• Investigative Magnetic Resonance Imaging
• /
• v.19 no.2
• /
• pp.67-75
• /
• 2015

Purpose: To investigate the value of image post-processing software (FreeSurfer, IBASPM [individual brain atlases using statistical parametric mapping software]) and inversion time (TI) in volumetric analyses of the hippocampus and to identify differences in comparison with manual tracing. Materials and Methods: Brain images from 12 normal adults were acquired using magnetization prepared rapid acquisition gradient echo (MPRAGE) with a slice thickness of 1.3 mm and TI of 800, 900, 1000, and 1100 ms. Hippocampal volumes were measured using FreeSurfer, IBASPM and manual tracing. Statistical differences were examined using correlation analyses accounting for spatial interpretations percent volume overlap and percent volume difference. Results: FreeSurfer revealed a maximum percent volume overlap and maximum percent volume difference at TI = 800 ms ($77.1{\pm}2.9%$) and TI = 1100 ms ($13.1{\pm}2.1%$), respectively. The respective values for IBASPM were TI = 1100 ms ($55.3{\pm}9.1%$) and TI = 800 ms ($43.1{\pm}10.7%$). FreeSurfer presented a higher correlation than IBASPM but it was not statistically significant. Conclusion: FreeSurfer performed better in volumetric determination than IBASPM. Given the subjective nature of manual tracing, automated image acquisition and analysis image is accurate and preferable.

• Nuclear Engineering and Technology
• /
• v.42 no.6
• /
• pp.670-679
• /
• 2010

In this paper, a new approach using a pixel-based correction method was developed to fix the non-uniform responses of flat-bed type scanners used for radiochromic film dosimetry. In order to validate the method's performance, two cases were tested: the first consisted of simple dose distributions delivered by a single port; the second was a complicated dose distribution composed of multiple beams. In the case of the simple individual dose condition, ten different doses, from 8.3 cGy to 307.1 cGy, were measured, horizontal profiles were analyzed using the pixel-based correcton method and compared with results measured by an ionization chamber and results corrected using the existing correction method. A complicated inverse pyramid dose distribution was made by piling up four different field shapes, which were measured with GAFCHROMIC$^{(R)}$EBT film and compared with the Monte Carlo calculation; as well as the dose distribution corrected using a conventional method. The results showed that a pixel-based correction method reduced dose difference from the reference measurement down to 1% in the flat dose distribution region or 2 mm in a steep dose gradient region compared to the reference data, which were ionization chamber measurement data for simple cases and the MC computed data for the complicated case, with an exception for very low doses of less than about 10 cGy in the simple case. Therefore, the pixel-based scanner correction method is expected to enhance the accuracy of GAFCHROMIC$^{(R)}$EBT film dosimetry, which is a widely used tool for two-dimensional dosimetry.

• Journal of Applied Biological Chemistry
• /
• v.62 no.2
• /
• pp.129-135
• /
• 2019

Salvia miltiorrhiza Radix is cultivated in Korea and China and is traditionally used to treat cardiovascular diseases. In this study, we developed and validated a quantitative analysis method for S. miltiorrhiza Radix using high-performance liquid chromatography (HPLC). Identification was performed using ultra performance liquid chromatography-tandem mass spectrometry. For quantitative analysis, we used seven marker compounds. Separation conditions for HPLC were optimized using an ODS column with gradient conditions of 1% formic acid in distilled water and 1% formic acid in acetonitrile, with a flow rate of 0.8 mL/min and a detection wavelength of 280 nm. This method showed good linearity ($R^2=0.9998$), precision (relative standard deviation ${\leq}3.3%$), accuracy (recovery of 94.16-102.89%), limit of detection ($7.53{\mu}g/mL$), and limit of quantification ($23.71{\mu}g/mL$). This approach successfully quantified marker compounds in S. miltiorrhiza Radix. The individual marker compounds were identified by comparing the molecular masses and retention times with does standard compounds. Marker compound contents of S. miltiorrhiza Radix were investigated with different cultivation regions. Seven marker compounds were detected and quantified in all samples. Among them, salvianolic acid B showed the highest contents and it ranged from 4.13 to 7.15%. The salvianolic acid B content (7.15%) of marker compound was the highest in Bonghwa, and the tanshinone IIA content (1.90%) was the highest in Pohang. The results of marker compounds and developed method were intended to provide a favorable reference for the study of S. miltiorrhiza Radix from different regions of Korea.

• The Korean Journal of Applied Statistics
• /
• v.34 no.2
• /
• pp.153-166
• /
• 2021

A main goal of pharmacogenomics studies is to predict individual's drug responsiveness based on high dimensional genetic variables. Due to a large number of variables, feature selection is required in order to reduce the number of variables. The selected features are used to construct a predictive model using machine learning algorithms. In the present study, we applied several hybrid feature selection methods such as combinations of logistic regression, ReliefF, TurF, random forest, and LASSO to a next generation sequencing data set of 400 epilepsy patients. We then applied the selected features to machine learning methods including random forest, gradient boosting, and support vector machine as well as a stacking ensemble method. Our results showed that the stacking model with a hybrid feature selection of random forest and ReliefF performs better than with other combinations of approaches. Based on a 5-fold cross validation partition, the mean test accuracy value of the best model was 0.727 and the mean test AUC value of the best model was 0.761. It also appeared that the stacking models outperform than single machine learning predictive models when using the same selected features.

