• The Journal of the Korea Contents Association
• /
• v.21 no.1
• /
• pp.531-540
• /
• 2021

As cyber attacks and crimes increase exponentially and hacking attacks become more intelligent and advanced, hacking attack methods and routes are evolving unpredictably and in real time. In order to reinforce the enemy's responsiveness, this study aims to propose a method for developing an artificial intelligence-based security control platform by building a next-generation security system using artificial intelligence to respond by self-learning, monitoring abnormal signs and blocking attacks.The artificial intelligence-based security control platform should be developed as the basis for data collection, data analysis, next-generation security system operation, and security system management. Big data base and control system, data collection step through external threat information, data analysis step of pre-processing and formalizing the collected data to perform positive/false detection and abnormal behavior analysis through deep learning-based algorithm, and analyzed data Through the operation of a security system of prevention, control, response, analysis, and organic circulation structure, the next generation security system to increase the scope and speed of handling new threats and to reinforce the identification of normal and abnormal behaviors, and management of the security threat response system, Harmful IP management, detection policy management, security business legal system management. Through this, we are trying to find a way to comprehensively analyze vast amounts of data and to respond preemptively in a short time.

• Journal of Wetlands Research
• /
• v.26 no.3
• /
• pp.197-203
• /
• 2024

The algal blooms in rivers can negatively affect water source management and water treatment processes, necessitating continuous management. In this study, a multi-classification model was developed to predict the concentration of chlorophyll-a (chl-a), one of the key indicators of algal blooms, using Tabular Prior Fitted Networks (TabPFN), a novel deep learning algorithm known for its relatively superior performance on small tabular datasets. The model was developed using daily observation data collected at Buyeo water quality monitoring station from January 1, 2014, to December 31, 2022. The collected data were averaged to construct input data sets with measurement frequencies of 1 day, 3 days, 6 days, 12 days. The performance comparison of the four models, constructed with input data on observation frequencies of 1 day, 3 days, 6 days, and 12 days, showed that the model exhibits stable performance even when the measurement frequency is longer and the number of observations is smaller. The macro average for each model were analyzed as follows: Precision was 0.77, 0.76, 0.83, 0.84; Recall was 0.63, 0.65, 0.66, 0.74; F1-score was 0.67, 0.69, 0.71, 0.78. For the weighted average, Precision was 0.76, 0.77, 0.81, 0.84; Recall was 0.76, 0.78, 0.81, 0.85; F1-score was 0.74, 0.77, 0.80, 0.84. This study demonstrates that the chl-a prediction model constructed using TabPFN exhibits stable performance even with small-scale input data, verifying the feasibility of its application in fields where the input data required for model construction is limited.

• Journal of Wetlands Research
• /
• v.24 no.3
• /
• pp.204-212
• /
• 2022

The LID technique began to be applied in Korea after 2009, and LID facilities are installed and operated for rainwater management in business districts such as the Ministry of Environment, the Ministry of Land, Infrastructure and Transport, and LH Corporation, public institutions, commercial land, housing, parks, and schools. However, looking at domestic cases, the application cases and operation periods are insufficient compared to those outside the country, so appropriate design standards and measures for operation and maintenance are insufficient. In particular, LID facilities constructed using LID techniques need to maintain the environment inside LID facilities because hydrological and environmental effects are expressed by material circulation and energy flow. The LID facility is designed with the treatment capacity planned for the water circulation target, and the proper maintenance, vegetation, and soil conditions are periodically identified, and the efficiency is maintained as much as possible. In other words, the soil created in LID is a very important design element because LID facilities are expected to have effects such as water pollution reduction, flood reduction, water resource acquisition, and temperature reduction while increasing water storage and penetration capacity through water circulation construction. In order to maintain and manage the functions of LID facilities accurately, the current state of the facilities and the cycle of replacement and maintenance should be accurately known through various quantitative data such as soil contamination, snow removal effects, and vegetation criteria. This study was conducted to investigate the current status of LID facilities installed in Korea from 2009 to 2020, and analyze soil changes through the continuity and current status of LID facilities applied over the past 10 years after collecting soil samples from the soil layer. Through analysis of Saturn, organic matter, hardness, water contents, pH, electrical conductivity, and salt, some vegetation-type LID facilities more than 5 to 7 years after construction showed results corresponding to the lower grade of landscape design. Facilities below the lower level can be recognized as a point of time when maintenance is necessary in a state that may cause problems in soil permeability and vegetation growth. Accordingly, it was found that LID facilities should be managed through soil replacement and replacement.

