• Korean Journal of Biological Psychiatry
• /
• v.30 no.1
• /
• pp.24-30
• /
• 2023

Objectives Alzheimer's disease (AD) is the most common form of dementia in older adults, damaging the brain and resulting in impaired memory, thinking, and behavior. The identification of differentially expressed genes and related pathways among affected brain regions can provide more information on the mechanisms of AD. The aim of our study was to identify differentially expressed genes associated with AD and combined biomarkers among them to improve AD risk prediction accuracy. Methods Machine learning methods were used to compare the performance of the identified combined biomarkers. In this study, three publicly available gene expression datasets from the hippocampal brain region were used. Results We detected 31 significant common genes from two different microarray datasets using the limma package. Some of them belonged to 11 biological pathways. Combined biomarkers were identified in two microarray datasets and were evaluated in a different dataset. The performance of the predictive models using the combined biomarkers was superior to those of models using a single gene. When two genes were combined, the most predictive gene set in the evaluation dataset was ATR and PRKCB when linear discriminant analysis was applied. Conclusions Combined biomarkers showed good performance in predicting the risk of AD. The constructed predictive nomogram using combined biomarkers could easily be used by clinicians to identify high-risk individuals so that more efficient trials could be designed to reduce the incidence of AD.

• Journal of Korean Association for Spatial Structures
• /
• v.23 no.4
• /
• pp.81-88
• /
• 2023

Numerous factors contribute to the deterioration of reinforced concrete structures. Elevated temperatures significantly alter the composition of the concrete ingredients, consequently diminishing the concrete's strength properties. With the escalation of global CO2 levels, the carbonation of concrete structures has emerged as a critical challenge, substantially affecting concrete durability research. Assessing and predicting concrete degradation due to thermal effects and carbonation are crucial yet intricate tasks. To address this, multiple prediction models for concrete carbonation and compressive strength under thermal impact have been developed. This study employs seven machine learning algorithms-specifically, multiple linear regression, decision trees, random forest, support vector machines, k-nearest neighbors, artificial neural networks, and extreme gradient boosting algorithms-to formulate predictive models for concrete carbonation and thermal impact. Two distinct datasets, derived from reported experimental studies, were utilized for training these predictive models. Performance evaluation relied on metrics like root mean square error, mean square error, mean absolute error, and coefficient of determination. The optimization of hyperparameters was achieved through k-fold cross-validation and grid search techniques. The analytical outcomes demonstrate that neural networks and extreme gradient boosting algorithms outshine the remaining five machine learning approaches, showcasing outstanding predictive performance for concrete carbonation and thermal effect modeling.

• Journal of the Korean Data and Information Science Society
• /
• v.27 no.1
• /
• pp.255-264
• /
• 2016

Classification is a predictive modeling for a categorical target variable. Various classification ensemble methods, which predict with better accuracy by combining multiple classifiers, became a powerful machine learning and data mining paradigm. Well-known methodologies of classification ensemble are boosting, bagging and random forest. In this article, we assume that decision trees are used as classifiers in the ensemble. Further, we hypothesized that tree size affects classification accuracy. To study how the tree size in uences accuracy, we performed experiments using twenty-eight data sets. Then we compare the performances of ensemble algorithms; bagging, double-bagging, boosting and random forest, with different tree sizes in the experiment.

• Geomechanics and Engineering
• /
• v.17 no.6
• /
• pp.597-606
• /
• 2019

Ultrasonic Time-of-Flight Diffraction (TOFD) techniques are useful methods for non-destructive evaluation of fracture characteristics. This study focuses on the reliability and accuracy of ultrasonic diffraction methods to estimate the depth of rock fractures. The study material includes three different rock types; andesite, basalt and ignimbrite. Four different ultrasonic techniques were performed on these intact rocks. Artificial near-surface fracture depths were created in the laboratory by sawing. The reliability and accuracy of each technique was assessed by comparison of the repeated measurements at different path lengths along the rock surface. The standard error associated with the predictive equations is very small and their reliability and accuracy seem to be high enough to be utilized in estimating the depth of rock fractures. The performances of these techniques were re-evaluated after filling the artificial fractures with another material to simulate natural infills.

• Molecules and Cells
• /
• v.46 no.1
• /
• pp.21-32
• /
• 2023

MicroRNAs (miRNAs) play cardinal roles in regulating biological pathways and processes, resulting in significant physiological effects. To understand the complex regulatory network of miRNAs, previous studies have utilized massivescale datasets of miRNA targeting and attempted to computationally predict the functional targets of miRNAs. Many miRNA target prediction tools have been developed and are widely used by scientists from various fields of biology and medicine. Most of these tools consider seed pairing between miRNAs and their mRNA targets and additionally consider other determinants to improve prediction accuracy. However, these tools exhibit limited prediction accuracy and high false positive rates. The utilization of additional determinants, such as RNA modifications and RNA-binding protein binding sites, may further improve miRNA target prediction. In this review, we discuss the determinants of functional miRNA targeting that are currently used in miRNA target prediction and the potentially predictive but unappreciated determinants that may improve prediction accuracy.