• The Journal of Information Systems
• /
• v.30 no.4
• /
• pp.21-42
• /
• 2021

Purpose In order for companies to continue to grow, they should properly manage human resources, which are the core of corporate competitiveness. Employee turnover means the loss of talent in the workforce. When an employee voluntarily leaves his or her company, it will lose hiring and training cost and lead to the withdrawal of key personnel and new costs to train a new employee. From an employee's viewpoint, moving to another company is also risky because it can be time consuming and costly. Therefore, in order to reduce the social and economic costs caused by employee turnover, it is necessary to accurately predict employee turnover intention, identify the factors affecting employee turnover, and manage them appropriately in the company. Design/methodology/approach Prior studies have mainly used logistic regression and decision trees, which have explanatory power but poor predictive accuracy. In order to develop a more accurate prediction model, XGBoost is proposed as the classification technique. Then, to compensate for the lack of explainability, SHAP, one of the XAI techniques, is applied. As a result, the prediction accuracy of the proposed model is improved compared to the conventional methods such as LOGIT and Decision Trees. By applying SHAP to the proposed model, the factors affecting the overall employee turnover intention as well as a specific sample's turnover intention are identified. Findings Experimental results show that the prediction accuracy of XGBoost is superior to that of logistic regression and decision trees. Using SHAP, we find that jobseeking, annuity, eng_test, comm_temp, seti_dev, seti_money, equl_ablt, and sati_safe significantly affect overall employee turnover intention. In addition, it is confirmed that the factors affecting an individual's turnover intention are more diverse. Our research findings imply that companies should adopt a personalized approach for each employee in order to effectively prevent his or her turnover.

• Journal of Information Technology Services
• /
• v.21 no.3
• /
• pp.63-72
• /
• 2022

The extinction crisis of local cities, caused by a population density increase phenomenon in capital regions, directly causes the increase of vacant houses in local cities. According to population and housing census, Gunsan-si has continuously shown increasing trend of vacant houses during 2015 to 2019. In particular, since Gunsan-si is the city which suffers from doughnut effect and industrial decline, problems regrading to vacant house seems to exacerbate. This study aims to provide a foundation of a system which can predict and deal with the building that has high risk of becoming vacant house through implementing a data driven vacant house prediction machine learning model. Methodologically, this study analyzes three types of machine learning model by differing the data components. First model is trained based on building register, individual declared land value, house price and socioeconomic data and second model is trained with the same data as first model but with additional POI(Point of Interest) data. Finally, third model is trained with same data as the second model but with excluding water usage and electricity usage data. As a result, second model shows the best performance based on F1-score. Random Forest, Gradient Boosting Machine, XGBoost and LightGBM which are tree ensemble series, show the best performance as a whole. Additionally, the complexity of the model can be reduced through eliminating independent variables that have correlation coefficient between the variables and vacant house status lower than the 0.1 based on absolute value. Finally, this study suggests XGBoost and LightGBM based machine learning model, which can handle missing values, as final vacant house prediction model.

• International Journal of Computer Science & Network Security
• /
• v.24 no.2
• /
• pp.101-112
• /
• 2024

Telugu language is considered as fourth most used language in India especially in the regions of Andhra Pradesh, Telangana, Karnataka etc. In international recognized countries also, Telugu is widely growing spoken language. This language comprises of different dependent and independent vowels, consonants and digits. In this aspect, the enhancement of Telugu Handwritten Character Recognition (HCR) has not been propagated. HCR is a neural network technique of converting a documented image to edited text one which can be used for many other applications. This reduces time and effort without starting over from the beginning every time. In this work, a Unicode based Handwritten Character Recognition(U-HCR) is developed for translating the handwritten Telugu characters into English language. With the use of Centre of Gravity (CG) in our model we can easily divide a compound character into individual character with the help of Unicode values. For training this model, we have used both online and offline Telugu character datasets. To extract the features in the scanned image we used convolutional neural network along with Machine Learning classifiers like Random Forest and Support Vector Machine. Stochastic Gradient Descent (SGD), Root Mean Square Propagation (RMS-P) and Adaptative Moment Estimation (ADAM)optimizers are used in this work to enhance the performance of U-HCR and to reduce the loss function value. This loss value reduction can be possible with optimizers by using CNN. In both online and offline datasets, proposed model showed promising results by maintaining the accuracies with 90.28% for SGD, 96.97% for RMS-P and 93.57% for ADAM respectively.

