• Journal of the Korea Society of Computer and Information
• /
• v.26 no.11
• /
• pp.21-31
• /
• 2021

As the COVID-19 pandemic rapidly changes healthcare around the globe, the need for smart healthcare that allows for remote diagnosis is increasing. The current classification of respiratory diseases cost high and requires a face-to-face visit with a skilled medical professional, thus the pandemic significantly hinders monitoring and early diagnosis. Therefore, the ability to accurately classify and diagnose respiratory sound using deep learning-based AI models is essential to modern medicine as a remote alternative to the current stethoscope. In this study, we propose a deep learning-based respiratory sound classification model using data collected from medical experts. The sound data were preprocessed with BandPassFilter, and the relevant respiratory audio features were extracted with Log-Mel Spectrogram and Mel Frequency Cepstral Coefficient (MFCC). Subsequently, a Parallel CNN network model was trained on these two inputs using stacking ensemble techniques combined with various machine learning classifiers to efficiently classify and detect abnormal respiratory sounds with high accuracy. The model proposed in this paper classified abnormal respiratory sounds with an accuracy of 96.9%, which is approximately 6.1% higher than the classification accuracy of baseline model.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.13 no.11
• /
• pp.5163-5168
• /
• 2012

The aim of this study is to develop the supply-demand model(dynamic recursive simulation model) on the Hallabong tangor. In order to analyze the effects of alternative policy scenarios on the Hallabong tangor sector. Simulation runs were experimented for the period, 2011~2021, with three different scenarios. The major simulation results are as follows. The results of baseline show that in the year, 2021, acreage, production, price received by farm would be 2,051.5ha, 62,049.1 ton, 2,537.4 won per kg respectively. The results of scenario I (shipping control scenario) show that in the year, 2021, acreage, production, price received by farm would be 2,079.4ha, 62,984.9 ton, 2,836.3 won per kg respectively. The results of scenario II(the rate of economic growth 3.5%) show that in the year, 2021, acreage, production, price received by farm would be 2,039.5ha, 61,647.5 ton, 2,417.3 won per kg respectively. Finally, The results of scenario III(Survey of experts) show that in the year, 2021, acreage, production, price received by farm would be 2,053.7ha, 62,124.4 ton, 2,574.8 won per kg respectively. Therefore, economic recession can be a negative role in the industrial growth and price of Halabong tangor, but expansion of Hallabong tagor's export and processing can be a very positive role in the industrial growth and price of Halabong tangor.

• Journal of Physiology & Pathology in Korean Medicine
• /
• v.22 no.4
• /
• pp.835-840
• /
• 2008

Acupuncture has long been contended to be effective in an ischemic stroke. A real-time monitoring of glutamate, an excitotoxin in the process of ischemic neuronal damage, in the striatum is tried in a rat model of global ischemia. Global ischemia was induced by the 11 vessel occlusion method for 10 minutes, during which acupuncture stimulation on GB34 and GB39 points was executed. Glutamate release in the rat striatum was monitored 256 times per second using real-time amperometric biosensor. Real time measurement data of 10 minutes prior to the induction of ischemia served as baseline data. Data acquisition continued for 30 minutes after the initiation of reperfusion. Peak concentration of glutamate release along with incidentally measured EEG and cerebral blood flow was compared between cases with and without acupuncture stimulation. Peak concentration of glutamate lowered when acupuncture stimulation was executed. A real time monitoring system of 11 vessel-occlusion induced global ischemia model was successfully established. The effect by acupuncture on acute global ischemia was successfully observed in this real-time monitoring setting, which may be one of the neuroprotective mechanism of acupuncture.

• Environmental and Resource Economics Review
• /
• v.16 no.1
• /
• pp.129-169
• /
• 2007

The purpose of this study is to experiment and simulate the newly-updated Second Generation Model for Korea (SGM-Korea). With the updated model, we tried to simulate effect of carbon tax on $CO_2$ emissions and other macroeconomic variables for Korea. The baseline data are compared with projected profiles by various scenarios to evaluate its performance. Our contribution in this study is to having up-graded the model from its earlier version by building new hybrid input-output table based on 2000 input-output and energy balanced tables. According to our estimation, total $CO_2$ emission in Korea has already increased in 2000 to about 1.86 times the 1990 figure. The level of carbon tax required for the current level of $CO_2$ emission to be reduced to the 1995 or 2000 level seems to be too high for Korean economy to bear. It is possible to find a reasonable level of carbon tax, however, if it can combine it with improvement of energy efficiency at the rate of 0.5% to 1% per year. For Korea to meet its obligation to reduce $CO_2$ emissions, therefore, it is imperative for her to improve energy efficiency as well as to develop alternative energy source reducing its dependence on fossil fuel.

• KDI Journal of Economic Policy
• /
• v.34 no.4
• /
• pp.117-156
• /
• 2012

This paper decomposes and estimates trend/cyclical components of some key macro variables-GDP, inflation, and interest rate, using a simple DSGE model along with flexible trend specification. The extracted cyclical components of output and interest rate are similar to HP-filtered counterparts, despite some differences in persistence and volatility, while inflation resembles that from BK filtering. This implies that the usual practice of applying a single filtering method to the data of interest may be problematic. When the baseline model is extended to incorporate consumption habit and price indexation, habit turns out to be important in explaining the persistence of business cycles. Comparison of several alternative models shows that the usual practice of estimation of DSGE model using filtered data leads to biased results. Finally, various sensitivity analyses illustrate that (1) allowing for correlation between structural cyclical shocks and trend shocks and (2) including irregular components (in inflation rate) may deliver interesting/important implication for gap estimates.

