• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.15 no.9
• /
• pp.2007-2012
• /
• 2011

To reduce huge computation in the block matching, this paper proposes a fast block matching algorithm which limits search points in the search area. On the basis of two facts that most motion vectors are located in central part of search area and matching error is monotonic decreasing toward the best similar block, the proposed algorithm moves a matching pattern between steps by the one pixel, predicts the motion direction for the best similar block from similar blocks decided in previous steps, and limits movements of search points to ${\pm}45^{\circ}C$ on it. As a result, it could remove the needless search points and reduce the block matching computation. In comparison with the conventional similar algorithms, the proposed algorithm caused the trivial image degradation in images with fast motion but kept the equivalent image quality in images with normal motion, and it, meanwhile, reduced from about 20% to over 67% of the their block matching computation.

• Proceedings of the KSMRM Conference
• /
• 2001.11a
• /
• pp.111-111
• /
• 2001

목적： To evaluate the feasibility of the event-related functional MR study using power grip studying the hand motor system 대상 및 방법： Event-related functional MRI was performed on a 1.5T MR unit in seven norm volunteers (man=7, right-handedness=2, left-handedness=5, mean age： 25 years). A single-shot GRE-EPI sequence (TR/TE/flip angle： 1000ms/40ms/90, FOV = 240 mm matrix= 64$\times$64, slice thickness/gap = 5mm/0mm, 7 true axial slices) was used for functiona MR images. A flow-sensitive conventional gradient echo sequence (TR/TE/flip angl 50ms/4ms/60) was used for high-resolution anatomical images. To minimize the gross hea motion, neck-holders (MJ-200, USA) were used. A series of MR images were obtained in axial planes covering motor areas. To exclude motion-corrupted images, all MR images wer surveyed in a movie procedure and evaluated using the estimation of center of mass of ima signal intensities. Power grip task consisted of the powerful grip of all right fingers and hand movement ta used very fast right finger tapping at a speed of 3 per 1 second. All tasks were visual-guid by LCD projector (SHARP, Japan). Two tasks consisted of 134 phases including 7 activatio and 8 rest periods. Active stimulations were performed during 2 seconds and rest period were 15 seconds and total scan time per one task was 2 min 14 sec. Statistical maps we obtained using cross-correlation method. Reference vector was time-shifted by 4 seconds an Gaussian convolution with a FWHM of 4 seconds was applied to it. The threshold in p val for the activation sites was set to be 0.001. All mapping procedures were peformed usin homemade program an IDL (Research Systems Inc., USA) platform. We evaluated the activation patterns of the motor system of power grip compared to hand movement in t event-related functional MRI.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.14 no.8
• /
• pp.3295-3311
• /
• 2020

With the wide application of hyperspectral images, it becomes more and more important to compress hyperspectral images. Conventional recursive least squares (CRLS) algorithm has great potentiality in lossless compression for hyperspectral images. The prediction accuracy of CRLS is closely related to the correlations between the reference bands and the current band, and the similarity between pixels in prediction context. According to this characteristic, we present an improved CRLS with adaptive band selection and adaptive predictor selection (CRLS-ABS-APS). Firstly, a spectral vector correlation coefficient-based k-means clustering algorithm is employed to generate clustering map. Afterwards, an adaptive band selection strategy based on inter-spectral correlation coefficient is adopted to select the reference bands for each band. Then, an adaptive predictor selection strategy based on clustering map is adopted to select the optimal CRLS predictor for each pixel. In addition, a double snake scan mode is used to further improve the similarity of prediction context, and a recursive average estimation method is used to accelerate the local average calculation. Finally, the prediction residuals are entropy encoded by arithmetic encoder. Experiments on the Airborne Visible Infrared Imaging Spectrometer (AVIRIS) 2006 data set show that the CRLS-ABS-APS achieves average bit rates of 3.28 bpp, 5.55 bpp and 2.39 bpp on the three subsets, respectively. The results indicate that the CRLS-ABS-APS effectively improves the compression effect with lower computation complexity, and outperforms to the current state-of-the-art methods.

• Journal of Broadcast Engineering
• /
• v.13 no.3
• /
• pp.339-349
• /
• 2008

We present a novel method to estimate the light source direction and relight a face texture image of a single 3D model under arbitrary unknown illumination conditions. We create a virtual irradiance sphere to detect the light source direction from a given illuminated texture image using both normal vector mapping and weighted bilinear interpolation. We then induce a relighting equation with estimated ambient and diffuse coefficients. We provide the result of a series of experiments on light source estimation, relighting and face recognition to show the efficiency and accuracy of the proposed method in restoring the shading and shadows areas of a face texture image. Our approach for face relighting can be used for not only illuminant invariant face recognition applications but also reducing visual load and Improving visual performance in tasks using 3D displays.

