• Journal of the Korea institute for structural maintenance and inspection
• /
• v.22 no.1
• /
• pp.199-207
• /
• 2018

Experimental programs were performed to evaluate the flexural performance of fiber reinforced concrete(FRC) beams using a hybrid double-layer arrangement of steel bars and fiber reinforced polymer(FRP) bars or using FRP bars only. A total of seven beam specimens were produced with type of tensile reinforcing bar(CFRP bar, GFRP bar, steel bar) and the poly vinyl alcohol(PVA) fiber mixing ratio(0.5%, 0%) as variable. An analysis method for predicting the flexural behaviors of FRC beams with hybrid arrangement of heterogeneous reinforcing bars through finite element analysis was proposed and verified. In case of the specimens with the double-layer reinforcing bars, the test results showed that the first cracking load of specimen with a double-layer arrangement of steel bars was greater by 26-34% than specimens with a hybrid double-layer arrangement of steel and FRP bars. In maximum flexural strengths, the specimen that used CFRP bars as bottom tensile reinforcing bar showed the greatest strength among the specimens with the double-layer reinforcing bars. When the maximum moment value obtained through experiments was compared with that obtained through analysis, the ratio was 1.2 on average, the standard deviation was 0.085, and the maximum error rate was 22% or less. Based on these results, the finite element analysis model proposed in this study can effectively simulate the actual behavior of the beams with hybrid double-layer reinforcing bars.

• Journal of the Korean Magnetics Society
• /
• v.25 no.3
• /
• pp.92-100
• /
• 2015

Electric Vehicle (EV) can be categorized by the driving method into in-wheel and in-line types. In-wheel type EV does not have transmission shaft, differential gear and other parts that are used in conventional cars, which simplifies and lightens the structure resulting in higher efficiency. In this paper, design method for in-wheel motor for automobiles using Parameter Map is proposed, and motor with continuous power of 5 kW is designed, built and its performance is verified. To decide the capacity of the in-wheel motor that meets the automobile's requirement, Vehicle Dynamic Simulation considering the total mass of vehicle, gear efficiency, effective radius of tire, slope ratio and others is performed. Through this step, the motor's capacity is decided and initial design to determine the motor shape and size is performed. Next, the motor parameters that meet the requirement is determined using parametric design that uses parametric map. After the motor parameters are decided using parametric map, optimal design to improve THD of back EMF, cogging torque, torque ripple and other factors is performed. The final design was built, and performance analysis and verification of the proposed method is conducted by performing load test.

• Journal of the Society of Disaster Information
• /
• v.11 no.4
• /
• pp.520-526
• /
• 2015

Reinforcing bar splices are inevitable in reinforced concrete structure. In these days, there are three main types of splices used in reinforced concrete construction site - lapped splice, mechanical splice and welded splice. Low cost, practicality in construction site, less time consuming and high performance make gas pressure welding become a favorable splice method. However, reinforcing bar splice experiences thermal loading history during the welding procedure. This may lead to the presence of residual stress in the vicinity of the splice which affects the fatigue life of the reinforcing bar. Therefore, residual stress analysis and tensile test of the gas pressure welded splice are carried out in order to verify the load bearing capacity of the gas pressure welded splice. The reinforcing bar used in this work is SD400, which is manufactured in accordance with KS D 3504. The results show that the residual stresses in welded splice is relatively small, thus not affecting the performance of the reinforcing bar. Moreover, the strength of the gas pressure welded splice is high enough for the development of yielding in the bar. As such, the reinforcing bar with gas pressure welded splice has enough capacity to behave as continuous bar.

