• Communications for Statistical Applications and Methods
• /
• v.26 no.5
• /
• pp.497-506
• /
• 2019

Forecasting the U.S. employment level is made using machine learning methods of the artificial neural network: deep neural network, long short term memory (LSTM), gated recurrent unit (GRU). We consider the big data of the federal reserve economic data among which 105 important macroeconomic variables chosen by McCracken and Ng (Journal of Business and Economic Statistics, 34, 574-589, 2016) are considered as predictors. We investigate the influence of the two statistical issues of the dimension reduction and time series differencing on the machine learning forecast. An out-of-sample forecast comparison shows that (LSTM, GRU) with differencing performs better than the autoregressive model and the dimension reduction improves long-term forecasts and some short-term forecasts.

• Investigative Magnetic Resonance Imaging
• /
• v.22 no.3
• /
• pp.158-167
• /
• 2018

Purpose: To investigate the surgical, perfusion, and molecular characteristics of glioblastomas which influence long-term survival after treatment, and to explore the association between MR perfusion parameters and the presence of MGMT methylation and 1p/19q deletions. Materials and Methods: This retrospective study was approved by our institutional review board. A total 43 patients were included, all with pathologic diagnosis of glioblastoma with known MGMT methylation and 1p/19q deletion statuses. We divided these patients into long-term (${\geq}60\;months$, n = 7) and short-term (< 60 months, n = 36) survivors, then compared surgical extent, molecular status, and rCBV parameters between the two groups using Fisher's exact test or Mann-Whitney test. The rCBV parameters were analyzed according to the presence of MGMT methylation and 1p/19q deletions. We investigated the relationship between the mean rCBV and overall survival using linear correlation. Multivariable linear regression was performed in order to find the variables related to overall survival. Results: Long-term survivors (100% [7 of 7]) demonstrated a greater percentage of gross total or near total resection than short-term survivors (54.5% [18 of 33]). A higher prevalence of 1p/19q deletions was also noted among the long-term survivors (42.9% [3 of 7]) than the short-term survivors (0.0% [0 of 36]). The rCBV parameters did not differ between the long-term and short-term survivors. The rCBV values were marginally lower in patients with MGMT methylation and 1p/19q deletions. Despite no correlation found between overall survival and rCBV in the whole group, the short-term survivor group showed negative correlation ($R^2=0.181$, P = 0.025). Multivariable linear regression revealed that surgical extent and 1p/19q deletions, but not rCBV values, were associated with prolonged overall survival. Conclusion: While preoperative rCBV and 1p/19q deletion status are related to each other, only surgical extent and the presence of 1p/19q deletion in GBM patients may predict long-term survival.

• Journal of Oral Medicine and Pain
• /
• v.11 no.1
• /
• pp.29-35
• /
• 1986

18 TMD patients who received occlusal adjustment in PNUH though Jan.1984 to 1985 were followed up for short-term(2-6yrs.) and long-term(1-2yrs.) evaluation. The obtained results were as follows : 1. Pain index showed gradual decrease after occlusal adjustment and significant change on long-term evaluation. 2. Noise index had no significant change throughout the all follow-up evaluation. 3. Opening limitation index showed gradual decrease after occlusal adjustment and significant change on both long-term and short-term evaluation. 4. Maximum comfortable opening exhibited more and more increase and significant change on long-term evaluation.

• 전기의세계
• /
• v.29 no.4
• /
• pp.260-264
• /
• 1980

In this paper, a new algorithm is derived for short term load forecasting. The load model is represented by the state variable form to exploit the Kalman filter techniques. The suggested model has advantages that it is unnecessarty to obtain the coefficients of the harmonic components and its coefficients are not explicitly included in the model. Case studies were carried out for the hourly power demand forecasting of the Korea electrical system.

• The Korean Journal of Physiology and Pharmacology
• /
• v.7 no.6
• /
• pp.303-306
• /
• 2003

Metabotropic glutamate receptors (mGluRs), classified into three groups (group I, II, III), play a critical role in modulation of synaptic transmission at central and peripheral synapses. In the present study, extracellular field potential recording techniques were used to investigate effects of mGluR agonists on excitatory synaptic transmission at thalamic input synapses onto the lateral amygdala. The non-selective mGluR agonist t-ACPD ($100{\mu}M$) produced reversible, short-term depression, but the group III mGluR agonist L-AP4 ($50{\mu}M$) did not have any significant effects on amygdala synaptic transmission, suggesting that group I and/or II mGluRs are involved in the modulation by t-ACPD. The group I mGluR agonist DHPG ($100{\mu}M$) produced reversible inhibition as did t-ACPD. Unexpectedly, the group II mGluR agonist LCCG-1 ($10{\mu}M$) induced long-term as well as short-term depression. Thus, our data suggest that activation of group I or II mGluRs produces short-term, reversible depression of excitatory synaptic transmission at thalamic input synapses onto the lateral amygdala. Considering the long-term effect upon activation of group II mGluRs, lack of long-term effects upon activation of group I and II mGluRs may indicate a possible cross-talk among different groups of mGluRs.

