• Journal of Intelligence and Information Systems
• /
• v.27 no.3
• /
• pp.57-73
• /
• 2021

Maintenance and prevention of failure through anomaly detection of ICT infrastructure is becoming important. System monitoring data is multidimensional time series data. When we deal with multidimensional time series data, we have difficulty in considering both characteristics of multidimensional data and characteristics of time series data. When dealing with multidimensional data, correlation between variables should be considered. Existing methods such as probability and linear base, distance base, etc. are degraded due to limitations called the curse of dimensions. In addition, time series data is preprocessed by applying sliding window technique and time series decomposition for self-correlation analysis. These techniques are the cause of increasing the dimension of data, so it is necessary to supplement them. The anomaly detection field is an old research field, and statistical methods and regression analysis were used in the early days. Currently, there are active studies to apply machine learning and artificial neural network technology to this field. Statistically based methods are difficult to apply when data is non-homogeneous, and do not detect local outliers well. The regression analysis method compares the predictive value and the actual value after learning the regression formula based on the parametric statistics and it detects abnormality. Anomaly detection using regression analysis has the disadvantage that the performance is lowered when the model is not solid and the noise or outliers of the data are included. There is a restriction that learning data with noise or outliers should be used. The autoencoder using artificial neural networks is learned to output as similar as possible to input data. It has many advantages compared to existing probability and linear model, cluster analysis, and map learning. It can be applied to data that does not satisfy probability distribution or linear assumption. In addition, it is possible to learn non-mapping without label data for teaching. However, there is a limitation of local outlier identification of multidimensional data in anomaly detection, and there is a problem that the dimension of data is greatly increased due to the characteristics of time series data. In this study, we propose a CMAE (Conditional Multimodal Autoencoder) that enhances the performance of anomaly detection by considering local outliers and time series characteristics. First, we applied Multimodal Autoencoder (MAE) to improve the limitations of local outlier identification of multidimensional data. Multimodals are commonly used to learn different types of inputs, such as voice and image. The different modal shares the bottleneck effect of Autoencoder and it learns correlation. In addition, CAE (Conditional Autoencoder) was used to learn the characteristics of time series data effectively without increasing the dimension of data. In general, conditional input mainly uses category variables, but in this study, time was used as a condition to learn periodicity. The CMAE model proposed in this paper was verified by comparing with the Unimodal Autoencoder (UAE) and Multi-modal Autoencoder (MAE). The restoration performance of Autoencoder for 41 variables was confirmed in the proposed model and the comparison model. The restoration performance is different by variables, and the restoration is normally well operated because the loss value is small for Memory, Disk, and Network modals in all three Autoencoder models. The process modal did not show a significant difference in all three models, and the CPU modal showed excellent performance in CMAE. ROC curve was prepared for the evaluation of anomaly detection performance in the proposed model and the comparison model, and AUC, accuracy, precision, recall, and F1-score were compared. In all indicators, the performance was shown in the order of CMAE, MAE, and AE. Especially, the reproduction rate was 0.9828 for CMAE, which can be confirmed to detect almost most of the abnormalities. The accuracy of the model was also improved and 87.12%, and the F1-score was 0.8883, which is considered to be suitable for anomaly detection. In practical aspect, the proposed model has an additional advantage in addition to performance improvement. The use of techniques such as time series decomposition and sliding windows has the disadvantage of managing unnecessary procedures; and their dimensional increase can cause a decrease in the computational speed in inference.The proposed model has characteristics that are easy to apply to practical tasks such as inference speed and model management.

• Korean Journal of Ecology and Environment
• /
• v.46 no.1
• /
• pp.33-40
• /
• 2013

From March 2012 to January 2013, this study was conducted as a part of the project for making a precise electronic ecological zoning map of vegetation on a highly reduced scale of 1 to 5,000 with a view to improving management efficiency of national parks and enlarging the availability of the data produced from the basic research monitoring the resources of national parks. For the research accuracy and rapidity, a vegetation map was specially created for the on-the-site-vegetation research. To make the map more meticulous, we categorized the vegetation database into five groups: broadleaved forest, coniferous forest, mixed forest, rock vegetation and miscellaneous one. After comparing the results of the data built for the vegetation research and the actual research findings, it was made clear that vegetation of both categories was almost the same in case of broad-leaved forest with 72.20% and 78.45% respectively, and also equivalent in other groups like, for example, coniferous forest (16.70%, 13.41%), mixed forest (9.50%, 7.49%) and rock vegetation (0.60%, 0.15%). According to the precise vegetation map produced from the research, the deciduous broad-leaved forest was the most widely prevalent type in the correlated hierarchical classification of vegetation, occupying 65.78% of the overall vegetation. It was followed by mountain valley forest (15.17%), coniferous forest (10.90%), and plantation forest (7.00%) in order. It is particularly noteworthy that Mt. Deogyusan national park has retained a very stable and versatile forest vegetation in the outstanding state since approximately 20% of the mountain turns out to belong to the I grade vegetation conservation classification which contains climax forests, unique vegetation, subalpine vegetation, matured stands which are older than 50 years and etc.

