• The Korean Journal of Applied Statistics
• /
• v.34 no.5
• /
• pp.745-760
• /
• 2021

Prediction of a stock price has been a subject of interest for a long time in financial markets, and thus, many studies have been conducted in various directions. As the efficient market hypothesis introduced in the 1970s acquired supports, it came to be the majority opinion that it was impossible to predict stock prices. However, recent advances in predictive models have led to new attempts to predict the future prices. Here, we summarize past studies on the price prediction by evaluation measures, and predict the direction of stock prices of Samsung Electronics, LG Chem, and NAVER by applying various machine learning models. In addition to widely used technical indicator variables, accounting indicators such as Price Earning Ratio and Price Book-value Ratio and outputs of the hidden Markov Model are used as predictors. From the results of our analysis, we conclude that no models show significantly better accuracy and it is not possible to predict the direction of stock prices with models used. Considering that the models with extra predictors show relatively high test accuracy, we may expect the possibility of a meaningful improvement in prediction accuracy if proper variables that reflect the opinions and sentiments of investors would be utilized.

• The Journal of The Korea Institute of Intelligent Transport Systems
• /
• v.20 no.6
• /
• pp.55-65
• /
• 2021

In January 2020, the first COVID-19 confirmed patient occurred in Korea, and the pandemic continues to this day. In unprecedented situations, COVID-19 also affected the transportation sector, and there were no appropriate measures against changes in traffic volume and use of public transportation due to changes in citizens' lifestyles. Currently, each local government has not established separate measures for pandemic disease measures. In order to establish future disease countermeasures in the transportation sector, a predictive model was developed by analyzing the traffic volume and the number of public transportation uses, and conducting correlation analysis with the current status of COVID-19. As a result of the analysis, the traffic volume decreased, but the traffic volume decreased due to the increase in personal transportation, but it did not reach the number of public transportation uses. In addition, it was analyzed that the use of public transportation was initially affected by the number of confirmed cases, but over time, it was more sensitive to death and mortality than to the number of confirmed cases.

• Investigative Magnetic Resonance Imaging
• /
• v.25 no.4
• /
• pp.313-322
• /
• 2021

Purpose: To find diagnostic image features, to compare diagnostic performance of multiphase CT versus gadoxetic acid disodium-enhanced MRI (GAD-MRI), and to evaluate the impact of analyzing Liver Imaging Reporting and Data System (LI-RADS) imaging features, for distinguishing combined hepatocellular-cholangiocarcinoma (CHC) from hepatocellular carcinoma (HCC). Materials and Methods: Ninety-six patients with pathologically proven CHC (n = 48) or HCC (n = 48), diagnosed June 2008 to May 2018 were retrospectively analyzed in random order by three radiologists with different experience levels. In the first analysis, the readers independently determined the probability of CHC based on their own knowledge and experiences. In the second analysis, they evaluated imaging features defined in LI-RADS 2018. Area under the curve (AUC) values for CHC diagnosis were compared between CT and MRI, and between the first and second analyses. Interobserver agreement was assessed using Cohen's weighted κ values. Results: Targetoid LR-M image features showed better specificities and positive predictive values (PPV) than the others. Among them, rim arterial phase hyperenhancement had the highest specificity and PPV. Average sensitivity, specificity, and AUC values were higher for MRI than for CT in both the first (P = 0.008, 0.005, 0.002, respectively) and second (P = 0.017, 0.026, 0.036) analyses. Interobserver agreements were higher for MRI in both analyses (κ = 0.307 for CT, κ = 0.332 for MRI in the first analysis; κ = 0.467 for CT, κ = 0.531 for MRI in the second analysis), with greater agreement in the second analysis for both CT (P = 0.001) and MRI (P < 0.001). Conclusion: Rim arterial phase hyperenhancement on GAD-MRI can be a good indicator suggesting CHC more than HCC. GAD-MRI may provide greater accuracy than CT for distinguishing CHC from HCC. Interobserver agreement can be improved for both CT and MRI by analyzing LI-RADS imaging features.

• Journal of Korea Water Resources Association
• /
• v.54 no.spc1
• /
• pp.1037-1051
• /
• 2021

Biochemical oxygen demand (BOD) concentration, one of important water quality indicators, is treated as the measuring item for the ecological chapter in lakes and rivers. This investigation employed novel two-stage hybrid paradigm (i.e., wavelet-based gated recurrent unit, wavelet-based generalized regression neural networks, and wavelet-based random forests) to predict BOD concentration in the Dosan and Hwangji stations, South Korea. These models were assessed with the corresponding independent models (i.e., gated recurrent unit, generalized regression neural networks, and random forests). Diverse water quality and quantity indicators were implemented for developing independent and two-stage hybrid models based on several input combinations (i.e., Divisions 1-5). The addressed models were evaluated using three statistical indices including the root mean square error (RMSE), Nash-Sutcliffe efficiency (NSE), and correlation coefficient (CC). It can be found from results that the two-stage hybrid models cannot always enhance the predictive precision of independent models confidently. Results showed that the DWT-RF5 (RMSE = 0.108 mg/L) model provided more accurate prediction of BOD concentration compared to other optimal models in Dosan station, and the DWT-GRNN4 (RMSE = 0.132 mg/L) model was the best for predicting BOD concentration in Hwangji station, South Korea.

