• Proceedings of the Korea Water Resources Association Conference
• /
• 2020.06a
• /
• pp.101-101
• /
• 2020

Traditional stochastic simulation of hydroclimatological variables often underestimates the variability and correlation structure of larger timescale due to the difficulty in preserving long-term memory. However, the Long Short-Term Memory (LSTM) model illustrates a remarkable long-term memory from the recursive hidden and cell states. The current study, therefore, employed the LSTM model in stochastic generation of hydrologic and climate variables to examine how much the LSTM model can preserve the long-term memory and overcome the drawbacks of conventional time series models such as autoregressive (AR). A trigonometric function and the Rössler system as well as real case studies for hydrological and climatological variables were tested. Results presented that the LSTM model reproduced the variability and correlation structure of the larger timescale as well as the key statistics of the original time domain better than the AR and other traditional models. The hidden and cell states of the LSTM containing the long-memory and oscillation structure following the observations allows better performance compared to the other tested conventional models. This good representation of the long-term variability can be important in water manager since future water resources planning and management is highly related with this long-term variability.

• Proceedings of the Korea Water Resources Association Conference
• /
• 2022.05a
• /
• pp.437-437
• /
• 2022

The prediction of dam inflow rate is crucial for the management of the largest multi-purpose dam in South Korea, the Soyang Dam. The main issue associated with the management of water resources is the stochastic nature of the reservoir inflow leading to an increase in uncertainty associated with the inflow prediction. The Autoregressive (AR) model is commonly used to provide the simulation and forecast of hydrometeorological data. However, because its estimation is based solely on the time-series data, it has the disadvantage of being unable to account for external variables such as climate information. This study proposes the use of the Autoregressive Exogenous Stochastic Volatility (ARXSV) model within a Bayesian modeling framework for increased predictability of the monthly dam inflow by addressing the exogenous and stochastic factors. This study analyzes 45 years of hydrological input data of the Soyang Dam from the year 1974 to 2019. The result of this study will be beneficial to strengthen the potential use of data-driven models for accurate inflow predictions and better reservoir management.

• Korea Trade Review
• /
• v.47 no.3
• /
• pp.211-232
• /
• 2022

Due to the impact of the public health event COVID-19 epidemic, the Chinese futures market showed "Black Swan". This has brought the unpredictable into the economic environment with many commodities falling by the daily limit, while gold performed well and closed in the sunshine(Yan-Li and Rui Qian-Wang, 2020). Volatility is integral part of financial market. As an emerging market and a special precious metal, it is important to forecast return of gold futures price. This study selected data of the SHFE gold futures returns and conducted an empirical analysis based on the generalised autoregressive conditional heteroskedasticity (GARCH)-type model. Comparing the statistics of AIC, SC and H-QC, ARMA (12,9) model was selected as the best model. But serial correlation in the squared returns suggests conditional heteroskedasticity. Next part we established the autoregressive moving average ARMA-GARCH-type model to analysis whether Volatility Clustering and the leverage effect exist in the Chinese gold futures market. we consider three different distributions of innovation to explain fat-tailed features of financial returns. Additionally, the error degree and prediction results of different models were evaluated in terms of mean squared error (MSE), mean absolute error (MAE), Theil inequality coefficient(TIC) and root mean-squared error (RMSE). The results show that the ARMA(12,9)-TGARCH(2,2) model under Student's t-distribution outperforms other models when predicting the Chinese gold futures return series.

• Journal of Forest and Environmental Science
• /
• v.39 no.4
• /
• pp.213-224
• /
• 2023

As abnormal weather events due to climate change continue to rise, landslide damage is also increasing. Given the substantial time and financial resources required for post-landslide recovery, it becomes imperative to formulate a proactive response plan. In this regard, landslide susceptibility analysis has emerged as a valuable tool for establishing preemptive measures against landslides. Accordingly, this study conducted an annual landslide susceptibility analysis using the history of landslides that occurred over many years in the Jeolla region, and analyzed areas with a high potential for landslides in the Jeolla region. The analysis employed an ensemble model that amalgamated 10 data-based models, aiming to mitigate uncertainties associated with a single-model approach. Furthermore, based on the cumulative data regarding landslide susceptible areas, this research identified regions vulnerable to recurring landslide damage in Jeolla region and proposed specific strategies for utilizing this information at various levels, including local government initiatives, adaptation plan development, and development approval processes. In particular, this study outlined approaches for local government utilization, the determination of adaptation plan types, and considerations for development permits. It is anticipated that this research will serve as a valuable opportunity to underscore the significance of information concerning regions vulnerable to recurring landslide damage.

• Asia pacific journal of information systems
• /
• v.30 no.4
• /
• pp.719-740
• /
• 2020

The stock market changes continuously as new information emerges, affecting the judgments of investors. Online news articles are valued as a traditional window to inform investors about various information that affects the stock market. This paper proposed new ways to utilize online news articles with technical indicators. The suggested hybrid model consists of three models. First, a self-attention-based convolutional neural network (CNN) model, considered to be better in interpreting the semantics of long texts, uses news content as inputs. Second, a self-attention-based, bi-long short-term memory (bi-LSTM) neural network model for short texts utilizes news titles as inputs. Third, a bi-LSTM model, considered to be better in analyzing context information and time-series models, uses 19 technical indicators as inputs. We used news articles from the previous day and technical indicators from the past seven days to predict the share price of the next day. An experiment was performed with Korean stock market data and news articles from 33 top companies over three years. Through this experiment, our proposed model showed better performance than previous approaches, which have mainly focused on news titles. This paper demonstrated that news titles and content should be treated in different ways for superior stock price prediction.

