• IEMEK Journal of Embedded Systems and Applications
• /
• v.19 no.2
• /
• pp.107-114
• /
• 2024

Mobile ad hoc networks represent self-configuring networks of mobile devices that communicate without relying on a fixed infrastructure. However, traditional routing protocols in such networks encounter challenges in selecting efficient and reliable routes due to dynamic nature of these networks caused by unpredictable mobility of nodes. This often results in a failure to meet the low-delay and low-energy consumption requirements crucial for such networks. In order to overcome such challenges, our paper introduces a novel multi-objective and adaptive routing scheme based on the Q-learning reinforcement learning algorithm. The proposed routing scheme dynamically adjusts itself based on measured network states, such as traffic congestion and mobility. The proposed approach utilizes Q-learning to select routes in a decentralized manner, considering factors like energy consumption, load balancing, and the selection of stable links. We present a formulation of the multi-objective optimization problem and discuss adaptive adjustments of the Q-learning parameters to handle the dynamic nature of the network. To speed up the learning process, our scheme incorporates informative shaped rewards, providing additional guidance to the learning agents for better solutions. Implemented on the widely-used AODV routing protocol, our proposed approaches demonstrate better performance in terms of energy efficiency and improved message delivery delay, even in highly dynamic network environments, when compared to the traditional AODV. These findings show the potential of leveraging reinforcement learning for efficient routing in ad hoc networks, making the way for future advancements in the field of mobile ad hoc networking.

• Journal of Information Technology Applications and Management
• /
• v.30 no.1
• /
• pp.97-114
• /
• 2023

The purpose of this study is to derive practical implications by verifying the influence of MSME owners' leadership type and management performance on knowledge management. In addition, we tried to verify the mediating role of knowledge management between the leadership type and management performance of MSME owners. Leadership types were divided into transformational leadership and transactional leadership. Transformational leadership consisted of charisma and inspirational motivation, while transactional leadership consisted of situational rewards and management by exception. For data collection, we conducted a survey targeting workers in small businesses. After excluding insincere data that were inappropriate for analysis, we used the remaining 243 samples for empirical analysis. To test the hypothesis, we adopted regression analysis and three-step mediated regression analysis as analysis methods. As a result of the empirical analysis, all seven hypotheses derived were supported, and the main results are summarized as follows. First, we found that MSME owners' transformational leadership and transactional leadership had a positive effect on knowledge management and management performance. Second, we found that knowledge management of MSME owners had a positive effect on business performance. Third, both transformational leadership and transactional leadership of MSME owners were found to be partially mediated by knowledge management in relation to management performance. Based on these research results, we derived practical implications for MSME owners.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.7 no.5
• /
• pp.1036-1057
• /
• 2013

Wireless body area network (WBAN) is a promising candidate for future health monitoring system. Nevertheless, the path to mature solutions is still facing a lot of challenges that need to be overcome. Energy efficient scheduling is one of these challenges given the scarcity of available energy of biosensors and the lack of portability. Therefore, researchers from academia, industry and health sectors are working together to realize practical solutions for these challenges. The main difficulty in WBAN is the uncertainty in the state of the monitored system. Intelligent learning approaches such as a Markov Decision Process (MDP) were proposed to tackle this issue. A Markov Decision Process (MDP) is a form of Markov Chain in which the transition matrix depends on the action taken by the decision maker (agent) at each time step. The agent receives a reward, which depends on the action and the state. The goal is to find a function, called a policy, which specifies which action to take in each state, so as to maximize some utility functions (e.g., the mean or expected discounted sum) of the sequence of rewards. A partially Observable Markov Decision Processes (POMDP) is a generalization of Markov decision processes that allows for the incomplete information regarding the state of the system. In this case, the state is not visible to the agent. This has many applications in operations research and artificial intelligence. Due to incomplete knowledge of the system, this uncertainty makes formulating and solving POMDP models mathematically complex and computationally expensive. Limited progress has been made in terms of applying POMPD to real applications. In this paper, we surveyed the existing methods and algorithms for solving POMDP in the general domain and in particular in Wireless body area network (WBAN). In addition, the papers discussed recent real implementation of POMDP on practical problems of WBAN. We believe that this work will provide valuable insights for the newcomers who would like to pursue related research in the domain of WBAN.

