• Economic and Environmental Geology
• /
• v.7 no.3
• /
• pp.123-152
• /
• 1974

The study focused to the so called "Yangpyeong Igneous Complex" which intruded into the Gyeong Gi gneiss complex of Pre-cambrian basement of Yangpyeong area. The geologic sequence of the mapped area was shown in table 1. In laboratory work, 31 modal analyses and 7 chemical analyses on the rock samples taken from the igneous complex have been made to discuss the nomenclature of the rocks and the petrological relationship between rock types. The petrographical and petrochemical features based on the analyses are as follow; 1) The classification of this rocks based on the systematics of igneous rocks of IUGS showed that Yangpyeong Igneous complex consist of hornblende gabbro, diorite and porphyritic monzonite. The major rock forming minerals in hornblende gabbro are hornblende and plagiodase ($An_{46{\sim}55}$), in diorite, hornblende, biotite and plagioclase ($An_{23{\sim}33}$) and in porphyritic monzonite, K-feldspar, plagioclase ($An_{21{\sim}35}$), hornblende and biotite. Hornblende gabbro and diorite show coarse to medium grained hypidiomorphic granular texture and porphyritic monzonite was named by the characteristically porphyritic texture of K-feldspar phenocrysts. 2) Silica-oxides variation diagram (Fig.4) illustrate that the igneous complex is similar ttl that of Daly's average basalt-andesite-dacite-rhyolite and equivalent to the calc-alkalic rock series of Peacock's rock series. In AMF diagram (Fig. 5), the trend of the igneous complex is nearly pararell to that of the Skaergaard intrusion which shows the trend of the fractional crystalization of magma. 3) In normative Or-Ab-An diagram (Fig. 6) the general trend of the data points from gabbro to porphyritic monzonite of the igneous complex directs to a point of Or/Ab=1:1 on the side of Or-Ab. The field and laboratory evidences suggested that the Yangpyeong igneous complex was thought to be a series of comagmatic differential products.

• Journal of the Korea Institute of Information Security & Cryptology
• /
• v.29 no.4
• /
• pp.785-794
• /
• 2019

Recently Deep Learning technology, one of the fourth industrial revolution technologies, is used to identify the hidden meaning of network data that is difficult to detect in the security arena and to predict attacks. Property and quality analysis of data sources are required before selecting the deep learning algorithm to be used for intrusion detection. This is because it affects the detection method depending on the contamination of the data used for learning. Therefore, the characteristics of the data should be identified and the characteristics selected. In this paper, the characteristics of malware were analyzed using network data set and the effect of each feature on performance was analyzed when the deep learning model was applied. The traffic classification experiment was conducted on the comparison of characteristics according to network characteristics and 96.52% accuracy was classified based on the selected characteristics.

• Journal of Soil and Groundwater Environment
• /
• v.27 no.6
• /
• pp.22-36
• /
• 2022

Water resources in Jeju Island are dependent virtually entirely on groundwater. For groundwater resources, drought damage can cause environmental and economic losses because it progresses slowly and occurs for a long time in a large area. Therefore, this study quantitatively evaluated groundwater level fluctuations using principal component and cluster analyses for 42 monitoring wells in Jeju Island, and further identified the types of groundwater fluctuations caused by drought. As a result of principal component analysis for the monthly average groundwater level during 2005-2019 and the daily average groundwater level during the dry season, it was found that the first three principal components account for most of the variance 74.5-93.5% of the total data. In the cluster analysis using these three principal components, most of wells belong to Cluster 1, and seasonal characteristics have a significant impact on groundwater fluctuations. However, wells belonging to Cluster 2 with high factor loadings of components 2 and 3 affected by groundwater pumping, tide levels, and nearby surface water are mainly distributed on the west coast. Based on these results, it is expected that groundwater in the western area will be more vulnerable to saltwater intrusion and groundwater depletion caused by drought.

