• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.12 no.3
• /
• pp.75-81
• /
• 2012

With the advance of internet technology and fast growing of data volume, it become very hard to find a demanding information from the huge amount of data. Recommender system can solve the delema by helping a user to find required information. This paper proposes a reinforcement learning based hybrid recommendation system to predict user's preference. The hybrid recommendation system combines the content based filtering and collaborate filtering, and the system was tested using 2000 images. We used mean abstract error(MAE) to compare the performance of the collaborative filtering, the content based filtering, the naive hybrid filtering, and the reinforcement learning algorithm based hybrid filtering methods. The experiment result shows that the performance of the proposed hybrid filtering performance based on reinforcement learning is superior to other methods.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.19 no.4
• /
• pp.519-524
• /
• 2009

Recently, reinforcement learning methods have drawn much interests in the area of machine learning. Dominant approaches in researches for the reinforcement learning include the value-function approach, the policy search approach, and the actor-critic approach, among which pertinent to this paper are algorithms studied for problems with continuous states and continuous actions along the line of the actor-critic strategy. In particular, this paper focuses on presenting a method combining the so-called ACFRL(actor-critic fuzzy reinforcement learning), which is an actor-critic type reinforcement learning based on fuzzy theory, together with the RLS-NAC which is based on the RLS filters and natural actor-critic methods. The presented method is applied to a control problem for crawling robots, and some results are reported from comparison of learning performance.

• Tunnel and Underground Space
• /
• v.25 no.3
• /
• pp.275-283
• /
• 2015

Excavation of underground space in soft ground implicate to the structure, such as subsidence. As a result, it has been acting as a serious risk to the stability of the roads and facilities. Therefore, in order to stabilize the soil stabilization and reinforcement of the structure, we have been using a number of methods and injecting material. In this study, we compared and analyzed the amount of subsidence regarding the ground reinforcement during underground excavation in soft ground by performing model test. And three-dimensional numerical analysis was performed using FLAC 3D. The subsidence was simulated numerically according to the tunnel excavation. The subsidence results of the model tests and numerical analyzes were relatively consistent. Thus comparing the ground subsidence by varying the reinforcement area on the numerical analysis was analyzed. As a results, three-dimensional numerical simulation could be regarded to simulate better on the ground subsidence by various kinds of underground excavation and it can be used as a material of subsidence prevention methods.

• KIPS Transactions on Software and Data Engineering
• /
• v.10 no.7
• /
• pp.263-270
• /
• 2021

Reinforcement learning(RL) is the method to find an optimal policy through training. and it is one of popular methods for solving lifesaving and disaster response problems effectively. However, the conventional reinforcement learning method for disaster response utilizes either simple environment such as. grid and graph or a self-developed environment that are hard to verify the practical effectiveness. In this paper, we propose the design of a disaster response RL environment which utilizes the detailed property information of the disaster simulation in order to utilize the reinforcement learning method in the real world. For the RL environment, we design and build the reinforcement learning communication as well as the interface between the RL agent and the disaster simulation. Also, we apply the dimension reduction method for converting non-image feature vectors into image format which is effectively utilized with convolution layer to utilize the high-dimensional and detailed property of the disaster simulation. To verify the effectiveness of our proposed method, we conducted empirical evaluations and it shows that our proposed method outperformed conventional methods in the building fire damage.

• Journal of Acupuncture Research
• /
• v.24 no.1
• /
• pp.111-125
• /
• 2007

Objection : The aim of this study was to investigate anti-ischemic effect of LR1 ${\cdot}$ HT8 ${\cdot}$ HT9 Reinforcement in Acupuncture. Methods : I designed to investigate whether LR1 ${\cdot}$ HT8 ${\cdot}$ HT9 Reinforcement in Acupuncture affects cerebral hemodynamics [regional cerebral blood flow(rCBF), pial arterial diameter(PAD), mean arterial blood pressure (MABP) ] in normal and cerebral ischemia rats by MCA occlusion method, and to make manifest whether LR1 ${\cdot}$ HT8 ${\cdot}$ HT9 Reinforcement in Acupuncture is mediated by cyclooxygenase or guanylate cyclase. The changes of rCBF and MABP were determinated by laser-doppler flowmetry(LDF), and the change of PAD was determinated by video microscope and width analyzer. Results: The results were as follows ; 1. LR1 ${\cdot}$ HT8 ${\cdot}$ HT9 Reinforcement in Acupuncture was significantly increased rCBF, PAD, but decreased MABP after withdrawing of the needle. This results suggest that LR1 ${\cdot}$ HT8 ${\cdot}$ HT9 Reinforcement in Acupuncture induced significantly rCBF by dilating PAD. 2. Pretreatment with indomethacin (1mg/kg, i.v.) was significantly inhibited LR1 ${\cdot}$ HT8 ${\cdot}$ HT9 Reinforcement in Acupuncture induced increase of rCBF and PAD, but increased LR1 ${\cdot}$ HT8 ${\cdot}$ HT9 Reinforcement in Acupuncture induced decrease of MABP after withdrawing of the needle. 3. Pretreatment with methylene blue(10/${\mu}$g/kg, i.v.) was decreased LR1 ${\cdot}$ HT8 ${\cdot}$ HT9 Reinforcement in Acupuncture induced increase of rCBF and MABP, but accelerated LR1 ${\cdot}$ HT8 ${\cdot}$ HT9 Reinforcement in Acupuncture induced decrease of PAD. This results suggest that the mechanism of LR1 ${\cdot}$ HT8 ${\cdot}$ HT9 Reinforcement in Acupuncture is mediated by cyclooxygenase or guanylate cyclase. Conclusion : I suggest that LR1 ${\cdot}$ HT8 ${\cdot}$ HT9 Reinforcement in Acupuncture has an anti-ischemic effect through the improvement of cerebral hemodynamics, and the mechanism IS mediated by cyclooxygenase.

