• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.10 no.8
• /
• pp.1810-1816
• /
• 2009

In 2007, 9,128 fires were actually caused by electrical faults and these fires resulted in 29 deaths and 262 injuries. Arc-faults were one of the major causes of these fires. When an unintended arc-fault occurs, it generates intense heat that can easily ignite surrounding combustibles. But, because conventional circuit breakers only respond to overloads, short circuits, and leakage currents, the breakers do not protect against arcing conditions. This paper presents results obtained in experiments on ignition behavior of wire by series arc fault currents and techniques developed to detect the arc-faults. The developed technique was tested after installation to make sure that they are working properly and protecting the circuit. If the developed arc fault detection technique is applied, the electrical fires caused by an arc-fault can be reduced.

• Journal of IKEEE
• /
• v.26 no.3
• /
• pp.380-388
• /
• 2022

The traditional malware detection technologies collect known malicious programs and analyze their characteristics. Then such a detection technology makes a blacklist based on the analyzed malicious characteristics and checks programs in the user's system based on the blacklist to determine whether each program is malware. However, such an approach can detect known malicious programs, but responding to unknown or variant malware is challenging. In addition, since such detection technologies generally monitor all programs in the system in real-time, there is a disadvantage that they can degrade the system performance. In order to solve such problems, various methods have been proposed to analyze major behaviors of malicious programs and to respond to them. The main characteristic of ransomware is to access and encrypt the user's file. So, a new approach is to produce the whitelist of programs installed in the user's system and allow the only programs listed on the whitelist to access the user's files. However, although it applies such an approach, attackers can still perform malicious behavior by performing a DLL(Dynamic-Link Library) injection attack on a regular program registered on the whitelist. This paper proposes a method to respond effectively to attacks using DLL injection.

• Smart Structures and Systems
• /
• v.30 no.6
• /
• pp.661-671
• /
• 2022

Stayed cables are the key components for transmitting loads in cable-stayed bridges. Therefore, it is very important to evaluate the cable force condition to ensure bridge safety. An online condition assessment and anomaly localization method is proposed for cables based on the spatiotemporal correlation of grouped cable forces. First, an anomaly sensitive feature index is obtained based on the distribution characteristics of grouped cable forces. Second, an adaptive anomaly detection method based on the k-nearest neighbor rule is used to perform dissimilarity measurements on the extracted feature index, and such a method can effectively remove the interference of environment factors and vehicle loads on online condition assessment of the grouped cable forces. Furthermore, an online anomaly isolation and localization method for stay cables is established, and the complete decomposition contributions method is used to decompose the feature matrix of the grouped cable forces and build an anomaly isolation index. Finally, case studies were carried out to validate the proposed method using an in-service cable-stayed bridge equipped with a structural health monitoring system. The results show that the proposed approach is sensitive to the abnormal distribution of grouped cable forces and is robust to the influence of interference factors. In addition, the proposed approach can also localize the cables with abnormal cable forces online, which can be successfully applied to the field monitoring of cables for cable-stayed bridges.

• Nuclear Engineering and Technology
• /
• v.54 no.12
• /
• pp.4431-4440
• /
• 2022

An advanced nuclear reactor based on molten salts including a molten salt reactor and pyroprocessing needs a sensitive monitoring system suitable for operation in harsh environments with limited access. Multi-element detection is challenging with the conventional technologies that are compatible with the in-situ operation; hence laser-induced breakdown spectroscopy (LIBS) has been investigated as a potential alternative. However, limited precision is a chronic problem with LIBS. We increased the precision of LIBS under high temperature by protecting optics using a gas protective layer and correcting for shotto-shot variance and lens-to-sample distance using a laser-induced acoustic signal. This study investigates cerium as a surrogate for uranium and corrosion products for simulating corrosive environments in LiCl-KCl. While the un-corrected limit of detection (LOD) range is 425-513 ppm, the acoustic-corrected LOD range is 360-397 ppm. The typical cerium concentrations in pyroprocessing are about two orders of magnitude higher than the LOD found in this study. A LIBS monitoring system that adopts these methods could have a significant impact on the ability to monitor and provide early detection of the transient behavior of salt composition in advanced molten salt-based nuclear reactors.

• KIPS Transactions on Software and Data Engineering
• /
• v.12 no.5
• /
• pp.237-242
• /
• 2023

Research on high-performance walking robots is being actively conducted, and quadruped walking robots are receiving a lot of attention due to their excellent mobility and adaptability on uneven terrain, but they are difficult to introduce and utilize due to high cost. In this paper, to increase utilization by applying intelligent functions to a low-cost quadruped robot, we present a method of improving uneven terrain overcoming ability by mounting IMU and reinforcement learning on embedded board and automatically detecting objects using camera and deep learning. The robot consists of the legs of a quadruped mammal, and each leg has three degrees of freedom. We train complex terrain in simulation environments with designed 3D model and apply it to real robot. Through the application of this research method, it was confirmed that there was no significant difference in walking ability between flat and non-flat terrain, and the behavior of performing person detection in real time under limited experimental conditions was confirmed.

