• International Journal of Highway Engineering
• /
• v.14 no.2
• /
• pp.11-17
• /
• 2012

This research describes how to predict a model of the tensile strain related to the fatigue cracking performance of several asphalt concrete structures through design of experiments(e.g., Response Surface Methodology) and harmony search(HS) algorithm. The axisymmetric analysis program of finite element method, which is the KICTPAVE, was used to determine the strain level at the interface layer between asphalt layer and lean concrete layer. Once the training database set of various strain levels was constructed under the several condition of layer stiffnesses and thicknesses in the asphalt concrete structures, the data set was trained through the HS algorithm in order to determine the regression coefficients defined based on a response surface methodology. Furthermore, the testing set, which was not used for the training procedure of HS algorithm, was also constructed in order to evaluate whether the regression coefficients of a prediction model can be appropriately applied for other cases in asphalt concrete structures.

• The Bulletin of The Korean Astronomical Society
• /
• v.44 no.2
• /
• pp.78.1-78.1
• /
• 2019

There are a huge number of faint objects that have not been observed due to the lack of large and deep surveys. In this study, we demonstrate that a deep learning approach can produce a better quality deep image from a single pass imaging so that could be an alternative of conventional image stacking technique or the expensive large and deep surveys. Using data from the Sloan Digital Sky Survey (SDSS) stripe 82 which provide repeatedly scanned imaging data, a training data set is constructed: g-, r-, and i-band images of single pass data as an input and r-band co-added image as a target. Out of 151 SDSS fields that have been repeatedly scanned 34 times, 120 fields were used for training and 31 fields for validation. The size of a frame selected for the training is 1k by 1k pixel scale. To avoid possible problems caused by the small number of training sets, frames are randomly selected within that field each iteration of training. Every 5000 iterations of training, the performance were evaluated with RMSE, peak signal-to-noise ratio which is given on logarithmic scale, structural symmetry index (SSIM) and difference in SSIM. We continued the training until a GAN model with the best performance is found. We apply the best GAN-model to NGC0941 located in SDSS stripe 82. By comparing the radial surface brightness and photometry error of images, we found the possibility that this technique could generate a deep image with statistics close to the stacked image from a single-pass image.

• Journal of the Korean Society of Fisheries and Ocean Technology
• /
• v.44 no.2
• /
• pp.112-119
• /
• 2008

The fundamental data on the catch fluctuation in the rectangular set net according to the tide age were developed based on the catches recorded from the year 1986 to 2004 in the coastal waters of Hamdeok, Jeju. Total catch by the rectangular set net had a deep connection with the tide age. In particular, during increasing tide, total catch were reduced gradually from the neap tide to the high tide. As it turned out, the slope of total catch declined by degree and showed a correlation coefficient of determination of 0.76. On the contrary, in the case of decreasing tide, there was little sign of rise in total catch. In particular, large catch seemed to occur at the next tide to the neap tide. In the relation between the catch and the tide age, the level of the correlation coefficient chosen at $p{\leq}0.05$ decreased in the order rabbitfish(-0.84) and horse mackerel(-0.71), while the significance of other dominant species were not selected.

• The Bulletin of The Korean Astronomical Society
• /
• v.36 no.2
• /
• pp.64-64
• /
• 2011

We present a new quasi-stellar object (QSO) selection algorithm using a Support Vector Machine, a supervised classification method, on a set of extracted time series features including period, amplitude, color, and autocorrelation value. We train a model that separates QSOs from variable stars, non-variable stars, and microlensing events using 58 known QSOs, 1629 variable stars, and 4288 non-variables in the MAssive Compact Halo Object (MACHO) database as a training set. To estimate the efficiency and the accuracy of the model, we perform a cross-validation test using the training set. The test shows that the model correctly identifies ~80% of known QSOs with a 25% false-positive rate. The majority of the false positives are Be stars. We applied the trained model to the MACHO Large Magellanic Cloud (LMC) data set, which consists of 40 million lightcurves, and found 1620 QSO candidates. During the selection, none of the 33,242 known MACHO variables were misclassified as QSO candidates. In order to estimate the true false-positive rate, we crossmatched the candidates with astronomical catalogs including the Spitzer Surveying the Agents of a Galaxy's Evolution (SAGE) LMC catalog and a few X-ray catalogs. The results further suggest that the majority of the candidates, more than 70%, are QSOs.

• Proceedings of the Korean Society for Agricultural Machinery Conference
• /
• 1993.10a
• /
• pp.1273-1281
• /
• 1993

Estimation of daily and seasonal evaportranspiration is essential for water resource planning irrigation feasibility study, and real-time irrigation water management . This paper is to evaluate the applicability of neural networks to the estimation of evapotranspiration . A neural network was developed to forecast daily evapotranspiration of the rice crop. It is a three-layer network with input, hidden , and output layers. Back-propagation algorithm with delta learning rule was used to train the neural network. Training neural network wasconducted usign daily actural evapotranspiration of rice crop and daily climatic data such as mean temperature, sunshine hours, solar radiation, relative humidity , and pan evaporation . During the training, neural network parameters were calibrated. The trained network was applied to a set of field data not used in the training . The created response of the neural network was in good agreement with desired values. Evaluating the neural networ performance indicates that neural network may be applied to the estimation of evapotranspiration of the rice crop.

