• KIPS Transactions on Software and Data Engineering
• /
• v.9 no.10
• /
• pp.309-316
• /
• 2020

We predict the mortality of the elderly patients visiting the emergency department who are over 65 years old using Feed Forward Neural Network (FFNN) and Convolutional Neural Network (CNN) respectively. Medical data consist of 99 features including basic information such as sex, age, temperature, and heart rate as well as past history, various blood tests and culture tests, and etc. Among these, we used random forest to select features by measuring the importance of features in the prediction of mortality. As a result, using the top 80 features with high importance is best in the mortality prediction. The performance of the FFNN and CNN is compared by using the selected features for training each neural network. To train CNN with images, we convert medical data to fixed size images. We acquire better results with CNN than with FFNN. With CNN for mortality prediction, F1 score and the AUC for test data are 56.9 and 92.1 respectively.

• Journal of the Korean GEO-environmental Society
• /
• v.14 no.5
• /
• pp.15-22
• /
• 2013

The submarine pipe, which is one of the most important coastal structures, is widely used in the development of coastal and ocean engineering. The scour of the submarine pipe occurs due to the wave and the current according to the state of the sea bed. The scour affects the submarine pipe and causes it to undergo settlement and fatigue. It is difficult to predict the local scour under complicated and various conditions of the coastal environment, even though many researches on the scour of the submarine pipe have been studied in recent years. This study analyzed the scour depth around a submarine pipe by using the Neural Network technique. The back-propagation algorithms was used to train the Neural Network. The 58 simulating experimental data for the performance and validation of the Neural Network technique were analyzed in this study. Then, the regression analysis for the same data was performed in this study to predict and compare with the Neural Network technique for the scour depth.

• Journal of the Korean Society for Railway
• /
• v.12 no.5
• /
• pp.641-648
• /
• 2009

Concrete structures become more common in railway systems with an advancement of high speed train technologies. As the service life of concrete structures increases, structural strengthening for concrete structures may be necessary. There are several typical strengthening techniques using steel plate and fiber reinforced polymer (FRP) materials, which have their own inherent shortcomings. In order to enhance greater durability and resistance to fire and other environmental attacks, basalt fiber material attracts engineer's attention due to its characteristics. This study investigates bonding performance of basalt fiber sheet as a structural strengthening material. Experimental variables include bond width, length and number of layer. From the bonding tests, there were three different types of bonding failure modes: debonding, rupture and rip-off. Among the variables, bond width indicated more significant effect on bonding characteristics. In addition the bond length did not contribute to bond strength in proportion to the bond length. Hence this study evaluated effective bond length and effective bond strength. The effective bond strength was compared to those suggested by other researches which used different types of FRP strengthening materials such as carbon FRP.

• Journal of the Korean Society for Railway
• /
• v.18 no.3
• /
• pp.270-277
• /
• 2015

In some sections of the Seoul Metropolitan Subway, severe congestion can be observed during rush hours and on specific days. The subway operators have been conducting regular surveys to measure the level of congestion on trains: the results are then used to make plans for congestion reduction. However, the survey has so far focused just on train' congestion and has been unable to determine non-recurring congestion due to special events. This study develops an algorithm to estimate the platform congestion rate by time using individual public transportation card data. The algorithm is evaluated by comparison of the estimated congestion rate and the ground truth data that are actually observed at non-transfer subway stations on Seoul subway line 2. The error rates are within ${pm}2%$ and the performance of the algorithm is fairly good. However, varying walking times from gates to platforms, which are applied to both non-peak periods and peak time periods, are needed to improve the algorithm.

• Journal of the Korean Society for Railway
• /
• v.18 no.3
• /
• pp.223-231
• /
• 2015

This paper proposes a new wireless backhaul technology based on MHN(Mobile Hotspot Network) which uses a wide frequency band of millimeter wave to provide wideband Wi-Fi services for subway passengers. Performance analysis of MHN up and down links, based on data: up and down links structure analysis of physical layer and simulation study of the MHN wireless backhaul link model, show that the proposed MHN-based wireless backhaul network can transmit data at a 1.2Gbps data rate and provide Internet service 100 times faster than that of conventional WiBro-based wireless backhaul networks. These results indicate that the proposed MHN technology is appropriate for subway mobile networks.