• Korean Journal of Heritage: History & Science
• /
• v.44 no.1
• /
• pp.106-121
• /
• 2011

The number of World Natural Heritage Sites is smaller than that of World Cultural Heritage Sites. As of 2010, the total number of natural sites was 180, which is less than 1/3 of all cultural sites. The reason why the number of natural sites is smaller can be attributed to the evaluating criteria of OUV(outstanding universal value). Only 9 fossil related sites were designated as World Heritage Sites among 180 Natural Sites. This study compares their OUVs including the academic value and characteristics of the 9 World Heritage Sites to provide data and reference for KCDC(Korean Cretaceous Dinosaur Coast) to apply as a World Natural Heritage Site. This study was carried out to obtain information and data on the Wadi Al-Hitan of Egypt which was designated as a World Natural Heritage Site. The study includes field investigation for whale fossils, interviews of site paleontologists and staff, and inspections of facilities. Three factors can likely be attributed to its successful management and operating system. First, there is a system for comprehensive research and a monitoring plan. Secondly, experts have been recruited and hired and professional training for staff members has been done properly. Finally, the Wadi Al-Hitan has developed local resources with specialized techniques for conservation and construction design, which matched well with whale fossils and the environment at the site. The Wadi Al-Hitan put a master plan into practice and achieved goals for action plans. To designate a future World Natural Heritage Site in Korea, it is important to be recognized by international experts including IUCN specialists as the best in one's field with OUV. Full-time regular-status employees for a research position are necessary from the preparation stage for the UNESCO World Heritage Site. Local government and related organizations must do their best to control monitoring plans and to improve academic value after the UNESCO World Heritage Site designation. As we experienced during the designation process of Jeju Volcanic Island and Lava Tubes as the first Korean World Natural Heritage Site, participation by various scholars and specialists need to be in harmony with active endeavors from local governments and NGOs.

• Korean Journal of Environmental Agriculture
• /
• v.38 no.4
• /
• pp.273-280
• /
• 2019

BACKGROUND: The reclaimed lands for agricultural use managed by the Korean government is consisted of 17,145 hectares of lands under construction and 13,384 hectares of completed lands. In order to utilize these reclaimed lands as competitive agricultural complexes, the government is preparing to develop comprehensive development plans for multiple purposes. For rational land-use planning and soil management, information of the soil chemical properties is necessary. METHODS AND RESULTS: From 2013 to 2016, soil samples were collected from 85 representative sampling sites of the reclaimed lands and analyzed for soil chemical properties including electric conductivity (EC), pH, soil organic matter (SOM), and nutrients. The annual mean soil EC ranged from 5.1 to 8.3 dS m^-1 and have continued to decrease over the years (estimation equation with EC as dependent and year as independent variable was y =0.0736x² - 1.4985x + 9.8305, R² = 0.9753). The pH ranged from 7.3 to 7.6, which was higher than the optimum range (5.5~7.0) for agricultural soils. Soil organic matter (8 to 11 g kg^-1) was lower level than the optimum range (20~30 kg^-1). Available silicate (Av.SiO₂) ranged from 169 to 229 mg kg^-1, which was close to the minimum content (≥157 mg kg^-1) for rice paddy field. Available phosphate (Av.P₂O₅) content (24~39 mg kg^-1) was lower than the optimum range (80~120 mg kg^-1) for rice paddy field. CONCLUSION: For efficient agricultural use of reclaimed lands under government management, our results suggest that the application of organic matter and supplying deficient nutrients as well as desalinization is required.

• Korean Journal of Environment and Ecology
• /
• v.20 no.3
• /
• pp.340-344
• /
• 2006

The objective of this paper was to investigate the potential of road-crossing structures as biological corridors that can overcome wildlife habitat fragmentation caused by road construction. Snow tracking on animal trace adjacent to and under bridges, underpasses, and culverts of eight rural highways in Korea was carried out. A total 89 structures were monitored and the results follow. First, the probability of road crossing increases with the increasing cross sectional size of crossing structures. Second, small to medium sized carnivores such as raccoon dog, leopard cat, and Siberian weasel use all types of structures. Finally, water deer, or large herbivore crossed only under bridges. Consequently, further studies are necessary to identify suitable types of road crossing structures that can mitigate the probability of road-kills and habitat fragmentation of water deer.

