• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2019.05a
• /
• pp.217-219
• /
• 2019

In response to the increased use of digital video device, more researches are actively made on the image processing technologies. Image processing is practically used on various applied fields such as medical photographic interpretation, and object recognition. The types of image noise include Gaussian Noise, Impulse Noise, and Salt and Pepper. Noise refers to the unnecessary information which damages the video and the noise is mainly removed by a filter. Typical noise removal methods are Median Filter and Average Filter. While Median Filter is effective for removing Salt and Pepper noise, the noise removal performance is relatively lower in the environment with high noise density. To address such issue, this study suggested an algorithm which utilizes neighboring pixels to remove noise.

• The Journal of Asian Finance, Economics and Business
• /
• v.8 no.4
• /
• pp.687-697
• /
• 2021

This study aims to address the prevailing skepticism that conventional leadership models are not effective in the Middle East. With the same logic, selecting leaders is a confusing task in the Middle East due to the haphazardness surrounding this task and the lack of clarity of appropriate selection criteria. This study employs samples of leadership theories and frameworks that were scrutinized to classify specific leadership dimensions. The triangular model stemmed from the previous studies that addressed Leadership in general and the Leadership model for the Middle East. With the use of the literature review methodologies and historical analysis, the leadership model's description will be demonstrated. The results revealed that there are various dimensions of Leadership, especially concerning the Middle East's organizational environment. The findings of this study suggested a new model which assists in clarifying the issue by setting a group of 10 personality traits with eight behavioral skills and social status. Implications of this study enable making Leadership easier in practice. Furthermore, this will enable recognition of Leadership according to specific criteria, which will help make greater equality and empowerment at all levels of the system. This research localizes Leadership and paves the way to automate leaders' selection process with a guarantee of fairness among candidates.

• Smart Structures and Systems
• /
• v.29 no.1
• /
• pp.153-166
• /
• 2022

Identifying fine cracks in steel bridge facilities is a challenging task of structural health monitoring (SHM). This study proposed an end-to-end crack image segmentation framework based on a one-step Convolutional Neural Network (CNN) for pixel-level object recognition with high accuracy. To particularly address the challenges arising from small object detection in complex background, efforts were made in loss function selection aiming at sample imbalance and module modification in order to improve the generalization ability on complicated images. Specifically, loss functions were compared among alternatives including the Binary Cross Entropy (BCE), Focal, Tversky and Dice loss, with the last three specialized for biased sample distribution. Structural modifications with dilated convolution, Spatial Pyramid Pooling (SPP) and Feature Pyramid Network (FPN) were also performed to form a new backbone termed CrackDet. Models of various loss functions and feature extraction modules were trained on crack images and tested on full-scale images collected on steel box girders. The CNN model incorporated the classic U-Net as its backbone, and Dice loss as its loss function achieved the highest mean Intersection-over-Union (mIoU) of 0.7571 on full-scale pictures. In contrast, the best performance on cropped crack images was achieved by integrating CrackDet with Dice loss at a mIoU of 0.7670.

• Journal of the Korean Society of Systems Engineering
• /
• v.18 no.1
• /
• pp.90-98
• /
• 2022

On February 12, 2019, the U.S. Department of Defense newly established and announced the "Defense AI Strategy" to accelerate the use of artificial intelligence (AI) technology for military purposes. As China and Russia invested heavily in AI for military purposes, the U.S. was concerned that it could eventually lose its advantage in AI technology to China and Russia. In response, China and Russia, which are hostile countries, and especially China, are speeding up the development of new military theories related to the overall construction and operation of the Chinese military based on AI. With the rapid development of AI technology, major advanced countries such as the U.S. and China are actively researching the application of AI technology, but most existing studies do not address the special topic of defense. Fortunately, the "Future Defense 2030 Technology Strategy" classified AI technology fields from a defense perspective and analyzed advanced overseas cases to present a roadmap in detail, but it has limitations in comparing private technology-oriented benchmarking and AI technology's maturity level. Therefore, this study tried to overcome the limitations of the "Future Defense 2030 Technology Strategy" by comparing and analyzing Chinese and U.S. military research cases and evaluating the maturity level of military use of AI technology, not AI technology itself.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.17 no.2
• /
• pp.559-575
• /
• 2023

3D human pose estimation is widely applied in various fields, including action recognition, sports analysis, and human-computer interaction. 3D human pose estimation has achieved significant progress with the introduction of convolutional neural network (CNN). Recently, several researches have proposed the use of multiview approaches to avoid occlusions in single-view approaches. However, as the number of cameras increases, a 3D pose estimation system relying on a CNN may lack in computational resources. In addition, when a single host system uses multiple cameras, the data transition speed becomes inadequate owing to bandwidth limitations. To address this problem, we propose a distributed real-time 3D pose estimation framework based on asynchronous multiple cameras. The proposed framework comprises a central server and multiple edge devices. Each multiple-edge device estimates a 2D human pose from its view and sendsit to the central server. Subsequently, the central server synchronizes the received 2D human pose data based on the timestamps. Finally, the central server reconstructs a 3D human pose using geometrical triangulation. We demonstrate that the proposed framework increases the percentage of detected joints and successfully estimates 3D human poses in real-time.

