• Industrial Engineering and Management Systems
• /
• v.16 no.1
• /
• pp.118-128
• /
• 2017

Uncertain factors in finical markets make the prediction of future returns and risk of asset much difficult. In this paper, a model,assuming the admissible errors on expected returns and risks of assets, assisted in the multiperiod mean variance portfolio selection problem is built. The model considers transaction costs, upper bound on borrowing risk-free asset constraints, cardinality constraints and threshold constraints. Cardinality constraints limit the number of assets to be held in an efficient portfolio. At the same time, threshold constraints limit the amount of capital to be invested in each stock and prevent very small investments in any stock. Because of these limitations, the proposed model is a mix integer dynamic optimization problem with path dependence. The forward dynamic programming method is designed to obtain the optimal portfolio strategy. Finally, to evaluate the model, our result of a meaning example is compared to the terminal wealth under different constraints.

• Journal of Korean Institute of Industrial Engineers
• /
• v.26 no.4
• /
• pp.315-324
• /
• 2000

This paper presents an efficient dynamic programming(DP) method, so called EDPAS (Efficient Dynamic Programming Algorithm for Signal), for optimally controlling traffic signal in real-time mode at a single intersection. The objective of EDPAS is to minimize total vehicle delay. It applies reaching method to solve forward DP functional equation, which does not need any priori knowledge on the states of DP network. Two acceleration techniques within reaching method are the main feature of EDPAS. They are devised to eliminate inferior DP states by comparing between states and maintaining incumbent value, resulting in a great amount of computational efficiency. An example is shown to verify the advantage of EDPAS.

• Industrial Engineering and Management Systems
• /
• v.15 no.1
• /
• pp.63-76
• /
• 2016

Multiperiod portfolio selection problem attracts more and more attentions because it is in accordance with the practical investment decision-making problem. However, the existing literature on this field is almost undertaken by regarding security returns as random variables in the framework of probability theory. Different from these works, we assume that security returns are uncertain variables which may be given by the experts, and take absolute deviation as a risk measure in the framework of uncertainty theory. In this paper, a new multiperiod mean absolute deviation uncertain portfolio selection models is presented by taking transaction costs, borrowing constraints and threshold constraints into account, which an optimal investment policy can be generated to help investors not only achieve an optimal return, but also have a good risk control. Threshold constraints limit the amount of capital to be invested in each stock and prevent very small investments in any stock. Based on uncertain theories, the model is converted to a dynamic optimization problem. Because of the transaction costs, the model is a dynamic optimization problem with path dependence. To solve the new model in general cases, the forward dynamic programming method is presented. In addition, a numerical example is also presented to illustrate the modeling idea and the effectiveness of the designed algorithm.

• Transactions of the Korean Society of Automotive Engineers
• /
• v.20 no.3
• /
• pp.98-105
• /
• 2012

Recently, most of the countries started to regulate the emission of vehicle because of the global warming. The engine scooter is also one of the factor which cause the pollution. The hybrid system of a vehicle has many advantages such as fuel saving and emission reduction. The purpose of this study is to choose optimal size of engine, motor and battery for hybrid scooter system using Dynamic programming. The dynamic programming is an effective method to find an optimal solution for the complicated nonlinear system, which contains various constraints of control variables. The power source size of hybrid scooter was chosen through the backward simulator using dynamic programming. From the analysis, we choose the optimal size of each power source. To verify the optimal size of the power source, the Forward simulation was carried out. As a result, the fuel efficiency of hybrid scooter has significantly increased in comparison with that of engine scooter.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.4 no.2
• /
• pp.87-95
• /
• 2003

Dynamic Programming Matching (DPM) is a mathematical optimization technique for sequentially structured problems, which has, over the years, played a major role in providing primary algorithms in pattern recognition fields. Most practical applications of this method in signature verification have been based on the practical implementational version proposed by Sakoe and Chiba [9], and il usually applied as a case of slope constraint p = 0. We found, in this case, a modified version of DPM by applying a heuristic (forward seeking) implementation is more efficient, offering significantly reduced processing complexity as well as slightly improved verification performance.

• The KIPS Transactions:PartB
• /
• v.10B no.4
• /
• pp.451-458
• /
• 2003

Dynamic Programming Matching (DPM) is a mathematical optimization technique for sequentially structured problems, which has, over the years, played a major role in providing primary algorithms in pattern recognition fields. Most practical applications of this method in signature verification have been based on the practical implementational version proposed by Sakoe and Chiba [9], and is usually applied as a case of slope constraint p = 0. We found, in this case, a modified version of DPM by applying a heuristic (forward seeking) implementation is more efficient, offering significantly reduced processing complexity as well as slightly improved verification performance.

