• The Journal of the Korea institute of electronic communication sciences
• /
• v.16 no.6
• /
• pp.1153-1160
• /
• 2021

This paper proposes a routing algorithm that determines the optimal path using deep reinforcement learning in software-defined networks. The deep reinforcement learning model for learning is based on DQN, the inputs are the current network state, source, and destination nodes, and the output returns a list of routes from source to destination. The routing task is defined as a discrete control problem, and the quality of service parameters for routing consider delay, bandwidth, and loss rate. The routing agent classifies the appropriate service class according to the user's quality of service profile, and converts the service class that can be provided for each link from the current network state collected from the SDN. Based on this converted information, it learns to select a route that satisfies the required service level from the source to the destination. The simulation results indicated that if the proposed algorithm proceeds with a certain episode, the correct path is selected and the learning is successfully performed.

• Journal of the Institute of Electronics Engineers of Korea TC
• /
• v.44 no.5
• /
• pp.1-6
• /
• 2007

In wireless mesh networks (WMNs), the end-to-end throughput of a flow decreases drastically according to the traversed number of hops due to interference among different hops of the same flow in addition to interference between hops of different flows with different paths. This paper proposes a distributed multi-channel assignment scheme based on hops (DMASH) to improve the performance of a static WMN. The proposed DMASH is a novel distributed multi-channel assignment scheme based on hops to enhance the end-to-end throughput by reducing interference between channels when transmitting packets in the IEEE 802.11 based multi-interface environments. The DMASH assigns a channel group to each hop, which has no interference between adjacent hops from a gateway in channel assignment phase, then each node selects its channel randomly among the channel group. Since the DMASH is a distributed scheme with unmanaged and auto-configuration of channel assignment, it has a less overhead and implementation complexity in algorithm than centralized multi-channel assignment schemes. Simulation results using the NS-2 showed that the DMASH could improve remarkably the total network throughput in multi-hop environments, comparing with a random channel assignment scheme.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.32 no.3A
• /
• pp.297-309
• /
• 2007

We introduce two distributed IP address auto-configuration mechanisms for mobile ad hoc networks. RADA (Random ADdress Allocation) is based on random IP address selection, while LiA (Linear Address Allocation) assigns new addresses sequentially, using the current maximum IP address. An improved version of LiA, hewn as LiACR (Linear Address Allocation with Collision Resolution) further reduces the control overhead. Simulation results show that, when many nodes join a network during a short period, RADA assigns addresses more quickly than LiA and LiACR. However, RADA uses the address space less efficiently, due to its random allocation of IP addresses. Hence, RADA is particularly useful in battlefield scenarios or rescue operations where fast setup is needed, while LiA and LiACR are more suitable for ad hoc networks that are moderate, confined and subject to some form of governance control, such as that orchestrated by a wireless service provider.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.5 no.4
• /
• pp.723-729
• /
• 2001

We are able to work on the shared virtual space in Web-based Collaborative Design System using only Internet and Web browser. The users connect to the Solid Modeler Server through m and they create 3D shape and manipulate them variously. Then the users will share 3D objects and two problems can arise. The users must be able to pick the objects effectively which they want to manipulate. When one of the users manipulates a particular object, others should not disturb with the same object. In this paper, picking is implemented not only by computing intersection of mouse pointer with the objects of the virtual world, but also by using capabilities and attributes of scene graph node, by setting bounds intersection testing instead of geometric intersection testing, by limiting the scope of the pick testing, using Java 3D. These methods can reduce the computation of picking and can pick 3D objects effectively and easily using the system of hierarchy. To have effective concurrency, we used shared lock and exclusive lock as the action in work space.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.35 no.4B
• /
• pp.566-575
• /
• 2010

In recent, artificial immune system has become an important research direction in the anomaly detection of networks. The conventional artificial immune systems are usually based on the negative selection that is one of the computational models of self/nonself discrimination. A main problem with self and non-self discrimination is the determination of the frontier between self and non-self. It causes false positive and false negative which are wrong detections. Therefore, additional functions are needed in order to detect potential anomaly while identifying abnormal behavior from analogous symptoms. In this paper, we design novel network attack detection and response schemes based on artificial immune system, and evaluate the performance of the proposed schemes. We firstly generate detector set and design detection and response modules through adopting the interaction between dendritic cells and T-cells. With the sequence of buffer occupancy, a set of detectors is generated by negative selection. The detection module detects the network anomaly with a set of detectors and generates alarm signal to the response module. In order to reduce wrong detections, we also utilize the fuzzy number theory that infers the degree of threat. The degree of threat is calculated by monitoring the number of alarm signals and the intensity of alarm occurrence. The response module sends the control signal to attackers to limit the attack traffic.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.11 no.3
• /
• pp.931-942
• /
• 2010

