• Journal of the Korea Society of Computer and Information
• /
• v.28 no.8
• /
• pp.49-58
• /
• 2023

Dropouts of students not only cause financial loss to the university, but also have negative impacts on individual students and society together. To resolve this issue, various studies have been conducted to predict student dropout using machine learning. This paper presents a model implemented using DNN (Deep Neural Network) and LGBM (Light Gradient Boosting Machine) to predict dropout of university students and compares their performance. The academic record and grade data collected from 20,050 students at A University, a small and medium-sized 4-year university in Seoul, were used for learning. Among the 140 attributes of the collected data, only the attributes with a correlation coefficient of 0.1 or higher with the attribute indicating dropout were extracted and used for learning. As learning algorithms, DNN (Deep Neural Network) and LightGBM (Light Gradient Boosting Machine) were used. Our experimental results showed that the F1-scores of DNN and LGBM were 0.798 and 0.826, respectively, indicating that LGBM provided 2.5% better prediction performance than DNN.

• Journal of Wetlands Research
• /
• v.26 no.2
• /
• pp.147-159
• /
• 2024

Lack of streamflow observations makes model calibration difficult and limits model performance improvement. Satellite-based remote sensing products offer a new alternative as they can be actively utilized to obtain hydrological data. Recently, several studies have shown that artificial intelligence-based solutions are more appropriate than traditional conceptual and physical models. In this study, a data-driven approach combining various recurrent neural networks and decision tree-based algorithms is proposed, and the utilization of satellite remote sensing information for AI training is investigated. The satellite imagery used in this study is from MODIS and SMAP. The proposed approach is validated using publicly available data from 25 watersheds. Inspired by the traditional regionalization approach, a strategy is adopted to learn one data-driven model by integrating data from all basins, and the potential of the proposed approach is evaluated by using a leave-one-out cross-validation regionalization setting to predict streamflow from different basins with one model. The GRU + Light GBM model was found to be a suitable model combination for target basins and showed good streamflow prediction performance in ungauged basins (The average model efficiency coefficient for predicting daily streamflow in 25 ungauged basins is 0.7187) except for the period when streamflow is very small. The influence of satellite remote sensing information was found to be up to 10%, with the additional application of satellite information having a greater impact on streamflow prediction during low or dry seasons than during wet or normal seasons.

• Geomechanics and Engineering
• /
• v.37 no.5
• /
• pp.475-498
• /
• 2024

The prediction of the susceptibility of soil to liquefaction using a limited set of parameters, particularly when dealing with highly unbalanced databases is a challenging problem. The current study focuses on different ensemble learning classification algorithms using highly unbalanced databases of results from in-situ tests; standard penetration test (SPT), shear wave velocity (V_s) test, and cone penetration test (CPT). The input parameters for these datasets consist of earthquake intensity parameters, strong ground motion parameters, and in-situ soil testing parameters. liquefaction index serving as the binary output parameter. After a rigorous comparison with existing literature, extreme gradient boosting (XGBoost), bagging, and random forest (RF) emerge as the most efficient models for liquefaction instance classification across different datasets. Notably, for SPT and V_s-based models, XGBoost exhibits superior performance, followed by Light gradient boosting machine (LightGBM) and Bagging, while for CPT-based models, Bagging ranks highest, followed by Gradient boosting and random forest, with CPT-based models demonstrating lower G_mean(error), rendering them preferable for soil liquefaction susceptibility prediction. Key parameters influencing model performance include internal friction angle of soil (ϕ) and percentage of fines less than 75 µ (F₇₅) for SPT and V_s data and normalized average cone tip resistance (q_c) and peak horizontal ground acceleration (a_max) for CPT data. It was also observed that the addition of V_s measurement to SPT data increased the efficiency of the prediction in comparison to only SPT data. Furthermore, to enhance usability, a graphical user interface (GUI) for seamless classification operations based on provided input parameters was proposed.

