• 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.

• Therapeutic Science for Rehabilitation
• /
• v.10 no.2
• /
• pp.95-108
• /
• 2021

Objective : This study aimed to develop prototypes of "smart stacking cones" by combining ICT to evaluate and train the upper extremity function and dual task performance in patients with central nervous system impairment, and to identify the complementary point to the completion of the device through a usability test. Methods : This prototype comprised of a hardware and software system that enabled the evaluation and training of patients and the management of data obtained from patients' performance. Specific measurement variables were established so that patient performance could be measured correctly. Based on the measurement variables, a the prototype included a 'single task evaluation modes', 'dual task evaluation mode', 'single task training mode', and 'dual task training modes'. Additionally, a usability test was conducted to assess clinical applicability and overall satisfaction for the prototype. Results : The results of the usability test were generally found to be appropriate. The 'content adequacy' in the usability test was the area with the highest level of adequacy and the lowest level of inadequacy. Additionally, overall 'satisfaction' in the usability test was the area with the highest appropriate and inappropriate levels. Hence, the overall satisfaction results were unstable. Conclusion : Future studies should be conducted to identify the clinical effectiveness of the device by applying an upgraded smart stacking cone to an actual patient group.

• Journal of the Korean Society of Safety
• /
• v.36 no.3
• /
• pp.7-14
• /
• 2021

Hybrid laminated Al/carbon-fiber-reinforced plastic (CFRP) composites are attracting considerable attention from industries such as aerospace and automobiles owing to their excellent specific strength and specific rigidity. However, when this material is used to fabricate high-pressure fuel storage containers subjected to repeated fatigue loads, fatigue life evaluation for the working load is regulated as an important criterion for operational safety and ease of maintenance. Among the existing evaluation methods for these vessels, the burst test and the hydraulic repeat test require expensive facilities. Thus, the present study aims to develop an improved fatigue life test for Al/CFRP laminated hybrid composites. The test specimen was manufactured using a curved mold considering the shape of a type III high-pressure storage container. The strain-life method was used for fatigue life evaluation, and the life was predicted based on the transition life. The results indicate that the more complex the CFRP stacking sequence, the longer is the transition life. This test method is expected to be useful for ensuring the fatigue safety and economy of hybrid laminate composites.

• Proceedings of the Korean Society For Composite Materials Conference
• /
• 2000.11a
• /
• pp.106-109
• /
• 2000

Impact tester was build up to evaluate the characterization of CFRP laminate plates under the low velocity impact. The tests were conducted on several laminates of different ply orientation A system was budded for the impact strength of CFRP laminates in consideration of stress wave propagation theory using drop-weight impact tester as one of impact test. Results indicate that absorbed energy of quasi-isotropic specimen having four interfaces is higher than that of orthotropic laminates with two interfaces. Also the damage area was measured with ultrasonic C-scanner on some samples. In the specimens the relationship was linear between damaged area and absorbed energy to some degree. Absorbed energy in the specimen that ply number, interface number and fiber stacking sequences is same but having hybrid is higher than that of orthotropic laminates without hybrid.

• Transactions of the Korean Society of Mechanical Engineers A
• /
• v.38 no.11
• /
• pp.1239-1243
• /
• 2014

This paper presents the application of carbon-fiber-reinforced polymer (CFRP) for the damage absorption and optimal design of portable smart devices to close in life. CFRP specimens are subjected to a tensile test to estimate their mechanical properties in terms of the stacking angles. Further, the screw reverse torque and screw torque at each stacking angle are determined using a torque tester after tapping holes on the CFRP specimens. Two experiments are performed for comparing their results in order to determine optimal conditions. In the tensile test, a woven specimen is found to have the highest strength and stiffness. In the case of the woven specimen, no difference is observed even when it is applied to prevent loosening of the coating. And average result value was excellent.

