• 감성과학
• /
• 제1권1호
• /
• pp.93-103
• /
• 1998

In this paper, we present change of human sensiblity when the 26 healthy female subjects were exposed with visual picture stimulus. We used Intermational Affective Picture System as the visual stimulus. The methods are AutoRegressive(AR) spectrum which is a linear method and Return Map which is a nonlinear mithod. SR spectrum may variability(HRV). The LF/HF of HRV and the variation of Return Map were analyzed from ECG signal of the female subjects. Return Map of RR intervals were analyzed by computiong the variation. When the subjets were stimulated by the pleasant pictures, LF/HF and variation were decreased compared with unpleasant stimulus, We may obtain good parameters for the measurement of the change of human sensibility for the visual picture stimulus.

• 대한산업공학회지
• /
• 제39권6호
• /
• pp.535-545
• /
• 2013

The goal of stock investment is earning high rate or return with stability. To accomplish this goal, using a portfolio that distributes stocks with high rate of return with less variability and a stock price prediction model with high accuracy is required. In this paper, three methods are suggested to require these conditions. First of all, in portfolio re-balance part, Max-Return and Min-Risk (MRMR) model is suggested to earn the largest rate of return with stability. Secondly, Entering/Leaving Rule (E/L) is suggested to upgrade portfolio when particular stock's rate of return is low. Finally, to use outstanding stock price prediction model, a model based on Semi-Supervised Learning (SSL) which was suggested in last research was applied. The suggested methods were validated and applied on stocks which are listed in KOSPI200 from January 2007 to August 2008.

• 경영과정보연구
• /
• 제26권
• /
• pp.1-26
• /
• 2008

Since Capital Asset Pricing Model(CAPM) was proposed in the early 1960s by William Sharpe(1964) and John Lintner(1965) researchers have investigated the validity of the model. The results of empirical researches do not show that expected returns of stocks seem to be determined solely by systematic risk of the stocks as precicted by CAPM. In this paper the relationship between transaction volume and expected returns of stocks was investigated. Empirical cross-sectional analysis about the data collected from Stock Market of Korea Exchange shows transaction volume and variability of stock returns play an important role in pricing assets. The well-known variables which were used traditionally to explain the differences of expected returns among stocks such as the size and beta of a stock seems to be unimportant in pricing assets.

• 경영과학
• /
• 제31권3호
• /
• pp.1-12
• /
• 2014

This study suggests the two types DEA models such as DEA CCR model and Super Efficiency model to evaluate the value of a company and to apply them for the investments. 14 kinds of real data of companies such as EV/EBITDA, EPS growth rate, PCR, PER, dividend yield, PBR, stock price/net current asset, debt ratio, current ratio, ROE, operating margin, inventory turnover, accounts receivable turnover, and sales growth ratio were used as input variables of DEA models. 12 year data from December 30, 2000 up to December 30, 2012 were collected, and the data with negative, missing and 0 values were removed reflecting the characteristics of the DEA. In order to verify the effectiveness of the models, we compared the historical variability and rate of return of both models those of the market. Study results are as follows. First, two DEA models are more stable than market in terms of rate of return because the historical variability of both models are less than that of market. Second, Super Efficiency model is more stable than CCR model. Lastly, the cumulative rate of return of Super Efficiency model (434%) is greater than that of the CCR model (420%) and that of the market (269%).

• 대기
• /
• 제33권1호
• /
• pp.1-20
• /
• 2023

Holding the longest observation data from April 1904, Busan is one of the essential points to understand the climate variability of the Korean Peninsula without missing data since implementing the modern weather observation of the South Korea. Busan is featured by coastal areas and affected by various climate factors and fluctuations. This study aims to investigate climate variability and changes in climatic variables, extremes, and several weather indexes. The statistically significant change points in daily mean rainfall intensity and temperature were found in 1964 and 1965. Based on the change point detection, 117 years were divided into two periods for daily mean rainfall intensity and temperature, respectively. In the long-term temperature analysis of Busan, the increasing trend of the daily maximum temperature during the period of 1965~2021 was larger than the daily mean temperature and the daily minimum temperature. Applying Ensemble Empirical Mode Decomposition, daily maximum temperature is largely affected by the decadal variability compared to the daily mean and minimum temperature. In addition, the trend of daily precipitation intensity from 1964~2021 shows a value of about 0.50 mm day^-1, suggesting that the rainfall intensity has increased compared to the preceding period. The results in extremes analysis demonstrate that return values of both extreme temperatures and precipitation show higher values in the latter than in the former period, indicating that the intensity of the current extreme phenomenon increases. For Wet-Bulb Globe Temperature (effective humidity), increasing (decreasing) trend is significant in Busan with the second (third)-largest change among four stations.

