• Journal of KIISE:Information Networking
• /
• v.33 no.1
• /
• pp.103-112
• /
• 2006

Priority-based network service has been widely adopted for the Internet traffic management in the context of IETF differentiated services, and computing optimal prices for such priority-based service is the key topic in many pricing literature. While the equilibrium analysis has been commonly used to this end, many have criticized the validity of the underlying assumption of equilibrium analysis that user utility functions are precisely known. In this paper, we propose a solution for bridging the gap between the existing theoretical work on optimal pricing and the unavailability of precise user utility information in real networks. In the proposed method, the service provider obtains more and more accurate estimates of user utility functions from the initial imprecise knowledge by iteratively changing the price of service levels and observing the users' decisions under the changed price. Our contribution is two-fold. First, we have developed a general principle for estimating the user utility functions. Second, we have developed a novel method for setting the prices that can optimize the extraction of the knowledge about user utility functions. The extensive simulation results demonstrate the effectiveness of our method.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.41 no.12
• /
• pp.1914-1924
• /
• 2016

In this paper, considering virtualized Evolved Packet Core(vEPC) network for 5G mobile network, we propose architecture for supporting Service Function Chaining(SFC) in 5G mobile network. Using SFC in 5G network, dynamic path configuration and providing network services based on subscriber and traffic information. SFC technology provides logical ordered set of network functions and delivers packet through providing logical path over the physical network. Based on the perspective of 5G core network in distributed manner, we design hierarchical SFC architecture to manage SFC for global path including vEPC and SGi-LAN network, and internal path between virtualized network functions in each cloud. In this paper, we define architecture and call flow for establishing data path using SFC. Finally, we design testbed architecture for real implementation based on open source software.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.16 no.12
• /
• pp.2628-2634
• /
• 2012

The GHG(green house gas) monitoring has been an essential method to prevent climate change. Service scenarios for GHG monitoring over NGN(next generation network), a global infrastructure, was proposed in the previous study, which stays at the abstract level that may lead to difficulties for the actual implementation of the monitoring service in NGN. This paper proposes GHG monitoring service scenarios, based on functions to be incorporated in NGN, that provides the basis for actual implementation in NGN.

• Journal of Information Processing Systems
• /
• v.16 no.5
• /
• pp.1074-1082
• /
• 2020

Recently, research has been actively conducted to create artificial intelligence agents that learn games through reinforcement learning. There are several factors that determine performance when the agent learns a game, but using any of the activation functions is also an important factor. This paper compares and evaluates which activation function gets the best results if the agent learns the game through reinforcement learning in the 2D racing game environment. We built the agent using a reinforcement learning algorithm and a neural network. We evaluated the activation functions in the network by switching them together. We measured the reward, the output of the advantage function, and the output of the loss function while training and testing. As a result of performance evaluation, we found out the best activation function for the agent to learn the game. The difference between the best and the worst was 35.4%.

• Journal of Internet Computing and Services
• /
• v.23 no.2
• /
• pp.9-17
• /
• 2022

In this paper, we propose a secure smart home network model and a novel cryptographic protocol called the Smart Home Security Protocol (SHSP). Authentication, key distribution, and encryption functions are properly supported in order to make a smart home secure, and a residential gateway (RG) plays a central role in performing these functions. According to the characteristics of networks and attached devices, we classify smart homes into three different types of sub-networks and these networks are interconnected with one another by the RG. Depending on a sub-network, we use different types of secure schemes to reduce the burden of the process and the delay in devices while it provides proper security functions. The proposed secure smart home model is implemented and verified by using a variety of embedded system environments.

• Journal of Institute of Control, Robotics and Systems
• /
• v.5 no.3
• /
• pp.281-287
• /
• 1999

In this paper, a design method based on evolutionary programming for feedforward neural networks which have a single hidden layer is presented. By using an evolutionary programming, the network parameters such as the network structure, weight, slope of sigmoid functions and bias of nodes can be acquired simultaneously. To check the effectiveness of the suggested method, two numerical examples are examined. The performance of the identified network is demonstrated.

• Journal of the Korean Operations Research and Management Science Society
• /
• v.18 no.1
• /
• pp.29-43
• /
• 1993

This paper condisers a problem of determining arc capacities for a communication network with fixed-charged linear arc-cost functions, which is known to be NP-hard. For the problem, an efficient heuristic solution procedure is derived. The procedure is further shown working well for designing arc capacities of a network in a situation where the network needs to be extended by connecting its nodes to some new nodes or where the network needs to be extended by expanding its arc capacities.

• 제어로봇시스템학회:학술대회논문집
• /
• 1994.10a
• /
• pp.313-318
• /
• 1994

It is well known that the neural network can be used as an universal approximater for functions and functionals. But these theoretical results are just an existence theorem and do not lead to decide the suitable network structure. This doubfulness whether a certain network can approximate a given function or not, brings about serious stability problems when it is used to identify a system. To overcome the stability problem, We suggest successive identification and control scheme with supervisory controller which always assures the identification process within a basin of attraction of one stable equilibrium point regardless of fittness of the network.

• 제어로봇시스템학회:학술대회논문집
• /
• 1991.10a
• /
• pp.861-865
• /
• 1991

In general, the fusion of neural network and fuzzy logic theory is based on the fact that neural network and fuzzy logic theory have the common properties that 1) the activation function of a neuron is similar to the membership function of fuzzy variable, and 2) the functions of summation and products of neural network are similar to the Max-Min operator of fuzzy logics. In this paper, a fuzzy-neural network will be proposed and a force controller of the robot gripper, utilizing the fuzzy-neural network, will be presented. The effectiveness of the proposed strategy will be demonstrated by computer simulation.

• IEMEK Journal of Embedded Systems and Applications
• /
• v.7 no.5
• /
• pp.227-239
• /
• 2012

Recent advances in electronics have enabled various conventional products to incorporate with numerous powerful microcontroller. Generally, an embedded system is a computer system designed for specific control functions within a larger system, often with real-time computing constraints. The growing performance and reliability of hardware components and the possibilities brought by various design method enabled implementing complex functions that improve the comport of the system's occupant as well as their safety. A cyber physical system (CPS) is a system featuring a tight combination of, and coordination between, the system's computational and physical elements. The concept of cyber physical system, including physical elements, cyber elements, and shared networks, has been introduced due to two general reasons: design flexibility and reliability. This paper presents a cyber physical system where system components are connected to a shared network, and control functions are divided into small tasks that are distributed over a number of embedded controllers with limited computing capacity. In order to demonstrate the effectiveness of cyber physical system, an unmanned forklift with autonomous obstacle avoidance ability is implemented and its performance is experimentally evaluated.