• 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.

• Proceedings of the Korean Society of Propulsion Engineers Conference
• /
• 2007.04a
• /
• pp.121-127
• /
• 2007

Direct acting pressure relief valve applicable to propellant tank of launch vehicle is modeled in this study The flow resistance of the partially opened valve is modeled as a function of the distance of the valve stem from the resting position. The position of the valve varies transiently as a function of its mass, the spring force, sliding friction, and the pressure differential. Choking at valve throat and compressibility are considered for the analysis. This study presents systematic analysis method for pressure relief valve applicable to propellant tank of liquid rocket. The results shows transient flow resistance caused by stem motion and the importance of choking at valve throat for pressure relief valve design.

• Journal of Korean Society of Industrial and Systems Engineering
• /
• v.44 no.1
• /
• pp.26-36
• /
• 2021

The topic of this study is the field of humanitarian logistics for disaster response. Many existing studies have revealed that compliance with the golden time in response to a disaster determines the success or failure of relief activities, and logistics costs account for 80% of the disaster response cost. Besides, the agility, responsiveness, and effectiveness of the humanitarian logistics system are emphasized in consideration of the disaster situation's characteristics, such as the urgency of life-saving and rapid environmental changes. In other words, they emphasize the importance of logistics activities in disaster response, which includes the effective and efficient distribution of relief supplies. This study proposes a mathematical model for establishing a transport plan to distribute relief supplies in a disaster situation. To determine vehicles' route and the amount of relief for cities suffering a disaster, it mainly considers the urgency, effectiveness (restoration rate), and uncertainty in the logistics system. The model is initially developed as a mixed-integer nonlinear programming (MINLP) model containing some nonlinear functions and transform into a Mixed-integer linear programming (MILP) model using a logarithmic transformation and piecewise linear approximation method. Furthermore, a minimax problem is suggested to search for breakpoints and slopes to define a piecewise linear function that minimizes the linear approximation error. A numerical experiment is performed to verify the MILP model, and linear approximation error is also analyzed in the experiment.

• The Korean Nurse
• /
• v.25 no.5 s.138
• /
• pp.52-62
• /
• 1986

The purpose of this study is to introduce the extended role of nurses in the labor and delivery room as a situational supporter thru the use of the psychoprophylactic method for relief of labor pain. The contents of this study is consisted of the evolutio

• The Journal of Korean Medicine
• /
• v.28 no.2 s.70
• /
• pp.93-113
• /
• 2007

Objective : To research Trends of studies about anti-inflammation and pain relief, obesity, and safety of herbal acupuncture therapy by analyzing domestic theses, published since 2001, about herbal acupuncture therapy. Methods : Domestic theses, published since 2001, mentioning anti-inflammation or pain relief, obesity, or safety of herbal acupuncture therapy were reviewed and analyzed. These theses were then classified by university, year, and subject. Results : The following results were obtained in this study. 1. Among published theses related to anti-inflammation effects of herbal-acupuncture, studies about arthritis comprised the most part, 52. In theses relating to causes of arthritis, 16 were about adjuvant, which was the most, followed by Type II collagen, LPS and carrageenan. Blood test, reactions of inflammation and revelation of cytokine and immune cellswere methods for evaluating anti-inflammation effect. The tendency of experimental methods was to focus on molecular biologic method. 2. In theses related to pain relief, many clinical attempts with herbal injection were carried out, and Carthami Flos and Scolopendrawere used most. Observing reduction of pain inducing factor and checking behavioral change were methods for evaluating pain relief. 3. In theses related to obesity, research focused on effects in association with spots on the body suitable for acupuncture. There were also attempts comparing effectiveness between single injections and complex injections. Astraball Radix, Angelica Gigantis Radix, Coicis Semen and Taeumjowetang were used. Evaluation of anti-obesity effects were by weight loss, food efficiency, blood lipid profile and evaluation of liver function. 4. In theses related to safety of herbal-acupuncture, Herba Chelidonii Chaenonelis Fructus, Clematis Florida Thunb, Corydalidis Tuber, Paeoniae Radix, and Carthami Flos which marked 2 theses each were most studied. Methods of evaluating safety were mostly by observing liver and kidney functions based on blood test, and by applying herbal injections to clinical treatment. Conclusion : Herbal acupuncture is being used in various ways associating with its anti-inflammation, pain relief and anti-obesity effect. Studies on efficacy and mechanism of herbal acupuncture are being conducted even at the molecular biology level.

