• Journal of Korea Multimedia Society
• /
• v.19 no.1
• /
• pp.22-29
• /
• 2016

Hidden Markov Model is one of the most successful and popular tools for modeling real world sequential data. Real world signals come in a variety of shapes and variabilities, among which temporal and spectral ones are the prime targets that the HMM aims at. A new problem that is gaining increasing attention is characterizing missing observations in incomplete data sequences. They are incomplete in that there are holes or omitted measurements. The standard HMM algorithms have been developed for complete data with a measurements at each regular point in time. This paper presents a modified algorithm for a discrete HMM that allows substantial amount of omissions in the input sequence. Basically it is a variant of Baum-Welch which explicitly considers the case of isolated or a number of omissions in succession. The algorithm has been tested on online handwriting samples expressed in direction codes. An extensive set of experiments show that the HMM so modeled are highly flexible showing a consistent and robust performance regardless of the amount of omissions.

• Proceedings of the KIEE Conference
• /
• 2004.07d
• /
• pp.2516-2518
• /
• 2004

This paper proposes a stability condition in discrete-time affine Takagi-Sugeno (T-S) fuzzy systems with parametric uncertainties and then, introduces the design method of a fuzzy-model-based controller which guarantees the stability. The analysis is based on Lyapunov functions that are continuous and piecewise quadratic. The search for a piecewise quadratic Lyapunov function can be represented in terms of linear matrix inequalities (LMIs).

• Proceedings of the KSME Conference
• /
• 2003.04a
• /
• pp.1839-1844
• /
• 2003

In order to provide a tool for designing more efficient methods of mixing fabric, a simplified discrete element computational model was developed for modeling fabric dynamics in a rotating horizontal drum. Because modeling the interactions between actual pieces of fabric is quite complex, a simplified model was developed where individual pieces of bundled fabric are represented by spherical particles. The simulations are used to investigate fabric bundle kinematics, the power required to drive the rotating drum, and the power dissipated through normal and tangential contacts. Parametric studies indicate only fill percentage, drum rotation speed, and friction coefficient play significant roles in the fabric bundle dynamics.

• Journal of the Korea Society for Simulation
• /
• v.10 no.1
• /
• pp.1-12
• /
• 2001

This article describes the application of discrete event simulation in a process industry (coffee manufacturing) as a daily production-scheduling tool. A large number of end products (around 300), sporadic demand, and limited shelf life of coffee (90 days) make it difficult to generate feasible production schedules manually. To solve this problem, an integrated system was developed incorporating discrete event simulation methodology into scheduling process. The integrated system is comprised of two components: a scheduling program and a simulation model. The scheduling program is used to generate daily schedules for roasting, grinding, and packing coffee. The simulation model uses the generated schedules to simulate the production of coffee and regenerates a modified production schedule. In this paper, each of the components will be described in detail, evaluated in terms of performance factors, and validated with a set of real production data. Although this article focuses on a specific system, we will share our experiences and Intuitions gained and encourage other process industries to develop simulation-based scheduling tools.

• Particle and aerosol research
• /
• v.8 no.2
• /
• pp.75-81
• /
• 2012

The strength of lumped cokes can be represented by some index numbers. Although some indexes are suggested, these indexes are not enough to enlighten fracture mechanism. To find essential mechanism, a computational way, discrete element method, is applied to the uniaxial compression test for cylindrical specimen. The cylindrical specimen is a kind of lumped particle mass with parallel bonding that will be broken when the normal stress and shear stress is over a critical value. It is revealed that the primary factors for cokes fracture are parallel spring constant, parallel bond strength, bonding radius and packing ratio the parallel bond strength and radius of the parallel combination the packing density. Especially, parallel spring constant is directly related with elastic constant and yield strength.

• Management Science and Financial Engineering
• /
• v.17 no.1
• /
• pp.65-78
• /
• 2011

In the continuous review (Q, r) model one continuously monitors inventory level and places a replenishment order when the inventory position reaches the reorder point. In many business practices, however, inventory decreases in a discrete fashion. As a result, replenishment orders are usually placed after the inventory position gets far below the reorder point. This makes a chance of shortage more likely and the service level lower than designed. Such a discrepancy can be compensated for by raising the reorder point to some extent. The question is how much the reorder point should be raised in order to compensate for a potential shortage. In this study, we present experimental analyses for this question. Regression models are also proposed for on-site use.

• Structural Engineering and Mechanics
• /
• v.55 no.4
• /
• pp.687-702
• /
• 2015

A method based on derivatives of eigen-parameters is presented for damage detection in discrete systems with dampers. The damage is simulated by decrease on the stiffness coefficient and increase of the damping coefficient. In the forward analysis, the derivatives of eigen-parameters are derived for the discrete system. In the inverse analysis, a derivative of eigen-parameters based model updating approach is used to identify damages in frequency domain. Two numerical examples are investigated to illustrate efficiency and accuracy of the proposed method. Studies in this paper indicate that the proposed method is efficient and robust for both single and multiple damages and is insensitive to measurement noise. And satisfactory identified results can be obtained from few numbers of iterations.

• Journal of Electrical Engineering and Technology
• /
• v.7 no.6
• /
• pp.911-917
• /
• 2012

In this paper, a digital speed regulator system design method is developed for a permanent magnet synchronous motor (PMSM). Firstly, an accurate approximate discrete-time model is proposed for a PMSM considering its inherent nonlinearities. Based on the discrete-time model, a digital acceleration observer as well as a digital speed regulator is designed. The exponential stability of the augmented control system is analyzed. The proposed digital speed regulator system is implemented by using a TMS320F28335 floating point DSP. Simulation and experimental results are given to verify the effectiveness of the proposed method.

• Proceedings of the KIPE Conference
• /
• 2007.07a
• /
• pp.135-137
• /
• 2007

A phase shifted full-bridge PWM converter (PSFBC) has been used as the most popular topology for many applications. But, for the reasons of the cost and performance, the control circuits for the PSFBC have generally been implemented using analog circuits. The studies on the digital control of the PSFBC were recently presented. However, they considered only the digital implementation of the analog controller. This paper presents the modeling and design of the digital controller for the PSFBC in the discrete time domain. The discretized PSFBC model is first derived considering the sampling effect. Based on this model, the digital controller is directly designed in discrete time domain. The simulation and experimental results are provided to verify the proposed modeling and controller design.

• Proceedings of the KIEE Conference
• /
• 1996.07b
• /
• pp.1056-1059
• /
• 1996

In this study, a new OSA controller is proposed for controlling discrete-time chaotic systems efficiently. A new OSA controller uses NARMAX models, and its feedback gain is designed on the basis of conventional linear control theory. In order to evaluate the performance of a new OSA controller, a new OSA controller is applied to Henon system which is a discrete-time chaotic system, and then the control performance of a new OSA controller are compared with that of the previous model-base controller through computer simulations.