• Proceedings of the Korean Society for Technology of Plasticity Conference
• /
• 2003.05a
• /
• pp.258-261
• /
• 2003

In this study, finite element analysis for multi-stage deep drawing process of rectangular configuration with extreme aspect ratio is carried out especially for the blank design. The analysis of rectangular deep drawing process with extreme aspect ratio is likewise very difficult with respect to the design process parameters including the intermediate die profile. In order to solve the difficulties, numerical approach using finite element method is performed in the present analysis and design. A series of experiments for multi-stage rectangular deep drawing process are conducted and the deformed configuration is investigated by comparing with the results of the finite element analysis. Additionally, to minimize amount of removal material after trimming process, finite element simulation is applied for the blank modification. The analysis incorporates brick elements for a rigid-plastic finite element method with an explicit time integration scheme using LS-DYNA3D.

• Proceedings of the Korea Concrete Institute Conference
• /
• 2000.10a
• /
• pp.577-582
• /
• 2000

This study is aimed to evaluate the shear strength of reinforced concrete deep beams subject to concentrated loads, using a simplified strut-tie model. For the shear strength prediction of deep beams, it is prerequisite to evaluate the effective width of strut and to verify the efficiency factors proposed by MacGregor et al.. The results analyzed by truss models have been compared with those calculated by domestic code for the existing data of 90 deep beam specimens. The shear strength of deep beams were reviewed with respect to concrete strength, the shear span-depth ratio, and the ratio of web reinforcements. The results showed that the shear strength of the proposed model gave a better agreement than the domestic code approach.

• Journal of the Korean Society for Precision Engineering
• /
• v.13 no.6
• /
• pp.27-33
• /
• 1996

In this study, a CAD/CAM system for axisymmetric deep drawing processes has been developed. An approach to the system is based on the knowledge based system. Under the environment of CAD/CAM software of Personal Designer, the system has been written in UPL. The geometries of intermediate and final object in deep drawing process, including processes parameters are input for the CAD/CAM system. The input data can be obtained from the results of Pro_Deep. The parts drawing of die sets for each process is generated in tool design module of the CAD/CAM system. Also. the die assembly drawings can be obtained. NC commands for machining of the part can be generated in the developed CAD/CAM system.

• Transactions of Materials Processing
• /
• v.12 no.7
• /
• pp.647-653
• /
• 2003

A systematic approach for the process design in deep drawing is necessary to improve the quality of drawn cups. This study concentrates mainly on the influence of process design strategy on the product quality. Different types of process design were chosen from initial blank of 100mm in diameter to make final cup of 50mm in diameter. In order to make this cup, we used 2-stage deep drawing. Forming analyses are carried out to find out better design in terms of drawing force. It is proposed that the process design, in which maximum drawing forces during successive operations are equal, is a more desirable one. Through experiment, it is found that the proposed case shows equivalent values in terms of maximum drawing force during successive operations in real process and can achieve the best product quality in terms of dimensional accuracy. Thus, it is shown that proposed design is very effective in the improvement of quality in drawn cups and may be extended to deep drawing with more stages.

• IEMEK Journal of Embedded Systems and Applications
• /
• v.16 no.5
• /
• pp.215-223
• /
• 2021

3D data can be categorized into two parts : Euclidean data and non-Euclidean data. In general, 3D data exists in the form of non-Euclidean data. Due to irregularities in non-Euclidean data such as mesh and point cloud, early 3D deep learning studies transformed these data into regular forms of Euclidean data to utilize them. This approach, however, cannot use memory efficiently and causes loses of essential information on objects. Thus, various approaches that can directly apply deep learning architecture to non-Euclidean 3D data have emerged. In this survey, we introduce various deep learning methods for mesh and point cloud data. After analyzing the operating principles of these methods designed for irregular data, we compare the performance of existing methods for shape classification and segmentation tasks.

• Journal of Korea Multimedia Society
• /
• v.25 no.8
• /
• pp.1203-1211
• /
• 2022

Melanoma is a skin cancer that starts in pigment-producing cells (melanocytes). The death rates of skin cancer like melanoma can be reduced by early detection and diagnosis of diseases. It is common for doctors to spend a lot of time trying to distinguish between skin lesions and healthy cells because of their striking similarities. The detection of melanoma lesions can be made easier for doctors with the help of an automated classification system that uses deep learning. This study presents a new approach for melanoma classification based on an ensemble of deep convolution neural networks and a Log-Gabor filter. First, we create the Log-Gabor representation of the original image. Then, we input the Log-Gabor representation into a new ensemble of deep convolution neural networks. We evaluated the proposed method on the melanoma dataset collected at Yonsei University and Dongsan Clinic. Based on our numerical results, the proposed framework achieves more accuracy than other approaches.

