• Proceedings of the Korean Institute of Navigation and Port Research Conference
• /
• 2012.10a
• /
• pp.49-50
• /
• 2012

This paper investigates the mandatory minimum requirements for certification of officers in charge of a navigational watch on ship specified in the international convention of STCW. The training education and evaluation systems for navigational competence of Korean navy were compared and analyzed. The paper suggests adjustment of the evaluation range, increment of evaluation items, diversification of evaluation types, differentiation of certification-related education by officer's commissioning program in order to improve the PQS system.

• Proceedings of the Korean Society of Computer Information Conference
• /
• 2019.07a
• /
• pp.381-382
• /
• 2019

Recently, various search techniques using artificial intelligence techniques have been introduced. It is also possible to use the artificial intelligence to grasp customer propensity. Analyzing the clothes that customers usually wear, it is possible to analyze various colors such as favorite colors, patterns, and fashion styles. In this study, we use artificial intelligence technology to create an application that distinguish between adults and children by combining various factors such as shape, type, color and size of human clothes. Through this, it will be possible to utilize it in a living area where children can be protected in advance by grasping the intrusion of unauthorized adults in the living area where children live mainly. In addition, in the future, we can obtain good results to detect stranger adult person if we apply this experimental result to the detection system using clothing information.

• The Bulletin of The Korean Astronomical Society
• /
• v.44 no.1
• /
• pp.82.3-82.3
• /
• 2019

In this study, we generate future full disk magnetograms in 12, 24, 36 and 48 hours advance from SDO/HMI images using deep learning. To perform this generation, we apply the convolutional generative adversarial network (cGAN) algorithm to a series of SDO/HMI magnetograms. We use SDO/HMI data from 2011 to 2016 for training four models. The models make AI-generated images for 2017 HMI data and compare them with the actual HMI magnetograms for evaluation. The AI-generated images by each model are very similar to the actual images. The average correlation coefficient between the two images for about 600 data sets are about 0.85 for four models. We are examining hundreds of active regions for more detail comparison. In the future we will use pix2pix HD and video2video translation networks for image prediction.

• Journal of information and communication convergence engineering
• /
• v.20 no.4
• /
• pp.295-302
• /
• 2022

This paper contains the development of a smart power device designed to collect load power data from industrial manufacturing machines, predict future variations in load power data, and detect abnormal data in advance by applying a machine learning-based prediction algorithm. The proposed load power data prediction model is implemented using a Long Short-Term Memory (LSTM) algorithm with high accuracy and relatively low complexity. The Flask and REST API are used to provide prediction results to users in a graphical interface. In addition, we present the results of experiments conducted to evaluate the performance of the proposed approach, which show that our model exhibited the highest accuracy compared with Multilayer Perceptron (MLP), Random Forest (RF), and Support Vector Machine (SVM) models. Moreover, we expect our method's accuracy could be improved by further optimizing the hyperparameter values and training the model for a longer period of time using a larger amount of data.

• International Journal of Advanced Culture Technology
• /
• v.11 no.4
• /
• pp.464-469
• /
• 2023

As modern society develops, the number of diseases caused by bad smells is increasing. As it can harm people's health, it is important to predict in advance the extent to which bad smells may occur, inform the public about this, and take preventive measures. In this paper, we propose a hybrid neural network structure of CNN and LSTM that can be used to detect or predict the occurrence of odors, which are most required in manufacturing or real life, using odor complex sensors. In addition, the proposed learning model uses a complex odor sensor to receive four types of data, including hydrogen sulfide, ammonia, benzene, and toluene, in real time, and applies this data to the inference model to detect and predict the odor state. The proposed model evaluated the prediction accuracy of the training model through performance indicators based on accuracy, and the evaluation results showed an average performance of more than 94%.

• Electronics and Telecommunications Trends
• /
• v.39 no.4
• /
• pp.21-31
• /
• 2024

Major global powers are investing heavily in artificial intelligence (AI) and hyper-connected networks, demonstrating their crucial role in future warfare. To advance and utilize AI in national defense, it is essential to have policy support at the governmental or national level. This includes establishing a research and development infrastructure, creating a common development environment, and fostering AI expertise through education and training programs. To achieve advancements in hyper-connected networks, it is essential to establish a foundation for a robust and resilient infrastructure by comprehensively building integrated satellite, aerial, and ground networks, along with developing 5G & edge computing and low-orbit satellite communication technologies. This multi-faceted approach will ensure the successful integration of AI and hyper-connected networks, strengthening national defense and positioning nations at the forefront of technological advancements in warfare.