• The Korean Journal of Pain
• /
• v.4 no.2
• /
• pp.196-199
• /
• 1991

Efforts from many different approaches have been made to manage malignant sacral pain that commonly occurs in cancers from pelvic origin. Radiofrequency thermocoagulation provides a safe method of achieving long standing relief of intractable pain without some of the objectable side effects associated with other forms of chemical or surgical therapy. Radiofrequency sacral rhizotomy is a new method for the relief of the sacrococcygeal pain. We report a case in which we managed a patient with malignant sacrococcygeal pain with radiofrequency thermocoagulation.

• Communications for Statistical Applications and Methods
• /
• v.10 no.3
• /
• pp.879-894
• /
• 2003

We evaluated the efficiencies of applying attribute selection methods and prior discretization to supervised learning, modelled by C4.5 and Naive Bayes. Three databases were obtained from UCI data archive, which consisted of continuous attributes except for one decision attribute. Four methods were used for attribute selection : MDI, ReliefF, Gain Ratio and Consistency-based method. MDI and ReliefF can be used for both continuous and discrete attributes, but the other two methods can be used only for discrete attributes. Discretization was performed using the Fayyad and Irani method. To investigate the effect of noise included in the database, noises were introduced into the data sets up to the extents of 10 or 20%, and then the data, including those either containing the noises or not, were processed through the steps of attribute selection, discretization and classification. The results of this study indicate that classification of the data based on selected attributes yields higher accuracy than in the case of classifying the full data set, and prior discretization does not lower the accuracy.

• Proceedings of the Korean Geotechical Society Conference
• /
• 2006.03a
• /
• pp.34-41
• /
• 2006

A 3-dimensional stress measurement system based on the bore hole bottom deformation method, which is one of the stress relief methods, was developed. A pilot bore hole is drilled from the bottom of a bore hole and the stress meter is inserted into the pilot bore hole in the method. The bore hole is advanced as an over coring and the deformations in seven directions are measured by cantilever type-sensors. Using the cantilever type-sensors saves time for hardening of glue. No cable connection between the stress meter and a data logger is necessary since a compact data logger is installed in the stress meter. The accuracy of the stress meter was confirmed by a biaxial test for a Shikotsu welded tuff block although in-situ tests have not been carried out yet.

• Transactions of the Korean Society of Automotive Engineers
• /
• v.23 no.6
• /
• pp.583-590
• /
• 2015

Automobile crash optimization is nonlinear dynamic response structural optimization that uses highly nonlinear crash analysis in the time domain. The equivalent static loads (ESLs) method has been proposed to solve such problems. The ESLs are the static load sets generating the same displacement field as that of nonlinear dynamic analysis. Linear static response structural optimization is employed with the ESLs as multiple loading conditions. Nonlinear dynamic analysis and linear static structural optimization are repeated until the convergence criteria are satisfied. Nonlinear dynamic crash analysis for frontal analysis may not have boundary conditions, but boundary conditions are required in linear static response optimization. This study proposes a method to use the inertia relief method to overcome the mismatch. An optimization problem is formulated for the design of an automobile frontal structure and solved by the proposed method.

• Geomechanics and Engineering
• /
• v.37 no.2
• /
• pp.135-147
• /
• 2024

A GIS-based landslide susceptibility mapping (LSM) was carried out using frequency ratio (FR), modified frequency ratio (M-FR), analytic hierarchy process (AHP), and modified analytic hierarchy process (M-AHP) methods to identify and delineate the potential failure zones along the Halong - Vandon expressway. The thematic layers of various landslide causative factors were generated for modeling in GIS, including geology, rainfall, distance to fault, distance to road, slope, aspect, landuse, density of landslide, vertical relief, and horizontal relief. In addition, a landslide inventory along the road network was prepared using data provided by the management department during the course of construction and operation from 2017 to 2019, when many landslides were documented. The validation results showed that the M-FR method had the highest AUC value (AUC = 0.971), which was followed by the FR method with AUC = 0.961. The AUC values were 0.939 and 0.892 for the M-AHP and AHP methods, respectively. The generated LSM obtained from M-FR method classified the study area into five susceptibility classes: very low (0), low (0-1), moderate (1-2), high (2-3), and very high (3-4) classes, which could be useful for various stakeholders like planners, engineers, designers, and local public for future construction and maintenance in the study area.