• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.10 no.1
• /
• pp.321-340
• /
• 2016

The Compressive Video Sensing (CVS) is a useful technology for wireless systems requiring simple encoders but handling more complex decoders, and its rate-distortion performance is highly affected by the quantization of measurements and reconstruction of video frame, which motivates us to presents the Space-Time Quantization (ST-Q) and Motion-Aligned Reconstruction (MA-R) in this paper to both improve the performance of CVS system. The ST-Q removes the space-time redundancy in the measurement vector to reduce the amount of bits required to encode the video frame, and it also guarantees a low quantization error due to the fact that the high frequency of small values close to zero in the predictive residuals limits the intensity of quantizing noise. The MA-R constructs the Multi-Hypothesis (MH) matrix by selecting the temporal neighbors along the motion trajectory of current to-be-reconstructed block to improve the accuracy of prediction, and besides it reduces the computational complexity of motion estimation by the extraction of static area and 3-D Recursive Search (3DRS). Extensive experiments validate that the significant improvements is achieved by ST-Q in the rate-distortion as compared with the existing quantization methods, and the MA-R improves both the objective and the subjective quality of the reconstructed video frame. Combined with ST-Q and MA-R, the CVS system obtains a significant rate-distortion performance gain when compared with the existing CS-based video codecs.

• Journal of the Institute of Electronics Engineers of Korea SP
• /
• v.41 no.2
• /
• pp.79-88
• /
• 2004

Gaze detection is to locate the position on a monitor screen where a user is looking by computer vision. Gaze detection systems have numerous fields of application. They are applicable to the man-machine interface for helping the handicapped to use computers and the view control in three dimensional simulation programs. In our work, we implement it with a computer vision system setting a IR-LED based single camera. To detect the gaze position, we locate facial features, which is effectively performed with IR-LED based camera and SVM(Support Vector Machine). When a user gazes at a position of monitor, we can compute the 3D positions of those features based on 3D rotation and translation estimation and affine transform. Finally, the gaze position by the facial movements is computed from the normal vector of the plane determined by those computed 3D positions of features. In addition, we use a trained neural network to detect the gaze position by eye's movement. As experimental results, we can obtain the facial and eye gaze position on a monitor and the gaze position accuracy between the computed positions and the real ones is about 4.8 cm of RMS error.

• Journal of Institute of Control, Robotics and Systems
• /
• v.10 no.12
• /
• pp.1295-1304
• /
• 2004

In this paper, the Bayesian recurrent neural network is proposed to predict time series data. A neural network predictor requests proper learning strategy to adjust the network weights, and one needs to prepare for non-linear and non-stationary evolution of network weights. The Bayesian neural network in this paper estimates not the single set of weights but the probability distributions of weights. In other words, the weights vector is set as a state vector of state space method, and its probability distributions are estimated in accordance with the particle filtering process. This approach makes it possible to obtain more exact estimation of the weights. In the aspect of network architecture, it is known that the recurrent feedback structure is superior to the feedforward structure for the problem of time series prediction. Therefore, the recurrent neural network with Bayesian inference, what we call Bayesian recurrent neural network (BRNN), is expected to show higher performance than the normal neural network. To verify the proposed method, the time series data are numerically generated and various kinds of neural network predictor are applied on it in order to be compared. As a result, feedback structure and Bayesian learning are better than feedforward structure and backpropagation learning, respectively. Consequently, it is verified that the Bayesian reccurent neural network shows better a prediction result than the common Bayesian neural network.

• Structural Engineering and Mechanics
• /
• v.57 no.4
• /
• pp.657-680
• /
• 2016

Reinforced concrete (RC) deep beams are structural members that predominantly fail in shear. Therefore, determining the shear strength of these types of beams is very important. The strut-and-tie method is commonly used to design deep beams, and this method has been adopted in many building codes (ACI318-14, Eurocode 2-2004, CSA A23.3-2004). In this study, the efficiency of artificial neural networks (ANNs) in predicting the shear strength of RC deep beams is investigated as a different approach to the strut-and-tie method. An ANN model was developed using experimental data for 214 normal and high-strength concrete deep beams from an existing literature database. Seven different input parameters affecting the shear strength of the RC deep beams were selected to create the ANN structure. Each parameter was arranged as an input vector and a corresponding output vector that includes the shear strength of the RC deep beam. The ANN model was trained and tested using a multi-layered back-propagation method. The most convenient ANN algorithm was determined as trainGDX. Additionally, the results in the existing literature and the accuracy of the strut-and-tie model in ACI318-14 in predicting the shear strength of the RC deep beams were investigated using the same test data. The study shows that the ANN model provides acceptable predictions of the ultimate shear strength of RC deep beams (maximum $R^2{\approx}0.97$). Additionally, the ANN model is shown to provide more accurate predictions of the shear capacity than all the other computed methods in this study. The ACI318-14-STM method was very conservative, as expected. Moreover, the study shows that the proposed ANN model predicts the shear strengths of RC deep beams better than does the strut-and-tie model approaches.

