• Journal of the Korean Society of Hazard Mitigation
• /
• v.4 no.2 s.13
• /
• pp.13-18
• /
• 2004

In this study, in the first place, parameters primarily influencing displacement and stress were constructed by using the Finite Difference Method; then using those parameters, the result of crown displacement and convergence among the existing, experimental values of a centrifuge model were compared with the result of numerical analysis; and then considering the stress and time effect of lining installation, parameters according to the difference of stiffness were studied. In the result of this study, it found out that rough, ground reinforcement effect manifests itself when reinforcement propert of the grouting of the big scale steel pipe through 3-D analysis is E= 4,000tf/m2 which of the stiffness of the original ground.

• Journal of Korea Multimedia Society
• /
• v.21 no.8
• /
• pp.969-981
• /
• 2018

Recent advances in machine learning approaches such as deep neural network and reinforcement learning offer significant performance improvements in generating detailed and varied motions in physically simulated virtual environments. The optimization methods are highly attractive because it allows for less understanding of underlying physics or mechanisms even for high-dimensional subtle control problems. In this paper, we propose an efficient learning method for stochastic policy represented as deep neural networks so that agent can generate various energetic motions adaptively to the changes of tasks and states without losing interactivity and robustness. This strategy could be realized by our novel trajectory search method motivated by the trust region policy optimization method. Our value-based trajectory smoothing technique finds stably learnable trajectories without consulting neural network responses directly. This policy is set as a trust region of the artificial neural network, so that it can learn the desired motion quickly.

• Journal of Korea Game Society
• /
• v.20 no.1
• /
• pp.57-66
• /
• 2020

The goal is to implement AI using reinforcement learning, which replaces the less favored Supporter in MOBA games. ML_Agent implements game rules, environment, observation information, rewards, and punishment. The experiment was divided into P and C group. Experiments were conducted to compare the cumulative compensation values and the number of deaths to draw conclusions. In group C, the mean cumulative compensation value was 3.3 higher than that in group P, and the total mean number of deaths was 3.15 lower. performed cooperative play to minimize death and maximize rewards was confirmed.

• Journal of Korea Game Society
• /
• v.18 no.4
• /
• pp.99-106
• /
• 2018

Board games have many game characters and many state spaces. Therefore, games must be long learning. This paper used reinforcement learning algorithm. But, there is weakness with reinforcement learning. At the beginning of learning, reinforcement learning has the drawback of slow learning speed. Therefore, we tried to improve the learning speed by using the heuristic using the knowledge of the problem domain considering the game tree when there is the same best value during learning. In order to compare the existing character the improved one. I produced a board game. So I compete with one-sided attacking character. Improved character attacked the opponent's one considering the game tree. As a result of experiment, improved character's capability was improved on learning speed.

• Computers and Concrete
• /
• v.22 no.5
• /
• pp.493-500
• /
• 2018

Due to the fact that the ratio of their height to their openings is very large compared to normal beams, there are difficulties in the design and analysis of deep beams, which differ in behavior. In this study, the optimum horizontal and vertical reinforcement diameters of 5 different beams were determined by using genetic algorithms (GA) due to the openness/height ratio (L/h), loading condition and the presence of spaces in the body. In this study, the effect of different mutation operators and improved double times sensitive mutation (DTM) operator on GA's performance was investigated. In the study following random mutation (RM), boundary mutation (BM), non-uniform random mutation (NRM), Makinen, Periaux and Toivanen (MPT) mutation, power mutation (PM), polynomial mutation (PNM), and developed DTM mutation operators were applied to five deep beam problems were used to determine the minimum reinforcement diameter. The fitness values obtained using developed DTM mutation operator was higher than obtained from existing mutation operators. Moreover; obtained reinforcement weight of the deep beams using the developed DTM mutation operator lower than obtained from the existing mutation operators. As a result of the analyzes, the highest fitness value was obtained from the applied double times sensitive mutation (DTM) operator. In addition, it was found that this study, which was carried out using GAs, contributed to the solution of the problems experienced in the design of deep beams.

• Journal of Information Technology Services
• /
• v.15 no.4
• /
• pp.85-95
• /
• 2016

Recently, deep learning and machine learning have attracted considerable attention and many supporting frameworks appeared. In artificial intelligence field, a large body of research is underway to apply the relevant knowledge for complex problem-solving, necessitating the application of various learning algorithms and training methods to artificial intelligence systems. In addition, there is a dearth of performance evaluation of decision making agents. The decision making agent that can find optimal solutions by using reinforcement learning methods designed through this research can collect raw pixel data observed from dynamic environments and make decisions by itself based on the data. The decision making agent uses convolutional neural networks to classify situations it confronts, and the data observed from the environment undergoes preprocessing before being used. This research represents how the convolutional neural networks and the decision making agent are configured, analyzes learning performance through a value-based algorithm and a policy-based algorithm : a Deep Q-Networks and a Policy Gradient, sets forth their differences and demonstrates how the convolutional neural networks affect entire learning performance when using pixel data. This research is expected to contribute to the improvement of artificial intelligence systems which can efficiently find optimal solutions by using features extracted from raw pixel data.