• Biomolecules & Therapeutics
• /
• v.30 no.2
• /
• pp.179-183
• /
• 2022

Traditionally, pathologists microscopically examine tissue sections to detect pathological lesions; the many slides that must be evaluated impose severe work burdens. Also, diagnostic accuracy varies by pathologist training and experience; better diagnostic tools are required. Given the rapid development of computer vision, automated deep learning is now used to classify microscopic images, including medical images. Here, we used a Inception-v3 deep learning model to detect mouse lung metastatic tumors via whole slide imaging (WSI); we cropped the images to 151 by 151 pixels. The images were divided into training (53.8%) and test (46.2%) sets (21,017 and 18,016 images, respectively). When images from lung tissue containing tumor tissues were evaluated, the model accuracy was 98.76%. When images from normal lung tissue were evaluated, the model accuracy ("no tumor") was 99.87%. Thus, the deep learning model distinguished metastatic lesions from normal lung tissue. Our approach will allow the rapid and accurate analysis of various tissues.

• Journal of the Korea Institute of Military Science and Technology
• /
• v.26 no.5
• /
• pp.392-399
• /
• 2023

This research paper investigates the effectiveness of using computer graphics(CG) based synthetic data for deep learning in military vehicle detection. In particular, we explore the use of synthetic image generation techniques to train deep neural networks for object detection tasks. Our approach involves the generation of a large dataset of synthetic images of military vehicles, which is then used to train a deep learning model. The resulting model is then evaluated on real-world images to measure its effectiveness. Our experimental results show that synthetic training data alone can achieve effective results in object detection. Our findings demonstrate the potential of CG-based synthetic data for deep learning and suggest its value as a tool for training models in a variety of applications, including military vehicle detection.

• International Journal of Naval Architecture and Ocean Engineering
• /
• v.11 no.2
• /
• pp.782-795
• /
• 2019

Safety is always acritical focus of exploration of ocean resources, and it is well recognized that human factor is one of the major causes of accidents and breakdowns. Our research developed a dynamic human reliability assessment approach, Predicted Mean Vote-Cognitive Reliability and Error Analysis Method (PMV-CREAM), that is applicable to monitoring the cognitive reliability of oceanauts during deep-sea missions. Taking into account the difficult and variable operating environment of manned submersibles, this paper analyzed the cognitive actions of oceanauts during the various procedures required by deep-sea missions, and calculated the PMV index using human factors and dynamic environmental data. The Cognitive Failure Probabilities (CFP) were calculated using the extended CREAM approach. Finally, the CFP were corrected using the PMV index. This PMV-CREAM hybrid model can be utilized to avoid human error in deep-sea research, thereby preventing injury and loss of life during undersea work. This paper verified the method with "Jiaolong" manned submersible 7,000 m dive test. The"Jiaolong" oceanauts CR(Corrected CFP) is dynamic from 3.0615E-3 to 4.2948E-3, the CR caused by the environment is 1.2333E-3. The result shown the PMV-CREAM method could describe the dynamic human reliability of manned submersible caused by thermal environment.

• Smart Media Journal
• /
• v.6 no.3
• /
• pp.41-48
• /
• 2017

Event detection using social media has been widespread since social network services have been an active communication channel for connecting with others, diffusing news message. Especially, the real-time characteristic of social media has created the opportunity for supporting for real-time applications/systems. Social network such as Twitter is the potential data source to explore useful information by mining messages posted by the user community. This paper proposed a novel system for temporal event detection by analyzing social data. As a result, this information can be used by first responders, decision makers, or news agents to gain insight of the situation. The proposed approach takes advantages of deep learning methods that play core techniques on the main tasks including informative data identifying from a noisy environment and temporal event detection. The former is the responsibility of Convolutional Neural Network model trained from labeled Twitter data. The latter is for event detection supported by Recurrent Neural Network module. We demonstrated our approach and experimental results on the case study of earthquake situations. Our system is more adaptive than other systems used traditional methods since deep learning enables to extract the features of data without spending lots of time constructing feature by hand. This benefit makes our approach adaptive to extend to a new context of practice. Moreover, the proposed system promised to respond to acceptable delay within several minutes that will helpful mean for supporting news channel agents or belief plan in case of disaster events.