• Journal of Intelligence and Information Systems
• /
• v.29 no.1
• /
• pp.377-396
• /
• 2023

As the cryptocurrency market continues to grow, it has developed into a new financial market. The need for investment strategy research on the cryptocurrency market is also emerging. This study aims to conduct an empirical analysis on an investment methodology of cryptocurrency that combines short-term trading strategy and deep learning. Daily price data of the Ethereum was collected through the API of Upbit, the Korean cryptocurrency exchange. The investment performance of the experimental model was analyzed by finding the optimal parameters based on past data. The experimental model is a volatility breakout strategy(VBS), a Long Short Term Memory(LSTM) model, moving average cross strategy and a combined model. VBS is a short-term trading strategy that buys when volatility rises significantly on a daily basis and sells at the closing price of the day. LSTM is suitable for time series data among deep learning models, and the predicted closing price obtained through the prediction model was applied to the simple trading rule. The moving average cross strategy determines whether to buy or sell when the moving average crosses. The combined model is a trading rule made by using derived variables of the VBS and LSTM model using AND/OR for the buy conditions. The result shows that combined model is better investment performance than the single model. This study has academic significance in that it goes beyond simple deep learning-based cryptocurrency price prediction and improves investment performance by combining deep learning and short-term trading strategies, and has practical significance in that it shows the applicability in actual investment.

• Journal of Radiation Protection and Research
• /
• v.26 no.2
• /
• pp.79-86
• /
• 2001

This study presents the quantitative exposure assessment of indoor radon released from groundwater. Most of the Indoor radon comes directly from soil beneath the basement or foundation. Recently, radon in groundwater releases to indoor air whenever the water is used and contributes to the total inhalation risk from indoor air. This study first develops a mathematical model to describe the transfer and distribution of radon released from groundwater in a house. Then, daily human exposures through inhalation or such radon are estimated with the model for an male adult based on two sets of exposure scenarios. The results obtained from the study would help increase the understanding of risk assessment issues associated with the indoor radon released from groundwater.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2007.06a
• /
• pp.794-798
• /
• 2007

As the development of information technology and thus the growth of security incidents, so implement are coming out for defense the intrusion about the system. However the error detection program has got a difficulty to find out the intrusions because that has become so many false alert messages. In this study is how to reduce the messages for the false alerts which come from the internal of the network and using the Fuzzy techniques for reduce the uncertainty of the judge. Therefore it makes the model which can decrease false alert message for better detection.

• Journal of Radiation Protection and Research
• /
• v.36 no.2
• /
• pp.99-106
• /
• 2011

Tritium is the one of the most important radionuclide for workers in nuclear power plants (NPPs) and the public, from the dosimetric point of view. Humans are likely to have internal radiation exposure by tritium inhalation. Radiation exposure by tritium accounts for approximately 7% and 60~90% of the total radiation exposure of NPP workers and the public during normal operation, respectively. Thus, many researches have been conducted to estimate the internal dose by tritium precisely in the world. In terms of tritium dosimetry, this paper provides the current status of research for tritium metabolism and dosimetry.

• Journal of Digital Convergence
• /
• v.11 no.11
• /
• pp.675-682
• /
• 2013

This paper tries to solve the problems which previous methods have the model using smart card for protecting digital contents. This study provides a contents distribution model to protect the rights of author, distributor, and user as well as user's information by using technologies such as cryptography, DRM(Digital Right Management), access control, etc. The proposed system is evaluated as the most safety model compared with previous methods because it not only solves the problems which the previous methods have, but also protects four type of risks such as use of contents which other mobile devices download, the attack on the key to decode the message, the attack on leaking the contents, and the internal attack such as an illegal reproduction.

• Journal of Radiation Protection and Research
• /
• v.17 no.2
• /
• pp.49-59
• /
• 1992

A new model was developed in order to investigate the effects of chelating agents on the migration of a radionuclide in the form of ion or chelate. The migration behavior of the chelated radionuclide was analyzed by formulating a convective-dispersion transport equation which included a degradation of chelating agent and chelated radionuclide. The mathematical model was analytically solved and checked with the existing retardation factor. The results show that the migration velocity of the chelated radionuclide was much faster than the ionic one due to the decreased retardation. Therefore, it was concluded that a new remedial action should be developed to reduce the generation and release of chelating agents from the nuclear power plant into the environment.