• The KIPS Transactions:PartB
• /
• v.10B no.3
• /
• pp.237-242
• /
• 2003

Ant Colony System (ACS) Algorithm is new meta heuristic for hard combinatorial optimization problem. It is a population based approach that uses exploitation of positive feedback as well as greedy search. It was first proposed for tackling the well known Traveling Salesman Problem (TSP). In this paper, we introduce ACS of new method that adds reinforcement value for each edge that visit to Local/Global updating rule. and the performance results under various conditions are conducted, and the comparision between the original ACS and the proposed method is shown. It turns out that our proposed method can compete with tile original ACS in terms of solution quality and computation speed to these problem.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.16 no.1
• /
• pp.334-349
• /
• 2022

The effectiveness of Wi-Fi networks is greatly influenced by the optimization of contention window (CW) parameters. Unfortunately, the conventional approach employed by IEEE 802.11 wireless networks is not scalable enough to sustain consistent performance for the increasing number of stations. Yet, it is still the default when accessing channels for single-users of 802.11 transmissions. Recently, there has been a spike in attempts to enhance network performance using a machine learning (ML) technique known as reinforcement learning (RL). Its advantage is interacting with the surrounding environment and making decisions based on its own experience. Deep RL (DRL) uses deep neural networks (DNN) to deal with more complex environments (such as continuous state spaces or actions spaces) and to get optimum rewards. As a result, we present a new approach of CW control mechanism, which is termed as contention window threshold (CW_Threshold). It uses the DRL principle to define the threshold value and learn optimal settings under various network scenarios. We demonstrate our proposed method, known as a smart exponential-threshold-linear backoff algorithm with a deep Q-learning network (SETL-DQN). The simulation results show that our proposed SETL-DQN algorithm can effectively improve the throughput and reduce the collision rates.

• Structural Engineering and Mechanics
• /
• v.88 no.2
• /
• pp.179-188
• /
• 2023

The mechanical behaviours of biopolymer-treated soil depend on the formation of soil-biopolymer matrices. In this study, various biopolymers(e.g., xanthan gum (XG), locust bean gum (LBG), sodium alginate (SA), agar gum (AG), gellan gum (GE) and carrageenan kappa gum (KG) are selected to treat three types of natural soil at different concentrations (e.g., 1%, 2% and 3%) and curing time (e.g., 4-365 days), and reveal the reinforcement effect on natural soil by using unconfined compression tests. The results show that biopolymer-treated soil obtains the maximum unconfined compressive strength (UCS) at curing 14-28 days. Although the UCS of biopolymer-treated soil has a 20-30% reduction after curing 1-year compared to the maximum value, it is still significantly larger than untreated soil. In addition, the UCS increment ratio of biopolymer-treated soil decreases with the increase of biopolymer concentration, and there exists the optimum concentration of 1%, 2-3%, 2%, 1% and 2% for XG, SA, LBG, KG and AG, respectively. Meanwhile, the optimum initial moisture content can form uniformly biopolymer-soil matrices to obtain better reinforcement efficiency. Furthermore, the best performance in increasing soil strength is XG following SAand LBG, which are significantly better than AG, KG and GE.

• Structural Engineering and Mechanics
• /
• v.91 no.4
• /
• pp.335-347
• /
• 2024

This paper presents the behavior of geopolymer concrete beams reinforced with glass fiber reinforced polymer (GFRP) bars. In the study, ordinary Portland cement concrete and geopolymer concrete beams having GFRP bars were prepared and tested under four-point loading. The load-deflection diagrams and load capacities of the tested beams were obtained. It was observed that the tested beams exhibited good ductility and significant deflection capacity. The results showed that increasing the tension GFRP reinforcement ratio caused enhancement in the strength capacity of geopolymer concrete beams. In addition, the tested beams were analyzed to obtain the load capacity and the load-deflection responses. The theoretical load-deflection curves and load bearing capacities have been predicted well with the test results. Parametric study has been performed to determine the influences of concrete strength, shear span to depth ratio (a/d) and reinforcement ratio on the behavior of geopolymer concrete beams longitudinally reinforced with GFRP bars. It was concluded that increasing concrete strength led to an increase in load capacity. Besides, the ultimate load increased as the reinforcement ratio increased. On the other hand, increasing a/d ratio reduced the ultimate load value of GFRP reinforced geopolymer concrete beams.