• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.26 no.3
• /
• pp.389-395
• /
• 2022

Because of improvement of deep learning techniques, deep learning using computer vision such as classification, detection and segmentation has also been used widely at many fields. Expecially, automatic driving is one of the major fields that applies computer vision systems. Also there are a lot of works and researches to combine multiple tasks in a single network. In this study, we propose the network that predicts the individual depth of pedestrians and vehicles. Proposed model is constructed based on YOLOv3 for object detection and Monodepth for depth estimation, and it process object detection and depth estimation consequently using encoder and decoder based on hard parameter sharing. We also used attention module to improve the accuracy of both object detection and depth estimation. Depth is predicted with monocular image, and is trained using self-supervised training method.

• Korean Journal of Remote Sensing
• /
• v.38 no.6_2
• /
• pp.1589-1605
• /
• 2022

Phase unwrapping is an essential procedure for interferometric synthetic aperture radar techniques. Accordingly, a lot of phase unwrapping methods have been developed. Deep-learning-based unwrapping methods have recently been proposed. In this paper, we reviewed state-of-the-art deep-learning-based unwrapping approaches in terms of 1) the approaches to predicting unwrapped phases, 2) deep learning model structures for phase unwrapping, and 3) training data generation. The research trend of the approaches to predicting unwrapped phases was introduced by categorizing wrap count segmentation, phase jump classification, phase regression, and deep-learning-assisted method. We introduced the case studies of deep learning model structure for phase unwrapping, and model structure optimization to relate the overall phase information. In addition, we summarized the research trend of the training data generation approaches in the views of phase gradient and noise in the main. And the future direction in deep-learning-based phase unwrapping was presented. It is expected that this paper is used as guideline for exploring future direction of deep-learning-based phase unwrapping research in Korea.

• Journal of Korea Society of Industrial Information Systems
• /
• v.27 no.5
• /
• pp.1-11
• /
• 2022

With the development of deep learning technology, various research and development are underway to estimate preference rankings through learning, and it is used in various fields such as web search, gene classification, recommendation system, and image search. Approximation algorithms are used to estimate deep learning-based preference ranking, which builds more than k comparison sets on all comparison targets to ensure proper accuracy, and how to build comparison sets affects learning. In this paper, we propose a k-disjoint comparison set generation algorithm and a k-chain comparison set generation algorithm, a novel algorithm for generating paired comparison sets for crowd-sourcing-based deep learning affinity measurements. In particular, the experiment confirmed that the k-chaining algorithm, like the conventional circular generation algorithm, also has a random nature that can support stable preference evaluation while ensuring connectivity between data.

• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.22 no.5
• /
• pp.55-61
• /
• 2022

With the rapid development of information technology, Metaverse and Non-Fungible Token (hereinafter referred to as NFT) technology will not only create new supply and demand markets for digital art creators, but also for existing art writers. As interest in and trading of virtual assets and coins increases, so does the demand for digital art trading in the NFT market. This study examines the theoretical content of NFTs, blockchains, and Metaverse, and analyzes various expressions of NFT art that are currently popular. As the case study, 100 projects were selected and analyzed in the overall OpenSea ranking, which included 2D graphics, 3D graphics and motion graphics works. Then, from the perspective of creators, the graphic styles of NFT digital art are divided into 4 types: 2D graphics, 3D graphics, 2D dynamic graphics, 3D dynamic graphics, and analyzed and studied. It is hoped that in the future, this study can suggest the direction of creating graphic styles to digital art NFT creators.

• Journal of Korea Port Economic Association
• /
• v.37 no.3
• /
• pp.105-116
• /
• 2021

Harbor floating pier is a structure in which one or several floating vessels are connected to have a port function so that ships can be bordered regardless of tide level in places where differences between tidal rocks are severe. There are 233 harbor floating piers in Korea, and 27.5% of harbor floating pier are over 30 years old. Harbor floating piers older than 30 years are potentially at high risk of accidents. However, there is no clear standard for disposal or sale of aging harbor floating pier, and the management regulations on the timing of maintenance inspection and repair are ambiguous. In this study, the AHP model was designed by classifying the problems and improvement factors of harbor floating pier facility operation through interviews with port managers and existing literature studies. The AHP analysis showed that the relative importance of the evaluation factors of the higher class was in the order of improvement of the legal system, improvement of operational management and technical improvement. This study can be used as basic data for improving the operation of Korea harbor floating pier facilities.