• Transactions of the Korean Society for Noise and Vibration Engineering
• /
• v.19 no.3
• /
• pp.313-319
• /
• 2009

The blasting has a lot of economic efficiency and speediness but it can damage to a neighbor structure, a domestic animal and a cultured fish due to the blasting vibration, then the public grievance is increased. Therefore, we need to manage the blasting vibration efficiently. The prediction of the correct vibration velocity is not easy because there are lots of different kinds of the scale of blasting vibration and it has a number of a variable effect. So we figure the optimum line through the least-squares regression by using the vibration data measured in hard rock blasting and compared with the design vibration prediction equation. As a result, we confirm that the vibration estimated in this paper is bigger than the design vibration prediction equation in the same charge and distance. If there is a Gaussian normal distribution data on the left-right side of the least squares regression, then we can estimate the vibration prediction equation on reliability 50%(${\beta}=0$), 90%(${\beta}=1.28$), 95%(${\beta}=1.64$). 99.9%(${\beta}=3.09$). As a result, it appears to be suitable that the reliability is 99% at the transverse component, the reliability 95% is at the vertical component, the reliability 90% is at the longitudinal component and the reliability is 95% at the peak vector sum component.

• The Journal of the Acoustical Society of Korea
• /
• v.16 no.5
• /
• pp.112-121
• /
• 1997

In this paper, we study a model parameter compensation method for noise-robust speech recognition. We study model parameter compensation on a sentence by sentence and no other informations are used. Parallel model combination(PMC), well known as a model parameter compensation algorithm, is implemented and used for a reference of performance comparision. We also propose a modified PMC method which tunes model parameter with an association factor that controls average variability of gaussian mixtures and variability of single gaussian mixture per state for more robust modeling. We obtain a re-estimation solution of environmental variables based on the expectation-maximization(EM) algorithm in the cepstral domain. To evaluate the performance of the model compensation methods, we perform experiments on speaker-independent isolated word recognition. Noise sources used are white gaussian and driving car noise. To get corrupted speech we added noise to clean speech at various signal-to-noise ratio(SNR). We use noise mean and variance modeled by 3 frame noise data. Experimental result of the VTS approach is superior to other methods. The scheme of the zero order VTS approach is similar to the modified PMC method in adapting mean vector only. But, the recognition rate of the Zero order VTS approach is higher than PMC and modified PMC method based on log-normal approximation.

• Journal of Korea Multimedia Society
• /
• v.5 no.4
• /
• pp.458-467
• /
• 2002

There has been proposed many simplification algorithms for effectively decreasing large-volumed polygonal surface data. These algorithms apply their own cost function for collapse to one of fundamental simplification unit, such as vertex, edge and triangle, and minimize the simplification error occurred in each simplification steps. Most of cost functions adopted in existing works use the error estimation method based on distance optimization. Unfortunately, it is hard to define the local characteristics of surface data using distance factor alone, which is basically scalar component. Therefore, the algorithms cannot preserve the characteristic features in surface areas with high curvature and, consequently, loss the detailed shape of original mesh in high simplification ratio. In this paper, we consider the vector component, such as surface orientation, as one of factors for cost function. The surface orientation is independent upon scalar component, distance value. This means that we can reconsider whether or not to preserve them as the amount of vector component, although they are elements with low scalar values. In addition, we develop a simplification algorithm based on half-edge collapse manner, which use the proposed cost function as the criterion for removing elements. In half-edge collapse, using one of endpoints in the edge represents a new vertex after collapse operation. The approach is memory efficient and effectively applicable to the rendering system requiring real-time transmission of large-volumed surface data.

• Journal of the Institute of Electronics Engineers of Korea SP
• /
• v.37 no.5
• /
• pp.54-63
• /
• 2000

We present a multi-resolution block matching algorithm (BMA) for fast motion estimation At the coarsest level, a motion vector (MV) having minimum matching error is chosen via a full search, and a MV with minimum matching error is concurrently found among the MVs of the spatially adjacent blocks Here, to examine the spatial MVs accurately, we propose an efficient method for searching full resolution MV s without MV quantization even at the coarsest level The chosen two MV s are used as the initial search centers at the middle level At the middle level, the local search is performed within much smaller search area around each search center If the method used at the coarsest level is adopted here, the local searches can be done at integer-pel accuracy A MV having minimum matching error is selected within the local search areas, and then the final level search is performed around this initial search center Since the local searches are performed at integer-pel accuracy at the middle level, the local search at the finest level does not take an effect on the overall performance So we can skip the final level search without performance degradation, thereby the search speed increases Simulation results show that in comparison with full search BMA, the proposed BMA without the final level search achieves a speed-up factor over 200 with minor PSNR degradation of 02dB at most, under a normal MPEG2 coding environment Furthermore, our scheme IS also suitable for hardware implementation due to regular data-flow.

