• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제9권6호
• /
• pp.1979-1995
• /
• 2015

Network convergence is regarded as the development tendency of the future wireless networks, for which self-organization paradigms provide a promising solution to alleviate the upgrading capital expenditures (CAPEX) and operating expenditures (OPEX). Self-optimization, as a critical functionality of self-organization, employs a decentralized paradigm to dynamically adapt the varying environmental circumstances while without relying on centralized control or human intervention. In this paper, we present comprehensive surveys of heterogeneous networks (HetNets) and investigate the enhanced self-optimization models. Self-optimization approaches such as dynamic mobile access network selection, spectrum resource allocation and power control for HetNets, etc., are surveyed and compared, with possible methodologies to achieve self-optimization summarized. We hope this survey paper can provide the insight and the roadmap for future research efforts in the self-optimization of convergence networks.

• 한국지능시스템학회:학술대회논문집
• /
• 한국퍼지및지능시스템학회 1995년도 추계학술대회 95 KFIS Workshop Realization of Human Friendly System Based on Soft Computiong Techniques
• /
• pp.124-140
• /
• 1995

The merit of fuzzy rule based systems stems from their capability of encoding qualitative knowledge of experts into quantitative rules. Recent advancement in automatic tuning or self-organization of fuzzy rules from experimental data further enhances their power, allowing the integration of the top-down encoding of knowledge with the bottom-up learning of rules. In this paper, methods of self-organizing fuzzy rules and of performing defuzzification and inference is presented based on a multi-resolution radial basis function network. The network learns an arbitrary input-output mapping from sample distribution as the union of hyper-ellipsoidal clusters of various locations, sizes and shapes. The hyper-ellipsoidal clusters, representing fuzzy rules, are self-organized based of global competition in such a way as to ensute uniform mapping errors. The cooperative interpolation among the multiple clusters associated with a mapping allows the network to perform a bidirectional many-to-many mapping, representing a particular from of defuzzification. Finally, an inference engine is constructed for the network to search for an optimal chain of rules or situation transitions under the constraint of transition feasibilities imposed by the learned mapping. Applications of the proposed network to skill acquisition are shown.

• 한국소음진동공학회:학술대회논문집
• /
• 한국소음진동공학회 2002년도 추계학술대회논문집
• /
• pp.832-835
• /
• 2002

This paper presents a new approach integrated Case-Based Reasoning with Self. Organization Map(SOM) in diagnosis systems. The causes of faults are obtained by case-base trained from SOM. When the vibration problem of rotating machinery occurs, this provides an exact diagnosis method that shows the fault cause of vibration problem. In order to verify the performance of algorithm, we applied it to diagnose the fault cause of the electric motor.

• 한국정밀공학회:학술대회논문집
• /
• 한국정밀공학회 1997년도 춘계학술대회 논문집
• /
• pp.379-383
• /
• 1997

This paper focuses on self-organization of fuzzy rules for performance management of computer communication networks serving manufacturingsystems. The performance managment aims to improve the network performance in handling various types of messages by on-line adjustment of protocol parameters. The principle of fuzzy logic has been used in repressenting the knowledge of human expert on the performance management and in deriving manafement decisions. In this paper, we present an of this self-organization is domonstrated by discrete simulation of an IEEE 802.4 network.

• Journal of Computing Science and Engineering
• /
• 제9권4호
• /
• pp.163-176
• /
• 2015

Self-organization of distributed wireless sensor nodes is a critical issue in wireless sensor networks (WSNs), since each sensor node has limited energy, bandwidth, and scalability. These issues prevent sensor nodes from actively collaborating with the other types of sensor nodes deployed in a typical heterogeneous and somewhat hostile environment. The automated self-organization of a WSN becomes more challenging as the number of sensor nodes increases in the network. In this paper, we propose a dynamic self-organized architecture that combines tree topology with a drawn-grid algorithm to automate the self-organization process for WSNs. In order to make our proposed architecture scalable, we assume that all participating active sensor nodes are unaware of their primary locations. In particular, this paper presents two algorithms called active-tree and drawn-grid. The proposed active-tree algorithm uses a tree topology to assign node IDs and define different roles to each participating sensor node. On the other hand, the drawn-grid algorithm divides the sensor nodes into cells with respect to the radio coverage area and the specific roles assigned by the active-tree algorithm. Thus, both proposed algorithms collaborate with each other to automate the self-organizing process for WSNs. The numerical and simulation results demonstrate that the proposed dynamic architecture performs much better than a static architecture in terms of the self-organization of wireless sensor nodes and energy consumption.

