• 제어로봇시스템학회:학술대회논문집
• /
• 1987.10b
• /
• pp.674-679
• /
• 1987

Process failures can occur at any time during operation, so a continuous effort of fault detection, diagsis, and correction is required. Expert system paridigm has been regarded as a promising approach to real time process supervisory control especially to fault diagnosis. The most important aspects of fault diagnostic expert systems(FDES) are the problem-solving inference strategy and knowledge organizations. The necessity of FDES, the nature of diagnostic knowledge, the representation of knowledge, and the inference mechanism of FDES, et al. are described, which are announced by previous researchers. And the existing FDES are categorized and critically reviewed in this work.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2008.10a
• /
• pp.744-747
• /
• 2008

Sensor networks will play an important role in the next generation pervasive computing. But its characteristic of wireless communication brings a peat challenge to the security measures used in the communication protocols. These measures are different from conventional security methods. In this paper, we proposed a security architecture for self-organizing mobile wireless sensor networks. It can prevent most of attacks based on intrusion detection.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2005.05a
• /
• pp.1225-1228
• /
• 2005

본 논문에서는 DDoS 공격 패킷을 사전에 탐지하고 트래픽 제어를 하기위한 방안을 제안한다. 제안된 모델은 공격대상에서 멀리 떨어 진 라우터에서 낮은 임계치를 적용하여 탐지 하게 되며 지역 연합 모델을 통한 지역적인 방어 행동을 취하게 된다. 사전에 취해지는 방어 행동으로 인해 본 시스템은 좋은 성능을 발휘 할 것이다. 시스템의 각 지역연합들은 DDoS 공격의 악의 적인 트래픽의 양을 줄이는 것에 기여 할 것이다.

• Journal of Welding and Joining
• /
• v.17 no.3
• /
• pp.26-35
• /
• 1999

On the laser weld production line, a slight alteration of the welding condition changes the bead size and the strength of the weldment. The measurement system is produced by using three photo-diodes for detection of the plasma and spatter signal in $CO_2$ laser welding. The relationship between the sensor signals of plasma or spatter and the bead shape, and the mechanism of the plasma and spatter were analyzed for the bead size estimation. The penetration depth and the bead width were estimated using the multiple regression analysis.

• Proceedings of the Korean Information Science Society Conference
• /
• 2003.10c
• /
• pp.697-699
• /
• 2003

본 논문은 스트리밍 환경에서 서버의 고장을 빠르게 탐지하기 위해 동적임계점을 사용하고 이에 대한 성능을 분석한다. 제안된 기법은 스트리밍의 특성을 이용하여 질의 전송 시간을 결정하게 되는데 서버의 패킷도착 지연으로 인해 발생되는 질의 전송 시간의 증가를 최소화시키기 위해 패킷 지연도착 시간을 반영하지 않는 알고리즘을 적용하였다. 고장탐지에 대한 성능분석을 위해 스트리밍의 종류에 따라 질의 전송 시간이 다양하게 적용될 수 있기 때문에 다양한 스트리밍 자료를 활용하여 실험하였으며 제안된 기법의 성능을 검증하였다.

• Proceedings of the Korean Information Science Society Conference
• /
• 2003.10a
• /
• pp.691-693
• /
• 2003

고 등급의 침입 탐지 시스템 평가를 받기 위해서는 반드시 정형적인 방법론을 적용하여 시스템을 설계하고 검증해야 한다. 그러나 침입 탐지 시스템의 설계에 적합한 정형기법을 선정하기는 매우 어렵다. 본 논문에서는 정형 기법의 일종인 모델 체킹 방법론을 침입 탐지 메커니즘의 설계에 적용하는 방법을 제안하고. 고 등급 침입 탐지 시스템의 개발에 사용할 수 있는 방향을 제시한다.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2004.05a
• /
• pp.1355-1358
• /
• 2004

This paper describes a modification to the SACK (Selective Acknowledgement) Transmission Control Protocol's (TCP), called SACK TCP with Probing Device, SACK works in conjunction with Probing Device, for improving SACK TCP performance when more than half a window of data lost that is typical in handoff as well as unreliable media. It shows that by slightly modifying the congestion control mechanism of the SACK TCP, it can be made to better performance to multiple packets lost from one window of data.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2009.04a
• /
• pp.1497-1499
• /
• 2009

최근 들어 스팸 메일, 키 로깅, DDoS와 같은 공격에 Botnet이 사용되고 있다. Botnet은 크래커에 의해 명령, 제어되는 Bot에 감염된 클라이언트로 이루어진 네트워크이다. 지금까지 유선망의 Botnet을 탐지하기 위한 많은 기법이 제안되었지만, 현재 많은 개발이 이루어지고 있는 6LoWPAN과 같은 무선 센서 네트워크상의 Botnet에 관한 연구와 그 대처방안은 전무한 상태이다. 본 논문에서는 6LoWPAN 환경에서 Botnet이 얼마나 위험할 수 있는지 살펴보고 이를 탐지하기 위한 메커니즘을 제안하고자 한다.

• Journal of Advanced Navigation Technology
• /
• v.27 no.2
• /
• pp.190-196
• /
• 2023

Recently, following the development of LIDAR technology which can detect distance from the object, the interest for LIDAR based 3D object detection network is getting higher. Previous networks generate inaccurate localization results due to spatial information loss during voxelization and downsampling. In this study, we propose an attention-based convergence method and a camera-LIDAR convergence system to acquire high-level features and high positional accuracy. First, by introducing the attention method into the Voxel-RCNN structure, which is a grid-based 3D object detection network, the multi-scale sparse 3D convolution feature is effectively fused to improve the performance of 3D object detection. Additionally, we propose the late-fusion mechanism for fusing outcomes in 3D object detection network and 2D object detection network to delete false positive. Comparative experiments with existing algorithms are performed using the KITTI data set, which is widely used in the field of autonomous driving. The proposed method showed performance improvement in both 2D object detection on BEV and 3D object detection. In particular, the precision was improved by about 0.54% for the car moderate class compared to Voxel-RCNN.

• The Transactions of the Korea Information Processing Society
• /
• v.13 no.4
• /
• pp.157-165
• /
• 2024

The evolution of the Distributed Denial of Service Attack(DDoS Attack) method has increased the difficulty in the detection process. One of the solutions to overcome the problems caused by the limitations of the existing victim-side detection method was the source-side detection technique. However, there was a problem of performance degradation due to network traffic irregularities. In order to solve this problem, research has been conducted to detect attacks using a collaborative network between several nodes based on artificial intelligence. Existing methods have shown limitations, especially in nonlinear traffic environments with high Burstness and jitter. To overcome this problem, this paper presents a collaborative source-side DDoS attack detection technique introduced with an attention mechanism. The proposed method aggregates detection results from multiple sources and assigns weights to each region, and through this, it is possible to effectively detect overall attacks and attacks in specific few areas. In particular, it shows a high detection rate with a low false positive of about 6% and a high detection rate of up to 4.3% in a nonlinear traffic dataset, and it can also confirm improvement in attack detection problems in a small number of regions compared to methods that showed limitations in the existing nonlinear traffic environment.