• KIPS Transactions on Software and Data Engineering
• /
• v.11 no.3
• /
• pp.141-148
• /
• 2022

Recently, reinforcement learning combined with deep neural network technology has achieved remarkable success in various fields such as board games such as Go and chess, computer games such as Atari and StartCraft, and robot object manipulation tasks. However, such deep reinforcement learning describes states, actions, and policies in vector representation. Therefore, the existing deep reinforcement learning has some limitations in generality and interpretability of the learned policy, and it is difficult to effectively incorporate domain knowledge into policy learning. On the other hand, dNL-RRL, a new relational reinforcement learning framework proposed to solve these problems, uses a kind of vector representation for sensor input data and lower-level motion control as in the existing deep reinforcement learning. However, for states, actions, and learned policies, It uses a relational representation with logic predicates and rules. In this paper, we present dNL-RRL-based policy learning for transportation mobile robots in a manufacturing environment. In particular, this study proposes a effective method to utilize the prior domain knowledge of human experts to improve the efficiency of relational reinforcement learning. Through various experiments, we demonstrate the performance improvement of the relational reinforcement learning by using domain knowledge as proposed in this paper.

• Journal of the Institute of Electronics and Information Engineers
• /
• v.51 no.7
• /
• pp.239-247
• /
• 2014

The CTSIB (Clinical Test of Sensory Integration on Balance) using high sensitive pressure sensors is normally used to assess the sense of balance in hospital. It takes an objective measurement of the amount of sway that occurs in the body trunk by observing the change in the center of pressure (CoP) on the foot at the upright posture. In this paper, we would like to propose method to easily measure trunk sway in home. Although the Wii balance board(WBB) is used for games, it can measures the center of pressure, which is highly correlated. The Wii remote controller(WRC) is inexpensive compared to the WBB, but it has problems with estimation of trunk sway because it can't measure pressure directly like WBB. We collected data from 10 normal subjects (5 males, 5 females) from two devices in order to compare the CoP from WBB and the center of mass (CoM) from WRC. The results of WRC and WBB was similar when the data were analyzed by the convex hull and ellipse area.

• Journal of Korean Society of Neurocognitive Rehabilitation
• /
• v.10 no.2
• /
• pp.35-44
• /
• 2018

This study was conducted to explore the effects of semi-structured $DIRFloortime^{(R)}$ treatment on the enhancement of language comprehension and information processing of children with high-performance autistic spectrum disabilities. We measured the general characteristics of the test subjects, which are level of autism, total intelligence, language comprehension and information processing indicators. The intervention method used was a semi-structured $DIRFloortime^{(R)}$ therapy using board game intervention program after revising and supplementing the expert content validity. A pre/post-test for a group was designed as a similar experiment and the pre/post test was initiated with the t certification at .05 of significance level. After initiating the program, the post test has shown that the language comprehension indicators showed statistically significant levels of difference (p<.001) and the information processing indicator also had a statistically significant effect (p<.001). There was a statistically significant difference (p<.001) in the level of verbal comprehension index after the program implementation, and statistically significant differences in the information processing index (p<.001). The semi-structured $DIRFloortime^{(R)}$ treatment using boardgames for enhancing the language comprehension and information processing indicators of children with high performance autistic spectrum disorder had a significant effect.

• The Journal of the Convergence on Culture Technology
• /
• v.10 no.2
• /
• pp.127-131
• /
• 2024

SW education was conducted for slow youth learners. 6 learners participatd in 8 sessions of an introductory course using several plays and 3 learners who more interested in introductory course participated in deeper course using normal method. After education, we survey and interview from learners, instructors and heads of welfare organizations. Learners showed interest and participated in the fact that they were participating in SW education, which was widely talked about. Learners were found to be more satisfied with introductory course education using play such as board games, and although they initially appeared to participate in unfamiliar learning content with low efficacy, it was observed that their efficacy increased with repetition. Additionally, it was observed that young people with an IQ of 80 or higher had a higher level of interest or interest in SW education than those with an IQ of 80 or lower. we discussed that there were not many opportunities to directly use the SW education content for youth who are slow learners in work or real life. We suggest this should be a focus education on the use of digital media - online meeting apps, office SW etc.- to improve digital literacy for life and work and that research on this should continue.

• The Korean Journal of Community Living Science
• /
• v.18 no.1
• /
• pp.3-20
• /
• 2007

The purpose of this study was diagnosed to grasp the needs for the elderly-elderly care activity in rural areas. The research was conducted in questions and case studies in 7 farming villages. The major findings of this study as follows: First, the senior citizens in rural areas were not in good health, and the illnesses were revealed to be arthritis, high blood pressure, and diabetes. At the occurrence of an illness, they complained about the discomfort in doing daily life routines and expected eir spouses or offsprings to te care of them. Elders in the rural community responded that they had difficulty and financial problems in family maintenance. Leisure activities included watching TV, playing card/board games, or spending time without any specific activities. Second, recipients of elderly-elderly care expected to receive services from a woman in her 50s $1{\sim}2$ hours, once to twice a week. Third, the service providers wanted to be elderly-elderly care takers, hoping to work once a week for $2{\sim}3$ hours. They wanted the education for the elderly-elderly care to be once a week for 3 hours, with understanding the elderly, consultation, preventing senile dementia, and health as the contents.