• Korean Journal of Heritage: History & Science
• /
• v.44 no.2
• /
• pp.4-25
• /
• 2011

This study was performed in 2010 to examine the flora and vegetation structure and chemical characteristics of soil in the growing community of Abeliophyllum distichum, located in the Byeonsanbando National Park. This Abeliophyllum distichum community has more individual numbers in Cheongrim-ni and Jungkye-ri, Byeonsan-myeon, and Buan-gun area, which is designated as a Natural Monument (No. 370), and also where the habitat conditions for Abeliophyllum distichum is more favorable. The authors recorded 100 taxa with 45 families, 82 genus, 93 species, 4 varieties, and 3 forms. Among them, species such as Abeliophyllum distichum (critically endangered), Asarum maculatum (near threatened) and Chionanthus retusa (near threatened), which are categorized as rare plants, were recorded. According to the list of Korean endemic plants, 4 taxa, particularly Philadelphus schrenckii, Abeliophyllum distichum, Weigela subsessilis, and Lonicera subsessili, were recorded. The community of Abeliophyllum distichum is located in the northwest slope of Baekcheon watershed and the community is comprised of healthy soil. The community structure was classified into three: the Castanea crenata community, Zelkova serrata community, and Quercus serrata community. The Castanea crenata community is composed of the Cornus walteri, Platycarya strobilacea, Zelkova serrata, Rhamnella frangulioides, arranged in terms of importance percentage. The Zelkova serrata community is composed of Celtis sinensis, Quercus aliena, Styrax japonica, and Acer pseudo-sieboldianum, also according to importance percentage. As for the Quercus serrata community, it is composed of Quercus variabilis, Castanea crenata, and Prunus sargentii, also arranged in terms of importance percentage. The importance percentage of Abeliophyllum distichum is 6.6% in the Castanea crenata community, 5.6% in the Zelkova serrata community and 5.1% in the Quercus serrata community. Moreover, in order of chemical characteristics of soil pH, electrical conductivity, available phosphoric, organic matter, and exchangeable cation (K, Ca, Mg) are analyzed. The No. 3 site was relatively higher than other districts of the same chemical characteristics of soil.

• Ecology and Resilient Infrastructure
• /
• v.9 no.1
• /
• pp.68-76
• /
• 2022

In this study, the Habitat Suitability Index (HSI) was calculated in the Miho stream of the Geum river system, and the environmental ecological flow by point was evaluated. Two points (St.3 and St.8) representing the up and downstream of Miho Stream were selected, in order to calculate the Habitat Suitability Index, the depth and velocity at point where each species is appeared were investigated. The Habitat Suitability Index (HSI) was calculated by the Washington Department of Fish and Wildlife (WDFW) method using the number collected by water depth and velocity section and the results of the flow rate survey. Two target species were selected in this study; dominant species and swimming species sensitive to flow. In the case of a single species of Zacco platypus, the water depth was 0.1 - 0.5 m and the velocity was 0.2 - 0.5 m/s. For species of swimming fish, the water depth was 0.2 - 0.5 m and the velocity was 0.2 - 0.5 m/s. The discharge-Weighted Useable Area (WUA) relationship curve and habitat suitability distribution were simulated at the Miho Stream points St.3 and St.8. At the upstream St.3 of Miho Stream, the optimal discharge was simulated as 4.0 m³/s for swimming fishes and 2.7 m³/s for Zacco platypus. At the downstream point of St.8, species of swimming fish were simulated as 8.8 m³/s and Zacco platypus was simulated as 7.6 m³/s. In both points, the optimal discharge of swimming fish was over estimated. This is a result that the Habitat Suitability Index for swimming fish requires a faster flow rate than the habitat conditions of the Zacco platypus. In the calculation of the minimum discharge, the discharge of Zacco platypus is smaller and is evaluated to provide more Weighted Useable Area. In the case of swimming fishes, narrow range of depth and velocity increases the required discharge and relatively decreases the Weighted Useable Area. Therefore, when calculating the Habitat Suitability Index for swimming fishes, it is more advantageous to calculate the index including the habitat of all fish species than to narrow the range.

