• Journal of the Korean Data and Information Science Society
• /
• v.26 no.2
• /
• pp.301-312
• /
• 2015

The purpose of this paper is to establish the epidemic model to explain the process of disease spread. The process of disease spread can be classified into two types: deterministic process and stochastic process. Most studies supposed that the process follows the deterministic process and established the model using the ordinary differential equation. In this article, we try to build the disease spread prediction model based on the SIR (Suspectible - Infectious - Recovered) model. we first estimated the model parameters using least squared method and applied to a deterministic model using ordinary differential equation. we also applied to a stochastic model based on Gillespie algorithm. The methods introduced in this paper are applied to the data on the number of cases of malaria every week from January 2001 to March 2003, released by Korea Centers for Disease Control and Prevention. As a result, we conclude that our model explains well the process of disease spread.

• Journal of the Society of Naval Architects of Korea
• /
• v.56 no.1
• /
• pp.58-65
• /
• 2019

The stability, reliability and efficiency of a smart ship are important issues as the interest in an autonomous ship has recently been high. An automatic collision avoidance system is an essential function of an autonomous ship. This system detects the possibility of collision and automatically takes avoidance actions in consideration of economy and safety. In order to construct an automatic collision avoidance system using reinforcement learning, in this work, the sequential decision problem of ship collision is mathematically formulated through a Markov Decision Process (MDP). A reinforcement learning environment is constructed based on the ship maneuvering equations, and then the three key components (state, action, and reward) of MDP are defined. The state uses parameters of the relationship between own-ship and target-ship, the action is the vertical distance away from the target course, and the reward is defined as a function considering safety and economics. In order to solve the sequential decision problem, the Deep Deterministic Policy Gradient (DDPG) algorithm which can express continuous action space and search an optimal action policy is utilized. The collision avoidance system is then tested assuming the $90^{\circ}$intersection encounter situation and yields a satisfactory result.

• 제어로봇시스템학회:학술대회논문집
• /
• 2001.10a
• /
• pp.73.5-73
• /
• 2001

In this paper, we present a procedure to design the robust optimal supervisor which has the minimal cost in the sense of average for a given multiple-modelled discrete event system DES. In order to design the robust optimal supervisor, we extend the optimal supervisor design algorithm for a deterministic DES to the case of multiple-modelled DESs. In addition, using the proposed algorithm with modified costs of events and penalities of states, we can show whether a robust supervisor for a given multiple-modelled DES exists and design the minimally restricted robust supervisor.

• Journal of Korean Institute of Industrial Engineers
• /
• v.31 no.3
• /
• pp.194-200
• /
• 2005

A stochastic dynamic lot sizing problem for multi-item is suggested in the case that the distribution of the cumulative demand is known over finite planning horizons and all unsatisfied demand is fully backlogged. Each item is produced simultaneously at a variable ratio of input resources employed whenever setup is incurred. A dynamic programming algorithm is proposed to find the optimal production policy, which resembles the Wagner-Whitin algorithm for the deterministic case problem but with some additional feasibility constraints.

• Journal of Korean Society of Industrial and Systems Engineering
• /
• v.13 no.21
• /
• pp.51-60
• /
• 1990

In this paper we deal with the miniaml cost network flow problem with uncertain arc capacity constraints. When the arc capacities are fuzzy with linear L-R type membership function, using parametric programming procedure, we reduced it to the deterministic minimal cost network flow problem which can be solved by various typical network flow algorithms. A modified Algorithm using the Out-of-kilter algorithm is developed.

• Journal of the Korean Society for Precision Engineering
• /
• v.12 no.8
• /
• pp.140-146
• /
• 1995

In case the uncertainty existing in a system is assumed to satisfy the matching condition and to be come-bounded. Y. H. Chen proposed an adaptive robust control algorithm which introduced adaptive sheme for a design parameter into robust deterministic controls. In this paper, the adaptive robust control algorithm is applied to the position tracking control of direct drive robots, and simulation and experimental studies are conducted to evaluate control performance.

