• Journal of Korea Multimedia Society
• /
• v.20 no.2
• /
• pp.144-152
• /
• 2017

Among the technologies for implementing autonomous vehicles, advanced driver assistance system is a key technology to support driver's safe driving. In the technology using the vision sensor having a high utility, various preprocessing methods are used prior to feature extraction for lane detection. However, in the existing methods, the unnecessary lane candidates such as cars, lawns, and road separator in the road area are false positive. In addition, there are cases where the lane candidate itself can not be extracted in the area under the overpass, the lane within the dark shadow, the center lane of yellow, and weak lane. In this paper, we propose an efficient preprocessing method using k-means clustering for image division and the HSV color model. When the proposed preprocessing method is applied, the true positive region is maximally maintained during the lane detection and many false positive regions are removed.

• The Transactions of The Korean Institute of Electrical Engineers
• /
• v.57 no.4
• /
• pp.537-542
• /
• 2008

The protection against transient instability and consequent out-of-step condition is a major concern for the utility industry. Unstable system may cause serious damage to system elements such as generators and transmission lines. Therefore, out-of-step detection is essential to operate a system safely. Also, a multi-agent system is one that consists of a number of agents, which interact with one another. Multi-agent systems(MAS) can offer the flexibility and the adaptability to the previous algorithm. In this paper, the detection algorithm of out-of-step is designed by multi-agent system and implemented by EMTP-MODELS. To verify performance of the proposed algorithm based on multi-agent system, simulations by EMTP have been carried out.

• Proceedings of the KIEE Conference
• /
• 2007.07a
• /
• pp.691-693
• /
• 2007

KEPCO, a Korean utility, has been operating a new lightning detection network since 2006. The lightning data detected by the new system named as Kepco Lightning Detection & information Network(KLDNet) is presented, and compared with ten-years-old-statistics accumulated by LPATS in order to look over the detection abilities.

• Journal of the Korea Institute of Information Security & Cryptology
• /
• v.34 no.1
• /
• pp.71-82
• /
• 2024

With the advancement of information and communication technology (ICT), the use of electronic document types such as PDF, MS Office, and HWP files has increased. Such trend has led the cyber attackers increasingly try to spread malicious documents through e-mails and messengers. To counter such attacks, AI-based methodologies have been actively employed in order to detect malicious document files. The main challenge in detecting malicious HWP(Hangul Word Processor) files is the lack of quality dataset due to its usage is limited in Korea, compared to PDF and MS-Office files that are highly being utilized worldwide. To address this limitation, data augmentation have been proposed to diversify training data by transforming existing dataset, but as the usefulness of the augmented data is not evaluated, augmented data could end up harming model's performance. In this paper, we propose an effective semi-supervised learning technique in detecting malicious HWP document files, which improves overall AI model performance via quantifying the utility of augmented data and filtering out useless training data.

• Journal of information and communication convergence engineering
• /
• v.21 no.1
• /
• pp.98-102
• /
• 2023

This paper presents a study on how augmenting semi-synthetic image data improves the performance of human detection algorithms. In the field of object detection, securing a high-quality data set plays the most important role in training deep learning algorithms. Recently, the acquisition of real image data has become time consuming and expensive; therefore, research using synthesized data has been conducted. Synthetic data haves the advantage of being able to generate a vast amount of data and accurately label it. However, the utility of synthetic data in human detection has not yet been demonstrated. Therefore, we use You Only Look Once (YOLO), the object detection algorithm most commonly used, to experimentally analyze the effect of synthetic data augmentation on human detection performance. As a result of training YOLO using the Penn-Fudan dataset, it was shown that the YOLO network model trained on a dataset augmented with synthetic data provided high-performance results in terms of the Precision-Recall Curve and F1-Confidence Curve.

• Proceedings of the Korean Institute of Electrical and Electronic Material Engineers Conference
• /
• 2002.05c
• /
• pp.189-193
• /
• 2002

Outage caused by contaminated insulator on high voltage transmission line and in substation is major concern for utility world-wide. To prevent these outages, it is necessary to develop an automatic salt contamination detecting device which provide the information about contamination level on utility for engineer to meet the emergency in advance. For that purpose, we have been developing an automatic salt contamination detecting device to monitor a salt amount on operating power utility area. In the salt contamination detecting device development, the most important thing is the sensor which can detect a salt amount and the understanding of sensor' s detecting principle. This paper describes the operating principle of the sensor and the experimental results about the detecting of salt amount. The results of this experiment wi1l be useful for detecting the contamination level.

• Proceedings of the KIEE Conference
• /
• 1995.07a
• /
• pp.440-442
• /
• 1995

In a recently as renewable energy source photovoltaic(PV) system using solar energy has been very widely researched because of its pollution-free and infinity. Especially many researches are intensively focused on small scale utility interactive PV system which can use dead space and easily make power stabilized from unstable natural energy source. In this system one of the most important matters is islanding protection. Islanding phenomenon appears when power failure occurs. For the safety of utility interactive PV system must has the function of not only system protection but also detection of islanding. This paper describes parallel operating alghorithm using reactive power variation method and twin peak band pass filter. This alghorithm is verified useful by simulation.

• Journal of Ocean Engineering and Technology
• /
• v.23 no.1
• /
• pp.122-128
• /
• 2009

In this study, damage detection method using harmony search method and frequency response is proposed. In order to verify this method, the following approaches are implemented. Firstly, damage detection method using harmony search was developed. To detect damage, objective functions that minimize difference with natural frequency and modal strain energy from undamaged and damaged model are used. Secondly, efficiency of developed damage detection method was verified by damage detection of beam structure. And results of harmony search and micro genetic algorithm are compared and evaluated. Thirdly, numerical model was implemented for harbor caisson structure and damage scenario was determined. Lastly, damage detection was performed by proposed method and utility of proposed method is verified.

• Transactions of the Korean Society of Mechanical Engineers B
• /
• v.29 no.11 s.242
• /
• pp.1220-1228
• /
• 2005

Fault detection and diagnostic (FDD) systems have the potential to reduce equipment downtime, service costs, and utility costs. In this study, model based algorithm and fuzzy algorithm were used to detect and diagnose various fault at System multi-air conditioner. various fault include the Refrigerant Low charging, Fouling of Indoor Heat Exchanger, Fouling of Outdoor Heat Exchanger A experimental verification was conducted in the 6HP System multi-air conditioner on an 8-floor building. Test results showed diagnosis result about 78 $\~$ 90$\%$ for given faults. This Study lays the foundation fur future work on develope the real-time fault detection and diagnosis system for the System multi-air conditioner.

• Proceedings of the KIEE Conference
• /
• 2003.07a
• /
• pp.335-337
• /
• 2003

The protection against transient instability and consequent out-of-step condition is a major concern for the utility. The unstable system may cause serious damage to system elements such as generators and transmission lines. Therefore, out-of-step detection is essential to operate a system safely. This paper presents the Out-of-Step detection algorithm using voltage frequency variation. The digital filters based on Discrete Fourier Transforms (DFT) to calculate the frequency of a sinusoid voltage are used, and the generator angle is estimated using the variation of the calculated voltage frequency. The proposed out-of-step algorithm is based on the assessment of a transient stability using equal area criterion. The proposed out-of-step algorithm is verified and tested by using EMTP MODELS.