• Journal of KIISE:Software and Applications
• /
• v.31 no.10
• /
• pp.1386-1399
• /
• 2004

This paper presents correlation-based automatic image captioning. Given a training set of annotated images, we want to discover correlations between visual features and textual features, so that we can automatically generate descriptive textual features for a new unseen image. We develop models with multiple design alternatives such as 1) adaptively clustering visual features, 2) weighting visual features and textual features, and 3) reducing dimensionality for noise sup-Pression. We experiment thoroughly on 10 data sets of various content styles from the Corel image database, about 680MB. The major contributions of this work are: (a) we show that careful weighting visual and textual features, as well as clustering visual features adaptively leads to consistent performance improvements, and (b) our proposed methods achieve a relative improvement of up to 45% on annotation accuracy over the state-of-the-art, EM approach.

• The KIPS Transactions:PartB
• /
• v.13B no.3 s.106
• /
• pp.197-204
• /
• 2006

Recent advances in information technology have resulted in rapid growth in the mobile communication. With this explosive growth, reliable transmission and error concealment technique become increasingly important to offer high quality multimedia services. In this paper, we propose an improved BMA(Boundary Matching Algorithm) method using gradient vectors to conceal channel errors in inter-frames of H.264 video images. General BMA method computes the sum of pixel differences of adjacent pixels of the candidate block and its neighbouring blocks, assuming that adjacent pixels have almost the same value. In real images, however, there exist some gradients, which means that the pixel values are increasing or decreasing in a specific direction. In this paper, we develop a precise estimation method of errors in candidates blocks using gradient information and try to recover lost blocks with this technique. Experimental results show the improvement of picture quality about $1{\sim}3dB$ compared to existing methods.

• The KIPS Transactions:PartB
• /
• v.14B no.2
• /
• pp.127-134
• /
• 2007

There are many researches about the intelligent stock trading systems with the help of the advance of the artificial intelligence such as machine learning techniques, Though the establishment of the reasonable trading policy plays an important role in the performance of the trading systems most researches focused on the improvement of the predictability. Also some previous works, which treated the trading policy, treated the simplified versions dependent on the predictors in less systematic ways. In this paper, we propose the integrated multiple simulation' as a method of optimizing trading performance of stock trading systems. The propose method is adopted in the NXShell a development environment for neural network based stock trading systems. Under the proposed integrated multiple simulation', we simulate the multiple tradings for all combinations of the neural network's outputs and the trading policy parameters, evaluate the learning performance according to the various metrics and establish the optimal policy for a given prediction module based on the resulting performance. In the experiment, we present the trading policy comparison results using the stock value data from the KOSPI and KOSDAQ.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.33 no.9C
• /
• pp.720-724
• /
• 2008

Channel estimation in OFDM systems is usually carried out in frequency domain based on the least-squares (LS) method and the minimum mean-square error (MMSE) method with known pilot symbols. The LS estimator has a merit of low complexity but may suffer from the noise because it does not consider any noise effect in obtaining its solution. To enhance the noise immunity of the LS estimator, we consider estimation noise in time domain. Residual noise existing at the estimated channel coefficients in time domain could be reduced by reasonable selection of a threshold value. To achieve this, we propose a channel-estimation method based on a time-domain threshold which is a standard deviation of noise obtained by wavelet decomposition. Computer simulation shows that the estimation performance of the proposed method approaches to that of the known-channel case in terms of bit-error rates after the Viterbi decoder in overall SNRs.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.42 no.5
• /
• pp.1058-1068
• /
• 2017

In V2X communication, a random based resource selection scheme is needed with considerations of cases that support devices without sidelink reception capabilities and require reduction of UE's power consumption. In this paper, as improvement of D2D's resource section scheme that one TRP is repeated to data subframe pool within a PSCCH period, it is proposed that different TRPs is applied for enhanced random resource selection based on pseudo-random sequence having UE-specific seed value. By results of proposed scheme's performance by numerical analysis, it is confirmed that collision probability among resources allocated to each UE for data TB is reduced, and a number of UEs which can avoid resource collision as much as possible and have simultaneous resource allocation is increased.

• Journal of the Institute of Convergence Signal Processing
• /
• v.10 no.1
• /
• pp.32-39
• /
• 2009

In this paper, the method of region segmentation using genetic algorithm is proposed for an improvement of efficiency in moving picture coding. A genetic algorithm is the method that searches a large probing space using only a function value for a optimal combination consecutively. By progressing both motion presumption and region segmentation at once, we can assign the motion vector in a image to a small block or a pixel respectively, and transform the capacity of coding and a signal to noise rate into a problem of optimization. That is to say, there is close correlation between region segmentation and motion presumption in motion-compensated prediction coding. This is to optimize the capacity of coding and a S/N ratio. This is to arrange the motion vector in each block of picture according to the state of optimization. Therefore, we examined both the data type of genetic algorithm and the method of data processing to obtain the results of optimal region segmentation in this paper. And we confirmed the validity of a proposed method using the test pictures by means of computer simulation.