• IEIE Transactions on Smart Processing and Computing
• /
• v.1 no.3
• /
• pp.161-170
• /
• 2012

This paper presents an efficient and robust approach for determining the correspondence between unbalanced stereo images. The disparity vectors were used instead of feature points, such as corners, to calculate a correspondence relationship. For a faster and optimal estimation, the vectors were classified into several regions, and the homography of each region was calculated using the RANSAC algorithm. The correspondence image was calculated from the images transformed by each homography. Although it provided good results under normal conditions, it was difficult to obtain reliable results in an unbalanced stereo pair. Therefore, a balancing method is also proposed to minimize the unbalance effects using the histogram specification and structural similarity index. The experimental results showed that the proposed approach outperformed the baseline algorithms with respect to the speed and peak-signal-to-noise ratio. This work can be applied to practical fields including 3D depth map acquisition, fast stereo coding, 2D-to-3D conversion, etc.

• 한국전산유체공학회:학술대회논문집
• /
• 2008.03b
• /
• pp.568-571
• /
• 2008

The computation of moving interface by the level set method typically requires reinitializations of level set function. An inaccurate estimation of level set function ${\phi}$ results in incorrect free-surface capturing and thus errors such as mass gain/loss. Therefore, accurate and robust reinitialization process is essential to the free-surface flows. In the present paper, we pursue further development of the reinitialization process, which evaluates directly level set function ${\phi}$ using a normal vector in the interface without solving the re-distancing equation of hyperbolic type. The Taylor-Galerkin approximation and P1P1splitting FEM are adopted to discretize advection equation of the level set function and the Navier-Stokes equation, respectively. Advection equation of free surface and re-initialization process are validated with benchmark problems, i.e., a broken dam flow and time-reversed single vortex flow. The simulation results are in good agreement with the existing results.

• Transactions of the Korean Society of Mechanical Engineers B
• /
• v.32 no.10
• /
• pp.754-760
• /
• 2008

Computation of moving interface by the level set method typically requires the reinitialization of level set function. An inaccurate estimation of level set function $\phi$ results in incorrect free-surface capturing and thus errors such as mass gain/loss. Therefore, an accurate and robust reinitialization process is essential to the simulation of free-surface flows. In the present paper, we pursue further development of the reinitialization process, which evaluates level set function directly using a normal vector on the interface without solving there-distancing equation of hyperbolic type. The Taylor-Galerkin approximation and P1P1 splitting/SUPG (Streamline Upwind Petrov-Galerkin) FEM are adopted to discretize advection equation of the level set function and the incompressible Navier-Stokes equation, respectively. Advection equation and re-initialization process of free surface capturing are validated with benchmark problems, i.e., a broken dam flow and timereversed single vortex flow. The simulation results are in good agreement with the existing results.

• Journal of Korea Trade
• /
• v.24 no.4
• /
• pp.18-33
• /
• 2020

Purpose - This paper investigated the effect of international trade affects income inequality. It also compares the different effects between developing and developed countries over the period from 2005 to 2014 for 58 countries. Design/methodology - The econometric estimation was used to identify the relationship between export, import, FDI, GDP, unemployment and income inequality. In this empirical analysis, we utilized a Vector Error Correction (VEC) model using panel data. Findings - The findings show that there is a close correlated between trade and income inequality. The higher export ratio of GDP tends to have a 1.79 times more income inequality in developing countries than in developed countries. The higher import ratio of GDP tends to have a 2.44 times higher income inequality in developing countries than in developed countries. Further, Increasing FDI tend to have an approximately 1.43 times higher income inequality in developing countries than in developed countries. Korea is in the middle of developed and developing countries' result. Originality/value - To correct the global income inequality regarding trade, developed countries' proactive trade policies, such as granting preferential tariff benefits to developing countries, are likely to be needed and Income Safety Net in international trade must be taken into account.

• Journal of the Korea Convergence Society
• /
• v.9 no.11
• /
• pp.15-21
• /
• 2018

In this study, we try to detect anomalies on the network intrusion detection system by learning only one class. We use KDD CUP 1999 dataset, an intrusion detection dataset, which is used to evaluate classification performance. One class classification is one of unsupervised learning methods that classifies attack class by learning only normal class. When using unsupervised learning, it difficult to achieve relatively high classification efficiency because it does not use negative instances for learning. However, unsupervised learning has the advantage for classifying unlabeled data. In this study, we use one class classifiers based on support vector machines and density estimation to detect new unknown attacks. The test using the classifier based on density estimation has shown relatively better performance and has a detection rate of about 96% while maintaining a low FPR for the new attacks.

• 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.