• Journal of Korean Neurosurgical Society
• /
• v.67 no.1
• /
• pp.94-102
• /
• 2024

Objective : The spontaneous intracerebral hemorrhage (ICH) remains a significant cause of mortality and morbidity throughout the world. The purpose of this retrospective study is to develop multiple models for predicting ICH outcomes using machine learning (ML). Methods : Between January 2014 and October 2021, we included ICH patients identified by computed tomography or magnetic resonance imaging and treated with surgery. At the 6-month check-up, outcomes were assessed using the modified Rankin Scale. In this study, four ML models, including Support Vector Machine (SVM), Decision Tree C5.0, Artificial Neural Network, Logistic Regression were used to build ICH prediction models. In order to evaluate the reliability and the ML models, we calculated the area under the receiver operating characteristic curve (AUC), specificity, sensitivity, accuracy, positive likelihood ratio (PLR), negative likelihood ratio (NLR), diagnostic odds ratio (DOR). Results : We identified 71 patients who had favorable outcomes and 156 who had unfavorable outcomes. The results showed that the SVM model achieved the best comprehensive prediction efficiency. For the SVM model, the AUC, accuracy, specificity, sensitivity, PLR, NLR, and DOR were 0.91, 0.92, 0.92, 0.93, 11.63, 0.076, and 153.03, respectively. For the SVM model, we found the importance value of time to operating room (TOR) was higher significantly than other variables. Conclusion : The analysis of clinical reliability showed that the SVM model achieved the best comprehensive prediction efficiency and the importance value of TOR was higher significantly than other variables.

• Proceedings of the Korea Concrete Institute Conference
• /
• 2004.05a
• /
• pp.568-571
• /
• 2004

This research estimated the physical. mechanical characteristic and the character of sound absorption according to target void ratio of porous concrete and the mixing ratio of recycled aggregate for the valid utilization of recycled aggregate using waste concrete and sound reduction out of a road, a railway, a residential street, and a downtown area. As a result of the test, compressive strength tended to be a radical strength fall when target void ratio was $25\%$ and contents of recycled aggregate exceeded over $50\%$. Also, the character of sound absorption of porous concrete which used recycled aggregate using waste concrete was the most excellent when target void ratio was $25\%$, and the influence by contents of recycled aggregate was trivial. Therefore, when the strength and the character of sound absorption of porous concrete are considered, it is proved valid that proper target void ratio was $25\%$ and contents of recycled aggregate using waste concrete was $50\%$ or so.

• Tunnel and Underground Space
• /
• v.24 no.5
• /
• pp.335-343
• /
• 2014

Room-and-pillar mining method is one of the most popular underground mining method in the world. If the room-and-pillar mining method is able to be adopted in civil works, it would be highly probable to reduce underground construction costs and to expand a underground structure in use. Therefore, this study aims to analyze the design procedure of unsupported rock pillars which are indispensable to ensure the stability of a room-and-pillar underground structure. Parametric studies on their key design parameters are also carried out for 125 different kinds of design conditions. From the study, the width of a rock pillar is found to show a linear relationship with its corresponding safety factor. The safety factor of a unsupported rock pillar decreased drastically like a negative exponential function as the ratio of room width to pillar width increases in the same rock strength condition. Based on the parametric studies, a design chart to simply evaluate the geometric design parameters of a unsupported rock pillar satisfying a design safety factor is also proposed in this study.

• Proceedings of the Korean Society for Technology of Plasticity Conference
• /
• 2003.10a
• /
• pp.117-120
• /
• 2003

Warm deep drawing which is one of the new forming technologies to improve formability of sheet metal is applied to the cylindrical cup drawing of Mg-alloy sheet metal. In experiments the temperature of die and blank holder is varied from room temperature to $300^{\circ}C$, while the punch is cooled by circulation of coolant to increase the fracture strength of workpiece on the punch corner area. Test material chosen for experiments is AZ31 magnesium sheet metal. Teflon film as a lubricant is used on both sides of a workpiece. The limit drawing ratio as well as thickness distributions of drawn cups are investigated and validity of warm deep drawing process is also discussed.

• Journal of the Korean Society of Safety
• /
• v.14 no.3
• /
• pp.40-47
• /
• 1999

A numerical study on gaseous explosion was carried out to predict the transient pressure behavior with the partial rupture in confined vessels. Equations, assumptions and solutions for central ignition of premixed gases in closed spherical vessels are proposed with various equivalence ratios of gas fuel, as $CH_4$ and $C_3H_8$, vent areas and vent opening pressures. Given vent opening pressure in a vessel, the magnitude of second peak pressure results from the vent areas and burning velocity, varied by equivalence ratio of gas fuel. In a living room of an apartment, the higher second peak pressure than the vent pressure is not appeared due to its large window areas. As vent opening pressure is higher, the larger damage by gaseous explosion is expected and the larger vent area is necessary for relieving the damage. In the same concentration, the gaseous explosion by propane rather than methane shows the larger damage due to its higher adiabatic flame temperature and equivalence ratio.

