• The Korean Journal of Applied Statistics
• /
• v.31 no.6
• /
• pp.801-810
• /
• 2018

Diffusion is a random process used to model financial and physical phenomena. When we construct statistical models for repeatedly observed diffusion processes, the idea of random effects needs to be considered. In this research, we introduce random parameters for an Ornstein-Uhlenbeck diffusion model and geometric Brownian motion diffusion model. In order to apply the maximum likelihood estimation method, we tried to build likelihoods in closed-forms, by assuming appropriate distributions for random effects. We applied the random effect models to data consisting of Dow Jones Industrial Average indices recorded daily over 27 years from 1991 to 2017.

• Anatomy and Cell Biology
• /
• v.57 no.1
• /
• pp.97-104
• /
• 2024

Heavy reliance on glucose metabolism and a reduced capacity to use ketone bodies makes glioblastoma (GBM) a promising candidate for ketone-based therapies. Ketogenic diet (KD) is well-known for its promising effects in controlling tumor growth in GBM. Moreover, synthetic ketone ester (KE) has demonstrated to increase blood ketone levels and enhance animal survival in a metastatic VM-M3 murine tumor model. Here, we compared the efficacy of a KE-supplemented Atkins-type diet (ATD-KE) to a classic KD in controlling tumor progression and enhancing survival in a clinically relevant orthotopic patient-derived xenograft GBM model. Our findings demonstrate that ATD-KE preserves body weight (percent change from the baseline; 112±2.99 vs. 116.9±2.52 and 104.8±3.67), decreases blood glucose (80.55±0.86 vs. 118.6±9.51 and 52.35±3.89 mg/dl), and increases ketone bodies in blood (1.15±0.03 mM vs. 0.55±0.04 and 2.66±0.21 mM) and brain tumor tissue (3.35±0.30 mM vs. 2.04±0.3 and 4.25±0.25 mM) comparable to the KD (results presented for ATD-KE vs. standard diet [STD] and KD, respectively). Importantly, the ATD-KE treatment significantly enhanced survival compared to the STD and was indistinguishable from the KD (47 days in STD vs. 56 days in KD and ATD-KE), suggesting that a nutritionally balanced low carbohydrate ATD combined with KE may be as effective as the KD alone in reducing brain tumor progression. Overall, these data support the rationale for clinical testing of KE-supplemented low-carb diet as an adjunct treatment for brain tumor patients.

• The Journal of Bigdata
• /
• v.6 no.1
• /
• pp.23-35
• /
• 2021

In the era of the 4th industrial revolution, smart factories have received great attention, where production and manufacturing technology and ICT converge. With the development of IoT technology and big data, automation of production systems has become possible. In the advanced manufacturing industry, production systems are subject to unscheduled performance degradation and downtime, and there is a demand to reduce safety risks by detecting and reparing potential errors as soon as possible. This study designs a model based on supervised and unsupervised learning for detecting anomalies. The accuracy of XGBoost, LightGBM, and CNN models was compared as a supervised learning analysis method. Through the evaluation index based on the confusion matrix, it was confirmed that LightGBM is most predictive (97%). In addition, as an unsupervised learning analysis method, MD, AE, and LSTM-AE models were constructed. Comparing three unsupervised learning analysis methods, the LSTM-AE model detected 75% of anomalies and showed the best performance. This study aims to contribute to the advancement of the smart factory by combining supervised and unsupervised learning techniques to accurately diagnose equipment failures and predict when abnormal situations occur, thereby laying the foundation for preemptive responses to abnormal situations. do.