• The Journal of Internal Korean Medicine
• /
• v.30 no.3
• /
• pp.495-509
• /
• 2009

Objective : Membranous nephropathy(MN) is an organ-specific autoimmune disease and a relatively common cause of nephrotic syndrome in adults worldwide. But treatment of MN is not defined. This study was to evaluate the effects of Acasia Catechu extract(ACE) on the MN induced by cBSA in mice. Methods : Mice were divided into 4 groups. The normal group was injected with a saline solution. The control group was treated with cBSA(10 mg/kg i.p.) only. The third group was treated with cBSA (10 mg/kg i.p.) and ACE (250 mg/kg, p.o.). The fourth group was treated with cBSA (10mg/kg i.p.) and ACE (500mg/kg, p.o.). After cBSA and ACE treatment for 6 weeks, we measured change of body weight, 24hrs proteinuria, serum albumin, total cholesterol, triglyceride, BUN, creatinine, TNF-$\alpha$, IL-6, IL-$1{\beta}$, IFN-$\gamma$, IgA, IgM and IgG levels. The morphologic changes of renal glomeruli were also observed with a light microscope. Results : The levels of 24 hrs proteinuria, total cholesterol, triglyceride, IgG, IgM, IgA, TNF-$\alpha$, IL-6, IL-$1{\beta}$, IFN-$\gamma$ significantly decreased in both ACE groups. The level of albumin significantly increased in both ACE groups. The mRNA expression of IL-$1{\beta}$ in splenocytes considerably decreased in the ACE-500 group. In histological findings of kidney tissue, thickening of GBM decreased in both ACE groups. Conclusions : This study shows that ACE might be effective for treatment of MN. More clinical data and studies are to be done for efficient application.

• Journal of Physiology & Pathology in Korean Medicine
• /
• v.23 no.5
• /
• pp.1063-1072
• /
• 2009

Membranous nephropathy(MN) is the most common cause of adult nephrotic syndrome worldwide. But treatment of MN is not defined. This study was to evaluate the effects of Lonicerae Flos Extract(LFE) on the MN induced by cBSA in mice. Mice were divided into 4 groups. The first group named for 'Normal' was injected with a saline solution. The second group named 'Control' treated with cBSA(10 mg/kg i.p) only. The third group named 'LFE-250', treated with cBSA(10 mg/kg i.p) and LFE(250 mg/kg, p.o). The fourth group named 'LFE-500'treated with cBSA(10 mg/kg i.p) and LFE(500 mg/kg, p.o). After cBSA and LFE treatment for 4 weeks, we measured change of body weight, 24hrs proteinuria, serum albumin, total cholesterol, triglyceride, BUN, creatinine, TNF-$\alpha$, IL-6, IL-$1{\beta}$, IL-10, IFN-$\gamma$, IgA, IgM and IgG levels. The morphologic changes of renal glomeruli were also observed with a light microscope. The levels of 24 hrs proteinuria, total cholesterol, IgG , IgM, IgA, IL-6 were significantly decreased in both LFE groups. The level of triglyceride, IL-$1{\beta}$ was significantly decreased in LFE-500 group. The level of Albumin was significantly increased in LFE-250 group. The level of TNF-$\alpha$, IFN-$\gamma$ were significantly decreased in LFE-250 group. The mRNA expression of IL-$1{\beta}$ in splenocytes was consideraly decreased in LFE-500 group. In histological findings of kidney tissue, thickening of GBM decreased in both LFE groups. This study shows that the LFE might be effective for treatment of MN. More clinical data and studies are to be done for efficient application.

• The Journal of Korean Medicine
• /
• v.30 no.4
• /
• pp.93-107
• /
• 2009

Objective: Membranous nephropathy (MN) is one of the most common causes of nephrotic syndrome in adults. However, there is not a satisfactory treatment for MN. This study aimed to evaluate the effect of Houttuyniae Herba Extract (HHE) on MN induced by cationic bovine serum albumin (cBSA). Methods: Mice were divided into 4 groups. The first group, Normal, was injected with saline. The second group, Control, was treated with cBSA (10mg/kg i.p) only. The third group, HHE-250, was treated with cBSA (10mg/kg i.p) and HHE (250mg/kg, p.o). The fourth group, HHE-500, was treated with cBSA (10mg/kg i.p) and HHE (500mg/kg, p.o). After treatment for 4 weeks, we measured change of body weight, 24 hrs proteinuria, serum albumin, total cholesterol, triglyceride, BUN, creatinine, IgA, IgM, IgG, TNF-${\alpha}$, IL-1${\beta}$ levels and the mRNA expression of IFN-${\gamma}$, IL-6, and IL-10. The morphologic changes of renal glomeruli were also observed with a light microscope and an electron microscope. Results: The levels of 24 hrs proteinuria and serum triglyceride, BUN, IgG, TNF-${\alpha}$, IL-1${\beta}$ significantly decreased in both HHE groups, while the level of serum albumin significantly increased in both HHE groups. The mRNA expression of IFN-${\gamma}$ and IL-6 in splenocytes considerably increased in both HHE groups. The mRNA expression of IL-10 in splenocytes considerably decreased in both HHE groups. In histological findings of kidney tissue, thickening of GBM decreased in both HHE groups. Conclusions: This study shows that HHE might be effective for treatment of acute stage MN. More clinical data and studies are to be done for efficient application.

