• The Journal of Korean Institute of Next Generation Computing
• /
• v.15 no.5
• /
• pp.64-74
• /
• 2019

Although a non-rigid registration has high demands in clinical practice, it has a high computational complexity and it is very difficult for ensuring the accuracy and robustness of registration. This study proposes a method of applying a non-rigid registration to 3D magnetic resonance images of brain in an unsupervised learning environment by using a deep-learning network. A feature vector between two images is produced through the network by receiving both images from two different patients as inputs and it transforms the target image to match the source image by creating a displacement vector field. The network is designed based on a U-Net shape so that feature vectors that consider all global and local differences between two images can be constructed when performing the registration. As a regularization term is added to a loss function, a transformation result similar to that of a real brain movement can be obtained after the application of trilinear interpolation. This method enables a non-rigid registration with a single-pass deformation by only receiving two arbitrary images as inputs through an unsupervised learning. Therefore, it can perform faster than other non-learning-based registration methods that require iterative optimization processes. Our experiment was performed with 3D magnetic resonance images of 50 human brains, and the measurement result of the dice similarity coefficient confirmed an approximately 16% similarity improvement by using our method after the registration. It also showed a similar performance compared with the non-learning-based method, with about 10,000 times speed increase. The proposed method can be used for non-rigid registration of various kinds of medical image data.

• The Journal of the Korea Contents Association
• /
• v.21 no.10
• /
• pp.90-102
• /
• 2021

Technology evaluation is to assess the ability of technology commercialization entities to generate profits by using the subject technology, and domestic technology evaluation agencies have established and implemented their own evaluation systems. In particular, the recently developed technology evaluation model in the fields of marine and fishery does not sufficiently reflect the poor environment for technology development compared to other industries, so it does not pass the level of T4 rating, which is considered appropriate for investment. This is recognized as a challenge that occurs when the common evaluation indicators and evaluation scales used in other industries, and when the scoring system for T1 to T10 grading is similarly or identically utilized. Therefore, through this study, we intend to secure the appropriateness and reliability of the results of the comprehensive rating calculation by developing technology evaluation models and indicators that well explain the nine marine and fisheries industry classification systems. Based on KED and technology evaluation case data, AHP-based index weighting and Monte Carlo simulation-based rating system are applied and the results of case studies are verified. Through the proposed model, we aim to enhance the usability of R&D and commercialization support programs based on fast, convenient and objective evaluation results by applying to upcoming technology evaluation cases.

• Journal of the Korean Society for Aeronautical & Space Sciences
• /
• v.49 no.5
• /
• pp.373-381
• /
• 2021

This paper details the result of flight experiment that examines performance of roll angle estimation algorithm of slowly rolling munition taking time delay of measurement into account when measurement comes in delayed fashion. As the measurement is passed through low pass filter for numerical stabilization and de-noising purpose which induces time delay, we design augmented state Kalman filter that incorporates distribution models of stochastic delay over time. Flight experiment was conducted to verify the algorithm at around 250m high AGL(Above Ground Level) conveying velocity of 28m/s from fixed-wing mother plane to the munition. Munition was made spun with respect to its roll axis using internal reaction wheel afterward. Numerical comparison of proposing method's roll estimation performance with that of commercial aerospace graded GPS/INS shows that proposed filter design can effectively compensate time delay of measurement.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2014.10a
• /
• pp.320-323
• /
• 2014

Today is going with the advancement of intelligent transportation systems and traffic environment and helping to provide safe and convenient service through a mobile device work with the popularization of the vehicle black box. The traffic flow by a variety of causes is constantly changing, it is often unable to prepare the driver, depending on external factors can not be controlled by the power of the public, leading to a major accident. The system needs to pass the real-time weather data in the inter-operator to prevent this. The proposed detection algorithm weather information delivered real-time weather information for this paper. The weather condition is detected by using the contrast between the histogram of the motion of the wiper and the clear day algorithm. In general, the wiper is worked in extreme weather conditions that will have a value different contrast due to rain or snow. Situation was considered clear, snowy conditions, such as using it on a rainy situation. First, designated as ROI (Region Of Interest) of the minimum area that can be detected in order to reduce the amount of calculation for the wiper, the wiper, which was detected through the operation of the threshold Thresholding the brightness of the vehicle wiper. In addition, we distinguish the value of each meteorological situation by using contrast. Results was obtained to 80% for the snow conditions, a rainy situation.

• Journal of the Korean Society of Radiology
• /
• v.14 no.7
• /
• pp.923-930
• /
• 2020

The COVID-19 crisis inevitably led to full-scale non-face-to-face education in 2020. The researchers selected five universities out of 48 universities in radiology and radiology departments nationwide (1.2 in 2019 and 1.2 in 2020) to examine the results of face-to-face training and non-face-to-face mock tests conducted by senior students in radiology departments and radiology departments of the national health department (12 in 2019 and 1.2 in 2020) in preparation for the license test. It turned out to be. Comparing the results of face-to-face and non-face-to-face training (two in 2019 and two in 2020), statistics were analyzed by nonparametric tests, and the results showed that there were differences in theory (Z=-2.023, p<0.05, application (Z=-2.023), p<0.05), practical skills (Z=-1.753, and p<0.05). As a result of the mock test, non-face-to-face education results in poor grades compared to face-to-face education, it is believed that lectures should be taught differently or various educational methods that can communicate with students should be combined.