• Korean Journal of Artificial Intelligence
• /
• v.11 no.1
• /
• pp.17-24
• /
• 2023

With the continuous growth in the amount of data collected and analyzed, deep learning has become increasingly popular for extracting meaningful insights from various fields. However, hardware limitations pose a challenge for achieving meaningful results with limited data. To address this challenge, this paper proposes an algorithm that leverages the characteristics of convolutional neural networks (CNNs) to reduce the size of image datasets by 20% through smoothing and shrinking the size of images using color elements. The proposed algorithm reduces the learning time and, as a result, the computational load on hardware. The experiments conducted in this study show that the proposed method achieves effective learning with similar or slightly higher accuracy than the original dataset while reducing computational and time costs. This color-centric dataset construction method using image smoothing techniques can lead to more efficient learning on CNNs. This method can be applied in various applications, such as image classification and recognition, and can contribute to more efficient and cost-effective deep learning. This paper presents a promising approach to reducing the computational load and time costs associated with deep learning and provides meaningful results with limited data, enabling them to apply deep learning to a broader range of applications.

• Korean Journal of Veterinary Service
• /
• v.45 no.4
• /
• pp.253-262
• /
• 2022

The applications of artificial intelligence (AI) can provide useful solutions to animal infectious diseases and their impact on humans. The advent of AI learning algorithms and recognition technologies is especially advantageous in applied studies, including the detection, analysis, impact assessment, simulation, and prediction of environmental impacts on malignant animal epidemics. To this end, this study specifically focused on environmental pollution and animal diseases. While the number of related studies is rapidly increasing, the research trends, evolution, and collaboration in this field are not yet well-established. We analyzed the bibliographic data of 1191 articles on AI applications to environmental pollution and animal diseases during the period of 2000~2019; these articles were collected from the Web of Science (WoS). The results revealed that PR China and the United States are the leaders in research production, impact, and collaboration. Finally, we provided research directions and practical implications for the incorporation of AI applications to address environmental impacts on animal diseases.

• Journal of Environmental Health Sciences
• /
• v.48 no.1
• /
• pp.19-27
• /
• 2022

The industrial development and socioeconomic structures of a society are inextricably linked to occupational accidents and diseases. Since the 1970s, a series of major occupational diseases have occurred in South Korea, such as mercury poisoning in Munsong-myeon, carbon disulfide poisoning at Wonjin Rayon, and leukemia at Samsung Electronics. These incidents have caused us to take a critical look at the level of worker safety and health management within companies and the government. These serve as symbolic and representational events. Doctors, lawyers, and labor activists concerned about employee safety and lives came together for years to struggle with the government and industry in order to determine what caused the diseases and to obtain compensation for victims. They finally achieved recognition for occupational diseases and recompense for losses. It is difficult to find similar cases to the baby powder asbestos talc cases and the radon bed case internationally, or there is no case where such a large number of consumers have been potentially harmed. It is also difficult to prove that the damage took place due to the victims' diverse geographic locations and ages, as well as the disease's long incubation period. Based on this premise, businesses and the government have been apathetic in acknowledging these diseases and compensating for damages, with few practical outcomes. Furthermore, unlike the large-scale occupational disease cases, only a few people including expert groups were organized and actively participated in the settlement of these issues, so it remains unfinished business for our society to address.

• Journal of Korean Society of Industrial and Systems Engineering
• /
• v.46 no.4
• /
• pp.101-106
• /
• 2023

With the recent surge in YouTube usage, there has been a proliferation of user-generated videos where individuals evaluate cosmetics. Consequently, many companies are increasingly utilizing evaluation videos for their product marketing and market research. However, a notable drawback is the manual classification of these product review videos incurring significant costs and time. Therefore, this paper proposes a deep learning-based cosmetics search algorithm to automate this task. The algorithm consists of two networks: One for detecting candidates in images using shape features such as circles, rectangles, etc and Another for filtering and categorizing these candidates. The reason for choosing a Two-Stage architecture over One-Stage is that, in videos containing background scenes, it is more robust to first detect cosmetic candidates before classifying them as specific objects. Although Two-Stage structures are generally known to outperform One-Stage structures in terms of model architecture, this study opts for Two-Stage to address issues related to the acquisition of training and validation data that arise when using One-Stage. Acquiring data for the algorithm that detects cosmetic candidates based on shape and the algorithm that classifies candidates into specific objects is cost-effective, ensuring the overall robustness of the algorithm.

• The Journal of the Acoustical Society of Korea
• /
• v.26 no.6
• /
• pp.243-249
• /
• 2007

We propose an effective voice-based gender identification using group delay(GD) Generally, features for speech recognition are composed of magnitude information rather than phase information. In our approach, we address a difference between male and female for GD which is a derivative of the Fourier transform phase. Also, we propose a novel way to incorporate the features fusion scheme based on a combination of GD and magnitude information such as mel-frequency cepstral coefficients(MFCC), linear predictive coding (LPC) coefficients, reflection coefficients and formant. The experimental results indicate that GD is effective in discriminating gender and the performance is significantly improved when the proposed feature fusion technique is applied.