• Journal of the Korean GEO-environmental Society
• /
• v.22 no.10
• /
• pp.13-19
• /
• 2021

Cracks in asphalt pavement occur due to changes in weather or impact from vehicles, and if cracks are left unattended, the life of the pavement may be shortened, and various accidents may occur. Therefore, studies have been conducted to detect cracks through images in order to quickly detect cracks in the asphalt pavement automatically and perform maintenance activity. Recent studies adopt machine-learning models for detecting cracks in asphalt road pavement using a Convolutional Neural Network. However, their practical use is limited because they require high-performance computing power. Therefore, this paper proposes a framework for detecting cracks in asphalt road pavement by applying a small deep learning model applicable to mobile devices. The small deep learning model proposed through the case study was compared with general deep learning models, and although it was a model with relatively few parameters, it showed similar performance to general deep learning models. The developed model is expected to be embedded and used in mobile devices or IoT for crack detection in asphalt pavement.

• The Journal of Korean Institute of Information Technology
• /
• v.17 no.6
• /
• pp.103-114
• /
• 2019

Moving-target detection using frequency-modulated continuous-wave (FMCW) radar systems has recently attracted attention. Detection tasks are more challenging with noise resulting from signals reflected from strong static objects or small moving objects(clutter) within radar range. Robust Principal Component Analysis (RPCA) approach for FMCW radar to detect moving objects in noisy environments is employed in this paper. In detail, compensation and calibration are first applied to raw input signals. Then, RPCA via Gradient Descents (RPCA-GD) is adopted to model the low-rank noisy background. A novel update algorithm for RPCA is proposed to reduce the computation cost. Finally, moving-targets are localized using an Automatic Multiscale-based Peak Detection (AMPD) method. All processing steps are based on a sliding window approach. The proposed scheme shows impressive results in both processing time and accuracy in comparison to other RPCA-based approaches on various experimental scenarios.

• Convergence Security Journal
• /
• v.23 no.5
• /
• pp.65-72
• /
• 2023

This paper proposes a method for detecting malicious domains considering human habitual characteristics by building a Deep Learning model based on LSTM (Long Short-Term Memory). DGA (Domain Generation Algorithm) malicious domains exploit human habitual errors, resulting in severe security threats. The objective is to swiftly and accurately respond to changes in malicious domains and their evasion techniques through typosquatting to minimize security threats. The LSTM-based Deep Learning model automatically analyzes and categorizes generated domains as malicious or benign based on malware-specific features. As a result of evaluating the model's performance based on ROC curve and AUC accuracy, it demonstrated 99.21% superior detection accuracy. Not only can this model detect malicious domains in real-time, but it also holds potential applications across various cyber security domains. This paper proposes and explores a novel approach aimed at safeguarding users and fostering a secure cyber environment against cyber attacks.

• Journal of KIISE:Information Networking
• /
• v.28 no.4
• /
• pp.489-497
• /
• 2001

In the coming age of information warfare, information security patterns take on a more offensive than defensive stance. It is necessary to develop an active form of offensive approach to security protection in order to guard vital information infrastructures and thwart hackers. Information security products need to support an automatic response facility without human intervention in order to minimize damage to the attacked system and cope with the intrusion immediately. This paper presents an automatic intrusion response model which is developed on a Self-Extension Monitoring. It also proposes an ARTEMIS(Advanced Realtime Emergency Management and Intruder Identification System), which is designed and implemented based on the suggested model. The Self-Extension Monitoring using self-protection and replication minimizes spatial limitations on collection of monitoring information and intruder tracing. It enhances the accuracy of intrusion detection and tracing.

• Journal of Biomedical Engineering Research
• /
• v.16 no.3
• /
• pp.337-344
• /
• 1995

Because of the high energy of the treatment beam, contrast of portal films is very poor. Many image processing techniques have been applied to the portal images but a significant drawback is the loss of definition on the edges of the treatment field. Analysis of this problem shows that it may be remedied by separating the treatment field from the background prior to enhancement and uslng only the pixels within the field boundary in the enhancement procedure. A new edge extraction algorithm for accurate extraction of the radiation field boundary from portal Images has been developed for contrast enhancement of portal images. In this paper, portal image segmentation algorithm based on Sobel filtration, labelling processes and morphological thinning has been presented. This algorithm could automatically search the optimal threshold value which is sensitive to the variation of the type and quality of portal images.

• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.10 no.2
• /
• pp.77-83
• /
• 2010

Vehicular Ad Hoc Networks are self-organizing Peer-to-Peer networks that typically have highly mobile vehicle nodes, moving at high speeds, very short-lasting and unstable communication links. VANETs are formed without fixed infrastructure, central administration, and dedicated routing equipment, and network nodes are mobile, joining and leaving the network over time. So, VANET-security is very vulnerable for the intrusion of malicious and misbehaving nodes in the network, since VANETs are mostly open networks, allowing everyone connect, without centralized control. In this paper, we propose a rough set based anomaly detection method that efficiently identify malicious behavior of vehicle node activities in these VANETs, and the performance of a proposed scheme is evaluated by a simulation in terms of anomaly detection rate and false alarm rate for the threshold ${\epsilon}$.

• Journal of the Institute of Electronics Engineers of Korea TC
• /
• v.48 no.4
• /
• pp.47-52
• /
• 2011

Constant false alarm rate (CFAR) is an automatic detection algorithm for active sonar system. Among several CFAR algorithms, ordered statistics (OS) CFAR has the best performance over cell averaging (CA), smallest of (SO), greatest of (GO) algorithms at non-homogeneous environments. However, OS CFAR has the disadvantage of bad detection performance in multiple target conditions. We suggest an ordered statistics ratio (OSR) CFAR algorithm that is robust to multiple target environments. The proposed and conventional schemes are compared with computer simulations.

• The KIPS Transactions:PartC
• /
• v.11C no.7 s.96
• /
• pp.993-998
• /
• 2004

As Worm Virus & DDoS attack appeares, the targets and damage of infringement accidents are extending from specific system or services to paralysis of the network itself. These attacks are expending very frequently and strongly, and ISP who will be used as the path of these attacks will face serious damages. But compare to Worm Virus & DDoS attack that generally occures in many Systems at one time with it's fast propagation velocity, network dimensional opposition is slow and disable to deal with the whole appearance for it is operated manually by the network manager. Therefore, this treatise present devices how to detect Worm Virus & DDoS attack's outbreak and the attacker(attacker IP adderss) automatically.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2005.05a
• /
• pp.1103-1106
• /
• 2005

IPv4 프로토콜의 주소 고갈 문제를 해결하기 위하여 IPv6 프로토콜이 제안되었고 한국전산원의 발표에 의하면 2010년 이후에는 IPv6 프로토콜이 광범위하게 사용될 것이라고 한다. 이러한 IPv6 프로토콜은 IPv4 프로토콜의 단점들을 해결하기 위하여 ND(Neighbor Discovery) 메커니즘, 주소자동설정, IPsec 등의 기술을 지원하며, 특히 IPv6 프로토콜은 보안 문제를 해결하기 위해서 인증, 데이터 무결성 보호를 위한 IPsec 기술을 사용한다. 이러한 IPsec 기술은 패킷 정보를 보호하기 위한 목적으로 사용되기 때문에 불특정 다수의 사용자를 대상으로 하는 네트워크에 행해지는 분산 서비스 거부 공격과 같은 비정상 대용량 트래픽에 대한 탐지 및 차단에 어려움이 있다. 현재 IPv6 프로토콜을 지원하는 네트워크 공격 대응 기술로 IPv6 네트워크용 방화벽/침입탐지 시스템이 개발되어 제품으로 판매되고 있지만, 대용량의 비정상 트래픽 대응 기술을 탐지하고 차단하기에는 한계가 있다. 본 논문에서는 IPv6 네트워크 환경에서 이러한 대용량의 비정상 트래픽을 제어할 수 있는 프레임워크를 제시한다.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.25 no.1B
• /
• pp.62-70
• /
• 2000

Intelligent vehicles are equipped with radar sensors for collision avoidance. We present a method of suppressing mutual interference among pulse-type radars, where all the radars are standardized. We developed a method of separating the true self-reflection from the false one by controlling the pulse emission of a radar in anorhogonal ON, OFF pattern. Interference signal identified in OFF-intervals is recorded to indicate the positions of the expected ghosts in ON-intervals. PFA and PM are derived for a radar system with I-Q demodulation scheme, where Gaussian noise alone is Rayleigh-distributed and Gaussian noise plus reflected radar pulse are Rician-distributed. The value of the threshold adaptively updated in order to prevent the deterioration of PM. In the experimental result, PFA decreases by an order of 10,000, when compared with the conventional M of N majority voting method.