• The Journal of Bigdata
• /
• v.8 no.2
• /
• pp.125-131
• /
• 2023

Globally, drug side effects rank among the top causes of death. To effectively respond to these adverse drug reactions, a shift towards an active real-time monitoring system, along with the standardization and quality improvement of data, is necessary. Integrating individual institutional data and utilizing large-scale data to enhance the accuracy of drug side effect predictions is critical. However, data sharing between institutions poses privacy concerns and involves varying data standards. To address this issue, our research adopts a federated learning approach, where data is not shared directly in compliance with privacy regulations, but rather the results of the model's learning are shared. We employ the Common Data Model (CDM) to standardize different data formats, ensuring accuracy and consistency of data. Additionally, we propose a drug monitoring system that enhances security and scalability management through a cloud-based federated learning environment. This system allows for effective monitoring and prediction of drug side effects while protecting the privacy of data shared between hospitals. The goal is to reduce mortality due to drug side effects and cut medical costs, exploring various technical approaches and methodologies to achieve this.

• Journal of Internet Computing and Services
• /
• v.25 no.3
• /
• pp.71-81
• /
• 2024

In response to the COVID-19 pandemic, the global airport industry is actively introducing 4th Industrial Revolution technology-based systems for quarantine and passenger safety, and test bed construction and prior verification using airport infrastructure and resources are actively being conducted. Analysis of recent cases shows that despite the changing travel patterns of airport users and the diversification of airport service demands, most testbeds construction studies are still focused on suppliers, and task prioritization is also determined by decision makers. There is a tendency to rely on subjective judgment. In order to find practical ways to become a first mover that leads innovation in the aviation industry, this study selected tasks and derived priorities to build testbeds from a service perspective that reflects various customer service needs and changes. Research results using the AHP analysis method resulted in priorities in the order of access transportation and parking services (29.2%), security screening services (23.4%), and departure services (21.8%), and these analysis results were tested in the airport industry. It shows that innovation in testbeds construction is an important factor. In particular, the establishment of smart parking and UAM transportation testbeds not only helps strengthen airports as centers of technological innovation, but also promotes cooperation with companies, research institutes, and governments, and provides an environment for testing and developing new technologies and services. It can be a foundation for what can be done. The results and implications produced through this study can serve as useful guidelines for domestic and foreign airport practitioners to build testbeds and establish strategies.

• The Journal of Bigdata
• /
• v.9 no.1
• /
• pp.101-113
• /
• 2024

Federated learning has garnered attention as an efficient method for training machine learning models in a distributed environment while maintaining data privacy and security. This study proposes a novel FedRFBagging algorithm to optimize the performance of random forest models in such federated learning environments. By dynamically adjusting the trees of local random forest models based on client-specific data characteristics, the proposed approach reduces communication costs and achieves high prediction accuracy even in environments with numerous clients. This method adapts to various data conditions, significantly enhancing model stability and training speed. While random forest models consist of multiple decision trees, transmitting all trees to the server in a federated learning environment results in exponentially increasing communication overhead, making their use impractical. Additionally, differences in data distribution among clients can lead to quality imbalances in the trees. To address this, the FedRFBagging algorithm selects only the highest-performing trees from each client for transmission to the server, which then reselects trees based on impurity values to construct the optimal global model. This reduces communication overhead and maintains high prediction performance across diverse data distributions. Although the global model reflects data from various clients, the data characteristics of each client may differ. To compensate for this, clients further train additional trees on the global model to perform local optimizations tailored to their data. This improves the overall model's prediction accuracy and adapts to changing data distributions. Our study demonstrates that the FedRFBagging algorithm effectively addresses the communication cost and performance issues associated with random forest models in federated learning environments, suggesting its applicability in such settings.

• Korean Journal of Remote Sensing
• /
• v.40 no.4
• /
• pp.343-350
• /
• 2024

Since the release of Meta's Segment Anything Model (SAM), a large-scale vision transformer generation model with rapid image segmentation capabilities, several studies have been conducted to apply this technology in various fields. In this study, we aimed to investigate the applicability of SAM for water bodies detection and extraction using the QGIS Geo-SAM plugin, which enables the use of SAM with satellite imagery. The experimental data consisted of Compact Advanced Satellite 500 (CAS500)-1 images. The results obtained by applying SAM to these data were compared with manually digitized water objects, Open Street Map (OSM), and water body data from the National Geographic Information Institute (NGII)-based hydrological digital map. The mean Intersection over Union (mIoU) calculated for all features extracted using SAM and these three-comparison data were 0.7490, 0.5905, and 0.4921, respectively. For features commonly appeared or extracted in all datasets, the results were 0.9189, 0.8779, and 0.7715, respectively. Based on analysis of the spatial consistency between SAM results and other comparison data, SAM showed limitations in detecting small-scale or poorly defined streams but provided meaningful segmentation results for water body classification.