• Journal of Korean Society on Water Environment
• /
• v.24 no.1
• /
• pp.91-98
• /
• 2008

This work was performed to develop a model possible to predict the influent flow and influent components, which are one of main disturbances causing process problems at the operation of municipal wastewater treatment plant. In this study, artificial neural network (ANN) was used in order to develop a model that was able to predict the influent flow, $COD_{Mn}$, SS, TN 1 day-ahead, 2day-ahead and 3 day ahead. Multi-layer feed-forward back-propagation network was chosen as neural network type, and tanh-sigmoid function was used as activation function to transport signal at the neural network. And Levenberg-Marquart (LM) algorithm was used as learning algorithm to train neural network. Among 420 data sets except missing data, which were collected between 2005 and 2006 at field plant, 210 data sets were used for training, and other 210 data sets were used for validation. As result of it, ANN model for predicting the influent flow and components 1-3day ahead could be developed successfully. It is expected that this developed model can be practically used as follows: Detecting the fault related to effluent concentration that can be happened in the future by combining with other models to predict process performance in advance, and minimization of the process fault through the establishment of various control strategies based on the detection result.

• Journal of the Korean Society for Railway
• /
• v.18 no.4
• /
• pp.354-362
• /
• 2015

Since allowable settlement of concrete slab track is about 30mm, a lot of attention must be paid to the settlement of the earthwork (reinforced trackbed, upper subgrade, under subgrade) under the concrete track. To this end, more experimental data should be accumulated through tests for these materials. In this study, we evaluate the long-term settlement of reinforced trackbed and subgrade materials using factors such as repeated loading conditions, water content, and grain size distributions in a large triaxial test and a large oedometer test. In cases in which the performance of the reinforced trackbed layer meets the design criteria, the settlement caused by train load was considerably small. But, when the water content increases in the subgrade, unexpectedly large settlement might occur for certain grain size distributions of the subgrade materials.

• Journal of the Institute of Electronics Engineers of Korea SC
• /
• v.37 no.3
• /
• pp.72-83
• /
• 2000

This paper presents the implementation of the position control system for 3 phase induction motor using reaching mode controller and neural networks. The reaching mode controller is used to bring the position error and speed error trajectories toward the sliding surface and to train neural networks at the first time. The structure of the reaching mode controller consists of the switch function of sliding surface. And feedforward neural networks approximates the equivalent control input using the reference speed and reference position and actual speed and actual position measured form an encoder and, are tuned on-line. The reaching mode controller and neural networks are applied to the position control system for 3 phase induction motor and, are compared with a PI controller through computer simulation and experiment respectively. The results are illustrated that the output of reaching mode controller is decreased and feedforward neural networks take charge of the main part for the control action, and the proposed controllers show better performance than the PI controller in abrupt load variation and the precise control is possible because the steady state error can be minimized by training neural networks.

• Journal of the Korea Computer Graphics Society
• /
• v.26 no.3
• /
• pp.61-68
• /
• 2020

In this paper, we propose a deep learning framework for predicting a depth map of a 360° panorama image. Previous works use synthetic 360° panorama datasets to train networks due to the lack of realistic datasets. However, the synthetic nature of the datasets induces features extracted by the networks to differ from those of real 360° panorama images, which inevitably leads previous methods to fail in depth prediction of real 360° panorama images. To address this gap, we use domain adaptation to learn features shared by real and synthetic panorama images. Experimental results show that our approach can greatly improve the accuracy of depth estimation on real panorama images while achieving the state-of-the-art performance on synthetic images.

• Journal of the Korea Convergence Society
• /
• v.9 no.2
• /
• pp.303-311
• /
• 2018

Squat exercise is one of the free weight exercises that are recognized as important from a bio-mechanical point of view. It is an important exercise to train lower extremity muscles in daily activities or sports activities and to strengthen trunk and lower body strength. It is effective and accurate to use a variety of assistive devices to calibrate athletic posture with squat exercise supported interactive device. The issues of the structural analysis for design a foot plate for squat exercise is to model the behavior by simplifying the dynamic behavior. In this paper, the authors proposed a exercise system design method for the vertical load distribution and bio-mechanical signal process used for the squat exercise mechanism analysis, and based on these results, designed device can make the more safe and reliable free weight exercise. It is applied to system design through design method with kinematic dynamic, VR device and estimation model of exercise.