• Journal of the Korean Society of Physical Medicine
• /
• v.11 no.1
• /
• pp.61-69
• /
• 2016

PURPOSE: This study was conducted to investigate the effect of the virtual reality training (VRT) using 3-dimensional video gaming technology on spatiotemporal gait parameters in older adults. METHODS: The study participants were divided into two groups: the VRT group and the control group. Those in the VRT group were enrolled in a VRT, which was conducted for 60 min per day, two times a week, during the 6-week research. The Wii-Fit balance board game was used for the VRT intervention. The VRT consisted of 6 different types of games, namely, jogging, swordplay, ski jump, hula hoop, tennis, and step dance. A 3-dimensional TV was used for 3-dimensional display. Participants in both the groups received 3 sessions of fall prevention education, at the first, third, and fifth weeks. Their gait parameters were measured by using OptoGait. RESULTS: After 6 weeks of the VRT, the spatial gait parameters of the participants, that is stride length and step length, were significantly improved compared with those of the control group participants (p<0.05). The temporal gait parameters, such as velocity, cadence, stride time, and step time, also showed improvement after the completion of the VRT training (p<0.05). Both the temporal and spatial gait parameters of the VRT group participants showed improvement after 6 weeks of the program compared with those of the control group participants (p<0.05). CONCLUSION: The VRT using 3-dimensional video gaming technology might be beneficial for improving gait parameters to prevent falls among older adults.

• Journal of Korea Game Society
• /
• v.14 no.3
• /
• pp.47-54
• /
• 2014

The game of Go is one of the oldest games and originated at least more than 2,500 years ago. In game programming the most successful approach is to use game tree searches using evaluation functions. However it is really difficult to construct feasible evaluation function in computer Go. Monte-Carlo Tree Search(MCTS) has created strong computer Go programs such as MoGo and CrazyStone which defeated human Go professionals played on the $9{\times}9$ board. MCTS is based on the winning rate estimated by Monte-Carlo simulation. Prior to implementing MCTS into computer Go, we tried to measure each winning rate of three positions, center, corner and side, in Tic-Tac-Toe playing as the best first move. The experimental result revealed that the center is the best, a corner the next and a side the last as the best first move.

• Journal of Korea Game Society
• /
• v.6 no.3
• /
• pp.13-22
• /
• 2006

Games such as sports, RTS, RPG, which teams of players play, require advanced artificial intelligence technology for team management. The existing artificial intelligence enables an intelligent agent to have the autonomy solving problem by itself, but to lack interaction and cooperation between agents. This paper presents "Level Unified Approach Method" with effective role allocation and autonomy in multiagent system. This method allots sub-goals to agents using role information to accomplish a global goal. Each agent makes a decision and takes actions by itself in dynamic environments. Global goal of Team coordinates to allocated role in tactics approach. Each agent leads interactive cooperation by sharing state information with another using Databoard, As each agent has planning capacity, an agent takes appropriate actions for playing allocated roles in dynamic environments. This cooperation and interactive operation between agents causes a collision problem, so it approaches at tactics side for controlling this problem. Our experimental result shows that "Level Unified Approach Method" has better performance than existing rental approach method or de-centralized approach method.

• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.12 no.6
• /
• pp.105-109
• /
• 2012

This paper proposed a method which enabled the designing and implementation of a serious game based on AVR microcontroller on a virtual serial port before making the actual circuit by performing simulation, and which made it possible to develop a serious game. The implemented serious game implemented a mole game which can be enjoyed by one person, a love game with which a male gamer and a female gamer can play, and a marathon game in which a gamer can run the marathon while listening to cheerful music and looking at a region he/she wants to visit. The development of a microcontroller device that provides those functions showed that not only does the device make it possible to develop games more easily and conveniently through the implementation of a game using virtual serial communications with a board designed by an ISIS simulator, but also it reduces trials and errors during game development.

• Journal of Korea Game Society
• /
• v.13 no.4
• /
• pp.15-24
• /
• 2013

The game of Go, which is originated at least more than 2,500 years ago, is one of the oldest board games in the world. So far the theoretical studies concerning to the Go openings are still insufficient. We applied traditional LDA algorithm to recognize a pro player's opening to a class obtained from the training openings. Both class-independent LDA and class-dependent LDA methods are conducted with the Go game records of the Korean top 10 professional Go players. Experimental result shows that the average recognition rate of class-independent LDA is 14% and class-dependent LDA 12%, respectively. Our research result also shows that in contrary to our common sense the algorithm based on PCA outperforms the algorithm based on LDA and reveals the new fact that the Euclidean distance metric method rarely does not inferior to LDA.