• Journal of Korean Institute of Industrial Engineers
• /
• v.26 no.4
• /
• pp.363-375
• /
• 2000

In this paper we propose a content-based image retrieval method that can search large image databases efficiently by color, texture, and shape content. Quantized RGB histograms and the dominant triple (hue, saturation, and value), which are extracted from quantized HSV joint histogram in the local image region, are used for representing global/local color information in the image. Entropy and maximum entry from co-occurrence matrices are used for texture information and edge angle histogram is used for representing shape information. Relevance feedback approach, which has coupled proposed features, is used for obtaining better retrieval accuracy. Simulation results illustrate the above method provides 77.5 percent precision rate without relevance feedback and increased precision rate using relevance feedback for overall queries. We also present a new indexing method that supports fast retrieval in large image databases. Tree structures constructed by k-means algorithm, along with the idea of triangle inequality, eliminate candidate images for similarity calculation between query image and each database image. We find that the proposed method reduces calculation up to average 92.9 percent of the images from direct comparison.

• 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.

• Journal of Astronomy and Space Sciences
• /
• v.20 no.2
• /
• pp.101-108
• /
• 2003

This study reports one approach for the classification of magnetic storms into recurrent patterns. A storm event is defined as a local minimum of Dst index. The analysis of Dst index for the period of year 1957 through year 2000 has demonstrated that a large portion of the storm events can be classified into a set of recurrent patterns. In our approach, the classification is performed by seeking a categorization that minimizes thermodynamic free energy which is defined as the sum of classification errors and entropy. The error is calculated as the squared sum of the value differences between events. The classification depends on the noise parameter T that represents the strength of the intrinsic error in the observation and classification process. The classification results would be applicable in space weather forecasting.

• Journal of Broadcast Engineering
• /
• v.7 no.4
• /
• pp.291-299
• /
• 2002

This paper proposes an efficient motion compensation algorithm for video sequences with brightness variations. In the proposed algorithm, the brightness variation parameters are estimated and local motions are compensated. To detect the frame with large brightness variations. we employ the frame classification based on the cross entropy between histograms of two successive frames, which can reduce the computational redundancy. Simulation results show that the proposed method yields a higher peak signal to noise ratio (PSNR) than the conventional methods, with a low computational load, when the video scene contains large brightness changes.

• Korean Management Science Review
• /
• v.18 no.2
• /
• pp.25-38
• /
• 2001

The well-known back-propagation algorithm for multi-layered neural network has successfully been applied to pattern c1assification problems with remarkable flexibility. Recently. the multi-layered neural network is used as a powerful data mining tool. Nevertheless, in many cases with complex boundary of classification, the successful learning is not guaranteed and the problems of long learning time and local minimum attraction restrict the field application. In this paper, an Improved learning procedure of multi-layered neural network is proposed. The procedure is based on the generalized delta rule but it is particular in the point that the architecture of network is not fixed but enlarged during learning. That is, the number of hidden nodes or hidden layers are increased to help finding the classification boundary and such procedure is controlled by entropy evaluation. The learning speed and the pattern classification performance are analyzed and compared with the back-propagation algorithm.

• Transactions of the Korean Society of Mechanical Engineers
• /
• v.14 no.5
• /
• pp.1200-1210
• /
• 1990

Conventional efficiencies of the adiabatic compression process such as isentropic efficiency and polytropic efficiency can be explained as exergetic efficiencies replacing the reference atmospheric temperature with the temperature which can be determined in the process itself. So that, other efficies such as maximum isentropic efficiency can be defined by giving proper reference temperatures. By applying the same logical principles, exergetic and other rational efficiencies for the non-adiabatic compression process are also defined and discussed for their physical meanings and reasonable engineering applications.

• Journal of Korean Society of Industrial and Systems Engineering
• /
• v.25 no.6
• /
• pp.36-41
• /
• 2002

We consider the Fuzzy clustering which is devised for partitioning a set of objects into a certain number of groups by assigning the membership probabilities to each object. The researches carried out in this field before show that the Fuzzy clustering concept is involved so much that for a certain set of data, the main purpose of the clustering cannot be attained as desired. Thus we propose a new objective function, named as Fuzzy-Entroppy Function in order to satisfy the main motivation of the clustering which is classifying the data clearly. Also we suggest Mean Field Annealing Algorithm as an optimization algorithm rather than the ISODATA used traditionally in this field since the objective function is changed. we show the Mean Field Annealing Algorithm works pretty well not only for the new objective function but also for the classical Fuzzy objective function by indicating that the local minimum problem resulted from the ISODATA can be improved.

• Bulletin of the Korean Chemical Society
• /
• v.22 no.4
• /
• pp.367-371
• /
• 2001

Lithium inserted into artificial carbon has been synthesized as a function of the Li concentration. The characteristics of these prepared compounds were determined from the studies using X-ray diffraction(XRD), solid nuclear magnetic resonance (NM R) spectrophotometric and differential scanning calorimeter(DSC) analysis. X-ray diffraction showed that lower stage intercalation compounds were formed with increasing Li concentration. In the case of the AG3, most compounds formed were of the stage 1 structure. Pure stage 1 structural defects of artificial graphite were not observed. 7Li-NMR data showed that bands are shifted toward higher frequencies with increasing lithium concentration; this is because non-occupied electron shells of Li increased in charge carrier density. Line widths of the Li inserted carbon compounds decreased slowly because of nonhomogeneous local magnetic order and the random electron spin direction for located Li between graphene layers. The enthalpy and entropy changes of the compounds can be obtained from the differential scanning calorimetric analysis results. From these results, it was found that exothermic and endothermic reactions of lithium inserted into artificial carbon are related to the thermal stability of lithium between artificial carbon graphene layers.

• Annual Conference on Human and Language Technology
• /
• 2020.10a
• /
• pp.93-97
• /
• 2020

본 연구는 딥 러닝 기반 의존 구문 분석에서, 학습에 적용하는 손실 함수에 따른 성능을 평가하였다. Pointer Network를 이용한 Left-To-Right 모델을 총 세 가지의 손실 함수(Maximize Golden Probability, Cross Entropy, Local Hinge)를 이용하여 학습시켰다. 그 결과 LH 손실 함수로 학습한 모델이 선행 연구와 같이 MGP 손실 함수로 학습한 것에 비해 UAS/LAS가 각각 0.86%p/0.87%p 상승하였으며, 특히 의존 거리가 먼 경우에 대하여 분석 성능이 크게 향상됨을 확인하였다. 딥러닝 의존 구문 분석기를 구현할 때 학습모델과 입력 표상뿐만 아니라 손실 함수 역시 중요하게 고려되어야 함을 보였다.