• Journal of the Institute of Electronics and Information Engineers
• /
• v.51 no.9
• /
• pp.111-118
• /
• 2014

This paper presents an efficient Markov feature extraction method for detecting splicing forged images. The Markov states used in our method are composed of the difference between DCT coefficients in the adjacent blocks. Various first-order Markov state transition probabilities are extracted as features for splicing detection. In addition, we propose a feature reduction algorithm by analysing the distribution of the Markov probability. After training the extracted feature vectors using the SVM classifier, we determine whether the presence of the image splicing forgery. Experimental results verify that the proposed method shows good detection performance with a smaller number of features compared to existing methods.

• The Journal of the Korea Contents Association
• /
• v.14 no.6
• /
• pp.499-512
• /
• 2014

Architecture is usually seen as a product of art and technology. However, most historical buildings also exemplify various sophisticated principles of mathematics. Outstanding examples of architecture around the world such as Seokguram, Daewoongjun of Bulguksa, Muryangsujeon of Buseoksa, and the Parthenon provide students with a great opportunity to study their underlying mathematical properties and principles. The activity of identifying and investigating such mathematical principles in historical buildings enables students to realize that mathematics is a practical subject, and thus provides justification for the study and importance of mathematics. For the purpose of this study historical architecture was reviewed with this in mind in order to develop STEAM education materials focused on elementary school mathematics. The result of this study is as follows: first of all, appropriate examples of historical architecture were selected on the basis of the 2009 revised curriculum's content and teaching goals. These involved chapters on 'proportion', 'symmetry', 'movement of figures', 'building blocks', and 'triangles'. Secondly, a meta-analysis was performed on the historical buildings that clearly illustrate mathematical principles. Thirdly, STEAM education materials focused on elementary mathematics using architectural examples were developed which made actual application in classrooms possible. And lastly, surveys of professional groups were conducted to verify whether the produced materials were suitable teaching resources.

• Journal of The Korean Association For Science Education
• /
• v.34 no.3
• /
• pp.221-233
• /
• 2014

In this study, we analyzed verbal interactions among 32 students in 7th graders' science cooperative learning at the levels of turns, interaction units, and conflict behavior units, and compared their verbal interaction patterns between the heterogeneous and homogeneous groups by students' collectivism. The relationships of verbal interactions with the achievement test scores and the increase of the achievement test scores were also investigated. In the analyses of turns, the distributions of the subcategories of the statements related to the task were found to be similar in both groups, and the frequency of 'explain' was highest. The frequencies of interaction units were higher in the homogeneous groups than the heterogeneous groups, and the frequency of 'symmetric interaction' was highest. In the heterogeneous groups, the frequencies of turns and interaction units for the students of high collectivism were higher than those of low collectivism. The frequencies of conflict behavior units were generally low, but the rates were similar in both groups. In the case of the homogeneous groups, the frequencies of 'avoiding' and 'competing' for the students of low collectivism were high, and the frequency of 'cooperating' for the students of high collectivism was high. In addition, the qualitative differences between the two groups were found in the interaction units and conflict behavior units. The achievement test scores and the increase of the achievement test scores were positively related with the sum of the frequencies of the statements related to the task.

• The Korean Journal of Applied Statistics
• /
• v.36 no.2
• /
• pp.101-114
• /
• 2023

The data augmentation technique is effectively used to solve the problem of overfitting the model by allowing the training dataset to be viewed from various perspectives. In addition to image augmentation techniques such as rotation, cropping, horizontal flip, and vertical flip, occlusion-based data augmentation methods such as Cutmix and Cutout have been proposed. For models based on speech data, it is possible to use an occlusion-based data-based augmentation technique after converting a 1D speech signal into a 2D spectrogram. In particular, SpecAugment is an occlusion-based augmentation technique for speech spectrograms. In this study, we intend to compare and study data augmentation techniques that can be used in the problem of false-voice detection. Using data from the ASVspoof2017 and ASVspoof2019 competitions held to detect fake audio, a dataset applied with Cutout, Cutmix, and SpecAugment, an occlusion-based data augmentation method, was trained through an LCNN model. All three augmentation techniques, Cutout, Cutmix, and SpecAugment, generally improved the performance of the model. In ASVspoof2017, Cutmix, in ASVspoof2019 LA, Mixup, and in ASVspoof2019 PA, SpecAugment showed the best performance. In addition, increasing the number of masks for SpecAugment helps to improve performance. In conclusion, it is understood that the appropriate augmentation technique differs depending on the situation and data.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.21 no.5
• /
• pp.14-21
• /
• 2020