• Transactions of the Korean Society of Machine Tool Engineers
• /
• v.17 no.3
• /
• pp.34-39
• /
• 2008

In this study, CFRP(Carbon Fiber Reinforced Plastics) that has high specific strength and elastic modulus and low thermal strain was used as a material for the lightweight structural member. CFRP is a fiber material as anisotropic material. The anisotropic material is characterized by the change of its mechanical properties according to stacking orientation angle. CFRP orientation angle was oriented in [A/B]s in order to examine the effect of CFRP orientation angle on the characteristics of energy absorption. CFRP is very weak to the impact from the outside. So, when impact is applied to CFRP, its strength is rapidly lowered. The hybrid material was manufactured by combining CFRP to aluminum which is lightweight and widely used for structural members of the automobile. The hybrid member was shaped as a side member that could support the automobile engine and mount and absorb a large amount of impact energy at the front-end in case of automobile collision. The bending test device was manufactured in accordance with ASTM standard, and mounted to UTM for bending test. For comparing bending characteristics of the hybrid member with those of Aluminum and CFRP member, tests were performed for aluminum, CFRP and hybrid member, respectively.

• The Transactions of The Korean Institute of Electrical Engineers
• /
• v.63 no.3
• /
• pp.395-403
• /
• 2014

This paper presents a new approach to improve the signal to noise ratio (SNR) for local seismic disaster preventing system in densely populated area. The seismic data measured in the local site includes various sensing noises (offset or measurement noise) and man-made/natural noises (road and rail traffic noise, rotating or hammering machinery noise, human activity noise such as walking and running, wind/atmospheric pressure-generated noise, etc.). These additive noises are different in time and frequency characters. The proposed method uses 3-stages processing to reduce these different additive noises. In the first stage, misalignment offset noise are diminished by time average processing, and then the second and third stages, coherent/incoherent noises such as man-made/natural noises are suppressed by array stacking. In addition, we derived the theoretical equation of the SNR gain improved by the proposed method. To evaluate the performance of the proposed method, computer simulations were performed with real seismic data and test equipment generated data as the input.

• Transactions of the Korean Society of Mechanical Engineers A
• /
• v.23 no.11 s.170
• /
• pp.1952-1959
• /
• 1999

The work factor approach, so-called single specimen technique could be used to determine energy release rate from a single test record for unidirectional CLS specimen. In the present study, the work factor approach was extended to determine the mixed-mode fracture toughness of multi-directional graphite/epoxy laminated composites. Multi-directional CLS specimens were used for fracture tests. The stacking sequences used for the lap and the strap were $[90_2/0_2]_s/[0_4/90_4]_s$ and $[0/\pm45/0]_s/[0_2/\pm45_2/0_2]_2$, respectively. For both cases, the fracture toughness determined from the work factor approach was compared with that determined from the compliance method. It was found that both methods produced fracture toughness within a maximum 15% difference for each stacking sequence. The fractography analysis also showed that the fiber bridging occurred for$[0/\pm45/0]_s/[0_2/\pm45_2/0_2]_2$ case while it did not occur for $[90_2/0_2]_s/[0_4/90_4]_s$ case.

• Korean Journal of Materials Research
• /
• v.29 no.3
• /
• pp.189-195
• /
• 2019

The effect of C, Mn, and Al additions on the tensile and Charpy impact properties of austenitic high-manganese steels for cryogenic applications is investigated in terms of the deformation mechanism dependent on stacking fault energy and austenite stability. The addition of the alloying elements usually increases the stacking fault energy, which is calculated using a modified thermodynamic model. Although the yield strength of austenitic high-manganese steels is increased by the addition of the alloying elements, the tensile strength is significantly affected by the deformation mechanism associated with stacking fault energy because of grain size refinement caused by deformation twinning and mobile dislocations generated during deformation-induced martensite transformation. None of the austenitic high-manganese steels exhibit clear ductile-brittle transition behavior, but their absorbed energy gradually decreases with lowering test temperature, regardless of the alloying elements. However, the combined addition of Mn and Al to the austenitic high-manganese steels suppresses the decrease in absorbed energy with a decreasing temperature by enhancing austenite stability.

• Journal of the Earthquake Engineering Society of Korea
• /
• v.27 no.6
• /
• pp.321-330
• /
• 2023

In this study, the structural performance of the specimen fabricated through 3D printing was evaluated through monotonic loading experiments analysis to apply to 3D printed structures. The compression and flexural experiments were carried out, and the experimental results were compared to the finite element model results. The loading directions of specimens were investigated to consider the capacity of specimens with different curing periods, such as 7 and 28 days. As a result, the strength tended to increase slightly depending on the stacking direction. Also, between the 3D-printed panel composite and the non-reinforced panel, the bending performance depended on the presence or absence of composite reinforcement.