• Journal of Korea Foundry Society
• /
• v.25 no.5
• /
• pp.195-202
• /
• 2005

In this study, we investigated the effect of Sb/RE on the microstructure and mechanical properties of as-cast heavy sectioned, over 250mm thickness, ferritic ductile cast iron. Exothermic and thermal insulation material were equipped on the wall of sand cast mold having the dimensions of $250{\times}250{\times}250$ mm. The nominal composition of the molten metal was controlled to be on the eutectic composition and Sb was added about 0, 0.005 and 0.02% respectively. In the center of as-cast ingot without Sb addition, the solidification of chunky graphite was induced by the eutectic reaction that took long time, which caused the decrease of elongation and impact energy. In case that the value of Sb/RE is 0.8, the solidification of chunky graphite could be suppressed and the improvement of nodularity was observed. On the other hand, the excessive addition of Sb suppressed the solidification of chunky graphite but gave rise to the solidification of flake graphite and the increase of pearlite contents. This results in poor elongation and impact energy which is lower than those in the case of no Sb addition.

• The KSFM Journal of Fluid Machinery
• /
• v.13 no.5
• /
• pp.43-53
• /
• 2010

This study investigates a design optimization of a rotating two-pass rectangular cooling channel with staggered arrays of pin-fins. The radial basis neural network method is used as an optimization technique with Reynolds-averaged Navier-Stokes analysis of fluid flow and heat transfer with shear stress transport turbulent model. The ratio of the diameter to height of the pin-fins and the ratio of the streamwise spacing between the pin-fins to height of the pin-fin are selected as design variables. The optimization problem has been defined as a minimization of the objective function, which is defined as a linear combination of heat transfer related term and friction loss related term with a weighting factor. Results are presented for streamlines, velocity vector fields, and contours of Nusselt numbers, friction coefficients, and turbulent kinetic energy. These results show how fluid flow in a two-pass square cooling channel evolves a converted secondary flows due to Coriolis force, staggered arrays of pin-fins, and a $180^{\circ}$ turn region. These results describe how the fluid flow affects surface heat transfer. The Coriolis force induces heat transfer discrepancy between leading and trailing surfaces, having higher Nusselt number on the leading surface in the second pass while having lower Nusselt number on the trailing surface. Dean vortices generated in $180^{\circ}$ turn region augment heat transfer in the turning region and in the upstream region of the second pass. As the result of optimization, in comparison with the reference geometry, thermal performance of the optimum geometry shows the improvement by 30.5%. Through the optimization, the diameter of pin-fin increased by 14.9% and the streamwise distance between pin-fins increased by 32.1%. And, the value of objective function decreased by 18.1%.

• Journal of Powder Materials
• /
• v.22 no.4
• /
• pp.254-259
• /
• 2015

$Bi_2Te_3$ related compounds show the best thermoelectric properties at room temperature. However, n-type $Bi_2Te_{2.7}Se_{0.3}$ showed no improvement on ZT values. To improve the thermolectric propterties of n-type $Bi_2Te_{2.7}Se_{0.3}$, this research has Cu-doped n-type powder. This study focused on effects of Cu-doping method on the thermoelectric properties of n-type materials, and evaluated the comparison between the Cu chemical and mechanical doping. The synthesized powder was manufactured by the spark plasma sintering(SPS). The thermoelectric properties of the sintered body were evaluated by measuring their Seebeck coefficient, electrical resistivity, thermal conductivity, and hall coefficient. An introduction of a small amount of Cu reduced the thermal conductivity and improved the electrical properties with Seebeck coefficient. The authors provided the optimal concentration of $Cu_{0.1}Bi_{1.99}Se_{0.3}Te_{2.7}$. A figure of merit (ZT) value of 1.22 was obtained for $Cu_{0.1}Bi_{1.9}Se_{0.3}Te_{2.7}$ at 373K by Cu chemical doping, which was obviously higher than those of $Cu_{0.1}Bi_{1.9}Se_{0.3}Te_{2.7}$ at 373K by Cu mechanical doping (ZT=0.56) and Cu-free $Bi_2Se_{0.3}Te_{2.7}$ (ZT=0.51).

• Environmental and Resource Economics Review
• /
• v.25 no.2
• /
• pp.321-349
• /
• 2016

According to the recent observation by NOAA(US National Oceanic and Atmospheric Administration), 2015 is the warmest year based on global average temperature since 1880. The air temperatures in the Arctic have been rising at almost twice the global average and the extent and thickness of sea ice in the Arctic have declined. And the warming process in the Arctic is accelerating rapidly. These impacts of drastic change in sea ice caused by climate change in the Arctic threaten the eco-system service and biodiversity in the Arctic. This study intends to estimate the economic value on changes in eco-system services and biodiversity of the Arctic caused by climate change. The result of the valuation indicates that the total benefit from improvement of ecosystem in the Arctic ranges from 318.6 billion won to 715.9 billion won per annum. Replication scenarios can be explored into two broad categories in future studies: scenarios in consideration of conflicts of different stakeholders and scenarios based on wider or narrower definition of biodiversity in the Arctic.