• The Transactions of the Korean Institute of Electrical Engineers D
• /
• v.53 no.5
• /
• pp.353-360
• /
• 2004

This paper considers reinforcement learning control with the self-organizing map. Reinforcement learning uses the observable states of objective system and signals from interaction of the system and environment as input data. For fast learning in neural network training, it is necessary to reduce learning data. In this paper, we use the self-organizing map to partition the observable states. Partitioning states reduces the number of learning data which is used for training neural networks. And neural dynamic programming design method is used for the controller. For evaluating the designed reinforcement learning controller, an inverted pendulum on the cart system is simulated. The designed controller is composed of serial connection of self-organizing map and two Multi-layer Feed-Forward Neural Networks.

• Journal of Korean Society of Industrial and Systems Engineering
• /
• v.11 no.18
• /
• pp.7-15
• /
• 1988

This study is concerned with selecting mutually dependent quality improvement alternatives with resource constraints. These qualify improvement alternatives art different fro the tradition at alternatives which are independent from each other. In other words, selection of any improvement alternative requires other related specific improvement. Also the overall product quality in a multi stage manufacturing process is characterized by a complex multiplication method rather than a simple addition method which dose not allow to solve a linear knapsack problem despite its popularity in the traditional study. This study suggests a non-linear integer programming model for selecting mutually dependent quality improvement alternatives in multi-stage manufacturing process. In order to apply the model to selecting alternatives. This study also suggests a heuristic mode1 based on a dynamic programming model which is more practical than the non-linear integer programming model. The logic of the heuristic model enables 1) to estimate improvement effectiveness values on all improvement alternatives specifically defined for this study. 2) to arrange the effectiveness values in a descending order, and 3) to select the best one among the alternatives based on their forward and backward linkage relationships. This process repeats to selects other best alternatives within the resource constraints. This process is presented in a Computer programming in Appendix A. Alsc a numerical example of model application is presented in Chapter 4.

• Journal of Korean Society of Industrial and Systems Engineering
• /
• v.35 no.2
• /
• pp.57-63
• /
• 2012

Software release planning model of software product lines was formulated as a precedence-constrained multiple 0-1 knapsack problem. The purpose of the model was to maximize the total profit of an entire set of selected features in a software product line over a multi-release planning horizon. The solution approach is a dynamic programming procedure. Feasible solutions at each stage in dynamic programming are determined by using backward dynamic programming approach while dynamic programming for multi-release planning is forward approach. The pre-processing procedure with a heuristic and reduction algorithm was applied to the single-release problems corresponding to each stage in multi-release dynamic programming in order to reduce the problem size. The heuristic algorithm is used to find a lower bound to the problem. The reduction method makes use of the lower bound to fix a number of variables at either 0 or 1. Then the reduced problem can be solved easily by the dynamic programming approaches. These procedures keep on going until release t = T. A numerical example was developed to show how well the solution procedures in this research works on it. Future work in this area could include the development of a heuristic to obtain lower bounds closer to the optimal solution to the model in this article, as well as computational test of the heuristic algorithm and the exact solution approach developed in this paper. Also, more constraints reflecting the characteristics of software product lines may be added to the model. For instance, other resources such as multiple teams, each developing one product or a platform in a software product line could be added to the model.

• 제어로봇시스템학회:학술대회논문집
• /
• 2003.10a
• /
• pp.142-145
• /
• 2003

Many control applications using Neural Network need a priori information about the objective system. But it is impossible to get exact information about the objective system in real world. To solve this problem, several control methods were proposed. Reinforcement learning control using neural network is one of them. Basically reinforcement learning control doesn't need a priori information of objective system. This method uses reinforcement signal from interaction of objective system and environment and observable states of objective system as input data. But many methods take too much time to apply to real-world. So we focus on faster learning to apply reinforcement learning control to real-world. Two data types are used for reinforcement learning. One is reinforcement signal data. It has only two fixed scalar values that are assigned for each success and fail state. The other is observable state data. There are infinitive states in real-world system. So the number of observable state data is also infinitive. This requires too much learning time for applying to real-world. So we try to reduce the number of observable states by classification of states with Self-Organizing Map. We also use neural dynamic programming for controller design. An inverted pendulum on the cart system is simulated. Failure signal is used for reinforcement signal. The failure signal occurs when the pendulum angle or cart position deviate from the defined control range. The control objective is to maintain the balanced pole and centered cart. And four states that is, position and velocity of cart, angle and angular velocity of pole are used for state signal. Learning controller is composed of serial connection of Self-Organizing Map and two Multi-layer Feed-Forward Neural Networks.