• Journal of the Korean Operations Research and Management Science Society
• /
• v.35 no.2
• /
• pp.71-88
• /
• 2010

A density-based outlier detection such as an LOF (Local Outlier Factor) tries to find an outlying observation by using density of its surrounding space. In spite of several advantages of a density-based outlier detection method, the computational complexity of outlier detection has been one of major barriers in its application. In this paper, we present an LOF algorithm that can reduce computation time of a density based outlier detection algorithm. A kd-tree indexing and approximated k-nearest neighbor search algorithm (ANN) are adopted in the proposed method. A set of experiments was conducted to examine performance of the proposed algorithm. The results show that the proposed method can effectively detect local outliers in reduced computation time.

• Journal of Korea Society of Digital Industry and Information Management
• /
• v.6 no.4
• /
• pp.161-170
• /
• 2010

This paper provides a novel approach for a user oriented system for face detection system for application developers. Even though there are many open source or commercial libraries to solve the problem of face detection, they are still hard to use because they require specific knowledge on detail algorithmic techniques. The purpose of this paper is to come up with a high-level system for face detection with which users can develop systems easily and even without specific knowledge on face detection theories and algorithms. Important conditions are firstly considered to categorize the large problem space of face detection. The conditions identified here are then represented as expressions so that application developers can use them to express various problems. Once the conditions are expressed by developers, the interpreter proposed take the role to interpret the conditions, find and organize the optimal algorithms to solve the represented problem with corresponding conditions. A proof-of-concept is implemented and some example problems are tested and analyzed to show the ease of use and usability.

• IEIE Transactions on Smart Processing and Computing
• /
• v.4 no.4
• /
• pp.265-271
• /
• 2015

This study proposes an algorithm for recognizing apple trees in images and detecting apples to measure the number of apples on the trees. The proposed algorithm explores whether there are apple trees or not based on the number of image block-unit edges, and then it detects apple areas. In order to extract colors appropriate for apple areas, the CIE $L^*a^*b^*$ color space is used. In order to extract apple characteristics strong against illumination changes, modified census transform (MCT) is used. Then, using the AdaBoost learning algorithm, characteristics data on the apples are learned and generated. With the generated data, the detection of apple areas is made. The proposed algorithm has a higher detection rate than existing pixel-based image processing algorithms and minimizes false detection.

• Economic and Environmental Geology
• /
• v.57 no.4
• /
• pp.353-362
• /
• 2024

This study examined the spectral characteristics of sediments according to moisture content using an unmanned aerial vehicle (UAV)-based hyperspectral sensor and evaluated the efficiency of moisture content detection at different flight altitudes. For this purpose, hyperspectral images in the 400-1000nm wavelength range were acquired and analyzed at altitudes of 40m and 80m for sediment samples with various moisture contents. The reflectance of the sediments generally showed a decreasing trend as the moisture content increased. Correlation analysis between moisture content and reflectance showed a strong negative correlation (r < -0.8) across the entire 400-900nm range. The moisture content detection model constructed using the Random Forest technique showed detection accuracies of RMSE 2.6%, R² 0.92 at 40m altitude and RMSE 2.2%, R² 0.95 at 80m altitude, confirming that the difference in accuracy between altitudes was minimal. Variable importance analysis revealed that the 600-700nm band played a crucial role in moisture content detection. This study is expected to be utilized in efficient sediment moisture management and natural disaster prediction in the field of environmental monitoring in the future.

• Journal of The Korean Astronomical Society
• /
• v.56 no.2
• /
• pp.213-224
• /
• 2023

Type II solar radio bursts show frequency drifts from high to low over time. They have been known as a signature of coronal shock associated with Coronal Mass Ejections (CMEs) and/or flares, which cause an abrupt change in the space environment near the Earth (space weather). Therefore, early detection of type II bursts is important for forecasting of space weather. In this study, we develop a deep-learning (DL) model for the automatic detection of type II bursts. For this purpose, we adopted a 1-D Convolution Neutral Network (CNN) as it is well-suited for processing spatiotemporal information within the applied data set. We utilized a total of 286 radio burst spectrum images obtained by Hiraiso Radio Spectrograph (HiRAS) from 1991 and 2012, along with 231 spectrum images without the bursts from 2009 to 2015, to recognizes type II bursts. The burst types were labeled manually according to their spectra features in an answer table. Subsequently, we applied the 1-D CNN technique to the spectrum images using two filter windows with different size along time axis. To develop the DL model, we randomly selected 412 spectrum images (80%) for training and validation. The train history shows that both train and validation losses drop rapidly, while train and validation accuracies increased within approximately 100 epoches. For evaluation of the model's performance, we used 105 test images (20%) and employed a contingence table. It is found that false alarm ratio (FAR) and critical success index (CSI) were 0.14 and 0.83, respectively. Furthermore, we confirmed above result by adopting five-fold cross-validation method, in which we re-sampled five groups randomly. The estimated mean FAR and CSI of the five groups were 0.05 and 0.87, respectively. For experimental purposes, we applied our proposed model to 85 HiRAS type II radio bursts listed in the NGDC catalogue from 2009 to 2016 and 184 quiet (no bursts) spectrum images before and after the type II bursts. As a result, our model successfully detected 79 events (93%) of type II events. This results demonstrates, for the first time, that the 1-D CNN algorithm is useful for detecting type II bursts.