• The Journal of the Convergence on Culture Technology
• /
• v.4 no.1
• /
• pp.299-306
• /
• 2018

As recent Jecheon and Milyang fire cases show, the need for fire disaster training to prepare for a fire disaster continues to grow. In the event of a disaster, people become mentally confused and are called disaster personalities. In order to survive in a disaster, it is necessary to develop the power to overcome the disaster personality by experiencing the disaster situation in advance. Therefore, training to overcome disaster personality is needed, and virtual reality can be a good training means in that it can experience without physical space. In addition, periodic actual disaster evacuation drills should be carried out to compensate for the shortcomings of virtual reality. In order to introduce fire disaster drill using virtual reality and to spread it to the public, the Korea National VR project should be introduced which benchmarked national PC project which succeeded in the past informatization project. Besides, the Korea National Safety Point system should be integrated to cover disaster preparedness training and building reinforcement. If the national VR project and the national safety point system are introduced successfully, Korea will be the basis for escaping the disgraceful nickname of 'disaster republic'.

• Journal of the Korean Society of Fisheries and Ocean Technology
• /
• v.41 no.2
• /
• pp.156-164
• /
• 2005

The size of the ship's turning circle is influenced by various factors, such as block coefficient, underwater side shape, rudder area ratio, draft, trim and Froude's number. Most of them are already fixed on departure from a port. However, the ship's speed and the rudder angle are controllable factors which operations are able to change optionally during sailing. The DGPS measured the turning circles according to the ship's speed and the rudder angle. The maximum advances by slow and full ahead were 302m and 311m, and the maximum transfers were 460m and 452m, respectively. There occurs almost no difference in size of the turning circle by variation of the ship's speeds. When the rudder angles were changed to $10^{\circ}$, $20^{\circ}$ and $30^{\circ}$, the maximum advances were 447m, 271m and 202m, and then also the maximum transfers 657m, 426m and 285m, respectively. The diameter of the tuning circle was decreased exponentially when the rudder angle was increased. The maneuverability was better when the direction of turning and propulsion of propeller are in the opposite direction rather than in the same one togetherm. The distance of the maximum transfer was always bigger than that of the maximum advance.

• Journal of the Society of Disaster Information
• /
• v.5 no.1
• /
• pp.78-100
• /
• 2009

This study is to protect peoples' life, minimize the property damage by coping with threats quickly and take more preventive measures in advance against nuclear bomb, CBR, and potential explosive. For this, CBRNE(Chemical, Biological, Radiological, Nuclear, Explosive) program research was used. Thanks to advance in technology, terrorist groups and even individuals make or keep nuclear and CBR weapons. And also it's likely that disaster and threats from a toxic gas, acute pathogens, accidents in the nuclear power plants and a high explosive could be happened a lot. Recently more organized terrorist groups maintain random attacks for unspecified individuals and also it's highly likely that a large-scale terrorist attack by WMD and CBRNEwill be done. To take strict measures against CBRNE attacks by terrorists is on the rise as an urgent national task. Moreover biological weapons are relatively easy and inexpensive to obtain or produce and cause mass casualties with a small amount. For this reason, more than 25 countries have already possessed them. In the 21 st century, the international safety environment marks the age of complicated threats : transnational threats such as comprehensive security and terror, organized crime, drug smuggling, illegal trade of weapons of mass destruction, and environmental disruption along with traditional security threats. These cause military threats, terror threats, and CBRNE threats in our daily life to grow. Therefore it needs to come up with measures in such areas as research development, policy, training program. Major industrial nations on CBRNE like USA, Canada, Switzerland, and Israel have implemented various educational programs. These researches could be utilized as basic materials for drawing up plans for civil defense, emergency services and worldwide countermeasures against CBRNE.

• Atmosphere
• /
• v.33 no.2
• /
• pp.297-306
• /
• 2023

Celebrating its 60th anniversary, this study suggests the future vision of the Korean Meteorological Society (KMS) for the next 60 years. The vision is "to advance atmospheric science and technology that contributes to human society as well as protect people from not only climate change risks but also weather, climate, and environmental disasters". Based on the suggestions from its members, this study proposes the KMS future development plan as follows. The first plan is to strengthen in leading the development and growth of atmospheric sciences in Korea, especially to improve weather, climate, and environment forecasts and to reduce uncertainty in future climate projections. The second is to enhance interaction not only among its members in academy, Korea Meteorological Administration and related organizations, meteorological industry, and science communicators but also with other related fields such as energy, water resources, agriculture, fishery, and forestry. The third is to enhance in nurturing young scientists by supporting domestic and international networks and training the state-of-the-art sciences, and to create opportunities for young scientists to advance into a wider field. The last is to expand its international activities for solving the challenges facing mankind, such as climate change risks and weather, climate, and environment disasters. The KMS should also continue the efforts to establish an integrative platform for leading fundamental and interdisciplinary research in weather, climate, and environment.