• Journal of Electrical Engineering and Technology
• /
• v.10 no.3
• /
• pp.1284-1292
• /
• 2015

As visual surveillance systems become more and more common in human lives, approaches based on these systems to solve security problems in practice are boosted, especially in railway applications. In this paper, we first propose a robust snag detection algorithm and then present a railway security system by using a combination of multiple sensors and the vision based snag detection algorithm. The system aims safety at several repeatedly occurred situations including slope protection, inspection of the falling-object from bridges, and the detection of snags and foreign objects on the rail. Experiments demonstrate that the snag detection is relatively robust and the system could guarantee the security of the railway through these real-time protections and detections.

• Proceedings of the Korean Nuclear Society Conference
• /
• 2005.10a
• /
• pp.366-367
• /
• 2005

• Proceedings of the Korean Information Science Society Conference
• /
• 2011.06d
• /
• pp.215-218
• /
• 2011

VoIP(Voice over Internet Protocol) 서비스는 기존의 음성전화 서비스(Public Switched Telephone Network, PSTN)와 달리 IP 프로토콜을 이용한 저렴한 통신비용 등의 장점이 있는 음성통신 기술로써, 기존의 아날로그 음성전화 서비스를 대신하는 서비스이며, 새로운 인터넷 융합서비스로 많은 사용자가 이용하고 있다. 하지만 VoIP 서비스가 인터넷망을 이용함으로 IP Spoofing, DoS (Denial of Server) / DDoS(Distributed Denial of Service), 등의 여러 가지 보안의 문제점을 가지고 있다. VoIP 서비스에서 DDoS 공격은 Proxy 서버 등에 대량의 공격 메시지를 보냄으로써 서버의 자원을 고갈시켜 정상적인 서비스를 하지 못하게 한다. DoS, DDoS 공격 중 Invite Flooding 공격은 1분에 수천 개의 Invite 메시지를 보내 회선의 자원을 고갈시키는 공격이다. 특히 IP/Port 위조하여 공격 경우 공격 패킷 탐지하기 어려우므로 차단할 수 없다. 따라서 본 논문에서는 VoIP의 DoS/DDoS 중 하나인 Invite Flooding 공격 시 SIP Proxy Server에서 메시지 분산시키는 방법과 MAC Address와 사용자 번호 등 IP 이외의 고정적인 사용자 정보를 확인하여 공격을 탐지하고, 공격 Agent에 감염된 Phone을 공격차단서비스로 보내 복구시키는 방법을 제안한다.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2002.04a
• /
• pp.647-650
• /
• 2002

The human faces do not have distinct features unlike other general objects. In general the features of eyes, nose and mouth which are first recognized when human being see the face are defined. These features have different characteristics depending on different human face. In this paper, We propose a face recognition algorithm using the hidden Markov model(HMM). In the preprocessing stage, we find edges of a face using the locally adaptive threshold scheme and extract features based on generic knowledge of a face, then construct a database with extracted features. In training stage, we generate HMM parameters for each person by using the forward-backward algorithm. In the recognition stage, we apply probability values calculated by the HMM to input data. Then the input face is recognized by the euclidean distance of face feature vector and the cross-correlation between the input image and the database image. Computer simulation shows that the proposed HMM algorithm gives higher recognition rate compared with conventional face recognition algorithms.

• Journal of Microbiology
• /
• v.35 no.3
• /
• pp.177-180
• /
• 1997

The purpose of this study was to evaluate the efficiency of Line Probe Assay (LiPA) in detecting the rpoB gene mutation of clinically isolated Mycobacterium tuberculosis (MTB) and to compare the level of resistance to the various rifamycins with their mutation sites. The mutation in the rpoB gene was found in 84 (97.6%) out of 86 rifampicin (RMP) resistant strains as determined by LiPA. No mutation was observed in 2 RMP resistant strains and in any of 38 RMP susceptible strains tested. Only one of 3 strains with .DELTA.5/R5, one of 2 strains with .DELTA.3, and one of 3 strains with .DELTA.2/R2 LiPA profile showed a slightly lower level of resistance to the rifapentine than the other strains. Although we could not find correlations between mutation sites in the rpoB gene and the level of susceptibility to the various rifamycins, the LiPA is recommended as a fast screening tool for detection of RMP resistant MTB.