• Proceedings of the Korea Inteligent Information System Society Conference
• /
• 2001.01a
• /
• pp.59-64
• /
• 2001

The robot soccer simulation game is a dynamic multi-agent environment. In this paper we suggest a new reinforcement learning approach to each agent's dynamic positioning in such dynamic environment. Reinforcement learning is the machine learning in which an agent learns from indirect, delayed reward an optimal policy to chose sequences of actions that produce the greatest cumulative reward. Therefore the reinforcement learning is different from supervised learning in the sense that there is no presentation of input pairs as training examples. Furthermore, model-free reinforcement learning algorithms like Q-learning do not require defining or learning any models of the surrounding environment. Nevertheless it can learn the optimal policy if the agent can visit every state- action pair infinitely. However, the biggest problem of monolithic reinforcement learning is that its straightforward applications do not successfully scale up to more complex environments due to the intractable large space of states. In order to address this problem. we suggest Adaptive Mediation-based Modular Q-Learning (AMMQL)as an improvement of the existing Modular Q-Learning (MQL). While simple modular Q-learning combines the results from each learning module in a fixed way, AMMQL combines them in a more flexible way by assigning different weight to each module according to its contribution to rewards. Therefore in addition to resolving the problem of large state effectively, AMMQL can show higher adaptability to environmental changes than pure MQL. This paper introduces the concept of AMMQL and presents details of its application into dynamic positioning of robot soccer agents.

• Proceedings of the Korea Society for Simulation Conference
• /
• 2001.10a
• /
• pp.321-324
• /
• 2001

The robot soccer simulation game is a dynamic multi-agent environment. In this paper we suggest a new reinforcement learning approach to each agent's dynamic positioning in such dynamic environment. Reinforcement Beaming is the machine learning in which an agent learns from indirect, delayed reward an optimal policy to choose sequences of actions that produce the greatest cumulative reward. Therefore the reinforcement loaming is different from supervised teaming in the sense that there is no presentation of input-output pairs as training examples. Furthermore, model-free reinforcement loaming algorithms like Q-learning do not require defining or loaming any models of the surrounding environment. Nevertheless it can learn the optimal policy if the agent can visit every state-action pair infinitely. However, the biggest problem of monolithic reinforcement learning is that its straightforward applications do not successfully scale up to more complex environments due to the intractable large space of states. In order to address this problem, we suggest Adaptive Mediation-based Modular Q-Learning(AMMQL) as an improvement of the existing Modular Q-Learning(MQL). While simple modular Q-learning combines the results from each learning module in a fixed way, AMMQL combines them in a more flexible way by assigning different weight to each module according to its contribution to rewards. Therefore in addition to resolving the problem of large state space effectively, AMMQL can show higher adaptability to environmental changes than pure MQL. This paper introduces the concept of AMMQL and presents details of its application into dynamic positioning of robot soccer agents.

• Journal of Convergence for Information Technology
• /
• v.10 no.2
• /
• pp.21-31
• /
• 2020

This study tested the effectiveness of commercialized smartphone apps in improving walking activities among college students. 66 participants were randomized into each of four groups that was used different behavior change strategies: monetary rewards app, goal setting and feedback app, gaming app, and self-monitoring control group. 45 participants who completed the experimentation was included in data analysis. Repeated measures ANOVA resulted in statistically significant time by groups interactions in recorded step counts, self-reported completed plans and self-reported walking activities scores. The Goal-setting and feedback group and the gaming group resulted in increase in both step counts and completed plans. The results were discussed in the framework of behaviorism.

