• Smart Structures and Systems
• /
• v.22 no.2
• /
• pp.201-207
• /
• 2018

This paper proposes a line laser thermography scanning (LLTS) system for multiple crack evaluation on a concrete structure, as the core technology for unmanned aerial vehicle-mounted crack inspection. The LLTS system consists of a line shape continuous-wave laser source, an infrared (IR) camera, a control computer and a scanning jig. The line laser generates thermal waves on a target concrete structure, and the IR camera simultaneously measures the corresponding thermal responses. By spatially scanning the LLTS system along a target concrete structure, multiple cracks even in a large scale concrete structure can be effectively visualized and evaluated. Since raw IR data obtained by scanning the LLTS system, however, includes timely- and spatially-varying IR images due to the limited field of view (FOV) of the LLTS system, a novel time-spatial-integrated (TSI) coordinate transform algorithm is developed for precise crack evaluation in a static condition. The proposed system has the following technical advantages: (1) the thermal wave propagation is effectively induced on a concrete structure with low thermal conductivity of approximately 0.8 W/m K; (2) the limited FOV issues can be solved by the TSI coordinate transform; and (3) multiple cracks are able to be visualized and evaluated by normalizing the responses based on phase mapping and spatial derivative processes. The proposed LLTS system is experimentally validated using a concrete specimen with various cracks. The experimental results reveal that the LLTS system successfully visualizes and evaluates multiple cracks without false alarms.

• Journal of the Institute of Electronics Engineers of Korea SC
• /
• v.41 no.4
• /
• pp.13-20
• /
• 2004

In this paper, we developed a method for predicting the tracking performance of the multiple hypothesis tracking (MHT) algorithm. The MHT algerithm is known to be a measurement-oriented optimal Bayesian approach and is superior to any other tracking filters because it takes into account the events that the measurements can be originated from new targets and false alarms as well as interesting targets. In the MHT algorithm, a number of candidate hypotheses are generated and evaluated later as more data are received. The probability of each candidate hypotheses is approximately evaluated by using the hybrid conditional average approach (HYCA). We performed numerical experiments to show the validity of our performance prediction.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.12 no.1
• /
• pp.454-475
• /
• 2018

This paper presents a novel Android malware classification model planned to classify and categorize Android malicious code at Drebin dataset. The amount of malicious mobile application targeting Android based smartphones has increased rapidly. In this paper, Restricted Boltzmann Machine and Deep Belief Network are used to classify malware into families of Android application. A texture-fingerprint based approach is proposed to extract or detect the feature of malware content. A malware has a unique "image texture" in feature spatial relations. The method uses information on texture image extracted from malicious or benign code, which are mapped to uncompressed gray-scale according to the texture image-based approach. By studying and extracting the implicit features of the API call from a large number of training samples, we get the original dynamic activity features sets. In order to improve the accuracy of classification algorithm on the features selection, on the basis of which, it combines the implicit features of the texture image and API call in malicious code, to train Restricted Boltzmann Machine and Back Propagation. In an evaluation with different malware and benign samples, the experimental results suggest that the usability of this method---using Deep Belief Network to classify Android malware by their texture images and API calls, it detects more than 94% of the malware with few false alarms. Which is higher than shallow machine learning algorithm clearly.

• Proceedings of the Korean Society for Noise and Vibration Engineering Conference
• /
• 2000.06a
• /
• pp.670-678
• /
• 2000

Loose parts monitoring system(LPMS) is one of the important monitoring systems for the safe and efficient operation of the nuclear reactor, since it is LPMS that can early detect loose parts which may cause a significant damage in facilities or components of the plant. Nuclear power plants in Korea have recently experienced several loose part alarms due to the metallic impact and it is expected that the frequency of the loose part will be increased along the aging of the plants. In this paper, the status of loose parts monitoring technologies and facilities in Korean nuclear power plants is presented for the establishment of LPMS installation plan in some nuclear reactors which are not yet equipped with LPMS. Sensor specification, location and mounting method for loose parts monitoring were reviewed. As a result, the location and the mounting method of the properly chosen sensor was recommended. Data acquisition algorithms and discriminating rules of loose part impact signals were also reviewed. Actual alarm cases occurred by true impact signal and false impact signal were stated here.