• The Journal of Internal Korean Medicine
• /
• v.30 no.1
• /
• pp.212-227
• /
• 2009

Objective : Membranous nephropathy (MN) is one of the most commonest forms of glomerular disease in man and the most frequent cause of the adult idiopathic nephrotic syndrome. Some investigators recommend no treatment, while others propose aggressive therapy, including prednisolone plus an immunosupressant such as chlorambucil or cyclophosphamide. But a more effective way to treat MN is not defined yet. This study was to evaluate the effects of Patriniae Radix extract (PRE) on the MN induced by cBSA in mice. Methods : Mice were divided into 4 groups. The first group (normal) was injected with saline. The second group (control) was treated with cBSA (10 mg/kg i.p) only. The third group, named PRE-2S0, was treated with cBSA (10 mg/kg i.p) and PRE (250 mg/kg, p.o). The fourth group, PRE-500, was treated with cBSA (10mg/kg i.p) and PRE (500mg/kg, p.o). After cBSA and PRE treatment for 4 weeks, we measured change of body weight, 24hrs proteinuria, serum albumin, total cholesterol, triglyceride, BUN, creatinine, IgG, IgA, IgM, $TNF-\alpha$, $IL-1\beta$, and $IFN-\gamma$ levels and the mRNA expression of $IFN-\gamma$, IL-6, and IL-10. The morphologic changes of renal glomeruli were also observed with a light microscope and an electron microscope. Results : The levels of 24 hrs proteinuria and serum triglyceride. BUN. IgG. $TNF-\alpha$, and $IL-1\beta$ significantly decreased in both PRE groups, while the level of serum albumin significantly increased in both PRE groups. The mRNA expression of IL-10 in splenocytes considerably increased in both PRE groups. The mRNA expression of $IFN-\gamma$ and IL-6 in splenocytes considerably increased in both PRE group. In histological findings of kidney tissue, thickening of GBM decreased in both PRE groups. Conclusions : The present study suggests that PRE is effective when treating mice with MN induced by cBSA. More clinical data and studies are to be done for efficient application.

• The Korea Journal of Herbology
• /
• v.24 no.1
• /
• pp.99-110
• /
• 2009

Objectives : The current treatment regimens for patients with nephrotic syndrome due to membranous nephropathy(MN) are based on steroids or immunosuppressive therapy with the aim of reducing proteinuria and improving outcome. Although these treatments attenuate the deterioration of renal function in MN patients, it has been suggested that all are burdened by significant toxicity. Therefore, more specific and less toxic therapies are needed. This study was to evaluate the effects of Coptidis Rhizoma Extract(CRE) on the MN induced by cBSA in mice. Methods : Mice were divided into 4 groups. One group named for 'Normal' was injected with a saline solution not to be immunized. The rest groups were treated as follows; After mice were immunized with 0.2 mg of cBSA and Freund's complete adjuvant one time every two weeks for 6 weeks, they received intra-peritoneal injection of 10 mg/kg of cBSA daily for 4 weeks. Also, they were divided into 3 groups. The first named for 'Control' was not given CRE. The second for 'CRE-250' was given oral administration of 250 mg/kg of CRE daily for 4 weeks. The third for 'CRE-500' was given 500 mg/kg of CRE. All of mice were sacrificed 4 weeks after the first immunization. We measured a body weight and 24hrs proteinuria as well as serological analysis. The morphologic changes of renal glomeruli were also observed with a light microscope and an electron microscope. Results : The levels of 24 hrs proteinuria, triglyceride, IgG, IL-6 were significantly decreased in both CRE groups. And the level of IgM was significantly decreased in CRE-250 group. In histological findings of kidney tissue, thickening of GBM and deposition of electron-density were consideraly decreased in both CRE groups. Conclusions : The present study suggests that CRE is highly effective when treating mice with MN induced by cBSA. More clinical data and studies are to be done for efficient application.