• The KIPS Transactions:PartC
• /
• v.10C no.5
• /
• pp.565-574
• /
• 2003

This paper implements an intrusion detection message exchange protocol library (IDMEPL) for SDMS-RTIR, which Korea Information Security Agency (KISA) has developed to hierarchically detect and respond to network vulnerability scan attacks. The IDMEPL, based on the IDMEF and the IAP of the IDWG, enables SDMS-RTIR to interact with other intrusion detection systems (IDS) in realtime, and supports the TLS protocol to prevent security threats in exchanging messages between its server and its agents. Especially, with the protocol selection stage, the IDMEPL can support various protocols such as the IDXP besides the IAP. Furthermore, it can allow for agents to choose an appropriate security protocol for their own network, achieving security stronger than mutual authentication. With the IDMEPL, SDMS-RTIR can receive massive intrusion detection messages from heterogeneous IDSes in large-scale networks and analyze them.

• Journal of Convergence Society for SMB
• /
• v.2 no.1
• /
• pp.25-31
• /
• 2012

Recently Wireless Communication technologies are widely used in Small And Medium Business fields. Wireless mesh networks have been studied as the next generation technology to solve problem of conventional wireless networks. Wireless mesh network uses a 802.11 when make up of network. mesh clients occurs Hard handover moving between ones. This increases the handover latency of the network mobility is a very great issues. Consequently, this paper propose a channel information previously methods to reduce the handover latency selective channels. Proposed scheme accounts for more than 90% of the probe delay to minimize the client had to move the mesh based on the old channel to retrieve information. Through simulation, the proposed scheme had shorter handover delay time than transitional full scan and selective scan. Through results of evaluation, the suggest PCISS scheme more fast 6.5% than transitional scheme.

• The KIPS Transactions:PartC
• /
• v.11C no.6 s.95
• /
• pp.719-724
• /
• 2004

Recently, since the number of internet users is increasing rapidly and, by using the public hacking tools, general network users can intrude computer systems easily, the hacking problem is getting more serious. In order to prevent the intrusion, it is needed to detect the sign in advance of intrusion in a positive prevention by detecting the various foms of hackers' intrusion trials to know the vulnerability of systems. The existing network-based anomaly detection algorithms that cope with port- scanning and the network vulnerability scans have some weakness in intrusion detection. they can not detect slow scans and coordinated scans. therefore, the new concept of algorithm is needed to detect effectively the various forms of abnormal accesses for intrusion regardless of the intrusion methods. In this paper, SPAD(Session Pattern Anomaly Detector) is presented, which detects the abnormal service patterns by comparing them with the ordinary normal service patterns.

• Journal of the Korean Society for Nondestructive Testing
• /
• v.23 no.1
• /
• pp.45-52
• /
• 2003

A number of stress corrosion cracks in turbine rotor disk keyway in power plants have been found and the necessity has been raised to detect and evaluate the cracks prior to the catastrophic failure of turbine disk. By ultrasonic RF signal analysis and using a neural network based on bark-propagation algorithm, we tried to evaluate the location, size and orientation of cracks around keyway. Because RF signals received from each reflector have a number of peaks, they were processed to have a single peak for each reflector. Using the processed RF signals, scan data that contain the information on the position of transducer and the arrival time of reflected waves from each reflector were obtained. The time difference between each reflector and the position of transducer extracted from the scan data were then applied to the back-propagation neural network. As a result, the neural network was found useful to evaluate the location, size and orientation of cracks initiated from keyway.

• Proceedings of the Korean Institute of Intelligent Systems Conference
• /
• 2003.09a
• /
• pp.644-647
• /
• 2003

This paper describes a neural network based machine vision system designed for inspecting yellow beans in real time. The system consists of a camera. lights, a belt conveyor, air ejectors, and a computer. Beans are conveyed in four lines on a belt and their images are taken by a monochrome line scan camera when they fall down from the belt. Beans are separated easily from their background on images by back-lighting. After analyzing the image, a decision is made by a multilayer artificial neural network (ANN) trained by the error back-propagation (EBP) algorithm. We use the global mean, variance and local change of gray levels of a bean for the input nodes of the network. In an our experiment, the system designed could process about 520kg/hour.

