• KIPS Transactions on Software and Data Engineering
• /
• v.10 no.7
• /
• pp.271-278
• /
• 2021

As the current cyber attacks become more intelligent, the existing Intrusion Detection System is difficult for detecting intelligent attacks that deviate from the existing stored patterns. In an attempt to solve this, a model of a deep learning-based intrusion detection system that analyzes the pattern of intelligent attacks through data learning has emerged. Intrusion detection systems are divided into host-based and network-based depending on the installation location. Unlike network-based intrusion detection systems, host-based intrusion detection systems have the disadvantage of having to observe the inside and outside of the system as a whole. However, it has the advantage of being able to detect intrusions that cannot be detected by a network-based intrusion detection system. Therefore, in this study, we conducted a study on a host-based intrusion detection system. In order to evaluate and improve the performance of the host-based intrusion detection system model, we used the host-based Leipzig Intrusion Detection-Data Set (LID-DS) published in 2018. In the performance evaluation of the model using that data set, in order to confirm the similarity of each data and reconstructed to identify whether it is normal data or abnormal data, 1D vector data is converted to 3D image data. Also, the deep learning model has the drawback of having to re-learn every time a new cyber attack method is seen. In other words, it is not efficient because it takes a long time to learn a large amount of data. To solve this problem, this paper proposes the Siamese Convolutional Neural Network (Siamese-CNN) to use the Few-Shot Learning method that shows excellent performance by learning the little amount of data. Siamese-CNN determines whether the attacks are of the same type by the similarity score of each sample of cyber attacks converted into images. The accuracy was calculated using Few-Shot Learning technique, and the performance of Vanilla Convolutional Neural Network (Vanilla-CNN) and Siamese-CNN was compared to confirm the performance of Siamese-CNN. As a result of measuring Accuracy, Precision, Recall and F1-Score index, it was confirmed that the recall of the Siamese-CNN model proposed in this study was increased by about 6% from the Vanilla-CNN model.

• Journal of Physiology & Pathology in Korean Medicine
• /
• v.21 no.1
• /
• pp.250-257
• /
• 2007

Uterus myoma is a benign tumor of smooth muscle in the wall of the uterus, In oriental medicine, we used to made an effort to management this patients without surgical operation. Doctors have treated patients of uterus myoma mainly by checking over each symptom they have. Then we think that patients have some symptoms in relation to an etiological cause. So I have carried out this study to investigate association of DSOM scores and an attack of uterus myoma in oriental medicine. We chose 3 groups, the first one is 257 uterus myoma patients who visited Dongeui University Oriental Medical Center from May 2001 to June 2006, the second one is 558 outpatients who didn't have uterus myoma from May 2005 to June 2005, the third one is 129 clinical trials who volunteered for Sasang constitutional medicine. Then we made up 3 groups to checkup DSOM, and investigated the All DSOM Fluents which effect uterus myoma patients using regression model. Logistic regression analysis indicate as follows ; In comparison with 558 outpatients data, blood stasis(血瘀), dryness(燥) is associated positively and insufficiency of Yang(陽虛), spleen(脾), phlegm(痰) negatively, and mean of the index for pathogenic factor(病機指標 平均) of deficiency of qi(氣虛), heart(心) negatively. In comparison with 129 clinical trials data, blood stasis(血瘀) is associated positively and phlegm(痰) negatively, and mean of the index for pathogenic factor(炳機指標 平均) of deficiency of Yin(陰虛), liver(肝), diarrhea positively, heart(心) negatively. 3. In investigation of DSOM items, items of blood stasis(血瘀), deficiency of Yin(陰虛), coldness(寒) is associated positively and items of heart(心), spleen(脾), Phlegm(痰) negatively.