• Journal of Environmental Health Sciences
• /
• v.48 no.4
• /
• pp.227-235
• /
• 2022

Background: Abandoned metal mines are classified as vulnerable areas with the highest level of soil contamination among risk regions. People living near abandoned metal mines are at increased risk of exposure to toxic metals. Objectives: This study aimed to evaluate the correlation between soil contamination levels in areas around abandoned metal mine and the blood lead levels of local residents. Moreover, we assess the possibility of using soil contamination levels as a predictive indicator for human exposure level. Methods: Data from the Survey of Residents around Abandoned Metal Mines (2013~2017, n=4,421) and Investigation of Soil Pollution in Abandoned Metal Mines (2000~2011) were used. A random coefficient model was conducted for estimation of the lower level (micro data) of the local resident unit and the upper level (macro data) of the abandoned metal mine unit. Through a fitted model, the variation of blood lead levels among abandoned metal mines was confirmed and the effect of the operationally defined soil contamination level was estimated. Results: Among the total variation in blood lead levels, the variation between abandoned mines was 18.6%, and the variation determined by the upper-level factors such as soil contamination and water contamination was 8.1%, which was statistically significant respectively. There was also a statistically significant difference in the least square mean of blood lead concentration according to the level of soil contamination (p=0.047, low: 2.32 ㎍/dL, middle: 2.38 ㎍/dL, high: 2.59 ㎍/dL). Conclusions: The blood lead concentration of residents living near abandoned metal mines was significantly correlated with the level of soil contamination. Therefore, in biomonitoring for vulnerable areas, operationally defined soil contamination can be used as a predictor for human exposure level to hazardous substances and discrimination of high-risk abandoned metal mines.

• Smart Media Journal
• /
• v.11 no.10
• /
• pp.9-21
• /
• 2022

The recent expansion of the use of social media has served as an opportunity to express users' opinions in real time in various fields such as society, economy, politics, and culture, and brought many platforms that provide various information about companies. Among them, Glassdoor.com which started 2008 in US provides users with evaluations of the current and the former employees of their companies and also provides a outlooks for the company's growth Such a platform has the utility of providing necessary information to whom want to find a job or change jobs. In addition to this, variable studies have shown that the company information provided through these platforms is useful for investors as well. In this study, it was tested whether the corporate growth prospects of employees provided by Jobplanet, a platform with a typical function similar to Glassdoor.com in Korea, have predictive power to predict actual corporate growth. The forecast provided by Jobplanet and the company's financial indicator data received from FnGuide were collected and composed of panel data and analyzed using fixed effect model regression analysis. As a result, it was found that companies with positive prospects had higher employment growth than companies with negative prospects. When the outlook was neutral, the employment growth rate was higher than that of companies with a negative outlook.

• Korean Journal of Radiology
• /
• v.23 no.1
• /
• pp.89-100
• /
• 2022

Objective: To improve the N biomarker in the amyloid/tau/neurodegeneration system by radiomics and study its value for predicting cognitive progression in individuals with mild cognitive impairment (MCI). Materials and Methods: A group of 147 healthy controls (HCs) (72 male; mean age ± standard deviation, 73.7 ± 6.3 years), 197 patients with MCI (114 male; 72.2 ± 7.1 years), and 128 patients with Alzheimer's disease (AD) (74 male; 73.7 ± 8.4 years) were included. Optimal A, T, and N biomarkers for discriminating HC and AD were selected using receiver operating characteristic (ROC) curve analysis. A radiomics model containing comprehensive information of the whole cerebral cortex and deep nuclei was established to create a new N biomarker. Cerebrospinal fluid (CSF) biomarkers were evaluated to determine the optimal A or T biomarkers. All MCI patients were followed up until AD conversion or for at least 60 months. The predictive value of A, T, and the radiomics-based N biomarker for cognitive progression of MCI to AD were analyzed using Kaplan-Meier estimates and the log-rank test. Results: The radiomics-based N biomarker showed an ROC curve area of 0.998 for discriminating between AD and HC. CSF Aβ42 and p-tau proteins were identified as the optimal A and T biomarkers, respectively. For MCI patients on the Alzheimer's continuum, isolated A+ was an indicator of cognitive stability, while abnormalities of T and N, separately or simultaneously, indicated a high risk of progression. For MCI patients with suspected non-Alzheimer's disease pathophysiology, isolated T+ indicated cognitive stability, while the appearance of the radiomics-based N+ indicated a high risk of progression to AD. Conclusion: We proposed a new radiomics-based improved N biomarker that could help identify patients with MCI who are at a higher risk for cognitive progression. In addition, we clarified the value of a single A/T/N biomarker for predicting the cognitive progression of MCI.

