• Proceedings of the IEEK Conference
• /
• 2009.05a
• /
• pp.387-389
• /
• 2009

본 논문에서는 다항식 기반 Radial Basis Function(RBF)신경 회로망을 설계하고 이를 패턴분류 문제에 적용하여 그 성능을 분석한다. 제안된 RBF 신경회로망은 입력층, 은닉층, 출력층으로 이루어진다. 입력층의 연결가중치는 1로서 입력층의 입력벡터는 그대로 은닉층으로 전달되고 은닉층은 FCM(Fuzzy C-means Clustering)방법을 통하여 뉴런의 출력 값으로 내보낸다. 은닉층과 출력층사이의 연결가중치는 상수, 선형식 또는 이차식으로 이루어지며 경사 하강법에 의해 학습되어진다. 네트워크의 최종 출력은 연결가중치와 은닉층 출력의 곱에 의한 퍼지추론의 결과로 얻어진다. 제안된 RBF 신경회로망은 여러 종류의 machine learning 데이터에 적용하여 패턴분류기로서의 성능을 평가받는다.

• Journal of Korea Multimedia Society
• /
• v.18 no.12
• /
• pp.1468-1474
• /
• 2015

Efficient spectrum sharing is an important issue in Device-to-Device (D2D) communications underlaying cellular networks as it can mitigate the interference to cellular users and improve the performance of the systems. In this paper, we formulate the radio resource allocation in D2D communications as a mixed nonlinear integer programing. We show the formulated problem is NP-hard and thus a polynomial time algorithm to solve is not possible. Since such a problem is very hard to obtain the optimal solution within a short running time, we instead propose a fast heuristic suboptimal algorithm to mitigate the interference caused to cellular users and improve the performance of the systems. Simulation results are provided to evaluate the performance of the proposed algorithm.

• Proceedings of the Korea Water Resources Association Conference
• /
• 2011.05a
• /
• pp.473-473
• /
• 2011

Group method of data handling neural networks model (GMDH-NNM) is used to estimate daily reference evapotranspiration (ETo) using limited climatic variables such as max temperature ($T_{max}$), min temperature ($T_{min}$), mean wind speed ($W_{mean}$), mean relative humidity ($RH_{mean}$) and sunshine duration (SD). And, for the performances of GMDH-NNM, it consists of training and test performances, respectively. The training and test performances are carried out using daily time series data, respectively. From this research, we evaluate the impact of GMDH-NNM for the modeling of the nonlinear time series data. We should, thus, construct the credible data of the daily ETo data using GMDH-NNM, and can suggest the methodology for the irrigation and drainage networks system. Furthermore, this research represents that the strong nonlinear relationship such as ETo modeling can be generalized using GMDH-NNM.

• International Journal of Fuzzy Logic and Intelligent Systems
• /
• v.2 no.3
• /
• pp.194-197
• /
• 2002

This paper considers the problem of routing connections in a optical multi tree networks using WDM (Wavelength Division Multiplexing), where each connection between a pair of nodes in the network is assigned a path through the network and a wavelength on that path, so that connections whose paths share a common link in the network are assigned different wavelengths. The problem of optimal coloring of the paths on the optical multi-networks is NP-hard[1], but if that is the coloring of all paths, then there exists efficient polynomial time algorithm. In this paper, using a "divide & conquer" method, we give efficient algorithm to assign wavelengths to all the paths of a tree network based on the theory of [7]. Here, our time complexity is 0(n4log n).

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.3 no.2
• /
• pp.195-208
• /
• 2009

In this paper, we introduce a grid-based key pre-distribution scheme in wireless sensor networks, which aims to improve the connectivity and resiliency while maintaining a reasonable overhead. We consider simplification of the key establishment logic and enhancement of the connectivity via plat polynomial assignment on a three-dimensional grid for node allocation and keying material assignment. We demonstrate that our scheme results in improvements via a detailed discussion on the connectivity, resource usage, security features and resiliency. A comparison with other relevant works from the literature along with a demonstrated implementation on typical sensor nodes shows the feasibility of the introduced scheme and its applicability for large networks.