• Journal of the Korean Association of Geographic Information Studies
• /
• v.12 no.1
• /
• pp.73-80
• /
• 2009

Recently in order to mange better life quality much effort was spent for environmental-friendly urban development project and environmental restoration project. During these projects, there should be deep understanding about atmospheric environment change analysis and long term monitoring so that it would be helpful for better environment promotion such as heat island mitigation effect and wind way construction. In this study, the surface temperature environment change between before and after Cheonggye Stream Restoration Project was mapped and analyzed by using ASTER(Advanced Spaceborne Thermal Emission Reflection Radiometer) TIR(Thermal Infrared) satellite imagery and finally the fact, that the heat island effect was mitigated, was clarified. For this study, the correlation analysis was conducted through comparing the difference between atmosphere temperature of AWS(Automatic Weather System) and surface temperature of ASTER. Furthermore, this study will be the infrastructure of urban meteorology model development by understanding surface temperature pattern change and executing quantitative analysis of heat island.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.25 no.3
• /
• pp.279-286
• /
• 2015

The rapid increase of the current marine accidents is mainly due to the human execution errors. In an effort to address this, various kinds of researches such as construction of the digital vessels and vessel information monitoring systems have been conducted. But for safe navigation of vessels, it lack on systems study which can efficiently store, utilize and manage the mass data accepted by the vessel. In this paper, we propose a VWS(Virtual World System) that is based on the architecture of intelligent systems RVC(Reactive Layer-Virtual World-Considerative Layer) model of intelligent autonomous navigation system. VWS is responsible to store all the necessary information for safe navigation of the vessel and the information services to the sub-system of intelligent autonomous navigation system. VWS uses topology database to express the specific problem area, and utilizes a scheduling to reflect the characteristics of the real-time processing environment. Also, Virtual World defines API for the system to reflect the characteristics of the distributed processing environment. As a case study, the VWS is applied to a intelligent ship autonomous navigation system, and simulation is done to prove the effectiveness of the proposed system.

• Analytical Science and Technology
• /
• v.27 no.2
• /
• pp.108-113
• /
• 2014

The harmful materials as volatile organic compounds (VOCS) that is easy for gas to be changed from liquid on ambient temperature, those should be controlled by Korea Chemicals Management Association. The VOCs samples should be collected directly in place so that those could be analyzed. Generally but it couldn't avoid to have the risk of analyst. Moreover, if there is the place limited to entrance, it is impossible to collect directly and measure. Owing to such problem, it tried to be solved by open path FT-IR spectrometer that could be studied on the combustion gases within long path and VOCs samples were tried to measure to large volume by remote and real time. Firstly, it was to investigate optimized measured length between the system and benzene sample of VOCs. As result, The optimized measured length was confirmed with 15 meter length and the qualitative analysis could be measured on seven VOC samples. The calibration curve as quantitative analysis of benzene samples could be worked. On the basis of the result, the system as remote monitor could show to have potentiality.

• Journal of the Microelectronics and Packaging Society
• /
• v.14 no.1
• /
• pp.49-53
• /
• 2007

The direct methanol fuel cell (DMFC) is a promising power source for portable applications due to many advantages such as simple construction, compact design, high energy density, and relatively high energy-conversion efficiency. In this work, an electrochemical methanol sensor for monitoring the methanol concentration in direct methanol fuel cells was fabricated using a thin composite nafion membrane as the electrolyte. We have analyzed the I-V characteristic of the fabricated methanol sensor as a function of methanol concentration, catalyst electrode and platinum(Pt) thickness. The fabricated sensor was analyzed by I-V measurement with various methanol concentration. When we measured the sensor characteristics with 10nm Pt and at 1V, the current value was $1.30{\times}10^{-6}A,\;1.96{\times}10^{-6}A\;and\;2.80{\times}10^{-6} A$ for three methanol concentration of 1M, 2M and 3M, respectively. When the methanol concentration was fixed at 2M, the current value of the fabricated device with Pt layers of 5, 10 and 15 nm thickness was $3.06{\times}10^{-6}A,\;1.96{\times}10^{-6}A\;and\;1.00{\times}10^{-6}A$, respectively. These results lead us to the conclusion that when the methanol concentration increases, the output current increases and when the catalyst electrode become thinner, the current increase more. It showed that, the thinner the catalyst electrode, the more electrochemistry become activation.