• Korean Circulation Journal
• /
• v.53 no.10
• /
• pp.677-689
• /
• 2023

Background and Objectives: There is limited evidence regarding machine-learning prediction for the recurrence of atrial fibrillation (AF) after electrical cardioversion (ECV). This study aimed to predict the recurrence of AF after ECV using machine learning of clinical features and electrocardiograms (ECGs) in persistent AF patients. Methods: We analyzed patients who underwent successful ECV for persistent AF. Machine learning was designed to predict patients with 1-month recurrence. Individual 12-lead ECGs were collected before and after ECV. Various clinical features were collected and trained the extreme gradient boost (XGBoost)-based model. Ten-fold cross-validation was used to evaluate the performance of the model. The performance was compared to the C-statistics of the selected clinical features. Results: Among 718 patients (mean age 63.5±9.3 years, men 78.8%), AF recurred in 435 (60.6%) patients after 1 month. With the XGBoost-based model, the areas under the receiver operating characteristic curves (AUROCs) were 0.57, 0.60, and 0.63 if the model was trained by clinical features, ECGs, and both (the final model), respectively. For the final model, the sensitivity, specificity, and F1-score were 84.7%, 28.2%, and 0.73, respectively. Although the AF duration showed the best predictive performance (AUROC, 0.58) among the clinical features, it was significantly lower than that of the final machine-learning model (p<0.001). Additional training of extended monitoring data of 15-minute single-lead ECG and photoplethysmography in available patients (n=261) did not significantly improve the model's performance. Conclusions: Machine learning showed modest performance in predicting AF recurrence after ECV in persistent AF patients, warranting further validation studies.

• Progress in Medical Physics
• /
• v.19 no.4
• /
• pp.269-275
• /
• 2008

Although MR imaging is generally applicable to depict knee joint deterioration it, is sometimes occurred to mis-read and mis-diagnose the common knee joint diseases. In this study, we employed magnetization transfer ratio (MTR) method to improve the diagnosis of the various knee joint diseases. Spin-echo (SE) T2-weighted images (TR/TE 3,400-3,500/90-100 ms) were obtained in seven cases of knee joint deterioration, FSE T2-weighted images (TR/TE 4,500-5,000/100-108 ms) were obtained in seven cases of knee joint deterioration, gradient-echo (GRE) T2-weighted images (TR/TE 9/4.56/$50^{\circ}$ flip angle, NEX 1) were obtained in 3 cases of knee joint deterioration, In six cases of knee joint deterioration, fat suppression was performed using a T2-weighted short T1/tau inverse recovery (STIR) sequence (TR/TE =2,894-3,215 ms/70 ms, NEX 3, ETL 9). Calculation of MTR for individual pixels was performed on registration of unsaturated and saturated images. After processing to make MTR images, the images were displayed in gray color. For improving diagnosis, three-dimensional isotropic volume images, the MR tristimulus color mapping and the MTR map was employed. MTR images showed diagnostic images quality to assess the patients' pathologies. The intensity difference between MTR images and conventional MRI was seen on the color bar. The profile graph on MTR imaging effect showed a quantitative measure of the relative decrease in signal intensity due to the MT pulse. To diagnose the pathologies of the knee joint, the profile graph data was shown on the image as a small cross. The present study indicated that MTR images in the knee joint were feasible. Investigation of physical change on MTR imaging enables to provide us more insight in the physical and technical basis of MTR imaging. MTR images could be useful for rapid assessment of diseases that we examine unambiguous contrast in MT images of knee disorder patients.

• Asian-Australasian Journal of Animal Sciences
• /
• v.27 no.11
• /
• pp.1562-1570
• /
• 2014

The effects of Lactobacillus mucosae (L. mucosae), a potential direct fed microbial previously isolated from the rumen of Korean native goat, on the rumen fermentation profile of brewers grain were evaluated. Fermentation was conducted in serum bottles each containing 1% dry matter (DM) of the test substrate and either no L. mucosae (control), 1% 24 h broth culture of L. mucosae (T1), or 1% inoculation with the cell-free culture supernatant (T2). Each serum bottle was filled anaerobically with 100 mL of buffered rumen fluid and sealed prior to incubation for 0, 6, 12, 24, and 48 h from which fermentation parameters were monitored and the microbial diversity was evaluated. The results revealed that T1 had higher total gas production (65.00 mL) than the control (61.33 mL) and T2 (62.00 mL) (p<0.05) at 48 h. Consequently, T1 had significantly lower pH values (p<0.05) than the other groups at 48 h. Ammonia nitrogen ($NH_3$-N), individual and total volatile fatty acids (VFA) concentration and acetate:propionate ratio were higher in T1 and T2 than the control, but T1 and T2 were comparable for these parameters. Total methane ($CH_4$) production and carbon dioxide ($CO_2$) were highest in T1. The percent DM and organic matter digestibilities were comparable between all groups at all times of incubation. The total bacterial population was significantly higher in T1 (p<0.05) at 24 h, but then decreased to levels comparable to the control and T2 at 48 h. The denaturing gradient gel electrophoresis profile of the total bacterial 16s rRNA showed higher similarity between T1 and T2 at 24 h and between the control and T1 at 48 h. Overall, these results suggest that addition of L. mucosae and cell-free supernatant during the in vitro fermentation of dried brewers grain increases the VFA production, but has no effect on digestibility. The addition of L. mucosae can also increase the total bacterial population, but has no significant effect on the total microbial diversity. However, inoculation of the bacterium may increase $CH_4$ and $CO_2$ in vitro.