• Annual Conference of KIPS
• /
• 2022.11a
• /
• pp.300-302
• /
• 2022

Palm vein identification has attracted attention due to its distinct characteristics and excellent recognition accuracy. However, many contactless palm vein identification systems suffer from the issue of having low-quality palm images, resulting in degradation of recognition accuracy. This paper proposes the use of U-Net architecture to correctly segment the vascular blood vessel from palm images. Attention gate mechanism and residual block are also utilized to effectively learn the crucial features of a specific segmentation task. The experiments were conducted on CASIA dataset. Hessian-based Jerman filtering method is applied to label the palm vein patterns from the original images, then the network is trained to segment the palm vein features from the background noise. The proposed method has obtained 96.24 IoU coefficient and 98.09 dice coefficient.

• KIPS Transactions on Software and Data Engineering
• /
• v.8 no.10
• /
• pp.403-410
• /
• 2019

Image de-snowing aims at eliminating the negative influence by snow particles and improving scene understanding in images. In this paper, a perceptual generative adversarial network based a single image snow removal method is proposed. The residual U-Net is designed as a generator to generate the snow free image. In order to handle various sizes of snow particles, the inception module with different filter kernels is adopted to extract multiple resolution features of the input snow image. Except the adversarial loss, the perceptual loss and total variation loss are employed to improve the quality of the resulted image. Experimental results indicate that our method can obtain excellent performance both on synthetic and realistic snow images in terms of visual observation and commonly used visual quality indices.

• Journal of the Korea institute for structural maintenance and inspection
• /
• v.26 no.2
• /
• pp.28-36
• /
• 2022

As port structures are exposed to various extreme external loads such as wind (typhoons), sea waves, or collision with ships; it is important to evaluate the structural safety periodically. To monitor the port structure, especially the rubber fender, a fender segmentation system using a vision sensor and deep learning method has been proposed in this study. For fender segmentation, a new deep learning network that improves the encoder-decoder framework with the receptive field block convolution module inspired by the eccentric function of the human visual system into the DenseNet format has been proposed. In order to train the network, various fender images such as BP, V, cell, cylindrical, and tire-types have been collected, and the images are augmented by applying four augmentation methods such as elastic distortion, horizontal flip, color jitter, and affine transforms. The proposed algorithm has been trained and verified with the collected various types of fender images, and the performance results showed that the system precisely segmented in real time with high IoU rate (84%) and F1 score (90%) in comparison with the conventional segmentation model, VGG16 with U-net. The trained network has been applied to the real images taken at one port in Republic of Korea, and found that the fenders are segmented with high accuracy even with a small dataset.

• Journal of The Korean Society of Grassland and Forage Science
• /
• v.6 no.2
• /
• pp.71-77
• /
• 1986

The field experiment was conducted to evaluate the effect of herbicide treatment (Banvel: 100, 200, U-46: 150, 300, Hedonal: 150, 300, Simazin: 100, 200g/10 a) on change in the botanical composition and dry matter productivity of ladino clover (Trifolium repens L.) dominated pasture mixtures. The experiment was laid down as a randomized block design with 4 replications at experimental field of Livestock Experiment Station in Suweon from 1983 to 1985. The results obtained are summarized as follows: 1. Against ladino clover in mixie grass-clover swards Banvel, U-46 and Hedonal gave good control. The percentage of ladino clover under herbicide tratment decreased to about 1-2%(Banvel), 11-18%(U-46) and 22-31%(Hedonal), respectively, while it increased to 71% in untreated pastures. However, in the second year this trend stated to reverse and occurred clover dominance again in U-46 and Hedonal application, while those remained approximately constant until end of the years under Banvel treatment. Simazin is to be not recommended. 2. The best time for herbicide treatment was found to be late summer before autumn sown 20-25 days. When it applied in early summer weed infestigation by Digitaria spp., Echinochloa spp. and other species was a severe problem. 3. Emergence and early development of introduced pastures were less satisfactory, if it oversown immediatley after herbicide treatments due to its phytotoxical damage. Residual chemicals remained about 7-10 days in topsoils. Perennial ryegrass and orchardgrass were slightly less tolerant than the other species. 4. In dry matter, taken as average of three year results, Banvel applied pastures produced the remarkably high yield of 1023 kg/10 a, which is as much as 44% higher than that of untreated plot. Dry matter yields under U-46 and Hedonal treatment were 842 and 811 kg/10 a, respectively. 5. Weender components and net energy concentration were affected by change in the botanical composition. Crude protein and NEL value were slightly higher in clover dominance than those in herbicide treatments. Total yields of net energy lactation, however, were the highest in Banvel application with 5401 MJ and the lowest in untreatment with 3889 MJ-NEL/10 a DM.

