• Journal of Korean Society of Industrial and Systems Engineering
• /
• v.22 no.49
• /
• pp.115-123
• /
• 1999

An optimization problem is to select the best of many possible design alternatives in a complex design space. Genetic algorithms, one of the numerous techniques to search optimal solution, have been successfully applied to various problems (for example, parameter tuning in expert systems, structural systems with a mix of continuous, integer and discrete design variables) that could not have been readily solved with more conventional computational technique. But, conventional genetic algorithms are ill defined for two classes of problems, ie., penalty function and fitness scaling. Therefore, this paper develops Improved genetic algorithms(IGA) to solve these problems. As a case study, numerical examples are demonstrated to show the effectiveness of the Improved genetic algorithms.

• Nuclear Engineering and Technology
• /
• v.1 no.2
• /
• pp.79-85
• /
• 1969

Determination of a two-point boundary value problem is the key of finding the control function u(f) with the application of the fundamental idea of Minimum principle. The late development shows the discovery of the initial testate vector for the solution of a two-point value problem. As a new technique of determining the optimal control function, Newton's sequential method is examined in this paper.

• Journal of IKEEE
• /
• v.22 no.4
• /
• pp.1222-1225
• /
• 2018

This paper proposes an image detection algorithm to implement gesture. By using a camera sensor, the performance of the extracted image algorithm based on the gesture pattern was verified through experiments. In addition, through the experiments, we confirmed the proposed method's possibility of the implementation. For efficient image detection, we applied a segmentation technique based on image transition which divides into small units. To improve gesture recognition, the proposed method not only has high recognition rate and low false acceptance rate in real gesture environment, but also designed an algorithm that efficiently finds optimal thresholds that can be applied.

• Structural Engineering and Mechanics
• /
• v.78 no.2
• /
• pp.145-161
• /
• 2021

Dynamic compaction of Aluminum powder using gas detonation forming technique was investigated. The experiments were carried out on four different conditions of total pre-detonation pressure. The effects of the initial powder mass and grain particle size on the green density and strength of compacted specimens were investigated. The relationships between the mentioned powder design parameters and the final features of specimens were characterized using Response Surface Methodology (RSM). Artificial Neural Network (ANN) models using the Group Method of Data Handling (GMDH) algorithm were also developed to predict the green density and green strength of compacted specimens. Furthermore, the desirability function was employed for multi-objective optimization purposes. The obtained optimal solutions were verified with three new experiments and ANN models. The obtained experimental results corresponding to the best optimal setting with the desirability of 1 are 2714 kg·m-3 and 21.5 MPa for the green density and green strength, respectively, which are very close to the predicted values.

• ETRI Journal
• /
• v.42 no.6
• /
• pp.846-858
• /
• 2020

The non-orthogonal multiple access (NOMA) technique offers throughput improvement to meet the demands of the future generation of wireless communication networks. The objective of this work is to further improve the throughput by including an underlay cognitive radio network with an existing multi-carrier NOMA network, using cooperative communication. The throughput is maximized by optimal resource allocation, namely, power allocation, subcarrier assignment, relay selection, user pairing, and subcarrier pairing. Optimal power allocation to the primary and secondary users is accomplished in a way that target rate constraints of the primary users are not affected. The throughput maximization is a combinatorial optimization problem, and the computational complexity increases as the number of users and/or subcarriers in the network increases. To this end, to reduce the computational complexity, a dynamic network resource allocation algorithm is proposed for combinatorial optimization. The simulation results show that the proposed network improves the throughput.

• The Journal of Korea Robotics Society
• /
• v.16 no.2
• /
• pp.122-129
• /
• 2021

For the Simultaneous Localization and Mapping (SLAM) problem, a different path results in different SLAM results. Usually, SLAM follows a trail of input data. Active SLAM, which determines where to sense for the next step, can suggest a better path for a better SLAM result during the data acquisition step. In this paper, we will use reinforcement learning to find where to perceive. By assigning entire target area coverage to a goal and uncertainty as a negative reward, the reinforcement learning network finds an optimal path to minimize trajectory uncertainty and maximize map coverage. However, most active SLAM researches are performed in indoor or aerial environments where robots can move in every direction. In the urban environment, vehicles only can move following road structure and traffic rules. Graph structure can efficiently express road environment, considering crossroads and streets as nodes and edges, respectively. In this paper, we propose a novel method to find optimal SLAM path using graph structure and reinforcement learning technique.

