• Journal of the Korean Geotechnical Society
• /
• v.37 no.3
• /
• pp.5-17
• /
• 2021

This study aims to investigate the causes and countermeasures for the occurrence of tension cracks in the slope of the rock mass of heavy equipment for road construction. Electric resistivity survey was performed to investigate the expandable tensile crack range. As a result of examining the distribution of soft zones in the rock mass, a low specific resistance zone was found at the bottom of the access road where tensile cracks occurred. It was confirmed that a low resistivity zone was distributed near the top of the excavation slope. Therefore, reinforcements was performed by determining the location of the possible tensile crack as the top of the excavation slope. Two rows of reinforced piles and anchors were proposed as a reinforcement method, and the slope stability analysis showed that the allowable safety factor was satisfied after reinforcements.

• Journal of the Korean Geotechnical Society
• /
• v.36 no.12
• /
• pp.87-97
• /
• 2020

Recently, interest in Tie-cell wave-dissipating blocks that can compensate for the disadvantages of block-type breakwaters and provide economically effective design is increasing. Tie-cell wave-dissipating block has high activity resistance due to its structure in which each block is held together by a pile. In this study, through the laboratory model experiments, it was possible to confirm the increase in lateral resistance of the Tie-cell wave-dissipating blocks due to the penetration of the piles. The lateral resistance of the piles appeared almost constant regardless of the overburden load of the blocks. The lateral resistance shared by the piles changed depending on the increase or decrease in the lateral resistance of the friction between blocks. In the experiment in which two piles were penetrated, the overall lateral resistance was larger than the case a single pile was used, but the resistance behavior of the piles was different.

• Explosives and Blasting
• /
• v.40 no.1
• /
• pp.29-38
• /
• 2022

Electronic detonators are now widely used in various construction sites and quarry mines. Including the sites where safety-thing is located nearby, Cases of using electronic detonators are increasing to maximize operational efficiency by improving blast fragmentation or reducing the cost of secondary blasting. This case study is about applying for electronic detonators on zone 00 construction site, which is the part of urban area metropolitan express rail A line project. Although the project was initially planned to utilize non-electric detonators, Electronic detonators are considered as the solution not only for safe and fast excavation, but also to minimize civil complaint and the damage of safety-thing. By applying electronic detonators, we were able to satisfy environmental regulations standards and prevent nearby safety-thing from getting damaged.

• The Journal of Engineering Geology
• /
• v.31 no.4
• /
• pp.549-559
• /
• 2021

The Arctic Circle's huge amounts of fossil fuels and mineral resources are being developed and subjected to active construction projects. Global efforts are continuing to actively respond to climate change, but the dependence on fossil fuels remains high. This study reports a preliminary survey conducted in Alberta, Canada, where oil sand resources are actively developed. A land cover map was prepared using satellite imagery to reduce the cost and time of surveying a wide area. Results likely useful to resource development projects such as ground surface temperature and snow cover distribution were derived by using the obtained image classification results. It is expected that the results of the present research and analysis will be used to establish strategies for the successful promotion and operation of projects to develop resources in the Arctic.

• Journal of Aerospace System Engineering
• /
• v.16 no.4
• /
• pp.109-115
• /
• 2022

The CNN (Convolution Neural Network) algorithm which combines a deep learning technique, and a computer vision technology, makes image classification feasible with the high-performance computing system. In this thesis, the CNN algorithm is applied to the classification problem, by using a typical deep learning framework of TensorFlow and machine learning techniques. The data set required for supervised learning is generated with the same type of bolts. some of which have undamaged threads, but others have damaged threads. The learning model with less quantity data showed good classification performance on detecting damage in a bolt image. Additionally, the model performance is reviewed by altering the quantity of convolution layers, or applying selectively the over and under fitting alleviation algorithm.