• Proceedings of the IEEK Conference
• /
• 2001.06d
• /
• pp.21-24
• /
• 2001

In this paper, we present a fast face detection algorithm by estimating the eye region using neural network. To implement a real time face detection system, it is necessary to reduce search space. We limit the search space just to a few pairs of eye candidates. For the selection of them, we first isolate possible eye regions in the fast and robust way by modified histogram equalization. The eye candidates are paired to form an eye pair and each of the eye pair is estimated how close it is to a true eye pair in two aspects : One is how similar the two eye candidates are in shape and the other is how close each of them is to a true eye image A multi-layer perceptron neural network is used to find the eye candidate region's closeness to the true eye image. Just a few best candidates are then verified by eigenfaces. The experimental results show that this approach is fast and reliable. We achieved 94% detection rate with average 0.1 sec Processing time in Pentium III PC in the experiment on 424 gray scale images from MIT, Yale, and Yonsei databases.

• Transactions of the Korean Society of Mechanical Engineers B
• /
• v.21 no.3
• /
• pp.427-435
• /
• 1997

Conditional sampling techniques are utilized to investigate the relation between the wall skin-friction and stream wise velocity fluctuations in a turbulent boundary layer. Conditionally averaged results using a peak detection and the VITA (variable-interval time-averaging) technique show that a high skin friction is associated with high frequency components of the wall skin-friction fluctuations. The conditionally averaged wall skin-friction fluctuations obtained by using the VITA technique have a positively-skewed characteristics compared with the conditionally averaged stream wise velocity fluctuations. It is confirmed that there exists a phase shift between the wall skin-friction and stream wise velocity fluctuations, which was also found from the long-time averaged space-time correlations. The amount of phase shift between the wall skin-friction and stream wise velocity fluctuations is the same as that from the long-time averaged space-time correlations and does not change despite the variation of the detection threshold.

• The Bulletin of The Korean Astronomical Society
• /
• v.38 no.2
• /
• pp.72.1-72.1
• /
• 2013

Even though current microlensing follow-up observations focus on high-magnification events due to the high efficiency of planet detection, it is very difficult to do a confident detection of planets in high-magnification events with extremely weak central perturbations (i.e., the fractional deviation is ${\delta}{\leq}0.02$). For the confident detection of planets in the extremely weak central perturbation events, it is needed both the high cadence monitoring and the high photometric accuracy. A next-generation ground-based observation project, KMTNet (Korea Microlensing Telescope Network), satisfies both the conditions. Here we investigate how well planets in high-magnification events with extremely weak central perturbations are detected by KMTNet. First, we determine the probability of occurrence of events with ${\delta}{\leq}0.02$. From this, we find that for ${\leq}100M_E$ planets in the separation of $0.2AU{\leq}d{\leq}20AU$, events with ${\delta}{\leq}0.02$ occur with a frequency of more than 70%, in which d is the projected planet-star separation. Second, we estimate the efficiency of detecting planetary signals in the events with ${\delta}{\leq}0.02$ via KMTNet. We find that for main-sequence and subgiant source stars, ${\geq}1M_E$ planets can be detected more than 50% in a certain range that has the efficiency of ${\geq}10%$ and changes with the planet mass.

• Proceedings of the Korean Information Science Society Conference
• /
• 2011.06b
• /
• pp.313-316
• /
• 2011

SRAM-based FPGAs are very sensitive to single event upset(SEU) induced by space irradiation. To mitigate SEU effects, space applications employ some mitigation schemes. The triple modular redundancy(TMR) is a well-known mitigation scheme. It uses one or three voters as well as three identical blocks performing the same work. The voters can mask out one error in the outputs from the three replicated blocks. One SEU error in TMRed circuits can be masked but it needs to be detected for some reasons such as to analyze the SEU effects in the satellite or to recover the circuits from the error before additional error occur. In this paper, we developed a fault detection circuit and reporting system to detect a fault on the TMRed circuits. To verify our error detection circuit and reporting circuit, we performed an irradiation test at MC-50 Cyclotron. Experimental results showed that error detection circuit can detect a fault on the TMRed test circuit in radiation environment.

• Smart Structures and Systems
• /
• v.6 no.2
• /
• pp.115-133
• /
• 2010

A modal filter is a tool used to extract the modal coordinates of each individual mode from a system's output. This is achieved by mapping the response vector from the physical space to the modal space. It decomposes the system's responses into modal coordinates, and thus, on the output of the filter, the frequency response with only one peak corresponding to the natural frequency to which the filter was tuned can be obtained. As was shown in the paper (Deraemecker and Preumont 2006), structural modification (e.g. a drop in stiffness or mass due to damage) causes the appearance of spurious peaks on the output of the modal filter. A modal filter is, therefore, a great indicator of damage detection, with such advantages as low computational effort due to data reduction, ease of automation and lack of sensitivity to environmental changes. This paper presents the application of modal filters for the detection of stiffness changes. Two experiments were conducted: the first one using the simulation data obtained from the numerical 7DOF model, and the second one on the experimental data from a laboratory stand in 4 states of damage.