A home network provides users with a variety of information services. The kind and quality of the services can be substantially enhanced by utilizing a variety of data from sensors. However, home networks currently limit their potential by focusing on providing multimedia services rather than services utilizing sensor data. Outdoor electronics are frequently made in a form that emphasizes only certain limited functions in contrast to home appliances. Thus, sensors with one or two functions rather than many can be used in outdoor systems and their use will be more economical than using sensor nodes indoors with more complex home appliances. In this study, we chose to work with motion sensors as they have many potential uses, and we selected a parking lot control system with to use the motion sensors. This parking lot control system was implemented and applied as part of a home network. For this purpose, we defined and implemented a protocol to manage the network in a ubiquitous sensor network environment for the wireless home network in this study. Although a network management system in a Ubiquitous Sensor Network (USN) related to this study is being advanced for other projects, the protocol interface and message system have not yet been clearly defined for use in a general purpose network or in an extension into heterogeneous kinds of networks, communication support, etc. Therefore, USN network management should be conducted for management of faults, composition, power, and applications. To verify the performance of the protocol interface designed in this study, we designed and implemented the necessary units (sensor nodes, sensor gateway, and server) for each network section and, with them, proved the validity of this study.

• Proceedings of the KOR-KST Conference
• /
• 1998.10a
• /
• pp.161-170
• /
• 1998

기존에 건설된 교통시설의 운영효율을 극대화하기 위한 지능형 교통체계의 한 분야인 ATIS는 도로를 이용하는 통행자에게 편리성을 제공하는 동시에 도로를 효율적으로 운영할 수 있는 정보체계이다. ATIS 체계하에서 통행자에게 신뢰성 있는 정보를 제공하기 위해서는 교차로서의 회전에 의한 지체를 정확하게 반영함은 물론이고 실시간으로 변화하는 교통상황을 반영할 수 있는 동적인 최단경로 탐색 알고리즘이 요구된다. 하지만 기존에 발표된 동적인 최단경로 탐색 알고리즘은 회전에 대한 정보를 반영하지 못하며 정적인 최단경로 탐색 알고리즘은 회전에 대한 정보를 반영하지 못하며 정적인 탐색알고리즘 조차 회전에 대한 정보를 정확히 반영하지 못한다. 본 연구에서는 이러한 이유에서 알고리즘 내부에서 회전을 반영하기 위해 수정형 덩굴망 알고리즘의 표지기법을 이용하여 동적인 최단경로 탐색알고리즘을 개발하였다. 본 연구에서 개발한 동적 최단경로 탐색 알고리즘은 정적인 상태의 수정형 덩굴망 알고리즘에 시간에 따라 변화하는 교통상황을 반영하기 위해 시간에 대한 변수를 추가하였다. 이렇게 해서 알고리즘은 시간대별로 변화하는 통행시간을 고려하여 최단 경로를 탐색하게 되며 출발시점을 기준으로 표지를 설정하여 모든 앞선 시간에 대해 경로를 고려하도록 하였다. 매 단계에서 전 노드를 추적하여 회전에 관한 정보를 반영하도록 하였다. 따라서 본 연구에서 개발한 최단경로 탐색 알고리즘은 교차로에서의 회전에 대한 정보와 통행금지 등을 정확히 반영하며 실시간으로 변화하는 통행시간을 반영함으로써 신뢰성 있는 노선 정보를 ATIS를 이용하는 통행자들에게 제공하는데 활용될 수 있는 기법이다.적으로 세부적 차종분류로 접근한다.의 영향들을 고려함으로써 가로망 설계 과정에서 가로망의 상반된 역할인 이동성과 접근성의 비교가 가능한 보다 현실적인 가로망 설계 모형을 구축하고자 한다. 지금까지 소개된 가로망 설계모형들은 용량변화에 대한 설계변수의 형태에 따라 이산적 가로망 설계 모형과 연속적 가로망 설계모형으로 나뉘어지게 된다. 본 논문의 경우, 계산속도의 향상 측면에서는 연속적 가로망 설계 모형을 도입할 수 있지만, 이때 요구되는 도로용량이 이산적인 변수(차선 수)로 결정되어야만 신호제어 변수를 결정할 수 있기 때문에, 이산적 가로망 설계 모형이 사용된다. 하지만, 이산적 설계모형의 경우 조합최적화 문제이므로 정확한 최적해를 구하기 위해서는 상당한 시간이 소요되며, 경우에 따라서는 국부 최적해에 빠지게 된다. 이러한 문제를 극복하기 위해, 우선 이상적 모형의 근사화, 혹은 조합최적화문제를 위해 개발된 Simulated Annealing기법의 적용, 연속적 모형의 변수를 이산화하는 방법 등 다양한 모형들을 고려해 본 뒤, 적절한 모형을 적용할 것이다. 가로망 설계 모형에서 신호제어를 고려하기 위해서는 주어진 가로망에 대한 통행 배정과정에서 고려되는 통행시간을 링크통행시간과 교차로 지체시간을 동시에 고려해야 하는데, 이러한 문제의 해결을 위해서 최근 활발히 논의되고 있는 교차로에서의 신호제어에 대응하는 통행배정 모형을 도입하여 고려하고자 한다. 이를 위해서 지금까지 연구되어온 Global Solution Approach와 Iterative Approach를 비교, 검토한 뒤 모형에 보다 알맞은 방법을 선택한다. 차량의 교차로 통행을 고려하는 perf

