• Journal of the Institute of Electronics Engineers of Korea SP
• /
• v.46 no.6
• /
• pp.112-122
• /
• 2009

In this paper, we present a novel space-frequency adaptive image restoration approach using vaguelette-wavelet decomposition (VWD). The proposed algorithm classifies a degraded image into flat and edge regions by using spatial information of the wavelet coefficient. For reducing the noise we perform an adaptive wavelet shrinkage process. At edge region candidates, we adopt entropy approach for estimating the noise and remove it by using relative between sub-bands. After shrinking wavelet coefficients process, we restore the degraded image using the VWD. The proposed algorithm can reduce the noise without affecting the sharpness details. Based on the experimental results, the proposed algorithm efficiently proved to be able to restore the degraded image while preserving details.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.11 no.2
• /
• pp.1134-1147
• /
• 2017

With the rise in popularity of photographic and video cameras, an increasing number of fields are now using thermal imaging cameras. One such application is in the diagnosis of breast cancer, as thermal imaging provides a low-cost and noninvasive method. Thermal imaging is particularly safe for pregnant women, and those with large, dense, or sensitive breasts. In addition, excessive doses of radiation, which may be used in traditional methods of breast cancer detection, can increase the risk of cancer. This paper presents one method of breast cancer detection. Breast images were taken using a thermal camera, with preliminary experiments conducted on Cambodian women. Then the experimental results were analyzed and compared using Shannon entropy and logistic regression.

• The Journal of the Acoustical Society of Korea
• /
• v.41 no.3
• /
• pp.335-341
• /
• 2022

In this paper, we adopt a transformer that shows remarkable performance in natural language processing as an acoustic model of hybrid speech recognition. The transformer acoustic model uses attention structures to process sequential data and shows high performance with low computational cost. This paper proposes a method to improve the performance of transformer AM by applying each of the four algorithms of sequence discriminative training, a weighted finite-state transducer (wFST)-based learning used in the existing DNN-HMM model. In addition, compared to the Cross Entropy (CE) learning method, sequence discriminative method shows 5 % of the relative Word Error Rate (WER).

• Journal of Soil and Groundwater Environment
• /
• v.11 no.3
• /
• pp.52-58
• /
• 2006

Kim and Lee (2005) suggested Minimum Entropy Deconvolution (MED) to estimate the temporal sequence of the relative recharge. However this study by Kim and Lee (2005) was just related to the verification of the conceptual approach with MED. In this study, we try to characterize the applicability of MED in the case of spatially heterogeneous recharge (distance from recharge area). Simulated results were recorded with some specific sampling points. Estimated results from this study show higher than 0.8 in cross-correlation with the original recharge sequence. In addition, the physical and mathematical meanings of the applied filter length was also investigated. It was revealed that the length of filter is highly related to the spatial distance between recharge area and the monitoring site, and the apparent shape of hydraulic head change.

• KSCE Journal of Civil and Environmental Engineering Research
• /
• v.29 no.4B
• /
• pp.357-363
• /
• 2009

When yields the mean velocity of the closed conduit which is used generally, it is available to use Darcy Weisbach Friction Loss Head equation. But, it is inconvenient very because Friction Loss coefficient f is the function of Reynolds Number and Relative roughness (${\varepsilon}$/d). So, it is demanded more convenient equation to estimate. In order to prove the reliability and an accuracy of Chiu's velocity equation from the research which sees hereupon, proved agreement very well about measured velocity measurement data by using Laser velocimeter which is a non-insertion velocity measuring equipment from the closed conduit (Laser Doppler Velocimeter: LDV) and an insertion velocity measuring equipment and the Pitot tube which is a supersonic flow meter (Transit-Time Flowmeters). By proving theoretical linear-relation between maximum velocity and mean velocity in laboratory flume without increase and decrease of discharge, the equilibrium state of velocity in the closed conduit which reachs to equilibrium state corresponding to entropy parameter M value has a trend maintaining consistently this state. If entropy M value which is representing one section is determinated, mean velocity can be gotten only by measuring the velocity in the point appearing the maximum velocity. So, it has been proved to estimate simply discharge and it indicates that this method can be a theoretical way, which is the most important in the future, when designing, managing and operating the closed conduit.

• Journal of the Korean association of regional geographers
• /
• v.20 no.1
• /
• pp.30-48
• /
• 2014

Relying on the interaction indices - dominance index, relative strength index and entropy index, this paper analyzes the structural features of urban network in the Seoul metropolitan area with the flows of commuting, business, and freight. Analytical results show that the Seoul metropolitan urban system is vertical, size-dependent, one-way, and the highest city-dominant network rather than horizontal, size-neutral, two-way, complementary one. The network of freight flow is a little bit more symmetrical than the networks of commuting and business. However, the interaction with Seoul is still determinant in all aspects of hierarchical structure, relative strength, and symmetry of flow.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.25 no.7A
• /
• pp.1017-1027
• /
• 2000

In this paper, we propose a new coding method based on the distance between vertex segments for vertex positions in the vertex-based shape coding. The pixel lines are divided into the segments of a fixed length, and the segments that have vertex pixels are called vertex segments. We analyze the probability distribution of the relative distance between vertex segments and prove that it depends only on the ratio between the number of vertices and the number of segments. Considering the coding efficiency and implementation complexity, we choose a particular ratio to make a code table. For each input image, the segment size is chosen according tothe ratio, and the relative segment distances are entropy coded. It is shown that the proposed method is efficient for the images with many vertices.

• Journal of Korea Multimedia Society
• /
• v.23 no.7
• /
• pp.883-890
• /
• 2020

In this paper, we propose a variational expectation-maximization algorithm that computes posterior probabilities from Latent Dirichlet Allocation (LDA) model. The algorithm approximates the intractable posterior distribution of a document term matrix generated from a corpus made up by 50 papers. It approximates the posterior by searching the local optima using lower bound of the true posterior distribution. Moreover, it maximizes the lower bound of the log-likelihood of the true posterior by minimizing the relative entropy of the prior and the posterior distribution known as KL-Divergence. The experimental results indicate that documents clustered to image classification and segmentation are correlated at 0.79 while those clustered to object detection and image segmentation are highly correlated at 0.96. The proposed variational inference algorithm performs efficiently and faster than Gibbs sampling at a computational time of 0.029s.

• Genomics & Informatics
• /
• v.7 no.3
• /
• pp.178-180
• /
• 2009

A few bioinformatics tools have been used to find out conserved regions as probes. We have developed a system based on a heuristic method with web interfaces to find out conserved regions against microbial genomes. The system runs in real time by using relative entropy in limited narrow regions and detecting similar regions between pair regions with local alignment. The system could be useful to find out conserved regions as genome-wide scale.

• International Journal of Aeronautical and Space Sciences
• /
• v.10 no.1
• /
• pp.1-14
• /
• 2009

When the stagnation temperature increases, the specific heat does not remain constant and start to vary with this temperature. The gas is perfect, it's state equation remains always valid, except, it was called by gas calorically imperfect or gas at high temperatures. The purpose of this work is to develop a mathematical model for a normal shock wave normal at high temperature when the stagnation temperature is taken into account, less than the dissociation of the molecules as a generalisation model of perfect for constant heat specific. A study on the error given by the perfect gas model compared to our model is presented in order to find a limit of application of the perfect gas model. The application is for air.