• Journal of Veterinary Science
• /
• v.23 no.1
• /
• pp.17.1-17.10
• /
• 2022

Background: Inspection of livestock farms using surveillance cameras is emerging as a means of early detection of transboundary animal disease such as African swine fever (ASF). Object tracking, a developing technology derived from object detection aims to the consistent identification of individual objects in farms. Objectives: This study was conducted as a preliminary investigation for practical application to livestock farms. With the use of a high-performance artificial intelligence (AI)-based 3D depth camera, the aim is to establish a pathway for utilizing AI models to perform advanced object tracking. Methods: Multiple crossovers by two humans will be simulated to investigate the potential of object tracking. Inspection of consistent identification will be the evidence of object tracking after crossing over. Two AI models, a fast model and an accurate model, were tested and compared with regard to their object tracking performance in 3D. Finally, the recording of pig pen was also processed with aforementioned AI model to test the possibility of 3D object detection. Results: Both AI successfully processed and provided a 3D bounding box, identification number, and distance away from camera for each individual human. The accurate detection model had better evidence than the fast detection model on 3D object tracking and showed the potential application onto pigs as a livestock. Conclusions: Preparing a custom dataset to train AI models in an appropriate farm is required for proper 3D object detection to operate object tracking for pigs at an ideal level. This will allow the farm to smoothly transit traditional methods to ASF-preventing precision livestock farming.

• The Bulletin of The Korean Astronomical Society
• /
• v.46 no.1
• /
• pp.60.2-60.2
• /
• 2021

In this study, we determinate the differential emission measure(DEM) of solar corona using three SDO/AIA EUV channel images and three AI-generated ones. To generate the AI-generated images, we apply a deep learning model based on multi-layer perceptrons by assuming that all pixels in solar EUV images are independent of one another. For the input data, we use three SDO/AIA EUV channels (171, 193, and 211). For the target data, we use other three SDO/AIA EUV channels (94, 131, and 335). We train the model using 358 pairs of SDO/AIA EUV images at every 00:00 UT in 2011. We use SDO/AIA pixels within 1.2 solar radii to consider not only the solar disk but also above the limb. We apply our model to several brightening patches and loops in SDO/AIA images for the determination of DEMs. Our main results from this study are as follows. First, our model successfully generates three solar EUV channel images using the other three channel images. Second, the noises in the AI-generated EUV channel images are greatly reduced compared to the original target ones. Third, the estimated DEMs using three SDO/AIA images and three AI-generated ones are similar to those using three SDO/AIA images and three stacked (50 frames) ones. These results imply that our deep learning model is able to analyze temperature response functions of SDO/AIA channel images, showing a sufficient possibility that AI-generated data can be used for multi-wavelength studies of various scientific fields. SDO: Solar Dynamics Observatory AIA: Atmospheric Imaging Assembly EUV: Extreme Ultra Violet DEM: Diffrential Emission Measure

• Journal of the Korean Society of Fisheries and Ocean Technology
• /
• v.59 no.4
• /
• pp.336-343
• /
• 2023

The aging fishery training vessels from the past have mostly been decommissioned, and many universities are introducing state-of-the-art large fishery training vessels. The purpose of these training vessels is to train marine professionals and above all, safety to prevent marine accidents should be of utmost priority as many students embark on the vessel. This study estimated the impact of the hydrodynamic interaction forces acting on the model vessel (fishery training vessel) from the bank when the vessel pass near the semi-circle bank wall in various conditions through the numerical calculation, especially concerning maneuvering motions of the vessel. For estimation, variables were mainly set as the size of the semi-circle shape, the lateral distance between the bank and the model vessel, and the depth near the bank. As a result, it was estimated that, in order for the model vessel to safely pass the semi-circle bank wall at a speed of 4 knots, the water depth to the vessel draft ratio should be 1.5 or more (approximately 8 m of water depth), and the lateral distance from the semi-circle bank wall should be 0.4 times the model vessel's length (L_pp) or more (a distance of 34 m or more). Under these conditions, it was expected that the model vessel would pass without significantly being affected by the bank wall.

• Journal of the Korean Society of Radiology
• /
• v.18 no.1
• /
• pp.21-26
• /
• 2024

The one of the famous deep learning models for object detection task is you only look once version 5 (YOLOv5) framework based on the one stage architecture. In addition, YOLOv5 model indicated high performance for accurate lesion detection using the bottleneck CSP layer and skip connection function. The purpose of this study was to evaluate the performance of YOLOv5 framework according to various hyperparameters in position emission tomogrpahy (PET) phantom images. The dataset was obtained from QIN PET segmentation challenge in 500 slices. We set the bounding box to generate ground truth dataset using labelImg software. The hyperparameters for network train were applied by changing optimization function (SDG, Adam, and AdamW), activation function (SiLU, LeakyRelu, Mish, and Hardwish), and YOLOv5 model size (nano, small, large, and xlarge). The intersection over union (IOU) method was used for performance evaluation. As a results, the condition of outstanding performance is to apply AdamW, Hardwish, and nano size for optimization function, activation function and model version, respectively. In conclusion, we confirmed the usefulness of YOLOv5 network for object detection performance in nuclear medicine images.