• Journal of Broadcast Engineering
• /
• v.27 no.4
• /
• pp.487-498
• /
• 2022

Depth map is an image that contains distance information in 3D space on a 2D plane and is used in various 3D vision tasks. Many existing depth estimation studies mainly use narrow FoV images, in which a significant portion of the entire scene is lost. In this paper, we propose a technique for generating 360° omnidirectional RGBD images from a sparse set of narrow FoV images. The proposed generative adversarial network based image generation model estimates the relative FoV for the entire panoramic image from a small number of non-overlapping images and produces a 360° RGB and depth image simultaneously. In addition, it shows improved performance by configuring a network reflecting the spherical characteristics of the 360° image.

• Journal of Broadcast Engineering
• /
• v.28 no.2
• /
• pp.178-184
• /
• 2023

Finding texts in general scene images and recognizing their contents is a very important task that can be used as a basis for robot vision, visual assistance, and so on. However, for the low-resolution text images, the degradations, such as noise or blur included in text images, are more noticeable, which leads to severe performance degradation of text recognition accuracy. In this paper, we propose a new Korean text image super-resolution based on a Transformer-based model, which generally shows higher performance than convolutional neural networks. In the experiments, we show that text recognition accuracy for Korean text images can be improved when our proposed text image super-resolution method is used. We also propose a new Korean text image dataset for training our model, which contains massive HR-LR Korean text image pairs.

• IEMEK Journal of Embedded Systems and Applications
• /
• v.18 no.3
• /
• pp.89-100
• /
• 2023

Recently, on-device artificial intelligence (AI) solutions using mobile devices and embedded edge devices have emerged in various fields, such as computer vision, to address network traffic burdens, low-energy operations, and security problems. Although vision transformer deep learning models have outperformed conventional convolutional neural network (CNN) models in computer vision, they require more computations and parameters than CNN models. Thus, they are not directly applicable to embedded edge devices with limited hardware resources. Many researchers have proposed various model compression methods or lightweight architectures for vision transformers; however, there are only a few studies evaluating the effects of model compression techniques of vision transformers on performance. Regarding this problem, this paper presents a performance evaluation of vision transformers on embedded platforms. We investigated the behaviors of three vision transformers: DeiT, LeViT, and MobileViT. Each model performance was evaluated by accuracy and inference time on edge devices using the ImageNet dataset. We assessed the effects of the quantization method applied to the models on latency enhancement and accuracy degradation by profiling the proportion of response time occupied by major operations. In addition, we evaluated the performance of each model on GPU and EdgeTPU-based edge devices. In our experimental results, LeViT showed the best performance in CPU-based edge devices, and DeiT-small showed the highest performance improvement in GPU-based edge devices. In addition, only MobileViT models showed performance improvement on EdgeTPU. Summarizing the analysis results through profiling, the degree of performance improvement of each vision transformer model was highly dependent on the proportion of parts that could be optimized in the target edge device. In summary, to apply vision transformers to on-device AI solutions, either proper operation composition and optimizations specific to target edge devices must be considered.

• Journal of Industrial Convergence
• /
• v.21 no.3
• /
• pp.17-27
• /
• 2023

This paper investigated and studied the influence of consultant's competence on CEO's values. There are many studies about relation between consultant's competence and company's accomplishment, but there are lack of research about how consultant's competence effected CEO's Value. The data source used in this study is a questionnaire survey involving 177 CEOs of SME who have experience in consulting. Based on this collected data, we conducted factor analysis, reliability and validity analysis, and hypotheses were verified through correlation analysis and regression analysis. This study shows that consultant's competence affected CEO's values in some ways, and also contributes to both academic and practical implications about corporate management that related sustainable growth between consultant and client.

• KIPS Transactions on Software and Data Engineering
• /
• v.11 no.12
• /
• pp.509-516
• /
• 2022

Accurate pose prediction of objects in 3D space is an important visual recognition technique widely used in many applications such as scene understanding in both indoor and outdoor environments, robotic object manipulation, autonomous driving, and augmented reality. Most previous works for object pose estimation have the limitation that they require an exact 3D CAD model for each object. Unlike such previous works, this paper proposes a novel neural network model that can predict the poses of unknown objects based on only their RGB color images without the corresponding 3D CAD models. The proposed model can obtain depth maps required for unknown object pose prediction by using an adaptive depth estimator, AdaBins,. In this paper, we evaluate the usefulness and the performance of the proposed model through experiments using benchmark datasets.