• Journal of KIISE:Software and Applications
• /
• v.31 no.2
• /
• pp.245-254
• /
• 2004

This paper deals with the problem of estimating structure and motion from long continuous image sequences, applying the Expectation Maximization algorithm based on extended Kalman smoother to impose the time-continuity of the motion parameters. By repeatedly estimating the state transition matrix of the dynamic equation and the parameters of noise processes in the dynamic and measurement equations, this optimization gives the maximum likelihood estimates of the motion and structure parameters. Practically, this research is essential for dealing with a long video-rate image sequence with partially unknown system equation and noise. The algorithm is implemented and tested for a real image sequence.

• 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.

• Proceedings of the KIEE Conference
• /
• 2011.07a
• /
• pp.270-271
• /
• 2011

Due to integration of wind power, its unpredictable uncertainty can be a very lethal factor in generation dispatch problem. To handle such uncertainty of wind power output, a profit maximization problem is formulated and random wind speed is modeled by Weibull distribution in this paper. A case study is calculated through profit maximization approach with random wind speed. The effect of case study results is evaluated on how the uncertain wind power integration into the power system affects on the generation dispatch.

• Journal of the Korean Operations Research and Management Science Society
• /
• v.30 no.2
• /
• pp.63-71
• /
• 2005

In the field of nuclear reactor safety study, common cause failures (CCFs) became significant contributors to system failure probability and core damage frequency in most Probabilistic risk assessments. However, it is hard to estimate the reliability of such a system, because of the dependency of components caused by CCFs. In order to analyze the system, we propose an analytic method that can find the parameters with lack of raw data. This study adopts the shock model in which the failure probability increases as the shock is cumulated. We use two-step Expectation and Maximization (EM) algorithm to find the unknown parameters. In order to verify the analysis result, we perform the simulation under same environment. This approach might be helpful to build the defensive strategy for the CCFs.

• International Journal of Advanced Culture Technology
• /
• v.8 no.3
• /
• pp.275-279
• /
• 2020

Due to the recent rapid industrialization worldwide, the number of pediatric asthma patients is increasing. And the fine dust containing heavy metals is linked to the characteristics of high toxic lead due to the increase heating in factory operation and automobile driving. It is the reason of arsenic increasing. In the treatment of pediatric asthma patients, drug administration, oral drug entry, and HMPC (Home Management Plan of Care) are used. In this paper, we analyze the relationship between the onset of asthma and the method of prescription for specific childhood asthma in the United States using EM (Expectation Maximization) and MDL (Minimum Description Length) algorithms. And the association is also analyzed by comparing the nature of specific congestion between the past prevalence of digestive asthma and the recent prevalence of environmental pollution.

• Management Science and Financial Engineering
• /
• v.17 no.2
• /
• pp.99-129
• /
• 2011

This paper analytically studies how to choose hedging instrument for firms with steady operating cash flows from value maximization perspective. I derive a formula to determine option's optimal strike that makes hedged cash flow have the best monetary payoff given a hedger's view on the underlying asset. I find that not only the expected mean but also the expected standard deviation of the underlying asset in relation to the forward price and the implied volatility play a crucial role in making optimal hedging decision. Higher moments play a certain part in hedging decision but to a lesser degree.

• Journal of Information Processing Systems
• /
• v.10 no.3
• /
• pp.471-482
• /
• 2014

Influence maximization is an important problem of finding a small subset of nodes in a social network, such that by targeting this set, one will maximize the expected spread of influence in the network. To improve the efficiency of algorithm KK_Greedy proposed by Kempe et al., we propose two improved algorithms, Lv_NewGreedy and Lv_CELF. By combining all of advantages of these two algorithms, we propose a mixed algorithm Lv_MixedGreedy. We conducted experiments on two synthetically datasets and show that our improved algorithms have a matching influence with their benchmark algorithms, while being faster than them.

• Proceedings of the Computational Structural Engineering Institute Conference
• /
• 2007.04a
• /
• pp.309-314
• /
• 2007

Optimal layer sequencing of a multi-layered acoustical foam is solved to maximize its sound transmission loss. A foam consisting of air and poroelastic layers can be optimized when a limited amount of a poroelastic material is allowed. By formulating the sound transmission loss maximization problem as a one dimensional topology optimization problem, optimal layer sequencing and thickness were systematically found for several frequencies. For optimization, the transmission losses of air and poroelastic layers were calculated by the transfer matrix derived from Biot's theory. By interpolating five intrinsic parameters among several poroelastic material parameters, dear air-poroelastic layer distributions were obtained; no filtering or post-processing was necessary. The optimized foam layouts by the proposed method were shown to differ depending on the frequency of interest.

• Atmosphere
• /
• v.16 no.2
• /
• pp.55-65
• /
• 2006

The characteristics of Depth-Area-Duration (DAD) for 50 storms over the Geumgang river basin have been analysed in terms of various storm causes using the precipitation data during the period from 1984 to 2003. Results show that the ratio of the precipitation depth to duration, and the ratio of decrease in the precipitation depth to area are the largest in the case of the tropical cyclone. Storm maximization ratios are in the range 1.03 to 2.66 for the 50 selected heavy precipitation cases over Geumgang river basin, with the largest value for the tropical cyclone case, suggesting that the tropical cyclone could cause heavier precipitation than the other storms. In addition, the 24-hour probable maximum precipitation for the Geumgang river basin is estimated to be about 745 mm in the maximum precipitation area.

• The Transactions of the Korean Institute of Electrical Engineers B
• /
• v.53 no.7
• /
• pp.430-436
• /
• 2004

This paper presents an advanced control technique for power density maximization of the Brushless DC (BLDC) generator by using the linear tracking method. In a generator of given rating, the weight and size of the system affect the fuel consumption directly. Therefore, power density is one of the most important issues in a stand-alone generator. BLDC generator has high power density in the machine point of view and additional increases of power density by control means can be expected. Conventional rectification methods cannot achieve the maximum power possible because of hon-optimal current waveforms. The optimal current waveform to maximize power density and minimize machine size and weight in a nonsinusoidal power supply system has been derived, incorporated in a control system, and verified by simulation and experimental work. A new simple algebraic method has been proposed to accomplish the proposed control without an FFT which is time consuming and complicated.