• Investigative Magnetic Resonance Imaging
• /
• v.6 no.2
• /
• pp.137-146
• /
• 2002

Purpose : This paper introduces an improved classification approach which adopts a deterministic relaxation method and an agglomerative clustering technique for the classification of MRI using neural network. The proposed approach can solve the problems of convergency to local optima and computational burden caused by a large number of input patterns when a neural network is used for image classification. Materials and methods : Application of Hopfield neural network has been solving various optimization problems. However, major problem of mapping an image classification problem into a neural network is that network is opt to converge to local optima and its convergency toward the global solution with a standard stochastic relaxation spends much time. Therefore, to avoid local solutions and to achieve fast convergency toward a global optimization, we adopt MFA to a Hopfield network during the classification. MFA replaces the stochastic nature of simulated annealing method with a set of deterministic update rules that act on the average value of the variable. By minimizing averages, it is possible to converge to an equilibrium state considerably faster than standard simulated annealing method. Moreover, the proposed agglomerative clustering algorithm which determines the underlying clusters of the image provides initial input values of Hopfield neural network. Results : The proposed approach which uses agglomerative clustering and deterministic relaxation approach resolves the problem of local optimization and achieves fast convergency toward a global optimization when a neural network is used for MRI classification. Conclusion : In this paper, we introduce a new paradigm to classify MRI using clustering analysis and deterministic relaxation for neural network to improve the classification results.

• Journal of the Institute of Electronics Engineers of Korea TC
• /
• v.38 no.6
• /
• pp.28-38
• /
• 2001

In this paper, we propose and analyze a more efficient and flexible dynamic data traffic system for a circuit switched satellite network. Our proposed system is more efficient than existing circuit switched satellite networks and allows for dynamic capacity in each connection without rebuilding or resetting the connection software or algorithms. We also discuss an algorithm for bandwidth allocation that provides deterministic quality of service guarantees. The traffic sources are regulated using standard dual leaky buckets; the system performance is analytically evaluated; and the algorithm is verified through simulation. Our analysis scheme and results should prove useful for the design and implementation of protocols in future circuit-switched satellite networks.

• Journal of the Korean Operations Research and Management Science Society
• /
• v.40 no.3
• /
• pp.63-72
• /
• 2015

This paper presents the issue that is predicting the movement of an agent in an enclosed space by using the MDP (Markov Decision Process). Recent researches on the optimal path finding are confined to derive the shortest path with the use of deterministic algorithm such as $A^*$ or Dijkstra. On the other hand, this study focuses in predicting the path that the agent chooses to escape the limited space as time passes, with the stochastic method. The MDP reward structure from GIS (Geographic Information System) data contributed this model to a feasible model. This model has been approved to have the high predictability after applied to the route of previous armed red guerilla.

• Journal of Advanced Marine Engineering and Technology
• /
• v.18 no.4
• /
• pp.102-111
• /
• 1994

This article deals with the problem of designing a robust algorithm for the motion control of robot manipulator whose nonlinear dynamics contain various uncertainties. To ensure high performance of control system, a model-based feedforward compensation with continuous robust control has been developed. The control structure based on the deterministic approach consists of two parts : the nominal control law is first introduced to stabilize the system without uncertainties, then a robust nonlinear control law is adopted to compensate for both the resulting errors(or structured uncertainties) and unstructured uncertainties. The uncertainties assumed in this study are bounded by polynomials in the Euclidean norms of system states with known bounding coefficients. The presented control scheme is relatively simple as well as computationally efficient. With a feasible class of desired trajectories, the proposed control law provides sufficient criteria which guarantee that all possible responses of the closed-loop system are uniformly ultimately bounded in the presence of uncertainties. Therefore, the control algorithm proposed is shown to be robust with respect to the involved uncertainties.