• Journal of the Korean Society of Marine Environment & Safety
• /
• v.27 no.7
• /
• pp.987-994
• /
• 2021

The Yellow sea, as described in article 123 of UNCLOS, is semi-enclosed sea surrounded by the Republic of Korea, the People's Republic of China and North Korea. In addition, the Yellow Sea is one of the 66 large marine ecosystems as it contains large amounts of marine resources. According to article 194 of UNCLOS, states should be aware of rights and duties with respect to the protection and preservation of the marine environment to be engaged with countries directly as regional entity or indirectly. Therefore, the legal blank is urgent in terms of trans-boundary environmental pollutant issues. The UNDP has conducted a project called Yellow Sea Large Marine Ecosystem (YSLME) which has reached the 2^nd phase. The project has some notable achievements, namely performing joint activities on analysis of diagnostic trans-boundary issues in collaboration with China and South Korea, developing a strategic action plan based on TDA, and establishing regional strategic action plan. However, on the other hand, the project could not reflect the full participation of North Korea as a state party. As a result, the project has a limitation on effective implementation of RSAP. Therefore, this study focuses on the suggestion of a legally-binding trilateral treaty as a blue print for the next, 3^rd phase of the project. By analyzing the best practice of the Wadden Sea Trilateral Treaty case, the study verifies the validity of legislative measures on establishing and managing a legally-binding trilateral YSLME Commission. By suggesting a three phase treaty, incorporating a joint declaration by establishing the commission, the signing of the treaty, and formulating an umbrella convention and implementation arrangement, the study expects to guarantee the consistency and sustainability of the trilateral treaty regardless of political issues pertaining to North Korea.

• Proceedings of the KSEEG Conference
• /
• 2001.05b
• /
• pp.42-63
• /
• 2001

The detail survey on the Songsanri tomb site including the Muryong royal tomb was carried out during the period from May 1 , 1996 to April 30, 1997. A quantitative analysis was tried to find changes of tomb itself since the excavation. Main subjects of the survey are to find out the cause of infiltration of rain water and groundwater into the tomb and the tomb site, monitoring of the movement of tomb structure and safety, removal method of the algae inside the tomb, and air controlling system to solve high humidity condition and dew inside the tomb. For these purposes, detail survery inside and outside the tombs using a electronic distance meter and small airplane, monitoring of temperature and humidity, geophysical exploration including electrical resistivity, geomagnetic, gravity and georadar methods, drilling, measurement of physical and chemical properties of drill core and measurement of groundwater permeability were conducted. We found that the center of the subsurface tomb and the center of soil mound on ground are different 4.5 meter and 5 meter for the 5th tomb and 7th tomb, respectively. The fact has caused unequal stress on the tomb structure. In the 7th tomb (the Muryong royal tomb), 435 bricks were broken out of 6025 bricks in 1972, but 1072 bricks are broken in 1996. The break rate has been increased about 250% for just 24 years. The break rate increased about 290% in the 6th tomb. The situation in 1996 is the result for just 24 years while the situation in 1972 was the result for about 1450 years. Status of breaking of bircks represents that a severe problem is undergoing. The eastern wall of the Muryong royal tomb is moving toward inside the tomb with the rate of 2.95 mm/myr in rainy season and 1.52 mm/myr in dry season. The frontal wall shows biggest movement in the 7th tomb having a rate of 2.05 mm/myr toward the passage way. The 6th tomb shows biggest movement among the three tombs having the rate of 7.44mm/myr and 3.61mm/myr toward east for the high break rate of bricks in the 6th tomb. Georadar section of the shallow soil layer represents several faults in the top soil layer of the 5th tomb and 7th tomb. Raninwater flew through faults tnto the tomb and nearby ground and high water content in nearby ground resulted in low resistance and high humidity inside tombs. High humidity inside tomb made a good condition for algae living with high temperature and moderate light source. The 6th tomb is most severe situation and the 7th tomb is the second in terms of algae living. Artificial change of the tomb environment since the excavation, infiltration of rain water and groundwater into the tombsite and bad drainage system had resulted in dangerous status for the tomb structure. Main cause for many problems including breaking of bricks, movement of tomb walls and algae living is infiltration of rainwater and groundwater into the tomb site. Therefore, protection of the tomb site from high water content should be carried out at first. Waterproofing method includes a cover system over the tomvsith using geotextile, clay layer and geomembrane and a deep trench which is 2 meter down to the base of the 5th tomb at the north of the tomv site. Decrease and balancing of soil weight above the tomb are also needed for the sfety of tomb structures. For the algae living inside tombs, we recommend to spray K101 which developed in this study on the surface of wall and then, exposure to ultraviolet light sources for 24 hours. Air controlling system should be changed to a constant temperature and humidity system for the 6th tomb and the 7th tomb. It seems to much better to place the system at frontal room and to ciculate cold air inside tombs to solve dew problem. Above mentioned preservation methods are suggested to give least changes to tomb site and to solve the most fundmental problems. Repairing should be planned in order and some special cares are needed for the safety of tombs in reparing work. Finally, a monitoring system measuring tilting of tomb walls, water content, groundwater level, temperature and humidity is required to monitor and to evaluate the repairing work.