• Applied Microscopy
• /
• v.50
• /
• pp.23.1-23.9
• /
• 2020

We propose an effective deep learning model to denoise scanning transmission electron microscopy (STEM) image series, named Noise2Atom, to map images from a source domain 𝓢 to a target domain 𝓒, where 𝓢 is for our noisy experimental dataset, and 𝓒 is for the desired clear atomic images. Noise2Atom uses two external networks to apply additional constraints from the domain knowledge. This model requires no signal prior, no noise model estimation, and no paired training images. The only assumption is that the inputs are acquired with identical experimental configurations. To evaluate the restoration performance of our model, as it is impossible to obtain ground truth for our experimental dataset, we propose consecutive structural similarity (CSS) for image quality assessment, based on the fact that the structures remain much the same as the previous frame(s) within small scan intervals. We demonstrate the superiority of our model by providing evaluation in terms of CSS and visual quality on different experimental datasets.

• Journal of the Semiconductor & Display Technology
• /
• v.23 no.3
• /
• pp.102-107
• /
• 2024

Previous research on solar power generation forecasting has generally relied on meteorological data, leading to lower prediction accuracy. This study, in contrast, uses actual measured power generation data to train various ANN (Artificial Neural Network) models and compares their prediction performance. Additionally, it describes the characteristics and advantages of each ANN model. The paper defines the principles of solar power generation, the characteristics of solar panels, and the model equations, and it also explains the I-V characteristics of solar cells. The results include a comparison between calculated and actual measured power generation, along with an evaluation of the accuracy of power generation predictions using artificial intelligence. The findings confirm that the LSTM (Long Short-Term Memory) model performs better than the MLP (Multi- Layer Perceptron) model in handling time-series data.

• Journal of Sensor Science and Technology
• /
• v.22 no.1
• /
• pp.38-43
• /
• 2013

In this study, the artery's compliance model and the pulsation waveform model was proposed to estimate blood pressure without applying HPF (High Pass Filter) on signal measured by the oscillometric method. The method proposed in the study considered two ways of estimating blood pressure. The first method of estimating blood pressure is by comparing and analyzing changes in pulsation waveform's dicrotic notch region during each cardiac period. The second method is by comparing and analyzing morphological changes in the pulsation waveform during each cardiac period, which occur in response to the change in pressure applied on the cuff. To implement these methods, we proposed the compliance model and the pulsation waveform model of the artery based on hemodynamic theory, and then conducted various simulations. The artery model presented in this study only took artery's compliance into account. Then, a pulsation waveform model was suggested, which uses characteristic changes in the pulsation waveform to estimate blood pressure. In addition, characteristic changes were observed in arterial volume by applying artery's pulsation waveform to the compliance model. The pulsation waveform model was suggested to estimate blood pressure using characteristic changes of the pulsation waveform in the arteries. This model was composed of the sum of sine waves and a Fourier's series in combination form up to 10th harmonics components of the sinusoidal waveform. Then characteristic of arterial volume change was observed by inputting pulsation waveform into the compliance model. The characteristic changes were also observed in the pulsation waveform by mapping the arterial volume change in accordance with applied cuff's pressure change to the pulsation waveform's change according to applied pressure changes by cuff. The systolic and diastolic blood pressures were estimated by applying positional change of pulsation waveform's dicrotic notch region.

• Journal of Korean Society of Coastal and Ocean Engineers
• /
• v.10 no.3
• /
• pp.109-119
• /
• 1998

A horizontal tow-dimensional version of POM (Princeton Ocean Model) was modified in representing the bottom friction and the open boundary conditions. To simulate the flooding and drying of intertidal flats, a wetting-and-drying scheme was incorporated into the model. The model then was applied to the Chunsu Bay and its adjacent coastal water. Only the water movement due to tides, the dominant forcing in the study area, was considered. This presents the procedure and the results of model calibration and verification for the Chunsu Bay system. The model was calibrated, using the average tidal characteristics in Tide Tables, for the amplitudes and the phases of tidal waves throughout the modeling domain. Calibration results showed that the model gave a good reproduction of tidal waves. The calibrated model was verified using the time-series measurements of surface elevation and current velocity in the summer of 1995. The model reproduced the tides currents very well. calibration and verification results demonstrated that the model is capable of reproducing the tidal dynamics in the Chunsu Bay system.

• Journal of Korea Water Resources Association
• /
• v.44 no.8
• /
• pp.667-681
• /
• 2011

The objective of this study is to evaluate the applicability of a Land Surface Model (LSM) for drought analysis in Korea. For evaluating the applicability of the model, the model was calibrated on several upper dam site watersheds and the hydrological components (runoff and soil moisture) were simulated over the whole South Korea at grid basis. After converting daily series of runoff and soil moisture data to accumulated time series (3, 6, 12 months), drought indices such as SRI and SSI are calculated through frequency analysis and standardization of accumulated probability. For evaluating the drought indices, past drought events are investigated and drought indices including SPI and PDSI are used for comparative analysis. Temporal and spatial analysis of the drought indices in addition to hydrologic component analysis are performed to evaluate the reproducibility of drought severity as well as relieving of drought. It can be concluded that the proposed indices obtained from the LSM model show good performance to reflect the historical drought events for both spatially and temporally. From this point of view, the LSM can be useful for drought management. It leads to the conclusion that these indices are applicable to domestic drought and water management.