• International Journal of Computer Science & Network Security
• /
• v.23 no.3
• /
• pp.49-56
• /
• 2023

Machine learning methods diversely applied to the Internet of Things (IoT) field have been successful due to the enhancement of computer processing power. They offer an effective way of detecting malicious intrusions in IoT because of their high-level feature extraction capabilities. In this paper, we proposed a novel feature selection method for malicious intrusion detection in IoT by using an evolutionary technique - Genetic Algorithm (GA) and Machine Learning (ML) algorithms. The proposed model is performing the classification of BoT-IoT dataset to evaluate its quality through the training and testing with classifiers. The data is reduced and several preprocessing steps are applied such as: unnecessary information removal, null value checking, label encoding, standard scaling and data balancing. GA has applied over the preprocessed data, to select the most relevant features and maintain model optimization. The selected features from GA are given to ML classifiers such as Logistic Regression (LR) and Support Vector Machine (SVM) and the results are evaluated using performance evaluation measures including recall, precision and f1-score. Two sets of experiments are conducted, and it is concluded that hyperparameter tuning has a significant consequence on the performance of both ML classifiers. Overall, SVM still remained the best model in both cases and overall results increased.

• Journal of the Korea Institute of Information Security & Cryptology
• /
• v.33 no.3
• /
• pp.411-425
• /
• 2023

Today, AI (Artificial Intelligence) technology is widely used in various fields, performing classification and regression tasks according to the purpose of use, and research is also actively progressing. Especially in the field of security, unexpected threats need to be detected, and unsupervised learning-based anomaly detection techniques that can detect threats without adding known threat information to the model training process are promising methods. However, most of the preceding studies that provide interpretability for AI judgments are designed for supervised learning, so it is difficult to apply them to unsupervised learning models with fundamentally different learning methods. In addition, previously researched vision-centered AI mechanism interpretation studies are not suitable for application to the security field that is not expressed in images. Therefore, In this paper, we use a technique that provides interpretability for detected anomalies by searching for and comparing optimization references, which are the source of intrusion attacks. In this paper, based on reference, we propose additional logic to search for data closest to real data. Based on real data, it aims to provide a more intuitive interpretation of anomalies and to promote effective use of an anomaly detection model in the security field.

• Convergence Security Journal
• /
• v.17 no.3
• /
• pp.41-49
• /
• 2017

According to a research by global IT market research institute IDC, CSIM(Converged Security Information Management) market of Korea was estimated to be 1.7 trillion KRW in 2010, and it has grown approximately 32% every year since. IDC forcasts this size to grow to 12.8 trillion KRW by 2018. Moreover, this case study exemplifies growing importance of CSIM market worldwide. Traditional CSIM solution consists of various security solutions(e.g. firewall, network intrusion detection system, etc.) and devices(e.g. CCTV, Access Control System, etc.). With this traditional solution, the the data collected from these is used to create events, which are then used by the on-site agents to determine and handle the situation. Recent development of IoT industry, however, has come with massive growth of IoT devices, and as these can be used for security command and control, it is expected that the overall amount of event created from these devices will increase as well. While massive amount of events could help determine and handle more situations, this also creates burden of having to process excessive amount of events. Therefore, in this paper, we discuss potential events that can happen in CSIM system and classify them into 3 groups, and present a model that can categorize and process these events effectively to increase overall efficieny of CSIM system.

• Journal of the Korean Geotechnical Society
• /
• v.30 no.5
• /
• pp.25-35
• /
• 2014

The sedimentary rocks exposed around Mt. Palgong were subjected to metamorphism due to a granitic magma intrusion at late Cretaceous, and they eventually metamorphosed to hornfels by the action of both hydrothermal solution and high temperature supplied from the magma. The hornfels zone around the granite body ranges from 2.0 to 3.5 km in width but the boundary between hornfels and sedimentary rocks is not obviously defined because the metamorphic grade gradually decreases with distance from the granite boundary. A series of laboratory tests on 350 core specimens made by 35 fresh rock blocks obtained from 5 selected locations around Mt. Palgong are performed to verify the variation of physical and mechanical properties related to metamorphic grade of the rock. Water content and absorption ratio of the hornfels linearly increase with distance to the granite boundary whereas dry unit weight, p-wave velocity, point load strength, and slake durability index linearly decrease with the distance. These results imply that the metamorphic grade of the hornfels also linearly decrease with the distance to granite boundary. Empirical equations for the variation of properties with the distance to granite boundary and relationship between a property and another one are deduced by regression analyses. And a criteria for classification of hornfels exposed in the study area based on the P-wave velocity and point load strength is proposed.