• IMMUNE NETWORK
• /
• v.23 no.4
• /
• pp.35.1-35.16
• /
• 2023

Defining the molecular dynamics associated with T cell differentiation enhances our understanding of T cell biology and opens up new possibilities for clinical implications. In this study, we investigated the dynamics of CD5 expression in CD8⁺ T cell differentiation and explored its potential clinical uses. Using PBMCs from 29 healthy donors, we observed a stepwise decrease in CD5 expression as CD8⁺ T cells progressed through the differentiation stages. Interestingly, we found that CD5 expression was initially upregulated in response to T cell receptor stimulation, but diminished as the cells underwent proliferation, potentially explaining the differentiation-associated CD5 downregulation. Based on the proliferation-dependent downregulation of CD5, we hypothesized that relative CD5 expression could serve as a marker to distinguish the heterogeneous CD8⁺ T cell population based on their proliferation history. In support of this, we demonstrated that effector memory CD8⁺ T cells with higher CD5 expression exhibited phenotypic and functional characteristics resembling less differentiated cells compared to those with lower CD5 expression. Furthermore, in the retrospective analysis of PBMCs from 30 non-small cell lung cancer patients, we found that patients with higher CD5 expression in effector memory T cells displayed CD8⁺ T cells with a phenotype closer to the less differentiated cells, leading to favorable clinical outcomes in response to immune checkpoint inhibitor (ICI) therapy. These findings highlight the dynamics of CD5 expression as an indicator of CD8⁺ T cell differentiation status, and have implications for the development of predictive biomarker for ICI therapy.

• Clinical and Experimental Pediatrics
• /
• v.46 no.8
• /
• pp.811-816
• /
• 2003

Purpose : Kawasaki disease is an acute systemic vasculitis of unknown etiology with a predilection for the coronary arteries. Vascular endothelial growth factor(VEGF) is a cytokine which promotes vascular permeability and angiogenesis. We investigated serum VEGF(sVEGF) levels in Kawasaki disease to determine whether sVEGF level can be used as a risk factor to predict the occurrence of coronary artery lesions(CAL) in Kawasaki disease. Methods : We measured sVEGF levels in 11 patients with Kawasaki disease in acute phase(patient group)and 11 normal children(control group) by enzyme-linked immunosorbent assay(ELISA) method. We investigated the relationship between sVEGF levels and the lumen diameters of coronary artery and other potential CAL risk factors; duration of fever, hemoglobin, WBC counts, platelet counts, ESR, CRP and LDH levels. Results : SVEGF levels of patients in the acute phase of Kawasaki disease(mean $847.9{\pm}495.7pg/mL$) were significantly higher than that of normal controls(mean $279.9{\pm}150.6pg/mL$; P<0.05). SVEGF levels showed significant positive correlation with the lumen diameters of the coronary artery(P<0.05, $r_s=0.75$) in the patient group. There was no significant correlation between sVEGF levels and duration of fever or other laboratory measurements. Conclusion : Our results support the notion that sVEGF level may be considered as a predictive indicator for the occurrence of coronary artery lesions in Kawasaki disease.

• Clinical and Experimental Pediatrics
• /
• v.49 no.11
• /
• pp.1180-1185
• /
• 2006

Purpose : The aims of this study were to verify the incidence of hypohidrosis and to determine the predictive value of noninvasive indicator test ($Neurocheck^{TM}$) for sweating after administration of topiramate in newly diagnosed pediatric epileptic patients. Methods : A total of 46 epileptic patients (22 boys; 24 girls) on topiramate treatment were evaluated in this study at the Department of Pediatrics, Chonbuk National University Hospital, from October 2004 to July 2005. We measured sweating functions using a noninvasive sweating test ($Neurocheck^{TM}$) before topiramate medication, and after 3 months when topiramate reached its target dosage. We performed a direct questionnaire survey for the hypohidrosis related symptoms during topiramate treatment. Results : The mean age was $7.8{\pm}3.2year$. The mean dosage of topiramate was $4.5{\pm}0.8mg/kg/day$. Among the patients, there were 40 complex partial seizures, one simple partial seizure, two partial seizures with secondarily generalization, two generalized seizures, and one Lennox-Gastaut syndrome case. Of the 46 epileptic patients, 17 patients (37.0 percent) experienced hypohidrosis and hypohidrosis related symptoms, 12 (26.1 percent) had facial flushing, four (8.7 percent) had heat intolerance, one (2.2 percent) had lethargy, but no one had anhidrosis. Among the 17 patients, the mild group numbered 12 and the severe group totalled five. Hypohidrosis by $Neurocheck^{TM}$ was diagnosed in 16 patients. The overall measures of agreement between $Neurocheck^{TM}$ and the survey was 76.5 percent. The specificity of this test was 89.7 percent. Patients who showed a time delay after medication, especially over 3 minutes, were seen only in the severe group. Conclusion : $Neurocheck^{TM}$ could be clinically useful to detect and predict topiramate induced hypohidrosis in pediatric epileptic patients. We recommend that patients who show a delay over 3 minutes in $Neurocheck^{TM}$ test after topiramate initiation should be monitored for hypohydrosis.