• International Journal of Naval Architecture and Ocean Engineering
• /
• v.12 no.1
• /
• pp.910-917
• /
• 2020

In fire suppression, continuous delivery of water or foam to the fire source is essential. The present study concerns fire suppression in a ship under sea condition, by introducing reinforcement learning technique to aiming of fire extinguishing nozzle, which works in a ship compartment with six degrees of freedom movement by irregular waves. The physical modeling of the water jet and compartment motion was provided using Unity 3D engine. In the reinforcement learning, the change of the nozzle angle during the scenario was set as the action, while the reward is proportional to the ratio of the water particle delivered to the fire source area. The optimal control of nozzle aiming for continuous delivery of water jet could be derived. Various algorithms of reinforcement learning were tested to select the optimal one, the proximal policy optimization.

• International conference on construction engineering and project management
• /
• 2015.10a
• /
• pp.158-160
• /
• 2015

Efficient scheduling and resource management are the key factor to reduce construction project budget (e.g., labor cost, equipment cost, material cost, etc.). Resource-based line of balance (LOB) technique has been used to complement the limitations of existing time-driven scheduling techniques (e.g., critical-path method). Optimizing construction alternatives contributes to cost savings while honoring the project deadline. However, existing LOB scheduling is lack of identifying optimal resource combination. This study presents a method which identifies the optimal construction alternatives, hence achieving resource minimization in a repetitive construction by using genetic algorithm (GA). The method provides efficient planning tool that enhances the usability of the system.

• Journal of Cerebrovascular and Endovascular Neurosurgery
• /
• v.25 no.1
• /
• pp.81-86
• /
• 2023

Basilar artery (BA) perforator aneurysms are exceedingly rare causes of subarachnoid hemorrhage. Therefore, the natural history and optimal treatment have not been established, and surgical, endovascular, and conservative management have been used. However, there is no consensus on the optimal treatment strategy. Herein, we report the case of a 52-year-old man presenting with a ruptured BA perforator aneurysm. First, we deployed an Enterprise stent from the left P1 segment to the BA because the microcatheter could not enter the aneurysm. Then, we deployed a helical coil on the orifice of the BA perforator. Finally, we deployed another Enterprise stent, sandwiching the helical coil between the two Enterprise stents. The aneurysm was completely obliterated without recurrence on the follow-up angiography. Our technique of sandwiching the small helical coil between two Enterprise stents might help other surgeons by offering another feasible treatment option for ruptured BA perforator aneurysms.

• International Journal of Highway Engineering
• /
• v.8 no.3 s.29
• /
• pp.63-76
• /
• 2006

For a private toll road project, deciding optimal toll is an important element of economic analysis for the project and a challengeable work. In this study, the optimal toll of a private toll bridge, Geoga Bridge which connects Geoje Island of Gyeongnam Province and Gaduk Island of Busan was estimated using Stated Preference (SP) data. The SP data were collected by interviewing the passenger car drivers travelling on the National Road 14. They are latent users of the bridge. A fuzzy approximate reasoning model to estimate the optimal toll was built using the SP data. For the input variable of the model, the saved travel time and toll level were employed and the diversion rate to the bridge was employed for the output variable. The diversion rates for each toll level and saved travel time were estimated and the toll level which had maximized the toll revenue was decided as optimal toll. The optimal toll was tested by comparing with the average pay rate of passenger car drivers. Since the optimal toll for passenger cars at one hour saving, the 6,250 won is about 50 % of the average pay rate of passenger car divers, the toll was evaluated not to be high. The technique employed in this study may be used for the estimation of the optimal tolls for other kinds of vehicles.