• Convergence Security Journal
• /
• v.15 no.1
• /
• pp.115-138
• /
• 2015

Expenses in the form of personnel expenses in the past, in modern times, machine guards to gradually transition has been. This is because the machine guard is more efficient than personnel expenses. But due to false alarms, despite the high expectations of the effects of electronic security in the operation of the electronic security system due to factors that hinder the development of machine guards growth slows. Defect removal aspects of this paper, using IPA (Importance Performance Analysis) techniques to study the operation of electronic security systems and its importance in the development of machine guards, look at how high the technical aspects of electronic security systems composite type of malfunction to minimize crime sensor are presented.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2003.10a
• /
• pp.580-583
• /
• 2003

This paper presents the motion detection algorithm that can run robustly about recusive motion. The existing motion detection algorithm that uses difference image is robustly in some degree brightness or noise, but it frequently causes false alarms to temporal clutter, at the repetitive motion within a certain area. We developed a motion detection algorithm using mean absoulte error(MAE) which calculates the set of Moving regions and performs block matching. The experimental results revealed that our approach is superior to existing methodologies to handling various temporal clutter.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.13 no.1
• /
• pp.382-389
• /
• 2012

The fabricated report attack will not only cause false alarms that waste real-world response efforts such as sending response teams to the event location, but also drains the finite amount of energy in a wireless sensor network. In this paper, we propose a probabilistic filtering method for sensor network security (PFSS) to deal with filtering for the fabricated report. On the basis of filtering scheme, PFSS combines cluster-based organization and probabilistic verification node assignment using distance of from cluster head to base station for energy efficiency and hot spot problem. Through both analysis and simulation, we demonstrate that PFSS could achieve efficient protection against fabricated report attack while maintaining a sufficiently high filtering power.

• Journal of Communications and Networks
• /
• v.18 no.6
• /
• pp.948-961
• /
• 2016

Internet protocol (IP) spoofing is a serious problem on the Internet. It is an attractive technique for adversaries who wish to amplify their network attacks and retain anonymity. Many approaches have been proposed to prevent IP spoofing attacks; however, they do not address a significant deployment issue, i.e., filtering inefficiency caused by a lack of deployment incentives for adopters. To defeat attacks effectively, one mechanism must be widely deployed on the network; however, the majority of the anti-spoofing mechanisms are unsuitable to solve the deployment issue by themselves. Each mechanism can work separately; however, their defensive power is considerably weak when insufficiently deployed. If we coordinate partially deployed mechanisms such that they work together, they demonstrate considerably superior performance by creating a synergy effect that overcomes their limited deployment. Therefore, we propose a universal anti-spoofing (UAS) mechanism that incorporates existing mechanisms to thwart IP spoofing attacks. In the proposed mechanism, intermediate routers utilize any existing anti-spoofing mechanism that can ascertain if a packet is spoofed and records this decision in the packet header. The edge routers of a victim network can estimate the forgery of a packet based on this information sent by the upstream routers. The results of experiments conducted with real Internet topologies indicate that UAS reduces false alarms up to 84.5% compared to the case where each mechanism operates individually.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.12 no.8
• /
• pp.4021-4037
• /
• 2018

In network intrusion detection research, two characteristics are generally considered vital to building efficient intrusion detection systems (IDSs): an optimal feature selection technique and robust classification schemes. However, the emergence of sophisticated network attacks and the advent of big data concepts in intrusion detection domains require two more significant aspects to be addressed: employing an appropriate big data computing framework and utilizing a contemporary dataset to deal with ongoing advancements. As such, we present a comprehensive approach to building an efficient IDS with the aim of strengthening academic anomaly detection research in real-world operational environments. The proposed system has the following four characteristics: (i) it performs optimal feature selection using information gain and branch-and-bound algorithms; (ii) it employs machine learning techniques for classification, namely, Logistic Regression, Naïve Bayes, and Random Forest; (iii) it introduces bulk synchronous parallel processing to handle the computational requirements of large-scale networks; and (iv) it utilizes a real-time contemporary dataset generated by the Information Security Centre of Excellence at the University of Brunswick (ISCX-UNB) to validate its efficacy. Experimental analysis shows the effectiveness of the proposed framework, which is able to achieve high accuracy, low computational cost, and reduced false alarms.

• Journal of Power Electronics
• /
• v.16 no.3
• /
• pp.1012-1024
• /
• 2016

This study deals with an on-line software fault detection, localization, and system reconfiguration method for electrical system drives composed of three-phase AC/DC/AC converters and three-phase permanent magnet synchronous machine (PMSM) drives. Current sensor failure (outage), speed/position sensor loss (disconnection), and damaged DC-link voltage sensor are considered faults. The occurrence of these faults in PMSM drive systems degrades system performance and affects the safety, maintenance, and service continuity of the electrical system drives. The proposed method is based on the monitoring signals of "abc" currents, DC-link voltage, and rotor speed/position using a measurement chain. The listed signals are analyzed and evaluated with the generated residuals and threshold values obtained from a Sliding Mode Current-Speed-DC-link Voltage Observer (SMCSVO) to acquire an on-line fault decision. The novelty of the method is the faults diagnosis algorithm that combines the use of SMCSVO and adaptive thresholds; thus, the number of false alarms is reduced, and the reliability and robustness of the fault detection system are guaranteed. Furthermore, the proposed algorithm's performance is experimentally analyzed and tested in real time using a dSPACE DS 1104 digital signal processor board.