• The Journal of the Convergence on Culture Technology
• /
• v.10 no.4
• /
• pp.389-395
• /
• 2024

This study aims to deeply analyze the military strategies and tactics used in the battles between Israel and Hamas, to understand the military approaches, technical capabilities, and their impact on the outcomes of the conflict. To achieve this, methodologies such as literature review, data analysis, and case studies were utilized. The research findings confirm that Hamas employed asymmetric tactics, such as rocket attacks and surprise attacks through underground tunnels, to counter Israel's military superiority. On the other hand, Israel responded to Hamas's attacks with the Iron Dome interception system and intelligence-gathering capabilities, but faced difficulties due to Hamas's underground tunnel network. After six months of fighting, the casualties in the Gaza Strip exceeded 30,000, and more than 1.7 million people became refugees. Israel also suffered over 1,200 deaths. Militarily, neither side achieved a decisive victory, resulting in a war of attrition. This study suggests that the Israel-Hamas war exemplifies the complexity of modern asymmetric warfare. Furthermore, it recommends that political compromise between the two sides and active mediation efforts by the international community are necessary for the peaceful resolution of the Israel-Palestine conflict.

• Journal of Radiation Industry
• /
• v.18 no.3
• /
• pp.183-193
• /
• 2024

As part of the social response to the radon bed incident in 2018, the Nuclear Safety and Security Commission took measures to collect and dispose of all radon beds. The Waste Management Act provides landfill disposal as one of the disposal methods for natural radioactive product waste, which is one of the NORM wastes. When NORM wastes are landfilled, workers and the public at the landfill site are exposed to radiation through various pathways, such as leaching of radionuclides through soil and groundwater, and multiple exposure factors are involved simultaneously. In order to improve the reliability of radiological impact assessment, the values of main exposure factors should be selected more accurately. Therefore, before developing the main exposure factors for site characteristics, it is necessary to prioritize main exposure factors reflecting domestic characteristics of NORM waste landfills. Therefore, in this study, the main exposure factors for NORM waste landfill were derived using NDD analysis. To derive the main exposure factors, the analysis tool was first selected as RESRAD-ONSITE computer code, and the exposure scenarios were mainly selected as a resident farmer and suburban resident scenario, recreation scenario, and industrial worker scenario. Then, the priority 1 and 2 factors were selected for sensitivity analysis, and a Korean standard model was established to reflect Korean characteristics. Finally, the sensitivity analysis was conducted through NDD, and the main exposure factors were derived based on this. In the resident farmer scenario, the contaminated zone distribution coefficients of ²²⁶Ra, ²¹⁰Pb, ²³²Th, ²²⁸Ra, ²³⁴U, and ²³⁸U, as well as precipitation and evapotranspiration factors, were derived as the main exposure factors. In the suburban resident scenario, the contaminated zone distribution coefficients of ²²⁶Ra, ²¹⁰Pb, ²³²Th, ²²⁸Ra, ²³⁴U, and ²³⁸U, as well as precipitation and evapotranspiration coefficients, were derived as the main exposure factors. In the recreation scenario, the contaminated zone distribution coefficient of ²³²Th was derived as the main exposure factor. For the industrial worker scenario, the erosion rate was derived as the main exposure factor. The main exposure factors for each scenario were analyzed to be different depending on the scenario characteristics. The results of this study can be utilized as a basis for radiological environmental impact assessment of NORM waste landfill in Korea.