• Journal of the Korea Society of Computer and Information
• /
• v.27 no.11
• /
• pp.147-155
• /
• 2022

In this study, we developed a system to dynamically balance a daily stock portfolio and performed trading simulations using gradient boosting and genetic algorithms. We collected various stock market data from stocks listed on the KOSPI and KOSDAQ markets, including investor-specific transaction data. Subsequently, we indexed the data as a preprocessing step, and used feature engineering to modify and generate variables for training. First, we experimentally compared the performance of three popular gradient boosting algorithms in terms of accuracy, precision, recall, and F1-score, including XGBoost, LightGBM, and CatBoost. Based on the results, in a second experiment, we used a LightGBM model trained on the collected data along with genetic algorithms to predict and select stocks with a high daily probability of profit. We also conducted simulations of trading during the period of the testing data to analyze the performance of the proposed approach compared with the KOSPI and KOSDAQ indices in terms of the CAGR (Compound Annual Growth Rate), MDD (Maximum Draw Down), Sharpe ratio, and volatility. The results showed that the proposed strategies outperformed those employed by the Korean stock market in terms of all performance metrics. Moreover, our proposed LightGBM model with a genetic algorithm exhibited competitive performance in predicting stock price movements.

• Journal of Industrial Convergence
• /
• v.21 no.7
• /
• pp.19-27
• /
• 2023

As the secondary battery market expands, the process of producing laterite ore using the rotary kiln and electric furnace method is expanding worldwide. As ESG management expands, the management of air pollutants such as nitrogen oxides in exhaust gases is strengthened. The rotary kiln, one of the main facilities of the pyrometallurgy process, is a facility for drying and preliminary reduction of ore, and it generate nitrogen oxides, thus prediction of nitrogen oxide is important. In this study, LSTM for regression prediction and LightGBM for classification prediction were used to predict and then model optimization was performed using AutoML. When applying LSTM, the predicted value after 5 minutes was 0.86, MAE 5.13ppm, and after 40 minutes, the predicted value was 0.38 and MAE 10.84ppm. As a result of applying LightGBM for classification prediction, the test accuracy rose from 0.75 after 5 minutes to 0.61 after 40 minutes, to a level that can be used for actual operation, and as a result of model optimization through AutoML, the accuracy of the prediction after 5 minutes improved from 0.75 to 0.80 and from 0.61 to 0.70. Through this study, nitrogen oxide prediction values can be applied to actual operations to contribute to compliance with air pollutant emission regulations and ESG management.

• Laboraroty Animal Research
• /
• v.34 no.4
• /
• pp.248-256
• /
• 2018

O-2-$^{18}F$-fluoroethyl-l-tyrosine ($[^{18}F]FET$) has been widely used for glioblastomas (GBM) in clinical practice, although evaluation of its applicability in non-clinical research is still lacking. The objective of this study was to examine the value of $[^{18}F]FET$ for treatment evaluation and prognosis prediction of anti-angiogenic drug in an orthotopic mouse model of GBM. Human U87MG cells were implanted into nude mice and then bevacizumab, a representative anti-angiogenic drug, was administered. We monitored the effect of anti-angiogenic agents using multiple imaging modalities, including bioluminescence imaging (BLI), magnetic resonance imaging (MRI), and positron emission tomography-computed tomography (PET/CT). Among these imaging methods analyzed, only $[^{18}F]FET$ uptake showed a statistically significant decrease in the treatment group compared to the control group (P=0.02 and P=0.03 at 5 and 20 mg/kg, respectively). This indicates that $[^{18}F]FET$ PET is a sensitive method to monitor the response of GBM bearing mice to anti-angiogenic drug. Moreover, $[^{18}F]FET$ uptake was confirmed to be a significant parameter for predicting the prognosis of anti-angiogenic drug (P=0.041 and P=0.007, on Days 7 and 12, respectively, on Pearson's correlation; P=0.048 and P=0.030, on Days 7 and 12, respectively, on Cox regression analysis). However, results of BLI or MRI were not significantly associated with survival time. In conclusion, this study suggests that $[^{18}F]FET$ PET imaging is a pertinent imaging modality for sensitive monitoring and accurate prediction of treatment response to anti-angiogenic agents in an orthotopic model of GBM.

