• Journal of Information Processing Systems
• /
• 제14권6호
• /
• pp.1508-1520
• /
• 2018

In this paper, we propose an improved model to provide users with a better long-term prediction of waterworks operation data. The existing prediction models have been studied in various types of models such as multiple linear regression model while considering time, days and seasonal characteristics. But the existing model shows the rate of prediction for demand fluctuation and long-term prediction is insufficient. Particularly in the deep running model, the long-short-term memory (LSTM) model has been applied to predict data of water purification plant because its time series prediction is highly reliable. However, it is necessary to reflect the correlation among various related factors, and a supplementary model is needed to improve the long-term predictability. In this paper, convolutional neural network (CNN) model is introduced to select various input variables that have a necessary correlation and to improve long term prediction rate, thus increasing the prediction rate through the LSTM predictive value and the combined structure. In addition, a multiple linear regression model is applied to compile the predicted data of CNN and LSTM, which then confirms the data as the final predicted outcome.

• Journal of the Korean Data and Information Science Society
• /
• 제25권6호
• /
• pp.1507-1520
• /
• 2014

본 연구는 금리변동성이 금리수준과 양의 상관관계가 있음을 밝힘으로써 현행 위험기준 자기자본제도 하에서 금리리스크의 측정에 사용되는 금리변동계수가 금리수준에 따라 달라질 필요가 있음을 제시한다. 이를 위해 본 연구는 국공채 금리 자료를 이용, 이자율의 역사적 변동성을 측정하여 이자율 수준과 금리변동성 간의 비례관계를 확인한다. 또한 균형이자율 모형 중 지수형 Vasicek 모형과 Cox-Ingersoll-Ross 모형을 통해 금리수준과 금리변동성의 상관관계를 분석한다. 이후 국공채 자료에 기반하여 두 이자율 모형의 모수를 추정하고 이에 따라 금리수준별 금리변동성을 측정한다. 이에 따르면 금리수준이 높을수록 금리변동성 역시 크게 나타난다. 금리가 2.8%일 경우 지수형 Vasicek 모형과 CIR 모형에서는 금리변동계수가 각각 0.9와 1.1로 현 제도 하에서 금리하락 시 적용되는 금리변동계수 1.5보다 작게 나타난다. 이는 금리리스크에 대응하여 보험사가 보유해야 하는 자기자본이 현재 수준의 60%와 73% 로 낮춰질 수 있음을 의미한다. 본 연구에서는 이러한 결과를 반영하여 수정 금리변동계수를 이자율 모형에 따라 금리수준별로 제시한다. 금리수준과 금리변동계수를 연동시킴으로써 금리리스크를 보다 합리적으로 측정하고 관리하는 방안을 제시하였다는 점에 본 연구의 의의가 있다.

• 한국음향학회지
• /
• 제18권1호
• /
• pp.72-77
• /
• 1999

본 논문에서는 Wavelet 변환과 Vector Quantization(VQ)을 이용한 VBR (variable-bit-rate) 비디오 트래픽 모델을 제안하고 있다. 여기에서 제안된 방법은 영상 트래픽을 Wavelet 변환한 후 두 개의 요소로 분해하여 각각을 분리하여 모델링한다. 첫 번째 요소는 AR(1) 프로세스 모델로 이것은 트래픽의 비교적 장시간에 걸친 변화 특성을 표현한다. 두 번째 요소는 벡터 양자화(VQ)를 사용하여 비교적 짧은 시간의 트래픽 특성을 표현한다. 다른 VBR 트래픽의 모델 방법과 비교해서 본 논문에서 제안하는 모델은 세 가지 장점을 가지고 있다. 첫째로 영상 트래픽의 특성을 장시간과 단시간의 형태로 나누어 모델링을 할 수 있다. 둘째로 트래픽 데이터의 주기적 코딩 구조를 보존한다. 마지막으로 프레임 레벨과 슬라이스 레벨의 트래픽 모델링을 통합할 수 있다. 통계적 측정과 네트워크 성능 실험을 통하여 제안된 모델의 타당성을 검증하였다.

• Journal of Information Technology Applications and Management
• /
• 제30권3호
• /
• pp.1-13
• /
• 2023

Demand forecasting is a crucial task for an online retail where has to manage daily fresh foods effectively. Failing in forecasting results loss of profitability because of incompetent inventory management. This study investigated the optimal performance of different forecasting models for a very short shelf-life product. Demand data of 13 perishable items with aging of 210 days were used for analysis. Our comparison results of four methods: Trivial Identity, Seasonal Naïve, Feed-Forward and Autoregressive Recurrent Neural Networks (DeepAR) reveals that DeepAR outperforms with the lowest MAPE. This study also suggests the managerial implications by employing coefficient of variation (CV) as demand variation indicators. Three classes: Low, Medium and High variation are introduced for classify 13 products into groups. Our analysis found that DeepAR is suitable for medium and high variations, while the low group can use any methods. With this approach, the case can gain benefit of better fill-rate performance.

• 한국데이터정보과학회:학술대회논문집
• /
• 한국데이터정보과학회 2005년도 추계학술대회
• /
• pp.151-152
• /
• 2005

IGARCH and Stochastic Volatility Model(SVM, for short) have frequently provided useful approximations to the real aspects of financial time series. This article is concerned with modeling various Korean financial time series using both IGARCH and Stochastic Volatility Models. Daily data sets with sample period ranging from 2000 and 2004 including KOSPI, KOSDAQ and won-dollar exchange rate are comparatively analyzed using IGARCH and SVM.