• Journal of Navigation and Port Research
• /
• v.48 no.4
• /
• pp.335-341
• /
• 2024

Recently, research, development, and commercialization of maritime autonomous surface ships (MASS) and remote control are in progress. Remote control is intended to secure autonomous navigation environments for existing ships or early-stage MASS using a remote control system (RCS). The main function of an RCS is to control MASS using data transmission between the MASS and the remote control centre. Remote control by a remote control officer also has an important function. The purpose of this study was to develop RCS and a performance evaluation technique for operation data provided by the RCS. The experiment was conducted during the navigation period of a training ship 'Hannara' after building experimental equipment at both an onshore remote control center and a training ship. As a result of evaluating data transmitted and received using the developed RCS, it was confirmed that data transmission was possible within an error range of 0.1%p. Fourteen types of ship information reflecting the navigation environment of the training ship were confirmed to be transmitted and received. The RCS developed in this work complies with the three principles of remote control: safety, reliability, and availability. This study provides a core technology for the development of RCSs for MASS and the evaluation of data transmission performance.

• The Journal of the Convergence on Culture Technology
• /
• v.10 no.5
• /
• pp.827-832
• /
• 2024

The AI program Sora is a video production model that can be used innovatively and is the starting point of a major paradigm shift in video planning and production in the future. In this paper, through consideration of the characteristics, application, and process of the AI video production program, the characteristics of the AI design video production method were understood, and the production algorithm was considered. The detailed consideration and characteristics of the work creation process for the video graphic AI video generation program that will be intensified every year were examined. Next, the method of generating a customized video with a text prompt and the process of innovative production results different from the previous production method were considered. In addition, the design direction through the generation of AI images was studied through the review of the strengths and weaknesses of the image details of the recently announced AI music video results. By considering the security of the AI generation video Sora and looking at the internal process of the actual AI process, it will be possible to present indicators for the future direction of AI video model production and education along with the direction of the design designer and education system. In the text and conclusion, we analyzed the strengths and weaknesses and future status of OpenAI Sora image, concluded how to apply the Sora model's capabilities, limitations, quality, and human creativity, and presented problems and alternatives through examples of the Sora model's capabilities and limitations to increase human creativity.

• The Journal of the Convergence on Culture Technology
• /
• v.10 no.5
• /
• pp.219-227
• /
• 2024

The rapidly changing security environment and technological innovations of the 21st century present new challenges to military organizations. Particularly, as the MZ generation, comprised of Millennials (born 1981-1996) and Generation Z (born 1997-2012), emerges as the primary workforce in the military, traditional military personnel management methods are being called into question. The MZ generation, as digital natives, are technologically proficient, prioritize personal growth and quality of life, and prefer horizontal communication and participation. The purpose of this study is to reestablish talent acquisition and retention strategies for military organizations, considering the characteristics and demands of the MZ generation. To this end, we analyzed advanced talent management techniques from the corporate sector and explored ways to apply them to the unique context of military organizations. Additionally, by examining the current status and challenges of the Korean military, we attempted a balanced approach that considers both global trends and Korea's specific circumstances. The research results suggest various strategies including career development programs, cultural innovation, improvement of reward systems, participatory decision-making, enhancement of digital competencies, and creation of flexible work environments. These strategies are expected to improve the efficiency and competitiveness of military organizations while simultaneously enhancing job satisfaction and organizational commitment among MZ generation service members.

• The Journal of the Convergence on Culture Technology
• /
• v.10 no.5
• /
• pp.153-161
• /
• 2024

This study proposes improvements to the personnel management system for military officers in South Korea, addressing challenges posed by rapidly changing security environments and population decline due to low birth rates. The research identifies key issues in the current system, including lack of predictability in long-term service selection, limited opportunities for professional development, uncertainties in post-retirement careers, rigid organizational culture, and inadequate responses to demographic changes. To address these issues, the study analyzes personnel management practices in foreign militaries, including the United States, United Kingdom, and Israel, deriving valuable insights. Based on this analysis, the research suggests several improvement measures: enhancing predictability in long-term service selection, providing tailored job transition support for different military specialties, and expanding personnel exchanges between military and civilian sectors. Specific recommendations include clarifying long-term service selection criteria, introducing a phased selection system, strengthening connections between military specialties and civilian job sectors, expanding support for professional certifications, and increasing personnel exchange programs with public institutions and private companies. The study also outlines necessary legal and institutional reforms, strategies for securing and allocating budgets, and a phased implementation plan. The research proposes amendments to the Military Personnel Management Act, legislation for supporting retired military personnel, and the introduction of a performance-based budget management system. A systematic implementation plan is presented, divided into short-term, medium-term, and long-term phases.