suite of seasonal forecast is performed for each year in recent 12 years (1999-2010) with and without the snow depth initialization to evaluate the performance of the developed technique. The results show that the seasonal forecast of surface air temperature over East Asian region sensitively depends on the initial snow depth anomaly over the region. However, the sensitivity shows large differences for different timing of the initialization and forecast lead time. Especially, the snow depth anomaly initialized in the late winter (Mar. 1) is the most effective in modulating the surface air temperature anomaly after one month. The real predictability gained by the snow depth initialization is also examined from the comparison with observation. The gain of the real predictability is generally small except for the forecasting experiment in the early winter (Nov. 1), which shows some skillful forecasts. Implications of these results and future directions for further development are discussed.

• 대기
• /
• 제26권1호
• /
• pp.35-45
• /
• 2016

Initialization of the global seasonal forecast system is as much important as the quality of the embedded climate model for the climate prediction in sub-seasonal time scale. Recent studies have emphasized the important role of soil moisture initialization, suggesting a significant increase in the prediction skill particularly in the mid-latitude land area where the influence of sea surface temperature in the tropics is less crucial and the potential predictability is supplemented by land-atmosphere interaction. This study developed a new soil moisture initialization method applicable to the KMA operational seasonal forecasting system. The method includes first the long-term integration of the offline land surface model driven by observed atmospheric forcing and precipitation. This soil moisture reanalysis is given for the initial state in the ensemble seasonal forecasts through a simple anomaly initialization technique to avoid the simulation drift caused by the systematic model bias. To evaluate the impact of the soil moisture initialization, two sets of long-term, 10-member ensemble experiment runs have been conducted for 1996~2009. As a result, the soil moisture initialization improves the prediction skill of surface air temperature significantly at the zero to one month forecast lead (up to ~60 days forecast lead), although the skill increase in precipitation is less significant. This study suggests that improvements of the prediction in the sub-seasonal timescale require the improvement in the quality of initial data as well as the adequate treatment of the model systematic bias.

• 한국지구과학회지
• /
• 제36권5호
• /
• pp.460-475
• /
• 2015

A number of heavy rainfall events on the Korean Peninsula are indirectly influenced by tropical cyclones (TCs) when they are located in southeastern China. In this study, a heavy rainfall case in the middle Korean region is selected to examine the influence of typhoon simulation performance on predictability of remote rainfall over Korea as well as direct rainfall over Taiwan. Four different numerical experiments are conducted using Weather Research and Forecasting (WRF) model, toggling on and off two different improvements on typhoon in the model initial condition (IC), which are TC bogussing initialization and dropwindsonde observation data assimilation (DA). The Geophysical Fluid Dynamics Laboratory TC initialization algorithm is implemented to generate the bogused vortex instead of the initial typhoon, while the airborne observation obtained from dropwindsonde is applied by WRF Three-dimensional variational data assimilation. Results show that use of both TC initialization and DA improves predictability of TC track as well as rainfall over Korea and Taiwan. Without any of IC improvement usage, the intensity of TC is underestimated during the simulation. Using TC initialization alone improves simulation of direct rainfall but not of indirect rainfall, while using DA alone has a negative impact on the TC track forecast. This study confirms that the well-suited TC simulation over southeastern China improves remote rainfall predictability over Korea as well as TC direct rainfall over Taiwan.

• 한국ITS학회 논문지
• /
• 제4권2호
• /
• pp.23-31
• /
• 2005

고속으로 이동하는 차량에 대한 정보수집 및 제공 등의 서비스를 구현해야 하는 지능형 교통시스템(WS : Intelligent Transponation System)은 단거리전용 무선통신(RF-DSRC : Radio Frequency Dedicated Short Range Communication)과 같은 특수목적의 통신시스템이 필수적이다. RF-DSRC를 사용하기 위해서는 먼저 차량 탑재장치(OBE : On-Board Equipment)는 슬롯화된 알로하방식에 의해 할당된 접속요구슬롯(ACTS$\cdot$Activation Slot)내의 접속요구채널(ACTC$\cdot$Activation Channel)을 이용하여 링크초기접속 요구를 한다. 링크초기접속은 통신 시스템의 성능을 결정하는 중요한 요소임에도 불구하고, 링크 초기접속에 대한 수학적 모델링 연구는 미흡한 상태이다. 본 논문에서는 RF-DSRC에 대한 링크초기접속에 관한 수학적 모델링을 제시하고, 모델링의 성능을 분석하기 위한 제시된 부하(G)를 RF-DSRC의 특성에 맞게 정의하여 링크초기접속 확률을 계산하였다.

• 전자공학회논문지SC
• /
• 제39권2호
• /
• pp.85-94
• /
• 2002

본 논문에서는 CITE를 포함한 2차 반복 학습제어 방법이 수렴 성능의 향상과 외란에 대한 강인성 향상에 덧붙여 초기 오차가 있음에도 불구하고 이를 극복할 뿐만 아니라 기존의 알고리즘보다 더 빠른 수렴 능력이 있음을 확인한다. 또한 불안정한 결과를 낳는 높은 학습 게인의 경우에도 CITE를 추가한 본 학습제어 방법에 의해 안정화됨으로써, 빠른 수렴 특성과 강인성 향상을 가져올 수 있음을 보인다. 그리고 본 알고리즘을 선형 시변 시스템에 대해 적용한 시뮬레이션 결과를 통해 초기 오차의 극복 능력이 뛰어남을 확인하고, 아울러 각 학습 게인들이 수렴 속도와 안정성에 미치는 영향을 상세히 분석한다.

• International journal of advanced smart convergence
• /
• 제8권2호
• /
• pp.132-139
• /
• 2019

We address the problem about forecasting the direction of stock price movement in the Korea market. Recently, the deep neural network is popularly applied in this area of research. In deep neural network systems, proper parameter initialization reduces training time and improves the performance of the model. Therefore, in our study, we propose a novel parameter initialization technique and apply this technique for the stock price movement prediction model. Specifically, we design a framework which consists of two models: a base model and a main prediction model. The base model constructed with LSTM is trained by using the large data which is generated by a large amount of the stock data to achieve optimal parameters. The main prediction model with the same architecture as the base model uses the optimal parameter initialization. Thus, the main prediction model is trained by only using the data of the given stock. Moreover, the stock price movements can be affected by other related information in the stock market. For this reason, we conducted our research with two types of inputs. The first type is the stock features, and the second type is a combination of the stock features and the Korea Composite Stock Price Index (KOSPI) features. Empirical results conducted on the top five stocks in the KOSPI list in terms of market capitalization indicate that our approaches achieve better predictive accuracy and F1-score comparing to other baseline models.

• 한국철도학회:학술대회논문집
• /
• 한국철도학회 2001년도 추계학술대회 논문집
• /
• pp.97.1-103
• /
• 2001

Railway passenger demand forecasts may be used directly, or as inputs to other optimization model which is use the demand forecasts to produce estimates of other activities. The optimization models require demand forecasts at the most detailed level. In this environment exponential smoothing forecasting methods such as Holt-Winters are appropriate because it is simple and inexpensive in terms of computation. There are several initialization methods for Holt-Winters Model. The purpose of this paper is to compare the initialization methods for Holt-Winters model.