• Journal of the Korean Data and Information Science Society
• /
• 제16권4호
• /
• pp.835-841
• /
• 2005

IGARCH and Stochastic Volatility Model(SVM, for short) have frequently provided useful approximations to the real aspects of financial time series. This article is concerned with modeling various Korean financial time series using both IGARCH and stochastic volatility models. Daily data sets with sample period ranging from 2000 and 2004 including KOSPI, KOSDAQ and won-dollar exchange rate are comparatively analyzed using IGARCH and SVM.

• 수산경영론집
• /
• 제40권3호
• /
• pp.169-187
• /
• 2009

This study analyzes the long and short term effect of exchange rate on the import of Korea's fisheries focussed on main fisheries imported from China. The estimation models consist of the following contents. The first model consists of one dependent variable-import quantity of fisheries imported from China(${IMQ_t}^{CHO}$) and three independent variables-${RP_t}^{CHO}$, $EXC_t$ and $GDP_t$. The second one-one dependent variable-import quantity of fisheries imported from China(${JMQ_t}^{NAG})$ and three independent variables-${RP_t}^{NAG}$, $EX_t$ and $GDP_t$. the third one-one dependent variable-import quantity of fisheries imported from China(${IMQ_t}^{AH}$) and three independent variables-${RP_t}^{AH}$, $EX_t$ and $GDP_t$. the forth one-one dependent variable-import quantity of fisheries imported from China(${IMQ_t}^{KO}$) and three independent variables-${RP_t}^{KO)$, $EX_t$ and $GDP_t$. the last one is made up of one dependent variable-import quantity of fisheries imported from China(${IMQ_t}^{GAL}$) and three independent variables-, ${RP_t}^{GAL}$, $EX_t$ and $GDP_t$. and. The estimation results show that exchange rate of the independent variables are statistically significant in only the first model. The figure is elastic. Especially, the effect of exchange rate in first model is grater than that of the. However, the effect of exchange rate, one of independent variables in the ECM, is not statistically significant.

• 음성과학
• /
• 제7권1호
• /
• pp.17-29
• /
• 2000

The STC(Sinusoidal Transform Coding) is a vocoding technique that uses a sinusoidal speech model to obtain high- quality speech at low data rate. It models and synthesizes the speech signal with fundamental frequency and its harmonic elements in frequency domain. To reduce the data rate, it is necessary to represent the sinusoidal amplitudes and phases with as small number of peaks as possible while maintaining the speech quality. As a basic research to develop a low-rate speech coding algorithm using the sinusoidal model, in this paper, we investigate the speech quality depending on the number of sinusoids. By varying the number of spectral peaks from 5 to 40 speech signals are reconstructed, and then their qualities are evaluated using spectral envelope distortion measure and MOS(Mean Opinion Score). Two approaches are used to obtain the spectral peaks: one is a conventional STFT (Short-Time Fourier Transform), and the other is a multiresolutional analysis method.

• 한국건축시공학회:학술대회논문집
• /
• 한국건축시공학회 2023년도 봄 학술논문 발표대회
• /
• pp.179-180
• /
• 2023

In this study, the performance of the prediction model was compared and analyzed using DNN and LSTM learning models to predict the amount of dry shrinkage of the concrete. As a result of the analysis, DNN model had a high error rate of about 51%, indicating overfitting to the training data. But, the LSTM learning model showed a relatively higher accuracy with an error rate of 12% compared to the DNN model. Also, the Pre_LSTM model which preprocess data, showed the performance with an error rate of 9% and a coefficient of determination of 0.887 in the LSTM learning model.

• Nutrition Research and Practice
• /
• 제4권5호
• /
• pp.375-382
• /
• 2010

The precise effects of protein intake on fractional synthesis rate (FSR) of muscle protein are still under debate. The sample size of these studies was small and the conclusions in young and elderly subjects were inconsistent. To assess the effect of dietary protein intake on the FSR level, we conducted a meta-analysis of controlled protein intake trials. Random-effects models were used to calculate the weighted mean differences (WMDs). Ten studies were included and effects of short-term protein intake were evaluated. In an overall pooled estimate, protein intake significantly increased the FSR (20 trials, 368 participants; WMD: 0.025%/h; 95%CI: 0.019-0.031; P < 0.0001). Meta-regression analysis suggested that the protein dose was positively related to the effect size (regression coefficient = 0.108%/h; 95%CI: 0.035, 0.182; P = 0.009). A subgroup analysis indicated that protein intake significantly increased FSR when the protein dose was ${\leq}$ 0.80 g/kg BW (16 trials, 308 participants; WMD: 0.027%/h; 95%CI: 0.019-0.031; P < 0.0001), but did not affect FSR when the protein dose was > 0.80 g/kg BW (4 trials, 60 participants; WMD: 0.016%/h; 95%CI: 0.004-0.029; P = 0.98). In conclusion, this study is the first integrated results showing that a short-term protein intake is effective at improving the FSR of muscle protein in the healthy elderly as well as young subjects. This beneficial effect seems to be dose-dependent when the dose levels of protein range from 0.08 to 0.80 g/kg BW.