• Land and Housing Review
• /
• v.13 no.4
• /
• pp.73-89
• /
• 2022

With the spread of COVID-19, the role of parks has been emphasized. Under the quarantine guidelines, including social distancing, people are visiting parks as a safe place. In line with these changes, parks need to be studied as pandemic adaptation measures according to their physical and location characteristics. This study aims to explore the potential of linear parks with accessibility and pass way functions based on the characteristics of surrounding land uses. The case study area was selected from Yeonnam-dong to Yeomni-dong of the Gyeongui Line Forest Park, and the area was divided into 4 sections based on the administrative boundary and surrounding land uses. Multiple regression models were adopted in each section using the total number of de facto population as a dependent variable and factors affecting external activities including COVID-19 as independent variables. The results show that first, the more diverse the interaction between commercial facilities and linear parks, the greater the impact of the pandemic. Second, where various commercial facilities are concentrated people respond more sensitively to short-term weather changes than seasonal ones. This study indicates that there are differences in the use of linear parks according to the surrounding land uses. In addition, it suggests that the linear park has potential as a means to overcome the Pandemic crisis of the city and to increase equity in access to green areas.

• Journal of the Korean Society of Marine Environment & Safety
• /
• v.27 no.4
• /
• pp.474-482
• /
• 2021

An average of two to three typhoons that occur in the Philippines or Taiwan pass through Korea each year owing to the influence of the geographical location and western winds. Because Jinhae Bay is known as Korea's representative typhoon refuge, it is filled with ships during typhoons and later becomes saturated with ships anchored to the surrounding routes. If a strong wind drags an anchored ship, a collision accident may occur because of the short distance between the ships. Therefore, a systematic anchoring safety management of Jinhae Bay is required. In this study, the minimum wind speeds of a dragging anchor based on the water depths of Jinhae Bay anchorages were investigated. When 7-9 shackles were given, the minimum wind speeds were 48-63, 46-61, and 39-54 knots at depths of 20, 35, and 50 m, respectively. As the water depth increased, the length of the cable laid on the sea bed became shorter than 5 m owing to the external force, and the minimum wind speed showed a significant difference of 4-8 knots. In addition, ships with high holding power anchors (AC-14 type) had higher minimum wind speeds than ships with conventional anchors (ASS type). Finally, it was confirmed that at a depth of 50 m, dragging easily occurred even when a high holding power anchor was applied.

• The Journal of Engineering Geology
• /
• v.30 no.4
• /
• pp.589-602
• /
• 2020

As can be seen in many earthquakes, liquefaction causes differential settlement, which sometimes produces serious damages such as building destruction and ground subsidence. There are many possible active faults near the Busan city and the Yangsan, Dongrae, and Ilgwang faults among them pass through the city. The Busan city is also located within the influence of recent earthquakes, which occurred in the Gyeongju, Pohang, and Kumamoto (Japan). Along the wide fault valleys in the city, the Quaternary unconsolidated alluvial sediments are thickly accumulated, and the reclaimed lands with beach sediments are widely distributed in the coastal area. A large earthquake near or in the Busan city is thus expected to cause major damage due to liquefaction in urban areas. This study conducted an assessment of the liquefaction hazard according to seismic recurrence intervals across the Busan city. As a result, although there are slight differences in degree depending on seismic recurrence intervals, it is predicted that the liquefaction potential is very high in the areas of the Nakdonggang Estuary, Busan Bay, Suyeong Bay, and Songjeong Station. In addition, it is shown that the shorter the seismic recurrence interval, the greater difference the liquefaction potential depending on site periods.

• Smart Media Journal
• /
• v.9 no.4
• /
• pp.102-108
• /
• 2020

In this paper, we propose a real-time method of detecting hand motions and extracting the signal frame induced by EF(Electric Field) sensors. The signal induced by hand motion includes not only noises caused by various environmental sources as well as sensor's physical placement, but also different initial off-set conditions. Thus, it has been considered as a challenging problem to detect the motion signal and extract the motion frame automatically in real-time. In this study, we remove the PLN(Power Line Noise) using LPF with 10Hz cut-off and successively apply MA(Moving Average) filter to obtain clean and smooth input motion signals. To sense a hand motion, we use two thresholds(positive and negative thresholds) with offset value to detect a starting as well as an ending moment of the motion. Using this approach, we can achieve the correct motion detection rate over 98%. Once the final motion frame is determined, the motion signals are normalized to be used in next process of classification or recognition stage such as LSTN deep neural networks. Our experiment and analysis show that our proposed methods produce better than 98% performance in correct motion detection rate as well as in frame-matching rate.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.21 no.12
• /
• pp.310-319
• /
• 2020

Korea estimates the traffic noise by measuring the total traffic noise when the traffic passes (SPB; Statistical Pass-By). Another method (CPX; Close Proximity) directly measures the tire/road noise by installing a microphone near the tire. The CPX method is not a formal test method in Korea. There has been little research between CPX and SPB. This study proposes a method for estimating SPB, using the CPX, which is easy to measure. This study used the results of a large-scale test conducted by Korea Expressway Corporation (KEC) and a research paper on CPX in this section. The results by the KEC showed that the low noise pavement has a noise reduction of 10.4dB. In CPX research, the noise reduction was 10.7dB and was similar to 10.4dB in SPB. This study shows why the noise reduction is the same regardless of the position, the reason that the amount of noise reduction is similar, the difference of the noise according to the position of the microphone using the concept of noise summation and distance reduction. This study shows that including the CPX as a variable in the traffic noise prediction program is very important to improve noise prediction reliability.