• Journal of Intelligence and Information Systems
• /
• v.23 no.3
• /
• pp.139-153
• /
• 2017

Corporate bankruptcy can cause great losses not only to stakeholders but also to many related sectors in society. Through the economic crises, bankruptcy have increased and bankruptcy prediction models have become more and more important. Therefore, corporate bankruptcy has been regarded as one of the major topics of research in business management. Also, many studies in the industry are in progress and important. Previous studies attempted to utilize various methodologies to improve the bankruptcy prediction accuracy and to resolve the overfitting problem, such as Multivariate Discriminant Analysis (MDA), Generalized Linear Model (GLM). These methods are based on statistics. Recently, researchers have used machine learning methodologies such as Support Vector Machine (SVM), Artificial Neural Network (ANN). Furthermore, fuzzy theory and genetic algorithms were used. Because of this change, many of bankruptcy models are developed. Also, performance has been improved. In general, the company's financial and accounting information will change over time. Likewise, the market situation also changes, so there are many difficulties in predicting bankruptcy only with information at a certain point in time. However, even though traditional research has problems that don't take into account the time effect, dynamic model has not been studied much. When we ignore the time effect, we get the biased results. So the static model may not be suitable for predicting bankruptcy. Thus, using the dynamic model, there is a possibility that bankruptcy prediction model is improved. In this paper, we propose RNN (Recurrent Neural Network) which is one of the deep learning methodologies. The RNN learns time series data and the performance is known to be good. Prior to experiment, we selected non-financial firms listed on the KOSPI, KOSDAQ and KONEX markets from 2010 to 2016 for the estimation of the bankruptcy prediction model and the comparison of forecasting performance. In order to prevent a mistake of predicting bankruptcy by using the financial information already reflected in the deterioration of the financial condition of the company, the financial information was collected with a lag of two years, and the default period was defined from January to December of the year. Then we defined the bankruptcy. The bankruptcy we defined is the abolition of the listing due to sluggish earnings. We confirmed abolition of the list at KIND that is corporate stock information website. Then we selected variables at previous papers. The first set of variables are Z-score variables. These variables have become traditional variables in predicting bankruptcy. The second set of variables are dynamic variable set. Finally we selected 240 normal companies and 226 bankrupt companies at the first variable set. Likewise, we selected 229 normal companies and 226 bankrupt companies at the second variable set. We created a model that reflects dynamic changes in time-series financial data and by comparing the suggested model with the analysis of existing bankruptcy predictive models, we found that the suggested model could help to improve the accuracy of bankruptcy predictions. We used financial data in KIS Value (Financial database) and selected Multivariate Discriminant Analysis (MDA), Generalized Linear Model called logistic regression (GLM), Support Vector Machine (SVM), Artificial Neural Network (ANN) model as benchmark. The result of the experiment proved that RNN's performance was better than comparative model. The accuracy of RNN was high in both sets of variables and the Area Under the Curve (AUC) value was also high. Also when we saw the hit-ratio table, the ratio of RNNs that predicted a poor company to be bankrupt was higher than that of other comparative models. However the limitation of this paper is that an overfitting problem occurs during RNN learning. But we expect to be able to solve the overfitting problem by selecting more learning data and appropriate variables. From these result, it is expected that this research will contribute to the development of a bankruptcy prediction by proposing a new dynamic model.

• Journal of the Korean Institute of Telematics and Electronics S
• /
• v.35S no.8
• /
• pp.96-105
• /
• 1998

The aim of this paper is to propose the method of WDHMM(Weighted DHMM), using the MLP-VQ for the improvement of speaker-independent connect-digit recognition system. MLP neural-network output distribution shows a probability distribution that presents the degree of similarity between each pattern by the non-linear mapping among the input patterns and learning patterns. MLP-VQ is proposed in this paper. It generates codewords by using the output node index which can reach the highest level within MLP neural-network output distribution. Different from the old VQ, the true characteristics of this new MLP-VQ lie in that the degree of similarity between present input patterns and each learned class pattern could be reflected for the recognition model. WDHMM is also proposed. It can use the MLP neural-network output distribution as the way of weighing the symbol generation probability of DHMMs. This newly-suggested method could shorten the time of HMM parameter estimation and recognition. The reason is that it is not necessary to regard symbol generation probability as multi-dimensional normal distribution, as opposed to the old SCHMM. This could also improve the recognition ability by 14.7% higher than DHMM, owing to the increase of small caculation amount. Because it can reflect phone class relations to the recognition model. The result of my research shows that speaker-independent connected-digit recognition, using MLP-VQ and WDHMM, is 84.22%.