• Annual Conference of KIPS
• /
• 2018.05a
• /
• pp.145-148
• /
• 2018

클라우드 컴퓨팅 기반 사물인터넷 환경은 급격히 증가하는 통신량, 기종 간 이질성, 지연 시간과 같은 문제점으로 인해 어려움을 겪고 있다. 이를 해결하기 위한 대표적인 방법 중 하나는 분산 모델을 통해 클라우드 컴퓨팅 환경에 집중된 네트워크 또는 컴퓨팅 파워를 분산시키는 포그 컴퓨팅 (Fog Computing) 또는 에지 컴퓨팅 (Edge Computing)을 활용하는 것이다. 그러나 이 분산형 네트워크의 단점을 보완하기 위해 사물인터넷 (IoT, Internet of Things)과 가장 가까이 존재하는 네트워크 모델로써 미스트 컴퓨팅 (Mist Computing)이 탄생하였다. 그러나 다양한 프로토콜에 의해 통신이 이루어지는 사물인터넷 환경에는 수천 가지 제로데이 공격이 존재한다. 이 공격들의 대부분은 이전에 알려진 공격의 작은 변형체이다. 이러한 공격을 효과적으로 막기 위해 사물인터넷 환경에서의 침입 탐지 시스템은 지능적이어야 한다. 따라서 본 논문에서는, 미스트 컴퓨팅 환경에서 새로운 또는 지속적으로 변화하는 사물인터넷 대상 공격을 효과적으로 방어하기 위한 인공지능 기반 침입 탐지 시스템을 제안한다.

• Journal of Radiation Protection and Research
• /
• v.8 no.2
• /
• pp.41-46
• /
• 1983

Annual collective dose within 50 miles radius of Ko-ri I reactor site due to normal airborne effluent discharges in 1979 has been estimated by AIRDOS-EPA computer code. Gaussian plume equation is used for estimation of both horizontal and vertical dispersion of radionuclide release into the atmosphere. Also, radionuclide concentrations in meat, milk, and fresh produce consumed by near-by population are estimated by coupling the output of the atmospheric transport models with the USNRC terrestrial food chain models. Annual collective doses are found to be $3.348{\times}10^{-1}$ whole body manrem and 84.95 thyroid manrem. Whole body manrem calculated by AIRDOS-EPA computer code do not differ greatly from that calculated by GASPAR computer code, but value for thyroid manrem have been estimated lower than that calculated by GASPAR computer code.

• Journal of Radiation Protection and Research
• /
• v.33 no.4
• /
• pp.167-172
• /
• 2008

Recently a high-quality voxel model of a Korean adult male was constructed at Hanyang University by using very high resolution serially-sectioned anatomical images of a cadaver, which was provided by the Korean Institute of Science and Technology Information (KISTI). Most existing voxel phantoms are developed based on an individual in the supine posture. This study converted the HDRK-Man voxel model into surface model and adjusted the flattened back of the HDRK-Man to a normal shape in the upright posture using 3D graphic softwares such as $3D-DOCTOR^{TM}$, $Rapidform^{(R)}$2006, $Rhinoceros^{(R)}$4.0, $MAYA^{(R)}$8.5. The effective doses of adjusted model were compared with those of unadjusted model for some standard irradiation geometries (i.e., AP, PA, LLAT, RLAT). In general, the differences were not very large and, among those, the largest difference was found for the PA radiation geometry, as expected. These methodologies can be used for the development of various deformed posture models of HDRK-Man in the later stage of this project.

• Journal of Radiation Protection and Research
• /
• v.22 no.4
• /
• pp.273-288
• /
• 1997

A three dimensional sea-land breeze model and Lagrangian particle dispersion model have been employed for the study on the mesoscale atmospheric dispersion of radioactive materials released from Wolsung NPPs. In this study, atmospheric dispersion simulations are carried out under two synoptic weather conditions : the geostrophic flow is a weak northerly wind(CASE 1) and a strong northerly wind(CASE 2) on a clear day in spring. The results show that atmospheric dispersion is affected by sea-land breeze and the recirculation of particles by the change of wind direction between sea breeze and land breeze plays an important role in atmospheric concentration distribution of radoactive materials.