• The Journal of the Acoustical Society of Korea
• /
• v.26 no.6
• /
• pp.259-268
• /
• 2007

This paper contributes to an improvement of the statistical bandwidth extension(BWE) system based on Hidden Markov Model(HMM). First, the existing HMM training method for BWE, which is suggested originally by Jax, is analyzed in comparison with the general Baum-Welch training method. Next, based on this analysis, a new HMM-based BWE method is suggested which adopts the Baum-Welch re-estimation algorithm instead of the Jax's to train HMM model. Conclusionally speaking, the Baum-Welch re-estimation algorithm is a generalized form of the Jax's training method. It is flexible and adaptive in modeling the statistical characteristic of training data. Therefore, it generates a better model to the training data, which results in an enhanced BWE system. According to experimental results, the new method performs much better than the Jax's BWE systemin all cases. Under the given test conditions, the RMS log spectral distortion(LSD) scores were improved ranged from 0.31dB to 0.8dB, and 0.52dB in average.

• Proceedings of the KSR Conference
• /
• 2011.10a
• /
• pp.793-799
• /
• 2011

A comprehensive analysis of wheel force spectrum is conducted to provide the KTX safety evaluation with structural behaviour of Pre-Stressed Concrete (PSC) box bridge due to various high speeds. The wheel spectrum for KTX locomotive running over road and PSC bridge tracks is compared using irregular track responses with numerical models of 170m approach road track and 40m span length of PSC box bridge The high-speed railway locomotive is used as 38-degree of freedom system. Three displacements (vertical, lateral, and longitudinal) and three rotational components (pitching, rolling, and yawing) for one car-body and two bogies are considered in the 38-degree of freedom model. Three dimensional frame element of finite element method (FEM) is used to model of the simply supported PSC box bridge. The irregulation of rail-way is derived using the experiential spectrum density function under assumption of twelve level tracks conditions based on the normal probability procedure. The dynamic analyses by Runge-Kutta method which are able to analyze the high frequency wheel force spectrum. A dynamic behaviour of KTX due to high speeds until 450km/h developing speed with relative time is analysed and compared the characteristics running over the road and PSC box bridge tracks. Finally, the KTX integrated evaluation method of safety between high speed train and bridge is presented.

• Journal of Navigation and Port Research
• /
• v.38 no.4
• /
• pp.421-427
• /
• 2014

In order to protect coastal facilities mainly from wave and current actions, the self-locking eco blocks constituting elements of protecting shore structures against scouring were designed. These blocks are adapted to the sloping bottom, coastal dunes, and submerged coastal pipelines, counteracting the destructive and erosive impulse action. A series of laboratory experiments has been conducted to investigate the reflection of water waves over and against a train of protruded or submerged shore structures and compare the reflecting capabilities of incident waves including wave forces. In this study the hydraulic model experiment was conducted to identify the performance of newly designed water affinity eco blocks to keep the coast slope and bottom mound from scouring by reduction of the wave reflection and to convince stability of the block placement. Revised design of each block element was also tested for field conditions. From the result of experiments, the field applicability of the developed blocks and placement was discussed afterward.

• KEPCO Journal on Electric Power and Energy
• /
• v.2 no.3
• /
• pp.415-419
• /
• 2016

As the need for clean coal technology has grown, so has the global research and development efforts into integrated gasification combined cycle (IGCC) plants. An IGCC plant couples a gas turbine to a gasification block. Various technical and economic problems exist in designing such a system. One such problem is the difficulty in realizing economies of scale because the single-train flow capacity of commercial IGCC synthetic gas turbine plants is limited; the capacity does not exceed a net power rating of 300 MW. To address this problem, this study modeled and simulated a synthetic gas turbine with the goal of evaluating the feasibility of a 500 MW or larger IGCC plant. First, a gas turbine with the best output and efficiency was chosen for use with natural gas. The turbine was modeled using GateCycle (a simulation tool), and the integrity of the model validated by comparing the result to the design value. Next, off-design modeling was carried out for a gas turbine with synthetic gas based on its on-design model, and the result was compared with the study result of the gas turbine manufacturer. The simulation confirmed that it is possible to create a large capacity IGCC plant by undertaking the remodeling of a gas turbine designed to use natural gas into one suitable for synthetic gas.

• Journal of Korean Society of Coastal and Ocean Engineers
• /
• v.13 no.3
• /
• pp.189-194
• /
• 2001

The present study describes the Bragg reflection of monochromatic water waves propagating over a train of doubly-sinusoidally varying topographies. A numerical model based on the boundary element method is firstly verified by calculating reflection and transmission coefficients of waves over a trench. Calculated solutions are compared with those of the eigenfunction expansion method. The model is then used to simulated reflection of monochromatic water waves propagating over doubly-sinusoidally varying bottom topographies. Obtained reflection coefficients are compared with those of available laboratory measurements, those of the eigenfunction expansion method and the extended mild-slope equation. A reasonable agreement is shown.

• Transactions of the Korean Society of Mechanical Engineers A
• /
• v.24 no.2 s.173
• /
• pp.455-463
• /
• 2000

In order to develop nondestructive techniques for the quantitative estimation of creep damage a series of crept copper samples were prepared and their ultrasonic velocities were measured. Velocities measured in three directions with respect to the loading axis decreased nonlinearly and their anisotropy increased as a function of creep-induced porosity. A progressive damage model was described to explain the void-velocity relationship, including the anisotropy. The comparison of modeling study showed that the creep voids evolved from sphere toward flat oblate spheroid with its minor axis aligned along the stress direction. This model allowed us to determine the average aspect ratio of voids for a given porosity content. A novel technique, the back propagation neural network (BPNN), was applied for estimating the porosity content due to the creep damage. The measured velocities were used to train the BP classifier, and its accuracy was tested on another set of creep samples containing 0 to 0.7 % void content. When the void aspect ratio was used as input parameter together with the velocity data, the NN algorithm provided much better estimation of void content.