• 한국지능시스템학회논문지
• /
• 제14권5호
• /
• pp.630-634
• /
• 2004

According to the progress of an information-oriented society, more human friendly systems are required. The systems can be implemented by a kind of intelligent algorithms. In this paper we propose the possibility of the implementation of an intelligent algorithm from gene, behavior of human beings, which has some properties such as self organization and self regulation. The regulation of gene behavior is widely analyzed by Boolean network. Also the SORE (Self Organizable and Regulating Engine) is one of those algorithms. This paper does not report detailed research results; rather, it studies the feasibility of gene behavior in biocontrol systems based upon computer simulations.

• 한국정밀공학회:학술대회논문집
• /
• 한국정밀공학회 1995년도 추계학술대회 논문집
• /
• pp.894-897
• /
• 1995

This paper focuses on self-organization of fuzzy rules for performance management of computer communication networks serving manufacturing systems. The performance management aims to improve the network performance in handling various types of messages by on-line adjustment of protocol parameters. The principle of fuzzy logic has been used in representing the knowledge of human expert on the performance management and in deriving management decisions. In this paper, we present applications of genetic algorithm, simulated annealing, and evolution strategies to find a better set of rules for various network conditions. The efficacy of this self-organization is demonstrated by discrete simulation of an IEEE 802.4 network.

• 한국정보처리학회:학술대회논문집
• /
• 한국정보처리학회 2015년도 추계학술발표대회
• /
• pp.406-408
• /
• 2015

최근 사물인터넷 환경은 다양한 서비스 개발로 인해 동일 지역 내에 다양한 서비스 디바이스로 구성된 네트워크가 형성되어 있다. 이런 네트워크 환경은 효율적 서비스 제공을 위해 스스로 서비스를 인지하고 서비스 별 네트워크 구성 기법이 필요하다. 따라서 본 논문에서는 Infra-less IoT 환경에서의 Self-Organization Network (SON) 기반 서비스 지향형 IoT 네트워크 구성 방법을 제안한다. 제안하는 기법은 서비스 제공 시 필요한 네트워크 시그널링을 최소활 할 수 있는 기법으로 활용될 수 있다.

• 한국실내디자인학회논문집
• /
• 제17권3호
• /
• pp.156-164
• /
• 2008

Through staggering advancements of technology and network as we know them as digital revolution, we have established a foundation of space in which we can express reality by eliminating the boundaries between expression, space, and movement. There are many ongoing approaches that aim to overcome the physically-fixed property of space where the mathematical-geometric notion of Voronoi Diagram is one of them. Although the repetitive increment based on self-organization during the process in which space is generated by the Voronoi Diagram forms a pattern and focuses on the formation, its pattern is not restricted to a single method of expression but evolves over self-control. The result of having analyzed spaces generated by the Voronoi Diagram in this study can be summarized as follows. First, the Voronoi computation method with self-organization property creates multiple levels, increments, and evolves through feedbacks among changes with the slightest order and in the absence of control. Secondly, after forming a pattern through such feedbacks comes the differentiation phase due to the presence of different properties. Thirdly, a space that has gone through the generation process retransforms through active interaction between changes and it obtains ambiguous boundaries and a repetitive pattern. This leads to an evolution of space through repetitive increments based on self-organization. Such flexible space creation is supported by various digital technologies where we believe a converging application of these studies, sciences, engineering concepts, and space design is and effective and new method in terms of space creation.

• 정보학연구
• /
• 제7권3호
• /
• pp.11-18
• /
• 2004

신경회로망의 학습은 신경사이의 연결강도 갱신과정으로 이루어진다. 이때, 학습계수를 잘못 설정하였을 경우, 과도한 학습 횟수를 요하거나, 올바른 학습을 수행하지 못하게 된다. 패턴분류에 자주 이용되는 코호넨 신경회로망의 경우 고정된 학습계수를 사용하여 연결강도를 일률적으로 갱신하는 방식을 취함으로서 학습효율을 저하시키는 문제점이 발생한다. 본 논문에서는 코호넨 신경회로망의 학습효율을 향상시키기 위하여 학습계수를 입력벡터와 연결강도 벡터의 차에 따라 가변적으로 적응하는 자율학습 알고리즘을 제안하였다. 제안된 학습 알고리즘의 검증을 위하여 온라인 필기체의 표준 획 분류에 적용하였다. 그 결과 약 1.44~3.65% 정도의 학습 효율이 향상됨을 고찰하였다.