• Journal of Communications and Networks
• /
• v.13 no.6
• /
• pp.633-638
• /
• 2011

In this paper, we consider resource allocation with proportional fairness in the downlink orthogonal frequency division multiple access relay networks, in which relay nodes operate in decode-and-forward mode. A joint optimization problem is formulated for relay selection, subcarrier assignment and power allocation. Since the formulated primal problem is nondeterministic polynomial time-complete, we make continuous relaxation and solve the dual problem by Lagrangian dual decomposition method. A near-optimal solution is obtained using Karush-Kuhn-Tucker conditions. Simulation results show that the proposed algorithm provides superior system throughput and much better fairness among users comparing with a heuristic algorithm.

• Management Science and Financial Engineering
• /
• v.9 no.1
• /
• pp.11-27
• /
• 2003

In this study, we propose a mathematical model based on the graph theory for the wavelength assignment problem arising in the design of SDH (Synchronous Digital Hierarchy) over WDM (Wavelength Division Multiplexing) ring networks. We propose a branch- and -price algorithm to solve the suggested models effectively within reasonable time in realistic SDH over WDM ring networks. By exploiting the structure of ring networks, we developed a polynomial time algorithm for efficient column generation and a branching rule that conserves the structure of column generation. In a computer simulation study, the suggested approach can find the optimal solutions within reasonable time and show better performance than the existing heuristics.

• Proceedings of the Korean Institute of Intelligent Systems Conference
• /
• 2000.05a
• /
• pp.114-117
• /
• 2000

In this paper, Fuzzy Self-organizing Neural Networks(FSONN) based on Fuzzy Neural Networks(FNN) is proposed to overcome some problems, such as the conflict between ovefitting and good generation, and low reliability. The proposed FSONN consists of FNN and SONN. Here, FNN is used as the premise part of FSONN and SONN is the consequnt part of FSONN. The FUN plays the preceding role of FSONN. For the fuzzy reasoning and learning method in FNN, Simplified fuzzy reasoning and backpropagation learning rule are utilized. The number of layers and the number of nodes in each layers of SONN that is based on the GMDH method are not predetermined, unlike in the case of the popular multi layer perceptron structure and can be generated. Also the partial descriptions of nodes can use various forms such as linear, modified quadratic, cubic, high-order polynomial and so on. In this paper, the optimal design procedure of the proposed FSONN is shown in each step and performance index related to approximation and generalization capabilities of model is evaluated and also discussed.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.13 no.11
• /
• pp.5487-5495
• /
• 2012

The important issue that applies security key are secure rekeying, processing time and cost reduction. Because of sensor node's limited energy, energy consumption for rekeying affects lifetime of network. Thus it is necessary a secure and efficient security key management method. In this paper, I propose an energy efficient group-based cluster key management (EEGCK) in the large scale sensor networks. EEGCK uses five security key for efficient key management and different polynomial degree using security fitness function of sector, cluster and group is applied for rekeying and security processing. Through both analysis and simulation, I also show that proposed EEGCK is better than previous security management method at point of network energy efficiency.

• Proceedings of the KIEE Conference
• /
• 2011.07a
• /
• pp.1966-1967
• /
• 2011

본 연구에서는 방사형 기저 함수를 이용한 다항식 신경회로망(Polynomial Neural Network) 분류기를 제안한다. 제안된 모델은 PNN을 기본 구조로 하여 1층의 다항식 노드 대신에 다중 출력 형태의 방사형 기저 함수를 사용하여 각 노드가 방사형 기저 함수 신경회로망(RBFNN)을 형성한다. RBFNN의 은닉층에는 fuzzy 클러스터링을 사용하여 입력 데이터의 특성을 고려한 적합도를 사용하였다. 제안된 분류기는 입력변수의 수와 다항식 차수가 모델의 성능을 결정함으로 최적화가 필요하며 본 논문에서는 Multiobjective Particle Swarm Optimization(MoPSO)을 사용하여 모델의 성능뿐만 아니라 모델의 복잡성 및 해석력을 고려하였다. 패턴 분류기로써의 제안된 모델을 평가하기 위해 Iris 데이터를 이용하였다.