• Journal of Korean Association for Spatial Structures
• /
• v.3 no.3 s.9
• /
• pp.29-37
• /
• 2003

• Journal of Oriental Neuropsychiatry
• /
• v.21 no.2
• /
• pp.87-101
• /
• 2010

Objectives : The aim of this experiment was to investigate the influences of Autonomic Nervous System and EEG by conducting Reinforcement-Reduction(補瀉) acupuncture stimulation to compare the changes in acupoints on the body before and after treatment of acupuncture at Xingjian(LR2) being referred as Fire-point(火穴) and Ququan(LR8) being referred as Water-point(水穴) of Yin Liver Meridian(足厥陰肝經). Methods : This study was carried out on 30 healthy female volunteers in their 20's. There were four tests conducted throughout and the period for each test was between 2 to 5days. HRV and EEG were measured for 5 minutes before acupuncture stimulation was conducted on LR2-Reinforcement, LR2-Reduction, LR8-Reinforcement and LR8-Reduction at random. During the 20 minutes of acupuncture treatment, same subjects were measured simultaneously to observe any significant changes in acupoints. Again, the same subjects were measured for 5 minutes after removing the acupuncture in order to perform a comparative analysis. Results : The measurement of HRV showed that LF, LFnorm and LF/HF ratio increased significantly(p<0.05) while HF, HF norm decreased significantly in case of LR2-Reinforcement & LR8-Reduction. Both LR2-Reduction and LR8-Reinforcement induced a significant increase in HFnorm. EEG measurement indicated low $\alpha$ wave decreased and high $\beta$ wave increased significantly at LR2-Reinforcement during post-acupuncture period compared with acupuncture stimulation period. Both LR2-Reduction and LR8-Reinforcement developed significantly low $\alpha$ wave and high $\alpha$ wave. High $\beta$ wave increased significantly at LR8-Reduction during the acupuncture stimulation in comparison with pre-acupuncture period. Conclusions : The manipulation of acupuncture stimulation at LR2-Reinforcement and LR8-Reduction enhanced the activity of sympathetic nerves and the state of arousal while that of para sympathetic nerves declined. On the other hand, LR2-Reduction and LR8-Reinforcement developed the levels of para sympathetic nerves and relaxation.

• Proceedings of the Korea Concrete Institute Conference
• /
• 2003.11a
• /
• pp.380-383
• /
• 2003

Deep pile caps usually contain no transverse shear reinforcement and only small percentages of longitudinal reinforcement. The current design procedures including ACI 318-02 for the pile caps do not provide engineers with a clear understanding of the physical behavior of deep pile caps. In this study, the failure strengths of nine pile cap specimens tested to failure were evaluated using 3-dimensional strut-tie models. The analysis results obtained from the present study were compared with those obtained from several design methods, and the validity of the present method implementing 3-dimensional strut-tie models was examined.

• Structural Engineering and Mechanics
• /
• v.27 no.4
• /
• pp.393-408
• /
• 2007

This paper presents the findings of an experimental study to evaluate retrofit methods which address particular weaknesses that are often found in reinforced concrete structures, especially older structures, namely the lack of the required flexural and shear reinforcement within the columns and the lack of the required shear reinforcement within the joints. Thus, the use of a high-strength fiber jacket for cases of post-earthquake and pre-earthquake retrofitting of columns and beam-column joints was investigated experimentally. In this paper, the effectiveness of the two jacket styles was also compared.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.11 no.5
• /
• pp.388-394
• /
• 2001

Reinforcement learning is a kind of unsupervised learning methods that an agent control rules from experiences acquired by interactions with environment. The eligibility is used to resolve the credit-assignment problem which is one of important problems in reinforcement learning, Conventional eligibilities such as the accumulating eligibility and the replacing eligibility are ineffective in use of rewards acquired in learning process, since on1y one executed action for a visited state is learned. In this paper, we propose a new eligibility, called the distributed eligibility, with which not only an executed action but also neighboring actions in a visited state are to be learned. The fuzzy Q-learning algorithm using the proposed eligibility is applied to a cart-pole balancing problem, which shows the superiority of the proposed method to conventional methods in terms of learning speed.