• Tuberculosis and Respiratory Diseases
• /
• v.86 no.3
• /
• pp.203-215
• /
• 2023

Background: Surgical resection is the standard treatment for early-stage lung cancer. Since postoperative lung function is related to mortality, predicted postoperative lung function is used to determine the treatment modality. The aim of this study was to evaluate the predictive performance of linear regression and machine learning models. Methods: We extracted data from the Clinical Data Warehouse and developed three sets: set I, the linear regression model; set II, machine learning models omitting the missing data: and set III, machine learning models imputing the missing data. Six machine learning models, the least absolute shrinkage and selection operator (LASSO), Ridge regression, ElasticNet, Random Forest, eXtreme gradient boosting (XGBoost), and the light gradient boosting machine (LightGBM) were implemented. The forced expiratory volume in 1 second measured 6 months after surgery was defined as the outcome. Five-fold cross-validation was performed for hyperparameter tuning of the machine learning models. The dataset was split into training and test datasets at a 70:30 ratio. Implementation was done after dataset splitting in set III. Predictive performance was evaluated by R² and mean squared error (MSE) in the three sets. Results: A total of 1,487 patients were included in sets I and III and 896 patients were included in set II. In set I, the R² value was 0.27 and in set II, LightGBM was the best model with the highest R² value of 0.5 and the lowest MSE of 154.95. In set III, LightGBM was the best model with the highest R² value of 0.56 and the lowest MSE of 174.07. Conclusion: The LightGBM model showed the best performance in predicting postoperative lung function.

• Journal of Korean Neurosurgical Society
• /
• v.63 no.1
• /
• pp.26-33
• /
• 2020

Glioblastoma (GBM) is a disease without any definite cure. Numerous approaches have been tested in efforts to conquer this brain disease, but patients invariably experience recurrence or develop resistance to treatment. New surgical tools, carefully chosen samples, and experimental methods are enabling discoveries at single-cell resolution. The present article reviews the cell-of-origin of isocitrate dehydrogenase (IDH)-wildtype GBM, beginning with the historical background for focusing on cellular origin and introducing the cancer genesis patterned on firework. The authors also review mutations associated with the senescence process in cells of the subventricular zone (SVZ), and biological validation of somatic mutations in a mouse SVZ model. Understanding GBM would facilitate research on the origin of other cancers and may catalyze the development of new management approaches or treatments against IDH-wildtype GBM.

• Journal of Information Processing Systems
• /
• v.18 no.3
• /
• pp.302-310
• /
• 2022

Efficient use of limited blood products is becoming very important in terms of socioeconomic status and patient recovery. To predict the appropriateness of patient-specific transfusions for the intensive care unit (ICU) patients who require real-time monitoring, we evaluated a model to predict the possibility of transfusion dynamically by using the Medical Information Mart for Intensive Care III (MIMIC-III), an ICU admission record at Harvard Medical School. In this study, we developed an explainable machine learning to predict the possibility of red blood cell transfusion for major medical diseases in the ICU. Target disease groups that received packed red blood cell transfusions at high frequency were selected and 16,222 patients were finally extracted. The prediction model achieved an area under the ROC curve of 0.9070 and an F1-score of 0.8166 (LightGBM). To explain the performance of the machine learning model, feature importance analysis and a partial dependence plot were used. The results of our study can be used as basic data for recommendations related to the adequacy of blood transfusions and are expected to ultimately contribute to the recovery of patients and prevention of excessive consumption of blood products.

• Journal of Cadastre & Land InformatiX
• /
• v.50 no.1
• /
• pp.181-200
• /
• 2020

This study used the OLS model to estimate the determinants affecting the tenure of a home and then compared the predictive power of each model with SVM, Decision Tree, Random Forest, Gradient Boosting, XGBooest and LightGBM. There is a difference from the preceding study in that the Stacking model, one of the ensemble models, can be used as a base model to establish a more predictable model to identify the volume of housing transactions in the housing market. OLS analysis showed that sales profits, housing prices, the number of household members, and the type of residential housing (detached housing, apartments) affected the period of housing ownership, and compared the predictability of the machine learning model with RMSE, the results showed that the machine learning model had higher predictability. Afterwards, the predictive power was compared by applying each machine learning after rebuilding the data with the influencing variables, and the analysis showed the best predictive power of Random Forest. In addition, the most predictable Random Forest, Decision Tree, Gradient Boosting, and XGBooost models were applied as individual models, and the Stacking model was constructed using Linear, Ridge, and Lasso models as meta models. As a result of the analysis, the RMSE value in the Ridge model was the lowest at 0.5181, thus building the highest predictive model.