• 한국가시화정보학회:학술대회논문집
• /
• 2004.11a
• /
• pp.48-51
• /
• 2004

Chemical Mechanical Polishing(CMP) is popularly used in production of semiconductor because of large area polishing ability probability of improvement for more integrated circuit. However, present CMP processing causes some non-uniformity errors which can be critical for highly integrated circuit. Previous studies predict that flow-field of slurry during CMP can create non-uniformity, but no quantitative measurement has conducted. In this study, using PIV, slurry velocity flow-field during CMP is measured by changing the ratio of RPM of pad and carrier with tuned PIV system adequate for small room in CMP machine and Cabot's non-groove pad Epad-A100. The result show that velocity of slurry is majorly determined by pad-rpm and the ratio of between carrier and pad rpm make some changes in streamlines.

• Proceedings of the KIEE Conference
• /
• 1998.07b
• /
• pp.555-559
• /
• 1998

The human chromosome analysis is widely used to diagnose genetic disease and various congenital anomalies. Many researches on automated chromosome karyotype analysis have been carried out, some of which produced commercial systems. However, there still remains much room for improving the accuracy of chromosome classification. In this paper, We proposed an optimal pattern classifier by neural network to improve the accuracy of chromosome classification. The proposed pattern classifier was built up of two-step multi-layer neural network(TMANN). We reconstructed chromosome image to improve the chromosome classification accuracy and extracted four morphological features parameters such as centromeric index (C.I.), relative length ratio(R.L.), relative area ratio(R.A.) and chromosome length(C.L.). These Parameters employed as input in neural network by preprocessing twenty human chromosome images. The experiment results shown that the chromosome classification error was reduced much more than that of the other classification methods.

• Journal of the Korean Solar Energy Society
• /
• v.40 no.1
• /
• pp.35-47
• /
• 2020

Due to the large window area, the lighting environment of the educational space between the window and deep part of the room is not uniformly illuminated, and the phenomenon of glare is severe. For this reason, the daylight performance of DSC-BIPV windows was analyzed in order to improve the natural lighting in the educational sector. The method derives the correlation with natural lighting by measurement and simulation. Dynamic simulation confirmed that the average illuminance of the target space was higher at later than the early afternoon. The performance of natural lighting at 40% and 30% transmission of DSC has the effect of significantly reducing the amount of excess light in existing windows. Nevertheless, the actual average illuminance in all seasons corresponds to the standard illuminance of the educational facility, 300 Lux. In addition, the uniformity is also seen through the skylight illuminance ratio.

• Journal of Biomedical Engineering Research
• /
• v.17 no.4
• /
• pp.545-552
• /
• 1996

Researches on chromosome are very significant in cytogenetics since a gene of the chromosome controls revelation of the inheritance plasma The human chromosome analysis is widely used to diagnose genetic disease and various congenital anomalies. Many researches on automated chromosome karyotype analysis has been carried out, some of which produced commercial systems. However, there still remains much room for improving the accuracy of chromosome classification. In this paper, we propose an algorithm for reconstruction of the chromosDme image to improve the chromosome classification accuracy. Morphological feature parameters are extracted from the reconstructed chromosome images. The reconstruction method from chromosome image is the 32 direction line algorithm. We extract three morphological feature parameters, centromeric index(C.I.), relative length ratio(R.L.), and relative area ratio(R.A.), by preprocessing ten human chromosDme images. The experimental results show that proposed algorithm is better than that of other researchers'comparing by feature parameter errors.

• Journal of the Korean Applied Science and Technology
• /
• v.21 no.2
• /
• pp.140-147
• /
• 2004

An aqueous solution of a commercial liquid synthetic detergent for kitchen use was photodecomposed in the presence of titanium dioxides powder under an atmosphere of air at room temperature. Titanium dioxides were prepared by sol-gel method from titanium iso-propoxide at different R ratio($H_2O$/titanium iso-propoxide) and calcined at $500^{\circ}C$. All titanium dioxides were characterized by XRD, BET surface area analyzer and UV-VIS spectrometer. The surface area of titanium dioxides prepared at R ratio=6 appeared higher volume about 20% than commercial $TiO_2$ catalysts. XRD patterns of titania particles were observed mixing phase together with rutile and anatase type. Titanium dioxides prepared by sol-gel method show higher activity about 6% than commercial $TiO_2$ catalysts on the photocatalytic degradation of a commercial liquid synthetic detergent for kitchen. The concentration of the detergent decreased to about 90% of its initial value at illumination times of 2 hour. Illumination for 30 minutes decreased the concentration of oxygen to about one-fifth of the initial value.