• 한국방재안전학회논문집
• /
• 제15권2호
• /
• pp.45-56
• /
• 2022

가뭄 및 갈수시에 용수부족 현상이 발생하나 회귀수량을 고려한 대응이나 대책 마련이 진행되지 않고 있다. 이에 본 연구에서 자료기반의 기계학습 모형(LSTM)을 통해 회귀수량 중 하수종말처리장의 방류량을 예측하였다. 입력자료로 방류량, 유입량, 강수량, 수위를 사용하였고 예측 결과의 정확도를 개선하기 위하여 추가적으로 입력변수의 변동성 분포를 고려하였다. 방류량 자료의 변동성을 확인하기 위해서 관측값과 분포 사이의 잔차를 복합삼각함수 형태로 가정하여 이론적인 확률분포와 함께 방류량 최적의 분포 형태로 나타내었다. 변동성 분포를 고려한 입력자료를 이용한 결과와 그렇지 않는 결과를 비교한 결과, 오차정도가 감소함을 보였으며 이는 변동성 분포가 계절성을 상대적으로 잘 재현하였기 때문이라 판단된다. 따라서 본 연구에서 구축한 하수종말장처리장의 방류량 예측 모형을 활용할 경우 보다 정확한 회귀수량 예측이 가능하여 효율적인 하천수 관리 체계를 수립하는데 기초자료로 활용될 수 있을 것으로 기대된다.

• Communications for Statistical Applications and Methods
• /
• 제15권6호
• /
• pp.925-937
• /
• 2008

본 논문에서는 주식시장에서 거래되는 다수의 주식거래종목들을 몇 개의 그룹으로 군집화하는 주제를 연구한다. 시간에 관계없이 분산이 일정한 ARMA모형과 다르게, 주가, 환율 등의 금융시계열자료에서는 조건부 이분산성을 따르게 된다. 또한, 많은 사람들이 금융시계열자료에서 관심을 갖는 것은 바로 이 변동성이다. 그러므로, 이 연구에서는 조건부 이분산성을 모형화하기에 적합하다고 알려진 일반화 조건부 이분산성 자기회귀모형에 초점을 맞춘다. 먼저 두 개의 주식종목들 사이에 변동성(volatility)의 유사성 그리고 구조의 유사성을 재는 거리를 정의하고, 모의실험을 수행한다. 실증자료로 최근 3년 동안 관찰된 국내 11개 주가의 수익률을 변동성과 구조에 따라 군집화한다.

• 아태비즈니스연구
• /
• 제13권1호
• /
• pp.247-262
• /
• 2022

Purpose - The purpose of this study is to examine the impact of the Pandamic Declaration on 'untact firms' listed in KOSPI and KOSDAQ market in order to verify Investor Mania Hypothesis. Design/methodology/approach - This study collected financial data for 44 untact firms in KOSPI and KOSDAQ market. Then, we employed ESM(Event Study Methodology), EGARCH model and DID(Difference-In-Difference) for analysis. Findings - First, in contrast with the benchmarking index, KOSPI 200 which shows a negative (-) abnormal return trend, the untact firms have positive abnormal return trend consistently. Second, after the Pandemic Declaration, the variability of abnormal return for the untact firms is found to be significantly positive. Third, we find that the cumulative abnormal return and volatility of the untact firms significantly increase after the Pandemic Declaration. Research implications or Originality - Based on the Investor Mania Hypothesis, we confirm that the market potential of untact firms after the Pandemic Declaration is observed when compared with the KOSPI 200.

• 대기
• /
• 제32권1호
• /
• pp.1-15
• /
• 2022

Recently, Japan's Meteorological Research Institute presented the d4PDF database (Database for Policy Decision-Making for Future Climate Change, d4PDF) through large-scale climate ensemble simulations to overcome uncertainty arising from variability when the general circulation model represents extreme-scale precipitation. In this study, the change of precipitation characteristics between the historical and future climate conditions in the Yongdam-dam basin was analyzed using the d4PDF data. The result shows that annual mean precipitation and seasonal mean precipitation increased by more than 10% in future climate conditions. This study also performed an analysis on the change of the return period rainfall. The annual maximum daily rainfall was extracted for each climatic condition, and the rainfall with each return period was estimated. In this process, we represent the extreme-scale rainfall corresponding to a very long return period without any statistical model and method as the d4PDF provides rainfall data during 3,000 years for historical climate conditions and during 5,400 years for future climate conditions. The rainfall with a 50-year return period under future climate conditions exceeded the rainfall with a 100-year return period under historical climate conditions. Consequently, in future climate conditions, the magnitude of rainfall increased at the same return period and, the return period decreased at the same magnitude of rainfall. In this study, by using the d4PDF data, it was possible to analyze the change in extreme magnitude of rainfall.

• 한국해안·해양공학회논문집
• /
• 제26권2호
• /
• pp.72-80
• /
• 2014

설계조위 산정에 종종 이용되고 있는 약최고고조위는 발생빈도가 불분명할 뿐 아니라 평균해수면 상승에 따른 시간적 편차 및 해역별 조위특성 차이에 기인한 공간적 편차 등의 문제점을 내포하고 있다. 이러한 문제점을 해결하기 위해 해역별로 주요 4대분조 및 연주조 등의 비율을 조사하였고 확률분포함수에 의한 해석을 시행하였다. 시간적 편차문제는 최신조위자료를 활용함으로써 쉽게 해결될 수 있다. 공간적 편차문제를 해결하기 위하여 연주조를 고려함으로써 하절기에 형성되는 약최고고조위를 대안으로 제시하였다. 분석결과 남해안에서 10 cm 이상, 동해안에서 15~25 cm 정도의 설계조위 증분이 필요한 것으로 나타났다.