• Journal of IKEEE
• /
• v.23 no.4
• /
• pp.1250-1256
• /
• 2019

Although one can easily generate real-world 3D mesh data using a 3D printer or a depth camera, the generated data inevitably includes unnecessary noise. Therefore, mesh denoising is essential to obtain intact 3D mesh data. However, conventional mathematical denoising methods require preprocessing and often eliminate some important features of the 3D mesh. To address this problem, this paper proposes a deep learning based 3D mesh denoising method. Specifically, we propose a convolution-based autoencoder model consisting of an encoder and a decoder. The convolution operation applied to the mesh data performs denoising considering the relationship between each vertex constituting the mesh data and the surrounding vertices. When the convolution is completed, a sampling operation is performed to improve the learning speed. Experimental results show that the proposed autoencoder model produces faster and higher quality denoised data than the conventional methods.

• Journal of IKEEE
• /
• v.19 no.3
• /
• pp.282-287
• /
• 2015

In this study, an optical fiber detector was constructed by using a Ce:GAGG scintillator, optical fiber, and photomultiplier. The single crystal size of the scintillator was set to $3{\times}3{\times}20mm^3$ after simulating the counting efficiency of gamma rays in the scintillator by using the MCNPX code. The constructed detector used the standard gamma ray sources $^{137}Cs$ and $^{133}Ba$ to measure radiation and analyze the spectral characteristics of gamma rays. The resulting trend curve showed excellent linearity with an R-squared value of 0.99741, and the detector characteristics were found to vary 2% or less with distance based on comparison with the MCNPX value. Furthermore, the spectroscopic analysis of the gamma ray energy from the single-ray and mixed-ray sources showed that $^{137}Cs$ had its peak energy at 662 keV, and $^{133}Ba$ had at 356 keV. It seems that if the fiber-optics detector is used, working hours and exposure of worker can be reduced.

• Transactions of the Korean Society of Mechanical Engineers A
• /
• v.38 no.1
• /
• pp.65-70
• /
• 2014

This paper introduces a preform design method for a ring rolling process with an outer step. Underfilling is one of the general defects of the profile ring rolling process. It occurs when the deformation amount is small or step depth of the profiled region is large. To prevent underfilling, increasing the deformation amount or using a preform of size similar to that of the final product are required. Furthermore, the filling limit equation is suggested based on the shape factor and deformation ratio for preventing defects in the products. The filling limit equation has been derived through finite element analyses and production tests for four different cases. For verifying the suggested method, realsized profile rolling tests were performed, and test results were compared with the predictions of the equation.

• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.17 no.2
• /
• pp.147-157
• /
• 2017

In recent years, Super-pixels have become very popular for use in computer vision applications. Super-pixel algorithm transforms pixels into perceptually feasible regions to reduce stiff features of grid pixel. In particular, super-pixels are useful to depth estimation, skeleton works, body labeling, and feature localization, etc. But, it is not easy to generate a good super-pixel partition for doing these tasks. Especially, super-pixels do not satisfy more meaningful features in view of the gestalt aspects such as non-sum, continuation, closure, perceptual constancy. In this paper, we suggest an advanced algorithm which combines simple linear iterative clustering with fuzzy clustering concepts. Simple linear iterative clustering technique has high adherence to image boundaries, speed, memory efficient than conventional methods. But, it does not suggest good compact and regular property to the super-pixel shapes in context of gestalt aspects. Fuzzy similarity measures provide a reasonable graph in view of bounded size and few neighbors. Thus, more compact and regular pixels are obtained, and can extract locally relevant features. Simulation shows that fuzzy similarity based super-pixel building represents natural features as the manner in which humans decompose images.

• Journal of the Korean Institute of Gas
• /
• v.21 no.6
• /
• pp.8-14
• /
• 2017

One of the main causes of gas pipeline accidents is mechanical impact(third party damage). The majority of high pressure gas pipelines buried in major domestic industrial complexes are old pipes which have being operated over 20 years. Therefore, if an accident occurs, there will be a full scale accident because there is no additional inspection and reinforcement time. In this study, the defects on the piping during the mechanical impact were studied through the third party damage(excavation) experiments. Experiments were carried out using the 21 ton excavator which is operated in the actual excavation work and the type of pipe to be struck are ASTM A106 Grade.B and ASTM A53 Grade.B. As a result, when the bucket used during excavator operation is a sawtooth bucket, the defect is more bigger. And the smaller the diameter of the pipe, the smaller the depth and length of the defect. Also, it was confirmed that the impact height had no effect on the defects on the buried pipe, during the excavation work.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.12 no.2
• /
• pp.605-610
• /
• 2011

