• The Bulletin of The Korean Astronomical Society
• /
• v.44 no.1
• /
• pp.54.2-54.2
• /
• 2019

Removing noise which occurs inevitably when taking image data has been a big concern. There is a way to raise signal-to-noise ratio and it is regarded as the only way, image stacking. Image stacking is averaging or just adding all pixel values of multiple pictures taken of a specific area. Its performance and reliability are unquestioned, but its weaknesses are also evident. Object with fast proper motion can be vanished, and most of all, it takes too long time. So if we can handle single shot image well and achieve similar performance, we can overcome those weaknesses. Recent developments in deep learning have enabled things that were not possible with former algorithm-based programming. One of the things is generating data with more information from data with less information. As a part of that, we reproduced stacked image from single shot image using a kind of deep learning, conditional generative adversarial network (cGAN). r-band camcol2 south data were used from SDSS Stripe 82 data. From all fields, image data which is stacked with only 22 individual images and, as a pair of stacked image, single pass data which were included in all stacked image were used. All used fields are cut in $128{\times}128$ pixel size, so total number of image is 17930. 14234 pairs of all images were used for training cGAN and 3696 pairs were used for verify the result. As a result, RMS error of pixel values between generated data from the best condition and target data were $7.67{\times}10^{-4}$ compared to original input data, $1.24{\times}10^{-3}$. We also applied to a few test galaxy images and generated images were similar to stacked images qualitatively compared to other de-noising methods. In addition, with photometry, The number count of stacked-cGAN matched sources is larger than that of single pass-stacked one, especially for fainter objects. Also, magnitude completeness became better in fainter objects. With this work, it is possible to observe reliably 1 magnitude fainter object.

• Journal of The Korean Astronomical Society
• /
• v.53 no.6
• /
• pp.161-168
• /
• 2020

We report the discovery of a giant exoplanet in the microlensing event OGLE-2017-BLG-1049, with a planet-host star mass ratio of q = 9.53 ± 0.39 × 10-3 and a caustic crossing feature in Korea Microlensing Telescope Network (KMTNet) observations. The caustic crossing feature yields an angular Einstein radius of θE = 0.52 ± 0.11 mas. However, the microlens parallax is not measured because the time scale of the event, tE ≃ 29 days, is too short. Thus, we perform a Bayesian analysis to estimate physical quantities of the lens system. We find that the lens system has a star with mass Mh = 0.55+0.36-0.29 M⊙ hosting a giant planet with Mp = 5.53+3.62-2.87 MJup, at a distance of DL = 5.67+1.11-1.52 kpc. The projected star-planet separation is a⊥ = 3.92+1.10-1.32 au. This means that the planet is located beyond the snow line of the host. The relative lens-source proper motion is μrel ~ 7 mas yr-1, thus the lens and source will be separated from each other within 10 years. After this, it will be possible to measure the flux of the host star with 30 meter class telescopes and to determine its mass.

• The Journal of the Convergence on Culture Technology
• /
• v.7 no.3
• /
• pp.571-576
• /
• 2021

This study was carried out to overcome the problems of the existing fitness business and to build a fitness system that can meet the increased demand in the Corona situation. As a platform technology for non-face-to-face fitness edutainment service, it is a next-generation fitness exercise device that can use various body parts and synchronize network-type information. By synchronizing the exercise information of the fitness equipment, it was composed of learning contents through MR-based avatars. A quantified result was derived from examining the applicability of the customized evaluation system through momentum analysis with A.I analysis applying the LSTM-based algorithm according to the cumulative exercise effect of the user. It is a motion capture and 3D visualization fitness program for the application of systematic exercise techniques through academic experts, and it is judged that it will contribute to the improvement of the user's fitness knowledge and exercise ability.

• Journal of the Korea Computer Graphics Society
• /
• v.27 no.3
• /
• pp.13-23
• /
• 2021

In this paper, we proposed a framework that generates the trajectory of a single rigid body based on its COM configuration and contact pose. Because we use a smaller input dimension than when we use a full body state, we can improve the learning time for reinforcement learning. Even with a 68% reduction in learning time (approximately two hours), the character trained by our network is more robust to external perturbations tolerating an external force of 1500 N which is about 7.5 times larger than the maximum magnitude from a previous approach. For this framework, we use centroidal dynamics to calculate the next configuration of the COM, and use reinforcement learning for obtaining a policy that gives us parameters for controlling the contact positions and forces.

• Journal of the Korea Society of Computer and Information
• /
• v.28 no.2
• /
• pp.39-46
• /
• 2023

We present an efficient packet transmission strategy for massively multiplayer online first-person shooter (MMOFPS) games using movement-adaptive packet transmission interval. The player motion in FPS games shows a wide spectrum of movement variability both in speed and orientation, where there is room for reducing the number of packets to be transmitted to the server depending on the predictability of the character's movement. In this work, the degree of variability (nonlinearity) of the player movements is measured at every packet transmission to calculate the next transmission time, which implements the adaptive transmission frequency according to the amount of movement change. Server-side prediction with a few auxiliary heuristics is performed in concert with the incoming packets to ensure reliability for synchronizing the connected clients. The comparison of our method with the previous fixed-interval transmission scheme is presented by demonstrating them using a test game environment.

