• Journal of the Korea Society of Computer and Information
• /
• v.10 no.6 s.38
• /
• pp.153-166
• /
• 2005

Existing single cache structure has shown difference of hit-ratio according to individually replacement strategy However. It needs new improved cache structure for reducing network traffic and providing advanced hit-ratio. Therefore, this Paper design push agent model using dual cache for increasing hit-ratio by reducing server overload and network traffic by repetition request of persistent and identical information. In this model proposes dual cache structure to do achievement replace gradual cache using by two caches storage space for reducing server overload and network traffic. Also, we show new cache replace techniques and algorithms which executes data update and delete based on replace strategy of Log(Size) +LRU, LFU and PLC for effectiveness of data search in cache. And through an experiment, it evaluates Performance of dual cache push agent model.

• Journal of KIISE:Information Networking
• /
• v.37 no.1
• /
• pp.16-26
• /
• 2010

We present a testbed for collecting log information and evaluating network security under various attacks. This testbed is modeled on real Internet, where attack traffic coexists with normal traffic. Attacks can be produced either by attack tools directly or by data sets including attack traffic. It costs less time and money than existing ones which are both costly and often time consuming in constructing. Also, it can be easily revised or extended according to the traffic types or the uses. Therefore, using our testbed can make various tests more efficient and facilitate collecting log information of sensors with attacks. We discuss how to use our testbed through replay procedures of DDoS attack and worm. We also discuss how we surmount some difficulty in constructing the testbed.

• Convergence Security Journal
• /
• v.22 no.2
• /
• pp.9-19
• /
• 2022

As the expansion of digital transformation, we are more exposed to the threat of cyber attacks, and many institution or company is operating a signature-based intrusion prevention system at the forefront of the network to prevent the inflow of attacks. However, in order to provide appropriate services to the related ICT system, strict blocking rules cannot be applied, causing many false events and lowering operational efficiency. Therefore, many research projects using artificial intelligence are being performed to improve attack detection accuracy. Most researches were performed using a specific research data set which cannot be seen in real network, so it was impossible to use in the actual system. In this paper, we propose a technique for classifying major attack keywords in the security event log collected from the actual system, assigning a weight to each key keyword, and then performing a similarity check using TF-IDF to determine whether an actual attack has occurred.

• Journal of the Korean Institute of Telematics and Electronics B
• /
• v.30B no.1
• /
• pp.90-98
• /
• 1993

A Gaussian is formed by diffusing a spot excitation. In this paper, a diffusion neural network model is derived from the diffusion equation. And it is shown that a difference of two Gaussians(DOG) may have the same shape as a Laplacian of Gaussian(LOG), A neural network model executing a DOG convolution by diffusing an external excitation is proposed. By this model intensity changes of image may be detected. This model may be implemented economically because each neuron has only four fixed-valued synapes.

• Proceedings of the KSRS Conference
• /
• 2005.10a
• /
• pp.785-788
• /
• 2005

We design as well as implement MRTG++ enhanced by eliminating drawbacks of original MRTG. Existing MRTG makes it easy to monitor network resources on the web, and it can show some trend utilization about resources of remote systems. However MRTG has only functions showing statistical information data with daily/monthly/yearly characteristics in real-time, and periodically deletes stored data. Thus we improve log file-based storing method as an effectivelly storing method with database, propose expended MRTG++ retrieving as well as managing with measured data. It also can be applied in ubiquitous environment.

• Proceedings of the Korea Society of Information Technology Applications Conference
• /
• 2005.11a
• /
• pp.183-186
• /
• 2005

WUSB is a new technology which combines the speed and the security of wired USB with the easy use of wireless technology. In this paper, GUI for WUSB is designed and implemented to show the connectivity and contents of the WUSB devices. Also, the proposed GUI shows the log window while content transfers occur between the host and device. The proposed GUI can be used for various wireless technologies which provide wireless function with existing USB hosts and devices.

• Proceedings of the Korean Society of Machine Tool Engineers Conference
• /
• 2001.04a
• /
• pp.229-233
• /
• 2001

In this paper, we propose a remote controller for robot manipulator using local area network(LAN) and internet. To do this, we develope a server-client system as used in the network field. The client system is in any computer in remote place for the user to log-in the server and manage the remote factory. the server system is a computer which controls the manipulator and waits for a access from client. The server system consists of several control algorithms which is needed to drive the manipulator and networking system to transfer images that shows states of the work place, and to receive a Tmp data to run the manipulator. The client system consists of 3D(dimension) graphic user interface for teaching and off-line task like simulation, external hardware interface which makes it easier for the user to teach. Using this server-client system, the user who is on remote place can edit the work schedule of manipulator, then run the machine after it is transferred and monitor the results of the task.

• Proceedings of the KIEE Conference
• /
• 2002.11c
• /
• pp.39-41
• /
• 2002

Management of internal Internet servers is increasingly becoming an important task. According to meet this requirement, they use service log analysis tools and network monitoring tools. But these are not enough to produce advanced management information considering contents of Internet services. Therefor we propose a system and let it detect Internet server systems existing in internal network and individuate those systems with providing profile. Internet server profile includes system's basic information, network traffic information, and Internet service usage information.

• Journal of Internet Computing and Services
• /
• v.19 no.4
• /
• pp.35-44
• /
• 2018

Monitoring through Synthesis Aperture Radar (SAR) is responsible for marine safety from floating icebergs. However, there are limits to distinguishing between icebergs and ships in SAR images. Convolutional Neural Network (CNN) is used to distinguish the iceberg from the ship. The goal of this paper is to increase the accuracy of identifying icebergs from SAR images. The metrics for performance evaluation uses the log loss. The two-layer CNN model proposed in research of C.Bentes et al.[1] is used as a benchmark model and compared with the four-layer CNN model using data augmentation. Finally, the performance of the final CNN model using the VGG-16 pre-trained model is compared with the previous model. This paper shows how to improve the benchmark model and propose the final CNN model.

• Journal of the Korean Society for Precision Engineering
• /
• v.10 no.1
• /
• pp.77-88
• /
• 1993

In this paper, we propose a stereo vision system to solve correspondence problem with large disparity and sudden change in environment which result from small distance between camera and working objects. First of all, a specific feature is divided by predfined elementary feature. And then these are combined to obtain coded data for solving correspondence problem. We use Neural Network to extract elementary features from specific feature and to have adaptability to noise and some change of the shape. Fourier transformation and Log-polar mapping are used for obtaining appropriate Neural Network input data which has a shift, scale, and rotation invariability. Finally, we use associative memory to obtain coded data of the specific feature from the combination of elementary features. In spite of specific feature with some variation in shapes, we could obtain satisfactory 3-dimensional data from corresponded codes.