• Journal of the Korea Institute of Information Security & Cryptology
• /
• v.30 no.4
• /
• pp.617-629
• /
• 2020

In order to overcome the limitations of the rule-based intrusion detection system due to changes in Internet computing environments, the emergence of new services, and creativity of attackers, network anomaly detection (NAD) using machine learning and deep learning technologies has received much attention. Most of these existing machine learning and deep learning technologies for NAD use supervised learning methods to learn a set of training data set labeled 'normal' and 'attack'. This paper presents the feasibility of the unsupervised learning AutoEncoder(AE) to NAD from data sets collecting of secured network traffic without labeled responses. To verify the performance of the proposed AE mode, we present the experimental results in terms of accuracy, precision, recall, f1-score, and ROC AUC value on the NSL-KDD training and test data sets. In particular, we model a reference AE through the deep analysis of diverse AEs varying hyper-parameters such as the number of layers as well as considering the regularization and denoising effects. The reference model shows the f1-scores 90.4% and 89% of binary classification on the KDDTest+ and KDDTest-21 test data sets based on the threshold of the 82-th percentile of the AE reconstruction error of the training data set.

• The Korean Journal of Petroleum Geology
• /
• v.7 no.1_2 s.8
• /
• pp.28-34
• /
• 1999

The Cretaceous Poongam sedimentary Basin in Kangwon-do, Korea consists alluvial deposits of conglomerates, sandstones, mudstones or siltstones, and volcaniclastics. The Poongam Basin was formed as a fault margin sag or a transpressional basin developed along a strike-slip fault zone, and received huge amount of clastic sediments from the adjacent fault-scaip. It formed an aggrading alluvial fan system and a volcaniclast-supplied marginal lake environment, while tectonic activity and volcanism attenuated toward the end of basin formation. Following the Folk's classification, the sandstones of the Poongam Basin are identified as lithic wackes or feldspathic wackes. The areal and sequential variation of the mineral composition in the sandstones is not distinct. The results of K-Ar age dating from the intruding andesites, volcaniclastics and volcanic fragments in sedimentary rocks show a range of 70 Ma to 84 Ma. It suggests that volcarism occurred sequentially within a relatively short period as the pre-, syn-, and post-depositional events. It was the short period in the late Cretaceous that the basin had evolved i.e., the basin formation, the sediment input and fill, and the , intrusion and extrusion of volcanic rocks occurred. The Poongam sedimentary sequence is a typical tectonic-controlled coarse sedimentary facies which is texturally immature.

• Journal of Internet Computing and Services
• /
• v.18 no.1
• /
• pp.65-75
• /
• 2017

The Detection Model is the model to find the result of a certain purpose using artificial intelligent, data mining, intelligent algorithms In Cyber Security, it usually uses to detect intrusion, malwares, cyber incident, and attacks etc. There are an amount of unlabeled data that are collected in a real environment such as security data. Since the most of data are not defined the class labels, it is difficult to know type of data. Therefore, the label determination process is required to detect and analysis with accuracy. In this paper, we proposed a KDFL(K-means and D-S Fusion based Labeling) method using D-S inference and k-means(unsupervised) algorithms to decide label of data records by fusion, and a detection model architecture using a proposed labeling method. A proposed method has shown better performance on detection rate, accuracy, F1-measure index than other methods. In addition, since it has shown the improved results in error rate, we have verified good performance of our proposed method.