• 제어로봇시스템학회:학술대회논문집
• /
• 2001.10a
• /
• pp.102.3-102
• /
• 2001

In this paper, we propose a novel method that can detect face region effectively with fuzzy theory and neural network We make fuzzy rules and membership functions to describe the face color. In this algorithm, we use a perceptually uniform color space to increase the accuracy and stableness of the nonlinear color information. We use this model to extract the face candidate, and then scan it with the pre-built sliding window by using a neural network-based pattern-matching method to find eye. A neural network examines small windows of face candidate, and decides whether each window contains eye. We can standardize the face candidate geometrically with detected eyes.

• Journal of the Korea Society of Computer and Information
• /
• v.18 no.12
• /
• pp.113-121
• /
• 2013

In this paper, we design and implement a network weather map system, which provides a macroscopic view on the whole network topology as well as the network link status and utilization. The proposed system also provides distributed NetFlow-based database facility and Web-based query interface, through which network operators can check the detailed network router or link status as well as submit predefined queries to easily find out and locate heavy hitters and/or their usage. We believe that our develop system will be a useful tool for small-to-mid-scale ISPs or network operators, in managing their own networks in a cost-effective way.

• Proceedings of the Korean Institute of Navigation and Port Research Conference
• /
• 1998.10a
• /
• pp.137-141
• /
• 1998

Todays the efficient management of container has not been realized in container terminal, because of the excessive quantity of container transported and manual system. For the efficient and automated management of container in terminal, the automated container identifier recognition system in terminal is a significant problem. However, the identifier recognition rate is decreased owing to the difficulty of image preprocessing caused the refraction of container surface, the change of weather and the damaged identifier characters. Therefore, this paper proposes more accurate system for container identifier recognition as suggestion of Line-Scan Proper Region Detect for stronger preprocessing against external noisy element and Moment Back-Propagation Neural Network to recognize identifier.

• Journal of Korean Port Research
• /
• v.12 no.2
• /
• pp.225-232
• /
• 1998

Todays, the efficient management of container has not been realized in container terminal, because of the excessive quantity of container transported and manual system. For the efficient and automated management of container in terminal, the automated container identifier recognition system in terminal is a significant problem. However, the identifier recognition rate is decreased owing to the difficulty of image preprocessing caused the refraction of container surface, the change of weather and the damaged identifier characters. Therefore, this paper proposes more accurate system for container identifier recognition as suggestion of LSPRD(Line-Scan Proper Region Detection) for stronger preprocessing against external noisy element and MBP(Momentum Back-Propagation) neural network to recognize the identifier.

• Journal of Powder Materials
• /
• v.24 no.3
• /
• pp.202-209
• /
• 2017

A cold-work tool steel powder is used to fabricate 3-dimensional objects by selective laser melting using a high-pressure gas atomization process. The spherical powder particles form continuous carbide networks among the austenite matrix and its decomposition products. The carbides comprise Nb-rich MC and Mo-rich $M_2C$. In the SLM process, the process parameters such as the laser power (90 W), layer thickness ($25{\mu}m$), and hatch spacing ($80{\mu}m$) are kept fixed, while the scan speed is changed from 50 mm/s to 4000 mm/s. At a low scan speed of 50 mm/s, spherical cavities develop due to over melting, while they are substantially reduced on increasing the speed to 2000 mm/s. The carbide network spacing decreases with increasing speed. At an excessively high speed of 4000 mm/s, long and irregularly shaped cavities are developed due to incomplete melting. The influence of the scan pattern is examined, for which $1{\times}1 mm^2$ blocks constituting a processing layer are irradiated in a random sequence. This island-type pattern exhibits the same effect as that of a low scan speed. Post processing of an object using hot isostatic pressing leads to a great reduction in the porosity but causes coarsening of the microstructure.