• International Journal of Computer Science & Network Security
• /
• v.24 no.5
• /
• pp.11-20
• /
• 2024

While artificial neural networks are adept at identifying patterns, they can struggle to distinguish between actual correlations and false associations between extracted facial features and criminal behavior within the training data. These associations may not indicate causal connections. Socioeconomic factors, ethnicity, or even chance occurrences in the data can influence both facial features and criminal activity. Consequently, the artificial neural network might identify linked features without understanding the underlying cause. This raises concerns about incorrect linkages and potential misclassification of individuals based on features unrelated to criminal tendencies. To address this challenge, we propose a novel region-based training approach for artificial neural networks focused on criminal propensity detection. Instead of solely relying on overall facial recognition, the network would systematically analyze each facial feature in isolation. This fine-grained approach would enable the network to identify which specific features hold the strongest correlations with criminal activity within the training data. By focusing on these key features, the network can be optimized for more accurate and reliable criminal propensity prediction. This study examines the effectiveness of various algorithms for criminal propensity classification. We evaluate YOLO versions YOLOv5 and YOLOv8 alongside VGG-16. Our findings indicate that YOLO achieved the highest accuracy 0.93 in classifying criminal and non-criminal facial features. While these results are promising, we acknowledge the need for further research on bias and misclassification in criminal justice applications

• Asian Pacific Journal of Cancer Prevention
• /
• v.15 no.24
• /
• pp.10943-10947
• /
• 2015

Background: This study aimed to understand the relationship between knowledge level and behavior on breast care in Chinese students, so as to provide strategies for improving the health education of breast care and subsequently for aiding in breast cancer prevention. Materials and Methods: A self-designed questionnaire was used to evaluate breast care knowledge level and characterize related behavior. Correlation analysis was conducted for the knowledge level and behavior. The study was carried out using 597 female undergraduate students in medical and non-medical colleges in Wuhu, China. Results: The average score of breast care knowledge was $5.32{\pm}1.68$ ($5.62{\pm}1.68$ and $5.00{\pm}1.68$ for medical and non-medical students, respectively), with a greater score value for sophomores ($5.59{\pm}1.72$) than freshmen ($5.18{\pm}1.65$). The average score of breast care behavior was $2.21{\pm}1.13$, again with a greater value in sophomores ($2.37{\pm}1.15$) than freshmen ($2.21{\pm}1.13$). A significant positive correlation (r=0.231, p<0.01) between knowledge scores and behavior scores was observed. In addition, various factors, including paying attention to breast care information, receiving breast self-examination guidance, TV program and Internet, were found to influence breast care knowledge. Conclusions: In general, female undergraduate students lack of self-awareness of breast care with a low rate of breast self-examination. It is necessary to carry out health education to improve early detection of breast cancer.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.20 no.3
• /
• pp.422-427
• /
• 2010

Korean Game industry, especially MMORPG(Massively Multiplayer Online Game) has been rapidly expanding in these days. But As game industry is growing, lots of online game security incidents have also been increasing and getting prevailing. One of the most critical security incidents is 'Game Bots', which are programs to play MMORPG instead of human players. If player let the game bots play for them, they can get a lot of benefic game elements (experience points, items, etc.) without any effort, and it is considered unfair to other players. Plenty of game companies try to prevent bots, but it does not work well. In this paper, we propose a behavior pattern model for detecting bots. We analyzed behaviors of human players as well as bots and identified six game features to build the model to differentiate game bots from human players. Based on these features, we made a Naive Bayesian classifier to reasoning the game bot or not. To evaluated our method, we used 10 game bot data and 6 human Player data. As a result, we classify Game bot and human player with 88% accuracy.

• Journal of the Korea Society of Computer and Information
• /
• v.26 no.4
• /
• pp.11-19
• /
• 2021

An abnormal object refers to a person, an object, or a mechanical device that performs abnormal and unusual behavior and needs observation or supervision. In order to detect this through artificial intelligence algorithm without continuous human intervention, a method of observing the specificity of temporal features using optical flow technique is widely used. In this study, an abnormal situation is identified by learning an algorithm that translates an input image frame to an optical flow image using a Generative Adversarial Network (GAN). In particular, we propose a technique that improves the pre-processing process to exclude unnecessary outliers and the post-processing process to increase the accuracy of identification in the test dataset after learning to improve the performance of the model's abnormal behavior identification. UCSD Pedestrian and UMN Unusual Crowd Activity were used as training datasets to detect abnormal behavior. For the proposed method, the frame-level AUC 0.9450 and EER 0.1317 were shown in the UCSD Ped2 dataset, which shows performance improvement compared to the models in the previous studies.

• Bulletin of the Korean Chemical Society
• /
• v.31 no.5
• /
• pp.1262-1266
• /
• 2010

In this study, we investigated the use of liquid crystals to selectively detect the activity of enzymes at interfaces decorated with oligopeptide-based membranes. We prepared a mixed monolayer of tetra(ethylene glycol)-terminated lipids and carboxylic acid-terminated lipids at the aqueous-liquid crystal (LC) interface. The 17 amino-acid oligopeptide SNFKTIYDEANQFATYK was then immobilized onto this mixed monolayer through N-hydroxysuccinimide-activation of the carboxylic acid groups. We examined the orientational behavior of nematic 4-cyano-4'-pentylbiphenyl (5CB) after conjugation of the 17 amino-acid oligopeptide with the mixed monolayer assembled at the interface. Immobilization of the oligopeptide caused orientational transitions in 5CB, with a change from homeotropic (perpendicular) to tilted alignment, which was primarily due to the reorganization of the monolayer. The orientation of the 5CB molecules returned to its homeotropic state after contacting the interface containing ${\alpha}$-chymotrypsin, which can cleave the immobilized oligopeptide. Control experiments confirmed that the enzymatic activity of ${\alpha}$-chymotrypsin triggered the ordering transitions in the LC. These results suggest that the LC can provide a facile method for selective detection of enzymatic activity.