• Journal of Korean Academy of Nursing
• /
• v.30 no.1
• /
• pp.29-38
• /
• 2000

To determine whether personal history of lactation in premenopausal women influence bone mineral density, a cross-sectional study was conducted. One hundred eighty-four premenopausal women were selected from women who had been checked for bone mineral density by dual energy x-ray absortiometry in lumbar spine, femoral neck, Ward's triangle, and trochanteric site at general hospitals in Seoul and Pusan. They completed a questionnaire including life style factors and reproductive history. In the data analysis, Pearson correlation coefficients were used to test any association between individual variables and bone mineral density and a statistical comparisons between long term lactation(>24 months) and short term lactation(<24 months) were made by one way analysis of covariance. The results were summarized as follows: 1) There was no significant difference in the bone mineral density of the lumbar vertebrae in premenopausal women between the long term lactation group(>24months) and the short term lactation group(<24months). 2) There was no significant difference in the bone mineral density of the femur neck, Ward's triangle, and trochanteric site in premenopausal women between the long term lactation group (>24months) and the short term lactation group (<24months). Considering these results, we suggest prospective studies that measure bone mineral density before and after, in addition to those during lactation. We also suggest the further study with premenopausal women less than 35 who have achieved peak adult bone mass.

• Journal of Digital Convergence
• /
• v.15 no.4
• /
• pp.259-266
• /
• 2017

The massive traffic interferences in the wireless home IoT provides the reason for packet losses, and it degrades the QoS (Quality of Service) and throughput on the home network. This paper propose a new adaptive traffic interference control system, ATICS, for enhancing QoS and throughput for IoT services as detecting a traffic process and non-traffic process in the wireless home network. The proposed system control the traffic interferences as distinguishing the short-term traffic process and long-term traffic process by traffic characteristics in wireless home networks. The simulation results shows that the proposed scheme have more efficient traffic control performance than the other schemes.

• The Korean Journal of Financial Management
• /
• v.22 no.2
• /
• pp.91-105
• /
• 2005

Using Campa and Chang's Expectations Hypothesis model, We test the expectations hypothesis in the term structure of volatilities in options on KOSPI 200 by using daily dosing prices from January 1999 to December 2003. In particular, it addresses whether long-dated volatilities are consistent with expected future short-dated volatilities, assuming rational expectation. Our results do not support the expectations hypothesis : long-term volatilities rise relative to short-term volatilities, but the increases are not matched as predicted by the expectations hypothesis. In addition, an increase in the current long-term volatilities relative to the current short-term volatilities is followed by at a random.

• Journal of Society of Preventive Korean Medicine
• /
• v.22 no.2
• /
• pp.41-53
• /
• 2018

Objectives : It was to classify and its affecting factors to the patients of Korean medicine hospital with short term and long term hospitalization. Methods : I focused on long-term hospitalized patients. I was conducted on 344 hospitalized patients among the original data of usage and consumption of Korean medical report in 2014. Among those patients, I have classified them into long term inpatients(131 patients) and short term inpatients(213 patients) based on 16 days of hospitalization. Also multiple regression analysis was conducted to investigate the characteristics of the hospitalization, treatment satisfaction and dissatisfaction, the characteristics of long term hospitalization according to the sociodemographic of the subjects, the top 21 diseases and the distribution of human bodies, side effects and kinds of Korean medicine. Results : There was a statistically significant difference between the short term and long term hospitalized patients due to age, occupation, marital status, all 21 diseases and institutional fees, experience of Korean medical treatment due to traffic accidents. There was no significant difference in gender, education level, residence, income level, type of medical insurance, whether private insurance, type of medical treatment for Korean medicine, medical expenses for car accidents, reason for dissatisfaction with treatment. The number of long term patients at Korean medicine hospitals increased by a statistically significant by age in model 1 where confounding factors were differently controlled. In model 2, the number of long term patients at Korean medicine hospitals increased by a statistically significant by age, among those who earned 5,000,000 Korean won or more, and among those with nerve diseases. The number of long term patients at Korean medicine hospitals decreased by a statistically significant amount among the unemployed and others in model 2. In model 3, the number of long term patients at Korean medicine hospitals increased by a statistically significant by age, among those who earned 5,000,000 Korean won or more, and among those with nerve diseases, while the number decreased by a statistically significant amount among the married. Conclusions : These results suggest that the factors affecting the short term and long term hospitalization of patients with Korean medicine hospital are different from each other. Especially it was significant by age, over 5,000,000won Income per month, nerve disease, but decrease significant married.

• Journal of Intelligence and Information Systems
• /
• v.29 no.1
• /
• pp.377-396
• /
• 2023

As the cryptocurrency market continues to grow, it has developed into a new financial market. The need for investment strategy research on the cryptocurrency market is also emerging. This study aims to conduct an empirical analysis on an investment methodology of cryptocurrency that combines short-term trading strategy and deep learning. Daily price data of the Ethereum was collected through the API of Upbit, the Korean cryptocurrency exchange. The investment performance of the experimental model was analyzed by finding the optimal parameters based on past data. The experimental model is a volatility breakout strategy(VBS), a Long Short Term Memory(LSTM) model, moving average cross strategy and a combined model. VBS is a short-term trading strategy that buys when volatility rises significantly on a daily basis and sells at the closing price of the day. LSTM is suitable for time series data among deep learning models, and the predicted closing price obtained through the prediction model was applied to the simple trading rule. The moving average cross strategy determines whether to buy or sell when the moving average crosses. The combined model is a trading rule made by using derived variables of the VBS and LSTM model using AND/OR for the buy conditions. The result shows that combined model is better investment performance than the single model. This study has academic significance in that it goes beyond simple deep learning-based cryptocurrency price prediction and improves investment performance by combining deep learning and short-term trading strategies, and has practical significance in that it shows the applicability in actual investment.