• Annual Conference on Human and Language Technology
• /
• 2005.10a
• /
• pp.21-27
• /
• 2005

본 논문에서는 국가에서 추진하는 차세대신성장동력산업과 관련된 특정 분야('바이오 신약/장기' 분야 중 '면역 기능 제어')를 선택하여, 기구축된 면역학 전문용어사전을 비롯하여 의학용어사전, 표준국어대사전 등을 참조하여 핵심 용어와 관련 용어를 중심으로 면역학 시소러스(어휘 3,462개) 및 온톨로지(개념 노드 4,703개)를 구축하였다. 이것은 전문용어사전부터 온톨로지에 이르기까지 통일화된 표준 체계를 가지고 있으며, 도메인 온톨로지를 구축하여 향후 온톨로지 개발 방향을 설정할 수 있는 계기가 되었다고 할 수 있다. 또한 면역학 시소러스는 검색의 성능을 향상시킬 수 있도록 충분한 양의 데이터를 구축하였고 면역학 온톨로지는 언어처리적 관점에서의 온톨로지를 표현하였다. 이는 정보검색에서의 효율성을 비롯하여, 특정 웹 온톨로지 언어를 이용한 웹 온톨로지로의 변환성, 대규모 도메인 온톨로지라는 점에서 의미를 가진다고 할 수 있다.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.13 no.9
• /
• pp.4234-4243
• /
• 2012

USN(Ubiquitous Sensor Network) application S/W has a complex characteristic that it controls various kind of sensor nodes organically based on the core modules of various target operating systems. Currently, various researches for efficient S/W development are being performed in USN application field. In order to increase S/W productivity, the method such as product line development approach to specify core common functions of applications according to the domain and develop applications with the core common functions and variant functions selected according to the workflow of applications is efficient. To apply this approach to the USN domain, characteristics of USN application S/W and product line development should be specified with one consistent view. However, it is difficult to efficiently specify the characteristics using general UML notations. In order to solve the problem, this paper proposes a method to effectively specify the characteristics of USN applications and product line development using UML profile which is the extension mechanism of UML. The proposed UML profile for produce line based USN application development enables developers to effectively develop product line based USN applications using existing UML and UML support tools without new design methods or tools which are specified for USN or product line development.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2013.05a
• /
• pp.845-848
• /
• 2013

Due to intense climate changes and extreme weather conditions a noticeable decrease has been observed in the growth of certain plants. The indoor plant factories would have certain benefits including increase in crop yield, reduction in distribution cost, and maintains the healthy freshness level of the agricultural product. Recently, an artificial light source with optimum wavelength is spot lighted to fulfill the need of light for the indoor plant factories. The energy efficient light emitting diodes (LED) provide the essential light energy for the proper growth of indoor cultivated plants. This work focuses to utilize ubiquitous sensors network(USN) in providing suitable environment for the proper growth of agricultural product inside the indoor plant factory. The proposed system makes use of sensors and actuators, communicating each other through WPAN, ZigBee network. The proposed system obscured the traditional indoor plant factories with easy installation and wireless connectivity of the sensors and actuators along with eliminating the web of wires reducing the initial installation and maintenance cost.