• Journal of the Society of Naval Architects of Korea
• /
• v.58 no.5
• /
• pp.303-313
• /
• 2021

Recently, quality control of the Liquefied Natural Gas Carrier (LNGC) cargo hold and block-erection interference areas using 3D scanners have been performed, focusing on large shipyards and the international association of classification societies. In this study, as a part of the research on LNGC cargo hold quality management advancement, a study on deep-learning-based scaffolding system 3D point cloud object detection and post-processing were conducted using a LNGC cargo hold 3D point cloud. The scaffolding system point cloud object detection is based on the PointNet deep learning architecture that detects objects using point clouds, achieving 70% prediction accuracy. In addition, the possibility of improving the accuracy of object detection through parameter adjustment is confirmed, and the standard of Intersection over Union (IoU), an index for determining whether the object is the same, is achieved. To avoid the manual post-processing work, the object detection architecture allows automatic task performance and can achieve stable prediction accuracy through supplementation and improvement of learning data. In the future, an improved study will be conducted on not only the flat surface of the LNGC cargo hold but also complex systems such as curved surfaces, and the results are expected to be applicable in process progress automation rate monitoring and ship quality control.

• Nuclear Engineering and Technology
• /
• v.51 no.6
• /
• pp.1532-1539
• /
• 2019

This paper analyzes a new method for reducing boiling water reactor fuel temperature during a Loss of Coolant Accident (LOCA). The method uses a device called Reverse Flow Restriction Device (RFRD) at the inlet of fuel bundles in the core to prevent coolant loss from the bundle inlet due to the reverse flow after a large break in the recirculation loop. The device allows for flow in the forward direction which occurs during normal operation, while after the break, the RFRD device changes its status to prevent reverse flow. In this paper, a detailed simulation of LOCA has been carried out using the U.S. NRC's TRACE code to investigate the effect of RFRD on the flow rate as well as peak clad temperature of BWR fuel bundles during three different LOCA scenarios: small break LOCA (25% LOCA), large break LOCA (100% LOCA), and double-ended guillotine break (200% LOCA). The results demonstrated that the device could substantially block flow reversal in fuel bundles during LOCA, allowing for coolant to remain in the core during the coolant blowdown phase. The device can retain additional cooling water after activating the emergency systems, which maintains the peak clad temperature at lower levels. Moreover, the RFRD achieved the reflood phase (when the saturation temperature of the clad is restored) earlier than without the RFRD.

• IEMEK Journal of Embedded Systems and Applications
• /
• v.17 no.5
• /
• pp.265-272
• /
• 2022

As the risk of lung cancer has increased, early-stage detection and treatment of cancers have received a lot of attention. Among various medical imaging approaches, computer tomography (CT) has been widely utilized to examine the size and growth rate of lung nodules. However, the process of manual examination is a time-consuming task, and it causes physical and mental fatigue for medical professionals. Recently, many computer-aided diagnostic methods have been proposed to reduce the workload of medical professionals. In recent studies, encoder-decoder architectures have shown reliable performances in medical image segmentation, and it is adopted to predict lesion candidates. However, localizing nodules in lung CT images is a challenging problem due to the extremely small sizes and unstructured shapes of nodules. To solve these problems, we utilize atrous spatial pyramid pooling (ASPP) to minimize the loss of information for a general U-Net baseline model to extract rich representations from various receptive fields. Moreover, we propose mixed-up attention mechanism of reverse, boundary and convolutional block attention module (CBAM) to improve the accuracy of segmentation small scale of various shapes. The performance of the proposed model is compared with several previous attention mechanisms on the LIDC-IDRI dataset, and experimental results demonstrate that reverse, boundary, and CBAM (RB-CBAM) are effective in the segmentation of small nodules.

• Nuclear Engineering and Technology
• /
• v.55 no.6
• /
• pp.2335-2347
• /
• 2023

As medical facilities are usually built at urban areas, special concrete aggregates and evaluation methods are needed to optimize the design of concrete walls by balancing density, thickness, material composition, cost, and other factors. Carbon treatment rooms require a high radiation shielding requirement, as the neutron yield from carbon therapy is much higher than the neutron yield of protons. In this case study, the maximum carbon energy is 430 MeV/u and the maximum current is 0.27 nA from a hybrid particle therapy system. Hospital or facility construction should consider this requirement to design a special heavy concrete. In this work, magnetite is adopted as the major aggregate. Density is determined mainly by the major aggregate content of magnetite, and a heavy concrete test block was constructed for structural tests. The compressive strength is 35.7 MPa. The density ranges from 3.65 g/cm³ to 4.14 g/cm³, and the iron mass content ranges from 53.78% to 60.38% from the 12 cored sample measurements. It was found that there is a linear relationship between density and iron content, and mixing impurities should be the major reason leading to the nonuniform element and density distribution. The effect of this nonuniformity on radiation shielding properties for a carbon treatment room is investigated by three groups of Monte Carlo simulations. Higher density dominates to reduce shielding thickness. However, a higher content of high-Z elements will weaken the shielding strength, especially at a lower dose rate threshold and vice versa. The weakened side effect of a high iron content on the shielding property is obvious at 2.5 µSv=h. Therefore, we should not blindly pursue high Z content in engineering. If the thickness is constrained to 2 m, then the density can be reduced to 3.3 g/cm³, which will save cost by reducing the magnetite composition with 50.44% iron content. If a higher density of 3.9 g/cm³ with 57.65% iron content is selected for construction, then the thickness of the wall can be reduced to 174.2 cm, which will save space for equipment installation.