• Geomechanics and Engineering
• /
• v.33 no.3
• /
• pp.231-242
• /
• 2023

This paper represents a comparative study in which Gene Expression Programming (GEP), Group Method of Data Handling (GMDH), and multiple linear regressions (MLR) were utilized to derive new equations for the prediction of time-dependent bearing capacity of pile foundations driven in cohesive soil, technically called pile set-up. This term means that many piles which are installed in cohesive soil experience a noticeable increase in bearing capacity after a specific time. Results of researches indicate that side resistance encounters more increase than toe resistance. The main reason leading to pile setup in saturated soil has been found to be the dissipation of excess pore water pressure generated in the process of pile installation, while in unsaturated conditions aging is the major justification. In this study, a comprehensive dataset containing information about 169 test piles was obtained from literature reviews used to develop the models. to prepare the data for further developments using intelligent algorithms, Data mining techniques were performed as a fundamental stage of the study. To verify the models, the data were randomly divided into training and testing datasets. The most striking difference between this study and the previous researches is that the dataset used in this study includes different piles driven in soil with varied geotechnical characterization; therefore, the proposed equations are more generalizable. According to the evaluation criteria, GEP was found to be the most effective method to predict set-up among the other approaches developed earlier for the pertinent research.

• Journal of the Korea Institute of Information Security & Cryptology
• /
• v.30 no.4
• /
• pp.617-629
• /
• 2020

In order to overcome the limitations of the rule-based intrusion detection system due to changes in Internet computing environments, the emergence of new services, and creativity of attackers, network anomaly detection (NAD) using machine learning and deep learning technologies has received much attention. Most of these existing machine learning and deep learning technologies for NAD use supervised learning methods to learn a set of training data set labeled 'normal' and 'attack'. This paper presents the feasibility of the unsupervised learning AutoEncoder(AE) to NAD from data sets collecting of secured network traffic without labeled responses. To verify the performance of the proposed AE mode, we present the experimental results in terms of accuracy, precision, recall, f1-score, and ROC AUC value on the NSL-KDD training and test data sets. In particular, we model a reference AE through the deep analysis of diverse AEs varying hyper-parameters such as the number of layers as well as considering the regularization and denoising effects. The reference model shows the f1-scores 90.4% and 89% of binary classification on the KDDTest+ and KDDTest-21 test data sets based on the threshold of the 82-th percentile of the AE reconstruction error of the training data set.

• Journal of Korea Multimedia Society
• /
• v.19 no.1
• /
• pp.22-29
• /
• 2016

Hidden Markov Model is one of the most successful and popular tools for modeling real world sequential data. Real world signals come in a variety of shapes and variabilities, among which temporal and spectral ones are the prime targets that the HMM aims at. A new problem that is gaining increasing attention is characterizing missing observations in incomplete data sequences. They are incomplete in that there are holes or omitted measurements. The standard HMM algorithms have been developed for complete data with a measurements at each regular point in time. This paper presents a modified algorithm for a discrete HMM that allows substantial amount of omissions in the input sequence. Basically it is a variant of Baum-Welch which explicitly considers the case of isolated or a number of omissions in succession. The algorithm has been tested on online handwriting samples expressed in direction codes. An extensive set of experiments show that the HMM so modeled are highly flexible showing a consistent and robust performance regardless of the amount of omissions.

• Proceedings of the Korea Contents Association Conference
• /
• 2018.05a
• /
• pp.459-460
• /
• 2018

In this paper, we present a data augmentation method that generates synthetic plant disease images using Generative Adversarial Networks (GANs). We propose a training scheme that first uses classical data augmentation techniques to enlarge the training set and then further enlarges the data size and its diversity by applying GAN techniques for synthetic data augmentation. Our method is demonstrated on a limited dataset of 2789 images of tomato plant diseases (Gray mold, Canker, Leaf mold, Plague, Leaf miner, Whitefly etc.).

• Journal of the Korean Institute of Illuminating and Electrical Installation Engineers
• /
• v.20 no.9
• /
• pp.18-23
• /
• 2006

This paper presents an operator training simulator for power system restoration against massive blackout. The system is designed especially focused on the generality and convenient setting up for initial condition of simulation. The former is accomplished by using power flow calculation methodology, and PSS/E data is used to set up the initial state for easy setting. The proposed simulator consists of three major components-a power flow(PF), a data conversion(CONV), and, a GUI module. The PF module calculates power flow, and then checks over-voltages of buses and overloads of lines. The CONV module composes a Y-Bus array and a database at each restoration action. The initial Y-Bus array is composed from PSS/E data. A user friendly GUI module is developed including a graphic editor and a built-in operation manual. The maximum processing time for one step operation is 15 seconds, which is adequate for training purpose.