• Journal of Korean Tunnelling and Underground Space Association
• /
• v.20 no.5
• /
• pp.823-837
• /
• 2018

Congestion of the city with the rapid industrial development was accelerated to build complex social infrastructure. And numerous structures have been designed and constructed in accordance with these requirements. Recently, to solve complex urban traffic, many researches of large-diameter tunnel under construction downtown are in progress. The large-diameter tunnel has been developed with a versatile double-deck of deep depth tunnel. For the safe tunnel construction, ground reinforcement methods have been developed in the weakened pillar section like as junction of tunnel. This paper focuses on evaluation of the effects of new developed ground reinforcement methods in double-deck junction. The values of reinforcement determined from the existing and developed methods were compared to each other by numerical simulation.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.13 no.6
• /
• pp.635-642
• /
• 2003

Reinforcement learning got successful results in a lot of applications such as control and scheduling. Various function approximation methods have been studied in order to improve the learning speed and to solve the shortage of storage in the standard reinforcement learning algorithm of Q-Learning. Most function approximation methods remove some special quality of reinforcement learning and need prior knowledge and preprocessing. Fuzzy Q-Learning needs preprocessing to define fuzzy variables and Local Weighted Regression uses training examples. In this paper, we propose a function approximation method, Fuzzy Q-Map that is based on on-line fuzzy clustering. Fuzzy Q-Map classifies a query state and predicts a suitable action according to the membership degree. We applied the Fuzzy Q-Map, CMAC and LWR to the mountain car problem. Fuzzy Q-Map reached the optimal prediction rate faster than CMAC and the lower prediction rate was seen than LWR that uses training example.

• Women's Health Nursing
• /
• v.27 no.3
• /
• pp.230-242
• /
• 2021

Purpose: The purpose of this study was to develop a maternal nursing competency reinforcement program for nursing students and assess the program's effectiveness in Korea. Methods: The maternal nursing competency reinforcement program was developed following the ADDIE model. This study employed an explanatory sequential mixed methods design that applied a non-blinded, randomized controlled trial with nursing students (28 experimental, 33 control) followed by open-ended interviews with a subset (n=7). Data were analyzed by both qualitative and quantitative analysis methods. Results: Repeated measures analysis of variance showed that significant differences according to group and time in maternal nursing performance; assessment of and intervention in postpartum uterine involution and vaginal discharge (F=24.04, p<.001), assessment of and intervention in amniotic membrane rupture (F=36.39, p<.001), assessment of and intervention in delivery process through vaginal examination (F=32.42, p<.001), and nursing care of patients undergoing induced labor (F=48.03, p<.001). Group and time improvements were also noted for problem-solving ability (F=9.73, p<.001) and emotional intelligence (F=4.32, p=.016). There were significant differences between groups in self-directed learning ability (F=13.09, p=.001), but not over time. The three main categories derived from content analysis include "learning with a colleague by simulation promotes self-reflection and learning," "improvement in maternal nursing knowledge and performance by learning various countermeasures," and "learning of emotionally supportive care, but being insufficient." Conclusion: The maternal nursing competency reinforcement program can be effectively utilized to improve maternal nursing performance, problem-solving ability, and emotional intelligence for nursing students.

• Proceedings of the Korean Geotechical Society Conference
• /
• 2007.09a
• /
• pp.514-527
• /
• 2007

Earth reinforcement techniques are used worldwide and offer proven solutions to a wide range of geotechnical engineering problems. Here in this paper, recent developments of three major reinforced soil retaining wall methods in Japan were introduced in order to show how the current situation of this technique in Japan is. And the statistical data for the volume of the use was also shown, such as the total volume of the use, the scales of the structures, layout of the earth reinforcement, fill materials, and foundation conditions. Some of the case histories were also introduced with photographs and figures. And then, as one of recent research activity by the author, the study on the application of X-ray CT for the problem of earth reinforcement method combined with other method such as piling and soil improvement was introduced. In this study, a series of model test for several reinforced ground with geogrids was conducted using a newly developed test apparatus. Then, the behavior in the soil box was scanned after settlement using X-ray CT scanner. Based on these test results, the reinforcing effect by the geogrids and the soil arching effect over the pile heads was discussed precisely and those are done in 3-D with nondestructive condition. Finally, the effectiveness of the use of X-ray CT scanner in geotechnical engineering was promised.

• Journal of the Korean Society of Industry Convergence
• /
• v.12 no.2
• /
• pp.107-112
• /
• 2009

The effective reinforcement methods of structure is required to improve the durability of existing structures. Recently, the continuous fiber sheets to the concrete structures are widely used in the earthquake-proof reinforcement method. This study examines suitability and effect to concrete structure of fiber by FEM analysis. The result of analysis is as follows; All specimens occurred bending tensile failure at the middle span. Ultimate strength of specimen in the RC and reinforced RC specimen were 53.9 kN, 56.3 kN respectively and it was some low by degree 0.89, 0.82 to compare with calculated result. The deflection of specimen at the middle span occurred in approximately 0.2 mm, and did linear behavior in load 20 kN by seat reinforcement. Stiffness did not decrease by occurrence in the finer crack and reinforcement beam's flexure stiffness was increased until reach in failure. To compare calculated value and analysis value, it almost equal behavior in the elastic reign and can confirm effectiveness of analysis. Crack was distributed uniformly by reinforcement of fiber seat at failure and it do not occurred stiffness decreases.