• Korean Journal of Remote Sensing
• /
• v.38 no.5_3
• /
• pp.819-834
• /
• 2022

Artificial Intelligence (AI) techniques have been effectively used for image classification, object detection, and image segmentation. Along with the recent advancement of computing power, deep learning models can build deeper and thicker networks and achieve better performance by creating more appropriate feature maps based on effective activation functions and optimizer algorithms. This review paper examined technical and academic trends of Convolutional Neural Network (CNN) and Transformer models that are emerging techniques in remote sensing and suggested their utilization strategies and development directions. A timely supply of satellite images and real-time processing for deep learning to cope with disaster monitoring will be required for future work. In addition, a big data platform dedicated to satellite images should be developed and integrated with drone and Closed-circuit Television (CCTV) images.

• The Journal of the Korea Contents Association
• /
• v.22 no.9
• /
• pp.614-627
• /
• 2022

The purpose of this study was to explore the various data and methods employed by HR analytics studies. The researchers selected 78 KCI-indexed empirical articles on HR analytics and categorized them using the Employee Life Cycle framework. This yielded several important findings. First, employee retention has been the most common subject of extant studies, followed by performance management. Second, HR analytics studies have used a variety of data (structured and unstructured) according to their research questions, and the data sources have ranged from organizations' internal systems to national databases. Third, most domestic HR analytics studies have been descriptive and diagnostic, whereas predictive and prescriptive studies have been rare. These results have important theoretical and practical implications for future HR analytics research.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.25 no.7
• /
• pp.923-929
• /
• 2021

TCP communication and packet communication require transmission control technology to ensure high quality and high reliability. However, in the case of real-time data transmission, an inefficient transmission problem occurs. In order to overcome this problem and transmit the packet reliability, in general, early congestion control using the buffer level as an index was used. Control of the congestion control point and the cancellation point is delayed because the point at which congestion is controlled is based on the buffer level. Therefore, in this paper, not only the buffer level indicator, but also the ideal buffer level, which determines the packet discard probability, is classified so that the transmission rate and buffer level that measure network congestion are close to the level above the optimal setting. As a result, it was shown that the average buffer level can be directly controlled by maintaining the average buffer level by the ideal buffer level set in the experiment to prove the proposed method.

• Journal of the Korean Electrochemical Society
• /
• v.25 no.2
• /
• pp.51-68
• /
• 2022

Although lithium metal batteries have a high energy density, experimental skills capable of solving lots of problems induced by dendrite such as short circuit, low coulomb efficiency, capacity loss, and cycle performance are still only in academic research stage. In this paper, research cases for dendrite growth inhibition on lithium metal electrode were classified into four types: flexible SEI (solid electrolyte interface) layer responding to volume expansion of lithium metal electrode, SEI supporting layer to inhibit dendrite growth physically, SHES (self-healing electrostatic shield) mechanism to adjust lithium growth by leading uniform diffusion of Li⁺ ions, and finally micro-patterning to induce uniform deposition of lithium. We hope to advance the practical use of lithium metal electrode by analyzing pros and cons of this classification.

• Journal of the Korea Institute of Information Security & Cryptology
• /
• v.32 no.1
• /
• pp.89-98
• /
• 2022

As deep learning technology was applied to various fields, research on adversarial attack techniques, a security problem of deep learning models, was actively studied. adversarial attacks have been mainly studied in the field of images. Recently, they have even developed a complete decision-based attack technique that can attack with just the classification results of the model. However, in the case of the audio field, research is relatively slow. In this paper, we applied several decision-based attack techniques to the audio field and improved state-of-the-art attack techniques. State-of-the-art decision-attack techniques have the disadvantage of requiring many queries for gradient approximation. In this paper, we improve query efficiency by proposing a method of reducing the vector search space required for gradient approximation. Experimental results showed that the attack success rate was increased by 50%, and the difference between original audio and adversarial examples was reduced by 75%, proving that our method could generate adversarial examples with smaller noise.