• Journal of the Korea Society of Computer and Information
• /
• v.26 no.12
• /
• pp.69-75
• /
• 2021

Recently, deep learning, which is the most used in the field of artificial intelligence, has a structure that is gradually becoming larger and more complex. As the deep learning model grows, a large amount of data is required to learn it, but there are cases in which it is difficult to integrate and learn the data because the data is distributed among several owners and security issues. In that situation we conducted parallel learning for each users that own data and then studied how to integrate it. For this, distributed learning was performed for each owner assuming the security situation as V-environment and H-environment, and the results of distributed learning were integrated using Average, Max, and AbsMax. As a result of applying this to the mnist-fashion data, it was confirmed that there was no significant difference from the results obtained by integrating the data in the V-environment in terms of accuracy. In the H-environment, although there was a difference, meaningful results were obtained.

• Journal of Environmental Science International
• /
• v.32 no.8
• /
• pp.595-611
• /
• 2023

The purpose of this study is to improve the daily prediction results of PM2.5 from the air quality diagnosis and evaluation system operated by the Busan Institute of Health and Environment in real time. The air quality diagnosis and evaluation system is based on the photochemical numerical model, CMAQ (Community multiscale air quality modeling system), and includes a 3-day forecast at the end of the model's calculation. The photochemical numerical model basically has limitations because of the uncertainty of input data and simplification of physical and chemical processes. To overcome these limitations, this study applied DNN (Deep Neural Network), a deep learning technique, to the results of the numerical model. As a result of applying DNN, the r of the model was significantly improved. The r value for GFS (Global forecast system) and UM (Unified model) increased from 0.77 to 0.87 and 0.70 to 0.83, respectively. The RMSE (Root mean square error), which indicates the model's error rate, was also significantly improved (GFS: 5.01 to 6.52 ug/m³ , UM: 5.76 to 7.44 ug/m³ ). The prediction results for each concentration grade performed in the field also improved significantly (GFS: 74.4 to 80.1%, UM: 70.0 to 77.9%). In particular, it was confirmed that the improvement effect at the high concentration grade was excellent.

• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.23 no.6
• /
• pp.61-67
• /
• 2023

The rise of 5G and the proliferation of smart devices have underscored the significance of multi-access edge computing (MEC). Amidst this trend, interest in effectively processing computation-intensive and latency-sensitive applications has increased. This study investigated a novel task offloading strategy considering the probabilistic MEC environment to address these challenges. Initially, we considered the frequency of dynamic task requests and the unstable conditions of wireless channels to propose a method for minimizing vehicle power consumption and latency. Subsequently, our research delved into a deep reinforcement learning (DRL) based offloading technique, offering a way to achieve equilibrium between local computation and offloading transmission power. We analyzed the power consumption and queuing latency of vehicles using the deep deterministic policy gradient (DDPG) and deep Q-network (DQN) techniques. Finally, we derived and validated the optimal performance enhancement strategy in a vehicle based MEC environment.

• Journal of the Korean Society of Environmental Restoration Technology
• /
• v.26 no.6
• /
• pp.85-96
• /
• 2023

This study proposes a method for forest vegetation monitoring using high-resolution aerial imagery captured by unmanned aerial vehicles(UAV) and deep learning technology. The research site was selected in the forested area of Mountain Dogo, Asan City, Chungcheongnam-do, and the target species for monitoring included Pinus densiflora, Quercus mongolica, and Quercus acutissima. To classify vegetation species at the pixel level in UAV imagery based on characteristics such as leaf shape, size, and color, the study employed the semantic segmentation method using the prominent U-net deep learning model. The research results indicated that it was possible to visually distinguish Pinus densiflora Siebold & Zucc, Quercus mongolica Fisch. ex Ledeb, and Quercus acutissima Carruth in 135 aerial images captured by UAV. Out of these, 104 images were used as training data for the deep learning model, while 31 images were used for inference. The optimization of the deep learning model resulted in an overall average pixel accuracy of 92.60, with mIoU at 0.80 and FIoU at 0.82, demonstrating the successful construction of a reliable deep learning model. This study is significant as a pilot case for the application of UAV and deep learning to monitor and manage representative species among climate-vulnerable vegetation, including Pinus densiflora, Quercus mongolica, and Quercus acutissima. It is expected that in the future, UAV and deep learning models can be applied to a variety of vegetation species to better address forest management.