• Journal of the Korean Home Economics Association
• /
• v.31 no.1
• /
• pp.137-151
• /
• 1993

This study presents an appraisal of current theorizing process through the review of family studies. Also it shows the outlines of five sociological general theories and how to apply them to family studies. The field of family studies entered a new stage in the middle of the twentieth century. Especially the decade of the 1970s was a period of rapid development in family theories because middle-range theories were developed. Currently identified major conceptual frameworks of family studies are five sociological general theories. Exchange theory was utilized in several studies and the problems could have been conceptualized in a way that would have tested the general theory of rewards, costs, and profits, but in most instances the theory was developed at a limited substantive level. Symbolic interactionism is the most useful in understanding precarious human relationships, such as courtship processes, intergenerational relationships family roles, and powers. General systems theory have been provided generalizaitons useful for understanding the characteristics of the family systems and also useful in describing the interactions with the environment, and the functioning of a family along a continuum of open to closed. Conflict theorists point that the basic units of society comprise all persons who share a sense of status equality and there are continual struggles in society for various goods. This theory attemps to account for the development within the family of norms of equity, or fairness. Phenomenology becomes available when we cease to treat an object as real, and begin to treat the object as meant, as intended, as it appears. Therefore the formulation of an adequate and complete description of family is important. Family theorists must be urged to do a number of things including continuing to improve existing theory and continuing to develop metatheory and methodologies of building theory.

• Information Systems Review
• /
• v.7 no.2
• /
• pp.41-59
• /
• 2005

Mobile games have emerged as the most innovative entertainment technology adding new revenue streams, taking advantage of the potential of wireless consumer applications and service offerings. Mobile games, like any other types of computer game, offer a unique value for users in providing an exciting digital experience in virtual worlds. Players can become empowered through the development of new characters and strategies within games to achieve rewarding successes against the computers and other players. In this paper, we attempt to investigate the factors influencing the usage and acceptance of the mobile games in Korea, based on the extended version of the Technology Acceptance Model(TAM). Based on data collected from survey, we show that perceived usefulness is the major determinant for users to play mobile games. Two factors, including perceived enjoyment and self-expressiveness, are empirically shown to determine perceived usefulness. In addition, perceived ease of use, rewards, operational quality of device, and design/story have been showed to significantly and directly affect perceived enjoyment. It was also confirmed that self-efficacy and operational quality of device are the antecedents of perceived ease of use. Based upon the statistical results, some useful guidelines for game development and market penetration strategies are also provided.

• The KIPS Transactions:PartB
• /
• v.9B no.2
• /
• pp.139-146
• /
• 2002

The robot soccer simulation game is a dynamic multi-agent environment. In this paper we suggest a new reinforcement learning approach to each agent's dynamic positioning in such dynamic environment. Reinforcement learning is the machine learning in which an agent learns from indirect, delayed reward an optimal policy to choose sequences of actions that produce the greatest cumulative reward. Therefore the reinforcement learning is different from supervised learning in the sense that there is no presentation of input-output pairs as training examples. Furthermore, model-free reinforcement learning algorithms like Q-learning do not require defining or learning any models of the surrounding environment. Nevertheless these algorithms can learn the optimal policy if the agent can visit every state-action pair infinitely. However, the biggest problem of monolithic reinforcement learning is that its straightforward applications do not successfully scale up to more complex environments due to the intractable large space of states. In order to address this problem, we suggest Adaptive Mediation-based Modular Q-Learning (AMMQL) as an improvement of the existing Modular Q-Learning (MQL). While simple modular Q-learning combines the results from each learning module in a fixed way, AMMQL combines them in a more flexible way by assigning different weight to each module according to its contribution to rewards. Therefore in addition to resolving the problem of large state space effectively, AMMQL can show higher adaptability to environmental changes than pure MQL. In this paper we use the AMMQL algorithn as a learning method for dynamic positioning of the robot soccer agent, and implement a robot soccer agent system called Cogitoniks.