In order to provide confidential services between two communicating parties, block data encryption using a symmetric secret key is applied. A power analysis attack on a cryptosystem is a side channel-analysis method that can extract a secret key by measuring the power consumption traces of the crypto device. In this paper, we propose an attack model that can recover the secret key using a power analysis attack based on a deep learning convolutional neural network (CNN) algorithm. Considering that the CNN algorithm is suitable for image analysis, we particularly adopt the recurrence plot (RP) signal processing method, which transforms the one-dimensional power trace into two-dimensional data. As a result of executing the proposed CNN attack model on an XMEGA128 experimental board that implemented the AES-128 encryption algorithm, we recovered the secret key with 22.23% accuracy using raw power consumption traces, and obtained 97.93% accuracy using power traces on which we applied the RP processing method.

• Journal of Educational Research in Mathematics
• /
• v.18 no.2
• /
• pp.239-261
• /
• 2008

This study presents results by the content areas in mathematics. Average performance is provided for five content areas: number, algebra, measurement, geometry, and data. Relative achievement is shown among the content areas for 4 countries in comparison to Korea. In number, Korea had lower average achievement than Singapore, especially for ratio proportion percent. Among 5 countries, Korea had the highest average achievement in algebra and geometry, but the lowest in attributes and units of measurement. In data, Korean students didn't learn the followings successfully: a) comparing characteristics of data sets and using mean, median, range, and shape of distribution, b) interpreting data sets (e.g., draw conclusions, make predictions, and estimate values between and beyond given data points), c) evaluating interpretations of data with respect to correctness and completeness of interpretation.

• Journal of The Korean Association For Science Education
• /
• v.37 no.1
• /
• pp.87-101
• /
• 2017

The analysis was carried out with meta-analysis on master's and doctoral dissertations, and academic journals that analyzed the effects of STEAM education between 2012 and 2015. From the total number of 75 dissertations and articles analyzed, 183 different effect sizes were calculated. The analysis was done to find out the kinds of differences that would be created according to the effect size of creativity, problem-solving ability, and researcher, target area, student division research design type, and level of schools. The total effect size of creativity scored 0.776, and demonstrated satisfaction in symmetry of funnel plot, with no publication biases. The fail-safe N scored 780, and since the number is smaller than 8,945, the results of this research has credibility. Furthermore, problem-solving ability shows intermediate level of effect size with a score of 0.584. It also showed satisfaction in symmetry with funnel plot, with no publication bias. With the different research methods of the sub-factors of creativity, fluency scored the highest with 0.929, flexibility with 0.881, originality with 0.838, sophistication with 0.653, abstractness with title 0.705, and resistance to termination, 0.527. This study finds its significance in the demonstration of average effect size of STEAM education through meta-analysis. According to research results, the effects of inclusive education could be determined, yet the specific effect cause or learning principles were difficult to find. It was found that the effects of STEAM education do not rise or fall depending on school age, and demonstrated differences in creativity according to the research methods or the researchers.

• Communications of Mathematical Education
• /
• v.24 no.2
• /
• pp.445-474
• /
• 2010

The results of performing first survey after learning linear equation and second survey after 5 months to find out whether there is change in solving process while seventh grade students solve linear equations are as follows. First, as a result of performing McNemar Test in order to find out the correct answer ratio between first survey and second survey, it was shown as $p=.035^a$ in problem x+4=9 and $p=.012^a$ in problem $x+\frac{1}{4}=\frac{2}{3}$ of problem type A while being shown as $p=.012^a$ in problem x+3=8 and $p=.035^a$ in problem 5(x+2)=20 of problem type B. Second, while there were students not making errors in the second survey among students who made errors in the solving process of problem type A and B, students making errors in the second survey among the students who expressed the solving process correctly in the first survey were shown. Third, while there were students expressing the solving process of linear equation correctly for all problems (type A, type B and type C), there were students expressing several problems correctly and unable to do so for several problems. In conclusion, even if a student has expressed the solving process correctly on all problems, it would be difficult to foresee that the student is able to express properly in the solving process when another problem is given. According to the result of analyzing the reaction of students toward three problem types (type A, type B and type C), it is possible to determine whether a certain student is 'able' or 'unable' to express the solving process of linear equation by analyzing the problem solving process.