• Journal of the Korean Society for Railway
• /
• v.20 no.3
• /
• pp.311-319
• /
• 2017

The primary suspension system of a railway vehicle restrains the wheelset and the bogie, which greatly affects the dynamic characteristics of the vehicle depending on the stiffness in each direction. In order to improve the dynamic characteristics, different stiffness in each direction is required. However, designing different stiffness in each direction is difficult in the case of a general suspension device. To address this, in this paper, an optimization technique is applied to design different stiffness in each direction by using a conical rubber spring. The optimization is performed by using target and analysis RMS values. Lastly, the final model is proposed by complementing the shape of the weak part of the model. An actual model is developed and the reliability of the optimization model is proved on the basis of a deviation average of about 7.7% compared to the target stiffness through a static load test. In addition, the stiffness value is applied to a multibody dynamics model to analyze the stability and curve performance. The critical speed of the improved model was 190km/h, which was faster than the maximum speed of 110km/h. In addition, the steering performance is improved by 34% compared with the conventional model.

• Journal of the Korea institute for structural maintenance and inspection
• /
• v.25 no.4
• /
• pp.83-91
• /
• 2021

In this study, to improve the connection performance between the existing reinforced concrete (R/C) frame and the strengthening member, we proposed a new H-section steel frame with elastic pad (HSFEP) system for seismic rehabilitation of existing medium-to-low-rise reinforced concrete (R/C) buildings. This HSFEP strengthening system exhibits an excellent connection performance because an elastic pad is installed between the existing structure and reinforcing frame. The method shows a strength design approach implemented via retrofitting, to easily increase the ultimate lateral load capacity of R/C buildings lacking seismic data, which exhibit shear failure mechanism. Two full-size two-story R/C frame specimens were designed based on an existing R/C building in Korea lacking seismic data, and then strengthened using the HSFEP system; thus, one control specimen and one specimen strengthened with the HSFEP system were used. Pseudodynamic tests were conducted to verify the effects of seismic retrofitting, and the earthquake response behavior with use of the proposed method, in terms of the maximum response strength, response displacement, and degree of earthquake damage compared with the control R/C frame. Test results revealed that the proposed HSFEP strengthening method, internally applied to the R/C frame, effectively increased the lateral ultimate strength, resulting in reduced response displacement of R/C structures under large scale earthquake conditions.

• Journal of the Korean Geotechnical Society
• /
• v.34 no.12
• /
• pp.93-103
• /
• 2018

Behaviors of splices between bolts and welding spliced PHC piles using the tensile strength test were analyzed. The bolts spliced PHC piles, which were tightened over $200N{\cdot}m$ tightening torque, showed straight V shaped line at splices at the lowest 20 N load. Both sides of PHC piles stayed straight, so the full section of bolts spliced piles did not show the unifying behavior, which was the most important performance requirement as pile. Other bolts spliced PHC piles, tightened with $20N{\cdot}m$ loosening torque, also showed the same straight V shaped line at splices for each step of loading. The full section of bolts spliced piles did not return to the initial position after each step of unloading and did not show the elastic material behavior. The splices quality of bolts spliced piles is much lower than that of welding spliced piles with respect to displacement of splices during each step of loadings, residual displacements during each step of unloadings, and failure loads. Results showed that bolts spliced PHC piles, tightened with both over $200N{\cdot}m$ and as low as $20N{\cdot}m$ torque, fell short of performance requirements of spliced PHC pile.

• Journal of Biomedical Engineering Research
• /
• v.42 no.4
• /
• pp.150-158
• /
• 2021

Intracranial hemorrhage (ICH) refers to acute bleeding inside the intracranial vault. Not only does this devastating disease record a very high mortality rate, but it can also cause serious chronic impairment of sensory, motor, and cognitive functions. Therefore, a prompt and professional diagnosis of the disease is highly critical. Noninvasive brain imaging data are essential for clinicians to efficiently diagnose the locus of brain lesion, volume of bleeding, and subsequent cortical damage, and to take clinical interventions. In particular, computed tomography (CT) images are used most often for the diagnosis of ICH. In order to diagnose ICH through CT images, not only medical specialists with a sufficient number of diagnosis experiences are required, but even when this condition is met, there are many cases where bleeding cannot be successfully detected due to factors such as low signal ratio and artifacts of the image itself. In addition, discrepancies between interpretations or even misinterpretations might exist causing critical clinical consequences. To resolve these clinical problems, we developed a diagnostic model predicting intracranial bleeding and its subtypes (intraparenchymal, intraventricular, subarachnoid, subdural, and epidural) by applying deep learning algorithms to CT images. We also constructed a visualization tool highlighting important regions in a CT image for predicting ICH. Specifically, 1) 27,758 CT brain images from RSNA were pre-processed to minimize the computational load. 2) Three different CNN-based models (ResNet, EfficientNet-B2, and EfficientNet-B7) were trained based on a training image data set. 3) Diagnosis performance of each of the three models was evaluated based on an independent test image data set: As a result of the model comparison, EfficientNet-B7's performance (classification accuracy = 91%) was a way greater than the other models. 4) Finally, based on the result of EfficientNet-B7, we visualized the lesions of internal bleeding using the Grad-CAM. Our research suggests that artificial intelligence-based diagnostic systems can help diagnose and treat brain diseases resolving various problems in clinical situations.