• Journal of Navigation and Port Research
• /
• v.30 no.1 s.107
• /
• pp.97-104
• /
• 2006

Recently the first stage qf construction for Busan new port emerged over the sea surface at the north container terminal site. With this, there are lot of discussions and debates on increasing the water depth at the approaching channel and mooring basin from the existing 15m to 18m by dredging work in order to be able to serve 12,000TEU containership, and at the same time, correction to the reclamation plan of hinterland at the part of Undong Bay qf the new port site. Since the attack of typhoon 'Maemi' in 2003, it is expected that the design wave parameters for coastal and harbor structures in this area would be somewhat changed and so the extreme wave condition at each terminal and tranquility of berthing area does, and therefore, it is necessary to analyze the tranquility at each berth Hence in this study, we constructed a wave model for these conditions and performed simulation together with the circulation model simulation, compared with the field data collected The result showed the increase of the harbor response throughout the basin but not severe condition However, a certain location needs to be prepared for the rough sea condition when a severe typhoon hit the site.

• 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 Rehabilitation Nursing
• /
• v.1 no.1
• /
• pp.111-123
• /
• 1998

The related factors of the quality of life (QOL) in stroke patients was identified empirically. The subjects were 254 stroke patients who were discharged and taken follow-up care at the outpatient department. In this model, the physical, psychological, and social status were assumed to affect the QOL. And the social support was assumed to moderate these effects. NIH stroke state, ADL, and IADL were used to measure the physical status. Using CES-D, the psychological status was measured. The social status was defined as the job change after stroke attack. The satisfaction with the care by primary caregivers, significant others, and health professionals was measured as the social support. To identify the effect of the physical, psychological, and social status on the QOL, multiple regression analysis was carried out. The psychological and social status were found to be the significant predictors of the QOL(R2=0.27, p=0.00). Next, to identify the moderating effect of the social support, the subjects were divided into two groups, that is, the low social support group and the high social support group. It is found that the predicting variance is different between these two groups. In the low social support group, the psychological, social, and physical status predicted as much as 42% of the QOL. On the contrary, the psychological status predicted only 8% of the QOL in the high social support group. So it is concluded that the social support moderates the effects of the physical, psychological, and social status on QOL. Finally, to identify the social support which moderates those effects, the social support was divided into three classes. Each social support class was divided into the low and high social support group again. In the every class of social support, the difference between two groups was also identified. So the model of the QOL is recommended for the framework of the care for the stroke patients. Also these results support the claim that the long-term facilities for stroke patients are necessary.

• Proceedings of the Korean Institute of Navigation and Port Research Conference
• /
• 2005.10a
• /
• pp.117-124
• /
• 2005

Recently the first stage of construction for Busan new port emerged over the sea surface at the north container terminal site. With this, there are lot of discussions and debates on increasing the water depth at the approaching channel and mooring basin from the existing 15m to 18m by dredging work in order to be able to serve 12,000TEU containership, and at the same time, correction to the reclamation plan of hinterland at the part of Undong Bay of the new port site. Since the attack of typhoon 'Maemi' in 2003, it is expected that the design wave parameters for coastal and harbor structures in this area would be somewhat changed and so the extreme wave condition at each terminal and tranquility of berthing area does, and therefore, it is necessary to analyze the tranquility at each berth. Hence in this study, we constructed a wave model for these conditions and performed simulation together with the circulation model simulation, compared with the field data collected. The result showed the increase of the harbor response throughout the basin but not severe condition. However, a certain location needs to be prepared for the rough sea condition when a severe typhoon hit the site.

• Journal of the Korean Society for Aeronautical & Space Sciences
• /
• v.50 no.7
• /
• pp.445-454
• /
• 2022

Ice accretion on the aircraft components, such as wings, fuselage, and empennage, can occur when the aircraft encounters a cloud zone with high humidity and low temperature. The prevention of ice accretion is important because it causes a decrease in the aerodynamic performance and flight stability, thus leading to fatal safety problems. In this study, a shape design optimization of a multi-element airfoil is performed to minimize the amount of ice accretion on the high-lift device including leading-edge slat, main element, and trailing-edge flap. The design optimization framework proposed in this paper consists of four major parts: air flow, droplet impingement and ice accretion simulations and gradient-free optimization algorithm. Reynolds-averaged Navier-Stokes (RANS) simulation is used to predict the aerodynamic performance and flow field around the multi-element airfoil at the angle of attack 8°. Droplet impingement and ice accretion simulations are conducted using the multi-physics computational analysis tool. The objective function is to minimize the total mass of ice accretion and the design variables are the deflection angle, gap, and overhang of the flap and slat. Kriging surrogate model is used to construct the response surface, providing rapid approximations of time-consuming function evaluation, and genetic algorithm is employed to find the optimal solution. As a result of optimization, the total mass of ice accretion on the optimized multielement airfoil is reduced by about 8% compared to the baseline configuration.