• Journal of Acupuncture Research
• /
• v.39 no.3
• /
• pp.213-221
• /
• 2022

Background: This study investigated the clinical effectiveness of Korean medicine (KM) treatment for shoulder impingement syndrome (SIS). Methods: There were 61 patients who were diagnosed with SIS in the Jaseng hospital network of KM (7 hospitals located in Korea: Gangnam, Daejeon, Bucheon, Haeundae, Bundang, Ulsan, and Gwangju) between January 1^st, 2015 and December 31^st, 2020 who were retrospectively reviewed. The patients were grouped according to complications, intake of analgesics, duration of illness preadmission, and treatment. Treatments consisted of herbal medicine, acupuncture, cupping, Chuna, pharmacopuncture, bee venom pharmacopuncture, medicinal steaming, Daoyin exercises, and physical therapy. By comparing the Numeric Rating Scale (NRS), Shoulder Pain and Disability Index, and European Quality of Life 5-Dimensions questionnaire scores, the effectiveness of integrated KM treatment was evaluated. Results: There were 14 males and 47 females. For inpatients diagnosed with SIS, the mean NRS score decreased from 5.78 ± 1.33 to 3.40 ± 1.43 (p < 0.001). The mean Shoulder Pain and Disability Index score decreased from 53.87 ± 14.76 to 38.56 ± 18.87 (p < 0.001), and the mean European Quality of Life 5-Dimensions questionnaire increased from 0.67 ± 0.13 to 0.76 ± 0.09 (p < 0.001) after KM treatment. Medicinal steaming (0.398; p < 0.001), acupuncture (0.290), cupping (0.288), bee venom pharmacopuncture (0.282), and Daoyin exercises (0.262; p < 0.05) had a positive correlation with improved changes in the NRS score. Conclusion: Conclusion: Treatment with integrated KM treatment improved the pain, range of motion, shoulder function, and quality of life of patients with SIS.

• Steel and Composite Structures
• /
• v.41 no.5
• /
• pp.761-773
• /
• 2021

This study presents a 3D non-linear finite element (FE) assessment of dynamic soil-structure interaction (SSI). The numerical investigation has been performed on the time domain through a Finite Element (FE) system, while considering the nonlinear behavior of soil and the multi-directional nature of genuine seismic events. Later, the FE outcomes are analyzed to the recorded in-situ free-field and structural movements, emphasizing the numerical model's great result in duplicating the observed response. In this work, the soil response is simulated using an isotropic hardening elastic-plastic hysteretic model utilizing HSsmall. It is feasible to define the non-linear cycle response from small to large strain amplitudes through this model as well as for the shift in beginning stiffness with depth that happens during cyclic loading. One of the most difficult and unexpected tasks in resolving soil-structure interaction concerns is picking an appropriate ground motion predicted across an earthquake or assessing the geometrical abnormalities in the soil waves. Furthermore, an artificial neural network (ANN) has been utilized to properly forecast the non-linear behavior of soil and its multi-directional character, which demonstrated the accuracy of the ANN based on the RMSE and R² values. The total result of this research demonstrates that complicated dynamic soil-structure interaction processes may be addressed directly by passing the significant simplifications of well-established substructure techniques.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.26 no.9
• /
• pp.1272-1278
• /
• 2022

The government enacted and promulgated the 'Severe Accident Punishment Act' in January 2021 and is implementing this law. However, the number of occupational accidents in 2021 increased by 10.7% compared to the same period of the previous year. Therefore, safety measures are urgently needed in the industrial field. In this study, BLE Mesh networking technology is applied for safety management of high-risk industrial sites with poor communication environment. The complex sensor AIoT device collects gas sensing values, voice and motion values in real time, analyzes the information values through artificial intelligence LSTM algorithm and CNN algorithm, and recognizes dangerous situations and transmits them to the server. The server monitors the transmitted risk information in real time so that immediate relief measures are taken. By applying the AIoT device and safety management system proposed in this study to high-risk industrial sites, it will minimize industrial accidents and contribute to the expansion of the social safety net.

• KIPS Transactions on Software and Data Engineering
• /
• v.10 no.12
• /
• pp.561-568
• /
• 2021

In recent years, autonomous driving technologies have become a high-value-added technology that attracts attention in the fields of science and industry. For smooth Self-driving, it is necessary to accurately detect an object and estimate its movement speed in real time. CNN-based deep learning algorithms and conventional dense optical flows have a large consumption time, making it difficult to detect objects and estimate its movement speed in real time. In this paper, using a single camera image, fast object detection was performed using the YOLOv5 algorithm, a deep learning algorithm, and fast estimation of the speed of the object was performed by using a local dense optical flow modified from the existing dense optical flow based on the detected object. Based on this algorithm, we present a system that can predict the collision time and probability, and through this system, we intend to contribute to prevent tram accidents.

• Journal of Biomedical Engineering Research
• /
• v.44 no.4
• /
• pp.255-263
• /
• 2023

Clinical ultrasound (US) is a widely used imaging modality with various clinical applications. However, capturing a large field of view often requires specialized transducers which have limitations for specific clinical scenarios. Panoramic imaging offers an alternative approach by sequentially aligning image sections acquired from freehand sweeps using a standard transducer. To reconstruct a 3D volume from these 2D sections, an external device can be employed to track the transducer's motion accurately. However, the presence of optical or electrical interferences in a clinical setting often leads to incorrect measurements from such sensors. In this paper, we propose a deep learning (DL) framework that enables the prediction of scan trajectories using only US data, eliminating the need for an external tracking device. Our approach incorporates diverse data types, including correlation volume, optical flow, B-mode images, and rawer data (IQ data). We develop a DL network capable of effectively handling these data types and introduce an attention technique to emphasize crucial local areas for precise trajectory prediction. Through extensive experimentation, we demonstrate the superiority of our proposed method over other DL-based approaches in terms of long trajectory prediction performance. Our findings highlight the potential of employing DL techniques for trajectory estimation in clinical ultrasound, offering a promising alternative for panoramic imaging.