• Economic and Environmental Geology
• /
• v.56 no.4
• /
• pp.421-433
• /
• 2023

The final disposal of spent nuclear fuel(SNF) from nuclear power plants takes place in a deep geological repository. The metal canister encasing the SNF is made of cast iron and copper, and is engineered to effectively isolate radioactive isotopes for a long period of time. The SNF is further shielded by a multi-barrier disposal system comprising both engineering and natural barriers. The deep disposal environment gradually changes to an anaerobic reducing environment. In this environment, sulfide is one of the most probable substances to induce corrosion of copper canister. Stress-corrosion cracking(SCC) triggered by sulfide can carry substantial implications for the integrity of the copper canister, potentially posing a significant threat to the long-term safety of the deep disposal repository. Sulfate can exist in various forms within the deep disposal environment or be introduced from the geosphere. Sulfate has the potential to be transformed into sulfide by sulfate-reducing bacteria(SRB), and this converted sulfide can contribute to the corrosion of the copper canister. Bentonite, which is considered as a potential material for buffering and backfilling, contains oxidized sulfate minerals such as gypsum(CaSO4). If there is sufficient space for microorganisms to thrive in the deep disposal environment and if electron donors such as organic carbon are adequately supplied, sulfate can be converted to sulfide through microbial activity. However, the majority of the sulfides generated in the deep disposal system or introduced from the geosphere will be intercepted by the buffer, with only a small amount reaching the metal canister. Pyrite, one of the potential sulfide minerals present in the deep disposal environment, can generate sulfates during the dissolution process, thereby contributing to the corrosion of the copper canister. However, the quantity of oxidation byproducts from pyrite is anticipated to be minimal due to its extremely low solubility. Moreover, the migration of these oxidized byproducts to the metal canister will be restricted by the low hydraulic conductivity of saturated bentonite. We have comprehensively analyzed and summarized key research cases related to the presence of sulfates, reduction processes, and the formation and behavior characteristics of sulfides and pyrite in the deep disposal environment. Our objective was to gain an understanding of the impact of sulfates and sulfides on the long-term safety of high-level radioactive waste disposal repository.

• Journal of the Korean Society of Surveying, Geodesy, Photogrammetry and Cartography
• /
• v.37 no.2
• /
• pp.45-53
• /
• 2019

RGB-D SLAM (Simultaneous Localization and Mapping) refers to the technology of using deep camera as a visual sensor for SLAM. In view of the disadvantages of high cost and indefinite scale in the construction of maps for laser sensors and traditional single and binocular cameras, a method for creating three-dimensional map of indoor environment with deep environment data combined with RGB-D SLAM scheme is studied. The method uses a mobile robot system equipped with a consumer-grade RGB-D sensor (Kinect) to acquire depth data, and then creates indoor three-dimensional point cloud maps in real time through key technologies such as positioning point generation, closed-loop detection, and map construction. The actual field experiment results show that the average error of the point cloud map created by the algorithm is 0.0045m, which ensures the stability of the construction using deep data and can accurately create real-time three-dimensional maps of indoor unknown environment.

• Proceedings of the Korean Society of Soil and Groundwater Environment Conference
• /
• 2005.10a
• /
• pp.265-266
• /
• 2005

• Journal of the Korean Society of Marine Environment & Safety
• /
• v.5 no.2
• /
• pp.79-86
• /
• 1999

This study aims at improving the channel of Pudo-sudo in Chinhae-Man according to the development project of the port of Masan, by investigating the design criteria of harbour facilities for the maximum sized ship. The new deep-water route was proposed and according to it the present separation scheme was adjusted appropriately. The width of the deep-water route is suggested to be 350m and would be wide enough for the 30,000 DWT container ship to go through However, the proposed channel will be tested and validated by the shiphandling simulator.

• Proceedings of the Korea Committee for Ocean Resources and Engineering Conference
• /
• 2003.10a
• /
• pp.329-332
• /
• 2003

Aquaculture have been important role to supply food resources for mankind. However, competitive power of domestic mariculture industry was declined due to increase of labor and feed expenditures, and quantity import of low-priced livefishes from the developing underdeveloped nations in North and South East Asia. Mass production and quality enhancement can be pointed out to overcome such an industrial environment in this decade. To meet these requirement, movable mariculture base remodeling feasible vessel of chemical tanker or crude oil carrier has been proposed for more advanced mariculture management system by using deep seawater from about 200m which is sustainablely clean, nutrient-rich and cold seawater. Deep seawater can be applied for control of seawater temperature for mariculture base and cultivation phytoplankton and seaweed as feed. Besides mariculture, strategic marketing can be implemented by raw water and ice of deep seawater. Feasibility of applying deep seawater was considered after evaluating general movable mariculture base and management system.

• Journal of Distribution Science
• /
• v.20 no.11
• /
• pp.121-129
• /
• 2022

Purpose: Artificial intelligence is widely used, particularly in the popular neural network theory called Deep learning. The improvement of computing speed and capability expedited the progress of Deep learning applications. The application of Deep learning in education has various effects and possibilities in creating and managing educational content and services that can replace human cognitive activity. Among Deep learning, Deep fake technology is used to combine and synchronize human faces with voices. This paper will show how to develop e-Learning content videos using those technologies and open-source tools. Research design, data, and methodology: This paper proposes 4 step development process, which is presented step by step on the Google Collab environment with source codes. This technology can produce various video styles. The advantage of this technology is that the characters of the video can be extended to any historical figures, celebrities, or even movie heroes producing immersive videos. Results: Prototypes for each case are also designed, developed, presented, and shared on YouTube for each specific case development. Conclusions: The method and process of creating e-learning video contents from the image, video, and audio files using Deep fake open-source technology was successfully implemented.