• KSCE Journal of Civil and Environmental Engineering Research
• /
• v.28 no.5B
• /
• pp.547-558
• /
• 2008

With the advent of super cargo ship due to the explosive increase in the amount of cargo shipped via seas, some mega ports are under construction in South Korea, to accommodate the super cargo ship, and some of them already enter their final phase. To sustain the harbor tranquility, mega ports usually comprise huge vertical type breakwaters which are intrinsically vulnerable to the attack of long waves. In this rationale, we present the chamber type breakwater with a circular curtain wall - Eco-breaker 2, to alleviate the reflection of long waves and numerically investigate the hydraulic characteristics of Eco-breaker 2. As a wave driver, we use the Navier-Stokes eq., the most robust wave driver, using SPH (Smoothed Particle Hydrodynamics) and LES (Large Eddy Simulation). For the verification of numerical results, we also carried out hydraulic model test. It is shown that Eco-breaker 2 can effectively alleviate the reflection of long waves with its inherited large organized eddies encompassing the water chamber and some region off the curtain wall of varying size. It is also shown that the scope and strength of large organized eddies strongly depends on the incident wave period, and the reflection coefficient can be lowered to 0.18 by tuning the size of water chamber such that resident time at the chamber is just short of the half period of incident waves. Based on these results, we present the specification of Eco-breaker 2 to boost its use on the development of water environment friendly harbor worldwide.

• Journal of Navigation and Port Research
• /
• v.37 no.3
• /
• pp.257-262
• /
• 2013

A ship operating in rough sea may suffer from an undesirable motion which may severely degrade the performance of equipment onboard and give a person an uncomfortable feeling. Hence, roll stabilization received a considerable attention and various devices including bilge keels, stabilizing fins, gyroscopic, anti-rolling tanks, rudders and flaps have been conceived and utilized for the purpose. The Coanda effect is evident when a jet stream is applied tangential to a curved surface of a hydrofoil since then the jet increases the circulation around the foil and consequently the lift. Model tests and numerical simulation have been conducted to examine the practicality of a fixed type fin stabilizer augmented by the Coanda jet. The results show that the lift coefficient of the modified Coanda fin at the zero angle of attack identically coincides with that of the original fin at ${\alpha}=\26^{\circ}$ when Coanda jet is supplied at the rate of $C_j$ = 0.25. It is also shown that fixed type fin stabilizers for active control of the motions of ships and the other mobile units without rotation can be put to practical use if the Coanda effect is applied.

• The KIPS Transactions:PartD
• /
• v.13D no.1 s.104
• /
• pp.67-74
• /
• 2006

The security requirements identification in the software development has received some attention recently. However, previous methods do not provide clear method and process of security requirements identification. We propose a process that software developers can build application specific security requirements from state transition diagrams at the security threat location. The proposed process consists of building model and identifying application specific security requirements. The state transition diagram is constructed through subprocesses i) the identification of security threat locations using security failure data based on the point that attackers exploit software vulnerabilities and attack system assets, ii) the construction of a state transition diagram which is usable to protect, mitigate, and remove vulnerabilities of security threat locations. The identification Process of application specific security requirements consist of i) the analysis of the functional requirements of the software, which are decomposed into a DFD(Data Flow Diagram; the identification of the security threat location; and the appliance of the corresponding state transition diagram into the security threat locations, ii) the construction of the application specific state transition diagram, iii) the construction of security requirements based on the rule of the identification of security requirements. The proposed method is helpful to identify the security requirements easily at an early phase of software development.