Soft ground improvement is essential to enhance strength of ground for construction in reclaimed land or shore. There are many method of soft ground improvement, and vertical drain method was widely used in many countries including korea. As vertical drain method is to plant many Prefabricated Vertical Drains in soft ground, it promotes consolidation and enhances strength. The PBD(Plastci Board Drain) that is excellent economy and workability was widely used in many countries as Prefabricated Vertical Drains. Construction quality of PBD is affected installation depth, pressure, perpendicularity. This paper describes the system developed that can automatically measure installation depth, pressure and perpendicularity for PBD. This system can reduce fraction defective of construction by auto faulty alarm and keeps the safety of operator by auto control system.

• The Journal of the Korea Contents Association
• /
• v.19 no.7
• /
• pp.220-233
• /
• 2019

Hitherto there have been by and large three different approaches to the installation works of Olafur Eliasson; a soma-aethetic, politico-aesthetic and techno-aesthetic. But none of these provides us with the aesthetic descriptions of the light effect. This failure seems to arise from the lack of the conceptual tools suit for describing the atmospheric effect of 'light'. The symbolism of light, or the theological optics of Middle Age may help us to compensate for the lack of appropriate concepts needed for theorizing the effect of light used very frequently by contemporary installation artists. And this medieval aesthetics of light can also of service to elucidate some essential characteristics of the digtal visual culture in general.

• The Journal of Bigdata
• /
• v.7 no.2
• /
• pp.129-137
• /
• 2022

With the development of the 4th industry, the logistics industry is evolving into a smart logistics system. However, ship work that transports vehicles is progressing slowly due to various problems. In this paper, we propose an stowage automation algorithm that can be used for cargo loading of vehicle carriers that shortens loading and unloading work time. The stowage automation algorithm returns the shortest distance by searching for a loading space and a movable path in the ship in consideration of the structure of the ship. The algorithm identifies walls, ramps and vehicles that have already been shipped, and can work even with randomly placed. In particular, it is expected to contribute to developing a smart logistics system for vehicle carriers by referring to the ship's master plan to search for vehicle loading and unloading space in each port and predict the shortest movable path.

• KSCE Journal of Civil and Environmental Engineering Research
• /
• v.28 no.1D
• /
• pp.57-65
• /
• 2008

Joint of concrete pavement contributes to improvement of pavement performance by preventing occurrence of random cracking due to drying shrinkage and temperature changes of concrete slabs at early age. However, saw-cutting operations performed prior to sufficient concrete hardening develop micro-cracking of the concrete near the joints, which may develop to long-term distresses due to repetitious traffic and environmental loadings. To reduce the distresses, the joint crack inducers with heights of 100 mm, 150 mm, and 220 mm and the joint cracking slots with various depth were installed at a test section to investigate occurrence of the joint cracks and their behaviors over 5 months. As the results, higher efficiency of the crack inducing and larger behavior of the joint cracks were observed for the taller joint crack inducer. Higher efficiency of the crack inducing and improvement of the joint performance are warranted by additional investigation and reformation of the joint crack inducer.

• Science of Emotion and Sensibility
• /
• v.26 no.4
• /
• pp.115-124
• /
• 2023

This study explores the intersection of literary studies and artificial intelligence (AI), focusing on the common theme of human emotions to foster complementary advancements in both fields. By adopting a comparative perspective, the paper investigates emotion as a shared focal point, analyzing various emotion-related concepts from both literary and AI perspectives. Despite the scarcity of research on the fusion of AI and literary studies, this study pioneers an interdisciplinary approach within the humanities, anticipating future developments in AI. It proposes that literary sensibility can contribute to AI by formalizing subjective literary emotions, thereby enhancing AI's understanding of complex human emotions. This paper's methodology involves the terminology-centered extraction of emotions, aiming to blend subjective imagination with objective technology. This fusion is expected to not only deepen AI's comprehension of human complexities but also broaden literary research by rapidly analyzing diverse human data. The study emphasizes the need for a collaborative dialogue between literature and engineering, recognizing each field's limitations while pursuing a convergent enhancement that transcends these boundaries.