• Journal of the Society of Disaster Information
• /
• v.19 no.3
• /
• pp.572-581
• /
• 2023

Purpose: The purpose of this study is to improve the irregularity of the stress-strain curve and to ensure accuracy when calculating the damping effect by preventing members from moving in the off-plane direction due to eccentricity when loads are applied. Method: The specifications of the steel strips used in this study are the same, but the curvature of the strips to constitute each damper is different. Each steel strip with different curvature was arranged in an triangle, three dampers with different curvature were made, and repeated load tests were conducted, and the amount of energy dissipation was calculated to measure the performance of the damper. Result: The amount of energy dissipation significantly decreases compared to the case where there is no initial curvature, and the change in the test energy dissipation amount according to the size of the curvature is not large, and the presence or absence of the hyperbolic rate is considered an important variable. Conclusion: The period is about 78.7% longer from T=0.3 to T=0.536sec, and the response spectrum acceleration is reduced from Sa=0.54g to Sa=0.229g, so the damping effect of the damper is sufficient.

• Journal of Intelligence and Information Systems
• /
• v.18 no.4
• /
• pp.43-57
• /
• 2012

To enhance the competitive advantage in a constantly changing business environment, an enterprise management must make the right decision in many business activities based on both internal and external information. Thus, providing accurate information plays a prominent role in management's decision making. Intuitively, historical data can provide a feasible estimate through the forecasting models. Therefore, if the service department can estimate the service quantity for the next period, the service department can then effectively control the inventory of service related resources such as human, parts, and other facilities. In addition, the production department can make load map for improving its product quality. Therefore, obtaining an accurate service forecast most likely appears to be critical to manufacturing companies. Numerous investigations addressing this problem have generally employed statistical methods, such as regression or autoregressive and moving average simulation. However, these methods are only efficient for data with are seasonal or cyclical. If the data are influenced by the special characteristics of product, they are not feasible. In our research, we propose a forecasting framework that predicts service demand of manufacturing organization by combining Case-based reasoning (CBR) and leveraging an unsupervised artificial neural network based clustering analysis (i.e., Self-Organizing Maps; SOM). We believe that this is one of the first attempts at applying unsupervised artificial neural network-based machine-learning techniques in the service forecasting domain. Our proposed approach has several appealing features : (1) We applied CBR and SOM in a new forecasting domain such as service demand forecasting. (2) We proposed our combined approach between CBR and SOM in order to overcome limitations of traditional statistical forecasting methods and We have developed a service forecasting tool based on the proposed approach using an unsupervised artificial neural network and Case-based reasoning. In this research, we conducted an empirical study on a real digital TV manufacturer (i.e., Company A). In addition, we have empirically evaluated the proposed approach and tool using real sales and service related data from digital TV manufacturer. In our empirical experiments, we intend to explore the performance of our proposed service forecasting framework when compared to the performances predicted by other two service forecasting methods; one is traditional CBR based forecasting model and the other is the existing service forecasting model used by Company A. We ran each service forecasting 144 times; each time, input data were randomly sampled for each service forecasting framework. To evaluate accuracy of forecasting results, we used Mean Absolute Percentage Error (MAPE) as primary performance measure in our experiments. We conducted one-way ANOVA test with the 144 measurements of MAPE for three different service forecasting approaches. For example, the F-ratio of MAPE for three different service forecasting approaches is 67.25 and the p-value is 0.000. This means that the difference between the MAPE of the three different service forecasting approaches is significant at the level of 0.000. Since there is a significant difference among the different service forecasting approaches, we conducted Tukey's HSD post hoc test to determine exactly which means of MAPE are significantly different from which other ones. In terms of MAPE, Tukey's HSD post hoc test grouped the three different service forecasting approaches into three different subsets in the following order: our proposed approach > traditional CBR-based service forecasting approach > the existing forecasting approach used by Company A. Consequently, our empirical experiments show that our proposed approach outperformed the traditional CBR based forecasting model and the existing service forecasting model used by Company A. The rest of this paper is organized as follows. Section 2 provides some research background information such as summary of CBR and SOM. Section 3 presents a hybrid service forecasting framework based on Case-based Reasoning and Self-Organizing Maps, while the empirical evaluation results are summarized in Section 4. Conclusion and future research directions are finally discussed in Section 5.