• Journal of Intelligence and Information Systems
• /
• v.23 no.2
• /
• pp.107-122
• /
• 2017

Volatility in the stock market returns is a measure of investment risk. It plays a central role in portfolio optimization, asset pricing and risk management as well as most theoretical financial models. Engle(1982) presented a pioneering paper on the stock market volatility that explains the time-variant characteristics embedded in the stock market return volatility. His model, Autoregressive Conditional Heteroscedasticity (ARCH), was generalized by Bollerslev(1986) as GARCH models. Empirical studies have shown that GARCH models describes well the fat-tailed return distributions and volatility clustering phenomenon appearing in stock prices. The parameters of the GARCH models are generally estimated by the maximum likelihood estimation (MLE) based on the standard normal density. But, since 1987 Black Monday, the stock market prices have become very complex and shown a lot of noisy terms. Recent studies start to apply artificial intelligent approach in estimating the GARCH parameters as a substitute for the MLE. The paper presents SVR-based GARCH process and compares with MLE-based GARCH process to estimate the parameters of GARCH models which are known to well forecast stock market volatility. Kernel functions used in SVR estimation process are linear, polynomial and radial. We analyzed the suggested models with KOSPI 200 Index. This index is constituted by 200 blue chip stocks listed in the Korea Exchange. We sampled KOSPI 200 daily closing values from 2010 to 2015. Sample observations are 1487 days. We used 1187 days to train the suggested GARCH models and the remaining 300 days were used as testing data. First, symmetric and asymmetric GARCH models are estimated by MLE. We forecasted KOSPI 200 Index return volatility and the statistical metric MSE shows better results for the asymmetric GARCH models such as E-GARCH or GJR-GARCH. This is consistent with the documented non-normal return distribution characteristics with fat-tail and leptokurtosis. Compared with MLE estimation process, SVR-based GARCH models outperform the MLE methodology in KOSPI 200 Index return volatility forecasting. Polynomial kernel function shows exceptionally lower forecasting accuracy. We suggested Intelligent Volatility Trading System (IVTS) that utilizes the forecasted volatility results. IVTS entry rules are as follows. If forecasted tomorrow volatility will increase then buy volatility today. If forecasted tomorrow volatility will decrease then sell volatility today. If forecasted volatility direction does not change we hold the existing buy or sell positions. IVTS is assumed to buy and sell historical volatility values. This is somewhat unreal because we cannot trade historical volatility values themselves. But our simulation results are meaningful since the Korea Exchange introduced volatility futures contract that traders can trade since November 2014. The trading systems with SVR-based GARCH models show higher returns than MLE-based GARCH in the testing period. And trading profitable percentages of MLE-based GARCH IVTS models range from 47.5% to 50.0%, trading profitable percentages of SVR-based GARCH IVTS models range from 51.8% to 59.7%. MLE-based symmetric S-GARCH shows +150.2% return and SVR-based symmetric S-GARCH shows +526.4% return. MLE-based asymmetric E-GARCH shows -72% return and SVR-based asymmetric E-GARCH shows +245.6% return. MLE-based asymmetric GJR-GARCH shows -98.7% return and SVR-based asymmetric GJR-GARCH shows +126.3% return. Linear kernel function shows higher trading returns than radial kernel function. Best performance of SVR-based IVTS is +526.4% and that of MLE-based IVTS is +150.2%. SVR-based GARCH IVTS shows higher trading frequency. This study has some limitations. Our models are solely based on SVR. Other artificial intelligence models are needed to search for better performance. We do not consider costs incurred in the trading process including brokerage commissions and slippage costs. IVTS trading performance is unreal since we use historical volatility values as trading objects. The exact forecasting of stock market volatility is essential in the real trading as well as asset pricing models. Further studies on other machine learning-based GARCH models can give better information for the stock market investors.