• Asian Pacific Journal of Cancer Prevention
• /
• v.16 no.16
• /
• pp.7381-7384
• /
• 2015

This study was conducted to 1206 women who had cervical cancer screening at Chonburi Cancer Hospital. The spilt-sample study aimed to compare the efficacy of abnormal cervical cells detection between liquid-based cytology (LBC) and conventional cytology (CC). The collection of cervical cells was performed by broom and directly smeared on a glass slide for CC then the rest of specimen was prepared for LBC. All slides were evaluated and classified by The Bethesda System. The results of the two cytological tests were compared to the gold standard. The LBC smear significantly decreased inflammatory cell and thick smear on slides. These two techniques were not difference in detection rate of abnormal cytology and had high cytological diagnostic agreement of 95.7%. The histologic diagnosis of cervical tissue was used as the gold standard in 103 cases. Sensitivity, specificity, positive predictive value, negative predictive value, false positive, false negative and accuracy of LBC at ASC-US cut off were 81.4, 75.0, 70.0, 84.9, 25.0, 18.6 and 77.7%, respectively. CC had higher false positive and false negative than LBC. LBC had shown higher sensitivity, specificity, PPV, NPV and accuracy than CC but no statistical significance. In conclusion, LBC method can improve specimen quality, more sensitive, specific and accurate at ASC-US cut off and as effective as CC in detecting cervical epithelial cell abnormalities.

• The Korean Journal of Cytopathology
• /
• v.10 no.1
• /
• pp.13-19
• /
• 1999

The authors analysed 2,653 cases of transthoracic fine needle aspiration cytology of the lung to evaluate the diagnostic accuracy and its limitation. A comparison was made between the original cytologic and the final histologic diagnoses on 1,149 cases from 1,074 patients. A diagnosis of malignancy was established in 38.3% benign in 48.1%, atypical lesion in 2.3%, and inadequate one in 11.9% of the cases. Statistical data on cytologic diagnoses were as follows; specificity 98.9%: sensitivity of procedure, 76.8%: sensitivity of diagnosis, 95.5%: false positive 5 cases: false negative 18 cases: predictive value for malignancy, 98.8%: predictive value for benign lesion, 79.5%: overall diagnostic efficiency, 87.5%: typing accuracy in malignant tumor, 80%.

• The Korean Journal of Applied Statistics
• /
• v.32 no.5
• /
• pp.703-720
• /
• 2019

The influence of temperature on electricity demand is increasing due to extreme weather and climate change, and the climate impacts involves nonlinearity, asymmetry and complexity. Considering changes in government energy policy and the development of the fourth industrial revolution, it is important to assess the climate effect more accurately for stable management of electricity supply and demand. This study aims to analyze the effect of temperature change on electricity demand using the partial linear model. The main results obtained using the time-unit high frequency data for meteorological variables and electricity consumption are as follows. Estimation results show that the relationship between temperature change and electricity demand involves complexity, nonlinearity and asymmetry, which reflects the nonlinear effect of extreme weather. The prediction accuracy of in-sample and out-of-sample electricity forecasting using the partial linear model evidences better predictive accuracy than the conventional model based on the heating and cooling degree days. Diebold-Mariano test confirms significance of the predictive accuracy of the partial linear model.

• Clinical and Experimental Pediatrics
• /
• v.55 no.1
• /
• pp.11-17
• /
• 2012

Purpose: Early identification of neonatal sepsis is a global issue because of limitations in diagnostic procedures. The objective of this study was to compare the diagnostic accuracy of neutrophil CD64 and C-reactive protein (CRP) as a single test for the early detection of neonatal sepsis. Methods: A prospective study enrolled newborns with documented sepsis (n=11), clinical sepsis (n=12) and control newborns (n=14). CRP, neutrophil CD64, complete blood counts and blood culture were taken at the time of the suspected sepsis for the documented or clinical group and at the time of venipuncture for laboratory tests in control newborns. Neutrophil CD64 was analyzed by flow cytometry. Results: CD64 was significantly elevated in the groups with documented or clinical sepsis, whereas CRP was not significantly increased compared with controls. For documented sepsis, CD64 and CRP had a sensitivity of 91% and 9%, a specificity of 83% and 83%, a positive predictive value of 83% and 33% and a negative predictive value of 91% and 50%, respectively, with a cutoff value of 3.0 mg/dL for CD64 and 1.0 mg/dL for CRP. The area under the receiver-operating characteristic curves for CD64 index and CRP were 0.955 and 0.527 ($P$ <0.01), respectively. Conclusion: These preliminary data show that diagnostic accuracy of CD64 is superior to CRP when measured at the time of suspected sepsis, which implies that CD64 is a more reliable marker for the early identification of neonatal sepsis as a single determination compared with CRP.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.22 no.3
• /
• pp.20-29
• /
• 2021

In the Industry 4.0 era, artificial intelligence has attracted considerable interest for learning mass data to improve the accuracy of forecasting and classification. On the other hand, the current method of detecting anomalies relies on traditional statistical methods for a limited amount of data, making it difficult to detect accurate anomalies. Therefore, this paper proposes an artificial intelligence-based anomaly detection methodology to improve the prediction accuracy and identify new data patterns. In particular, data were collected and analyzed from the point of view that sensor data collected at vehicle idle could be used to detect abnormalities. To this end, a sensor was designed to determine the appropriate time length of the data entered into the forecast model, compare the results of idling data with the overall driving data utilization, and make optimal predictions through a combination of various sensor data. In addition, the predictive accuracy of artificial intelligence techniques was presented by comparing Convolutional Neural Networks (CNN) and Long Short Term Memory (LSTM) as the predictive methodologies. According to the analysis, using idle data, using 1.5 times of the data for the idling periods, and using CNN over LSTM showed better prediction results.