• Journal of Intelligence and Information Systems
• /
• v.27 no.3
• /
• pp.139-156
• /
• 2021

The biggest reason for using a deep learning model in image classification is that it is possible to consider the relationship between each region by extracting each region's features from the overall information of the image. However, the CNN model may not be suitable for emotional image data without the image's regional features. To solve the difficulty of classifying emotion images, many researchers each year propose a CNN-based architecture suitable for emotion images. Studies on the relationship between color and human emotion were also conducted, and results were derived that different emotions are induced according to color. In studies using deep learning, there have been studies that apply color information to image subtraction classification. The case where the image's color information is additionally used than the case where the classification model is trained with only the image improves the accuracy of classifying image emotions. This study proposes two ways to increase the accuracy by incorporating the result value after the model classifies an image's emotion. Both methods improve accuracy by modifying the result value based on statistics using the color of the picture. When performing the test by finding the two-color combinations most distributed for all training data, the two-color combinations most distributed for each test data image were found. The result values were corrected according to the color combination distribution. This method weights the result value obtained after the model classifies an image's emotion by creating an expression based on the log function and the exponential function. Emotion6, classified into six emotions, and Artphoto classified into eight categories were used for the image data. Densenet169, Mnasnet, Resnet101, Resnet152, and Vgg19 architectures were used for the CNN model, and the performance evaluation was compared before and after applying the two-stage learning to the CNN model. Inspired by color psychology, which deals with the relationship between colors and emotions, when creating a model that classifies an image's sentiment, we studied how to improve accuracy by modifying the result values based on color. Sixteen colors were used: red, orange, yellow, green, blue, indigo, purple, turquoise, pink, magenta, brown, gray, silver, gold, white, and black. It has meaning. Using Scikit-learn's Clustering, the seven colors that are primarily distributed in the image are checked. Then, the RGB coordinate values of the colors from the image are compared with the RGB coordinate values of the 16 colors presented in the above data. That is, it was converted to the closest color. Suppose three or more color combinations are selected. In that case, too many color combinations occur, resulting in a problem in which the distribution is scattered, so a situation fewer influences the result value. Therefore, to solve this problem, two-color combinations were found and weighted to the model. Before training, the most distributed color combinations were found for all training data images. The distribution of color combinations for each class was stored in a Python dictionary format to be used during testing. During the test, the two-color combinations that are most distributed for each test data image are found. After that, we checked how the color combinations were distributed in the training data and corrected the result. We devised several equations to weight the result value from the model based on the extracted color as described above. The data set was randomly divided by 80:20, and the model was verified using 20% of the data as a test set. After splitting the remaining 80% of the data into five divisions to perform 5-fold cross-validation, the model was trained five times using different verification datasets. Finally, the performance was checked using the test dataset that was previously separated. Adam was used as the activation function, and the learning rate was set to 0.01. The training was performed as much as 20 epochs, and if the validation loss value did not decrease during five epochs of learning, the experiment was stopped. Early tapping was set to load the model with the best validation loss value. The classification accuracy was better when the extracted information using color properties was used together than the case using only the CNN architecture.