• Journal of Korea Water Resources Association
• /
• v.40 no.3
• /
• pp.205-214
• /
• 2007

The objective of this study is to generate the regional scale runoff scenarios by using IPCC SRES A2 climate change scenario for analyzing the spatial variation of water resources in Korea. The PRMS model was adopted to simulate long-term stream discharge. To estimate the PRMS model parameters on each sub-basin, the streamflow data at 6 dam sites and Rosenbrock's scheme are used for model parameter calibration and those parameters are translated to ungauged catchments by regionalization method. The other 3 dam sites are selected for the verification of the adequateness of regionalized model parameters in ungagued catchments. The statistical results show that the simulated flows by using regionalized parameters well agree with observed ones. The generated runoff scenarios by climate change are compared with observed data on 4 dam sites for the reference period. The consequences show that the selection of climate station for generating climate scenario affects the reliability of climate scenario at sub-basin. The comparison results of the stream flows between the 30-year baseline period (1971-2000) and future 90-year (2001-2030, 2031-2060, 2061-2090) show that the long-term mean annual runoff in the Han River has increasing trend, while the Nakdong, the Gum, the Youngsan and the Sumjin Rivers have decreasing trend.

• Journal of Korea Water Resources Association
• /
• v.47 no.3
• /
• pp.257-267
• /
• 2014

The impact of the combination of changes in temperature and rainfall due to climate change on surface water resources is important in hydro-meteorological research. In this study, 4 hydro-meteorological (HM) models from the Rainfall Runoff Library in the Catchment Modeling Toolkit were used to model the impact of climate change on runoff in streams for 5 river basins in the Republic of Korea. Future projections from 2021 to 2040 (2030s), 2051 to 2070 (2060s) and 2081 to 2099 (2090s), were derived from 12 General Circulation Models (GCMs) and 3 representative concentration pathways (RCPs). GCM outputs were statistically adjusted and downscaled using Long-Ashton Research Station Weather Generator (LARS-WG) and the HM models were well calibrated and verified for the period from 1999 to 2009. The study showed that there is substantial spatial, temporal and HM uncertainty in the future runoff shown by the interquartile range, range and coefficient of variation. In summary, the aggregated runoff will increase in the future by 10~24%, 7~30% and 11~30% of the respective baseline runoff for the RCP2.6, RCP4.5 and RCP8.5, respectively. This study presents a method to model future stream-flow taking into account the HM model and climate based uncertainty.

• Korean Journal of Agricultural and Forest Meteorology
• /
• v.22 no.3
• /
• pp.164-170
• /
• 2020

The weather conditions, such as temperature, precipitation, and sunshine duration, play one of the key roles in Agriculture. In particular, extreme weather events have crucial impacts on growth and yields of crops. This study estimates statistics of extreme weather events in 167 Si-gun over South Korea derived from high-resolution(30 and 270m) topo-climatology model for key three meteorological variables(temperature, precipitation and sunshine duration). It is shown that the characteristic of each extreme weather frequency in the topo-climatology model is in good agreement with observation from Korean Meteorological Administration's Automatic Surface Observing System. Moreover, it is possible to analyze the statistics of extreme weather more realistically because this data can cover the weather at not-observed regions. Hence, this data is expected to be used as baseline data for assessing vulnerability to extreme weather and politic decisions for damage reduction in agricultural sector.

• Korean Journal of Remote Sensing
• /
• v.34 no.6_1
• /
• pp.1101-1117
• /
• 2018

The clear sky radiance (CSR) is one of the baseline products of the Himawari-8 which was launched on October, 2014. The CSR contributes to numerical weather prediction (NWP) accuracy through the data assimilation; especially water vapor channel CSR has good impact on the forecast in high level atmosphere. The focus of this study is the quality analysis of the CSR of the Himawari-8 geostationary satellite. We used the operational CSR (or clear sky brightness temperature) products in JMA (Japan Meteorological Agency) as observation data; for a background field, we employed the CSR simulated using the Radiative Transfer for TOVS (RTTOV) with the atmospheric state from the global model of KMA (Korea Meteorological Administration). We investigated data characteristics and analyzed observation minus background statistics of each channel with respect to regional and seasonal variability. Overall results for the analysis period showed that the water vapor channels (6.2, 6.9, and $7.3{\mu}m$) had a positive mean bias where as the window channels(10.4, 11.2, and $12.4{\mu}m$) had a negative mean bias. The magnitude of biases and Uncertainty result varied with the regional and the seasonal conditions, thus these should be taken into account when using CSR data. This study is helpful for the pre-processing of Himawari-8/Advanced Himawari Imager (AHI) CSR data assimilation. Furthermore, this study also can contribute to preparing for the utilization of products from the Geo-Kompsat-2A (GK-2A), which will be launched in 2018 by the National Meteorological Satellite Center (NMSC) of KMA.

• Journal of the Korea Society of Computer and Information
• /
• v.27 no.3
• /
• pp.13-23
• /
• 2022

In this study we leveraged a probing method to evaluate how a pre-trained L2 LSTM language model represents sentences with relative and coordinate clauses. The probing experiment employed adapted models based on the pre-trained L2 language models to trace the syntactic properties of sentence embedding vector representations. The dataset for probing was automatically generated using several templates related to different sentence structures. To classify the syntactic properties of sentences for each probing task, we measured the adaptation effects of the language models using syntactic priming. We performed linear mixed-effects model analyses to analyze the relation between adaptation effects in a complex statistical manner and reveal how the L2 language models represent syntactic features for English sentences. When the L2 language models were compared with the baseline L1 Gulordava language models, the analogous results were found for each probing task. In addition, it was confirmed that the L2 language models contain syntactic features of relative and coordinate clauses hierarchically in the sentence embedding representations.