• Computers and Concrete
• /
• v.3 no.2_3
• /
• pp.79-90
• /
• 2006

This paper describes the results of an investigation into high mass-low velocity impact behaviour of reinforced concrete beams. Tests have been conducted on fifteen 2.7 m or 1.5 m span beams under drop-weight loads. A high-speed video camera has been used at rates of up to 4,500 frames per second in order to record the crack formation, propagation, particle spallation and scabbing. In some tests the strain in the reinforcement has been recorded using "Durham" strain gauged bars, a technique developed by Scott and Marchand (2000) in which the strain gauges are embedded in the bars, so that the strains in the reinforcement can be recorded without affecting the bond between the concrete and the reinforcement. The impact force acting on the beams has been measured using a load cell placed within the impactor. A high-speed data logging system has been used to record the impact load, strains, accelerations, etc., so that time histories can be obtained. This research has led to the development of computational techniques based on combined continuum/discontinuum methods (finite/discrete element methods) to permit the simulation of impact loaded reinforced concrete beams. The implementation has been within the software package ELFEN (2004). Beams, similar to those tested, have been analysed using ELFEN a good agreement has been obtained for both the load-time histories and the crack patterns.

• 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.

• International Journal of Computer Science & Network Security
• /
• v.21 no.9
• /
• pp.125-131
• /
• 2021

Detecting fraudulent insurance claims is difficult due to small and unbalanced data. Some research has been carried out to better cope with various types of fraudulent claims. Nowadays, technology for detecting fraudulent insurance claims has been increasingly utilized in insurance and technology fields, thanks to the use of artificial intelligence (AI) methods in addition to traditional statistical detection and rule-based methods. This study obtained meaningful results for a fraudulent insurance claim detection model based on machine learning (ML) and deep learning (DL) technologies, using fraudulent insurance claim data from previous research. In our search for a method to enhance the detection of fraudulent insurance claims, we investigated the reinforcement learning (RL) method. We examined how we could apply the RL method to the detection of fraudulent insurance claims. There are limited previous cases of applying the RL method. Thus, we first had to define the RL essential elements based on previous research on detecting anomalies. We applied the deep Q-network (DQN) and double deep Q-network (DDQN) in the learning fraudulent insurance claim detection model. By doing so, we confirmed that our model demonstrated better performance than previous machine learning models.

• The Journal of Korea Robotics Society
• /
• v.14 no.1
• /
• pp.40-49
• /
• 2019

Reinforcement learning has been applied to various problems in robotics. However, it was still hard to train complex robotic manipulation tasks since there is a few models which can be applicable to general tasks. Such general models require a lot of training episodes. In these reasons, deep neural networks which have shown to be good function approximators have not been actively used for robot manipulation task. Recently, some of these challenges are solved by a set of methods, such as Guided Policy Search, which guide or limit search directions while training of a deep neural network based policy model. These frameworks are already applied to a humanoid robot, PR2. However, in robotics, it is not trivial to adjust existing algorithms designed for one robot to another robot. In this paper, we present our implementation of Guided Policy Search to the robotic arms of the Baxter Research Robot. To meet the goals and needs of the project, we build on an existing implementation of Baxter Agent class for the Guided Policy Search algorithm code using the built-in Python interface. This work is expected to play an important role in popularizing robot manipulation reinforcement learning methods on cost-effective robot platforms.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.15 no.9
• /
• pp.3444-3457
• /
• 2021

In the field of anti-jamming based on dynamic spectrum, most methods try to improve the ability to avoid jamming and seldom consider whether the jammer would perceive the user's signal. Although these existing methods work in some anti-jamming scenarios, their long-term performance may be depressed when intelligent jammers can learn user's waveform or decision information from user's historical activities. Hence, we proposed a hidden anti-jamming method to address this problem by reducing the jammer's sense probability. In the proposed method, the action correlation between the user and the jammer is used to evaluate the hiding effect of the user's actions. And a deep reinforcement learning framework, including specific action correlation calculation and iteration learning algorithm, is designed to maximize the hiding and communication performance of the user synchronously. The simulation result shows that the algorithm proposed reduces the jammer's sense probability significantly and improves the user's anti-jamming performance slightly compared to the existing algorithms based on jamming avoidance.