• Proceedings of the KIEE Conference
• /
• 2008.10b
• /
• pp.247-248
• /
• 2008

본 논문에서는 TYPE-2 퍼지 추론 기반의 RBF 뉴럴 네트워크(TYPE-2 Radial Basis Function Neural Network, T2RBFNN)를 설계하고 PSO(Particle Swarm Optimization) 알고리즘을 이용하여 모델의 파라미터를 동정한다. 제안된 모델의 은닉층은 TYPE-2 가우시안 활성 함수로 구성되며, 출력층은 Interval set 형태의 연결가중치를 갖는다. 여기에서 규칙 전반부 활성함수의 중심 선택은 C-means 클러스터링 알고리즘을 이용하고, 규칙 후반부 Interval set 형태의 연결가중치 결정에는 경사 하강법(Gradient descent method)을 이용한 오류 역전파 알고리즘을 사용하여 학습한다. 또한, 최적의 모델을 설계하기 위한 학습율 및 활성함수의 활성화 영역 결정에는 입자 군집 최적화(PSO; Particle Swarm Optimization) 알고리즘으로 동조한다. 마지막으로, 제안된 모델의 평가를 위하여 모의 데이터 집합(Synthetic dadaset)을 적용하고 근사화 및 일반화 능력에 대하여 토의한다.

• Journal of Communications and Networks
• /
• v.18 no.5
• /
• pp.796-805
• /
• 2016

In many wireless sensor network (WSN) applications, the information transmitted by an individual entity or node is of limited use without the knowledge of its location. Research in node localization is mostly geared towards multi-hop range-free localization algorithms to achieve accuracy by minimizing localization errors between the node's actual and estimated position. The existing localization algorithms are focused on improving localization accuracy without considering efficiency in terms of energy costs and algorithm convergence time. In this work, we show that our proposed localization scheme, called DV-maxHop, can achieve good accuracy and efficiency. We formulate the multi-objective optimization functions to minimize localization errors as well as the number of transmission during localization phase. We evaluate the performance of our scheme using extensive simulation on several anisotropic and isotropic topologies. Our scheme can achieve dual objective of accuracy and efficiency for various scenarios. Furthermore, the recently proposed algorithms require random uniform distribution of anchors. We also utilized our proposed scheme to compare and study some practical anchor distribution schemes.

• Magazine of the Korean Society of Agricultural Engineers
• /
• v.45 no.6
• /
• pp.83-95
• /
• 2003

In this study, a new concept in a paddy consolidation project is introduced in that curved parallel terracing with contour-lined layout is adopted in sloping areas instead of conventional rectangular terracing. The contoured layout reduces earth-moving considerably compared to rectangular methods in consolidation projects. The objective of the paper is to develop a combinatorial optimization model using the network theory for the design of contour-lined plots which minimizes the volume of earth moving. The results showed that as the length of short side of plot is longer or the land slope is steeper, the volume of earth moving for land leveling increases. The developed optimization model is applied for three consolidated districts and the resulting optimal earth moving is compared with the volume of earth from the conventional method. The shorter is the minimum length of short side of a polt with increases the number of plots, the less is the volume of earth. As the minimum length of short side is 20 m for efficient field works by farm machinery, the volume of earth moving of optimal plot is less by 21.0∼27.1 % than that of the conventional consolidated plots.

• Structural Engineering and Mechanics
• /
• v.61 no.2
• /
• pp.283-293
• /
• 2017

The main contribution of the present paper is to propose an intelligent fuzzy inference system approach for modeling the debonding strength of masonry elements retrofitted with Fiber Reinforced Polymer (FRP). To achieve this, the hybrid of meta-heuristic optimization methods and adaptive-network-based fuzzy inference system (ANFIS) is implemented. In this study, particle swarm optimization with passive congregation (PSOPC) and real coded genetic algorithm (RCGA) are used to determine the best parameters of ANFIS from which better bond strength models in terms of modeling accuracy can be generated. To evaluate the accuracy of the proposed PSOPC-ANFIS and RCGA-ANFIS approaches, the numerical results are compared based on a database from laboratory testing results of 109 sub-assemblages. The statistical evaluation results demonstrate that PSOPC-ANFIS in comparison with ANFIS-RCGA considerably enhances the accuracy of the ANFIS approach. Furthermore, the comparison between the proposed approaches and other soft computing methods indicate that the approaches can effectively predict the debonding strength and that their modeling results outperform those based on the other methods.

• KIEE International Transactions on Power Engineering
• /
• v.5A no.4
• /
• pp.331-338
• /
• 2005

In this paper, an improved maintenance scheduling approach suitable for the competitive environment is proposed by taking account of profits and costs of generation companies and the formulated combinatorial optimization problem is solved by using Reactive Tabu search (RTS). In competitive power markets, electricity prices are determined by the balance between demand and supply through electric power exchanges or by bilateral contracts. Therefore, in decision makings, it is essential for system operation planners and market participants to take the volatility of electricity price into consideration. In the proposed maintenance scheduling approach, firstly, electricity prices over the targeted period are forecasted based on Artificial Neural Network (ANN) and also a newly proposed aggregated bidding curve. Secondary, the maintenance scheduling is formulated as a combinatorial optimization problem with a novel objective function by which the most profitable maintenance schedule would be attained. As an objective function, Opportunity Loss by Maintenance (OLM) is adopted to maximize the profit of generation companies (GENCOS). Thirdly, the combinatorial optimization maintenance scheduling problem is solved by using Reactive Tabu Search in the light of the objective functions and forecasted electricity prices. Finally, the proposed maintenance scheduling is applied to a practical test power system to verify the advantages and practicability of the proposed method.

• Journal of the Korean Institute of Telematics and Electronics B
• /
• v.31B no.4
• /
• pp.145-154
• /
• 1994

This paper proposes an efficient method for improving the training performance of the neural network by using a hybrid of a stochastic approximation and a backpropagation algorithm. The proposed method improves the performance of the training by appliying a global optimization method which is a hybrid of a stochastic approximation and a backpropagation algorithm. The approximate initial point for a stochastic approximation and a backpropagation algorihtm. The approximate initial point for fast global optimization is estimated first by applying the stochastic approximation, and then the backpropagation algorithm, which is the fast gradient descent method, is applied for a high speed global optimization. And further speed-up of training is made possible by adjusting the training parameters of each of the output and the hidden layer adaptively to the standard deviation of the neuron output of each layer. The proposed method has been applied to the parity checking and the pattern classification, and the simulation results show that the performance of the proposed method is superior to that of the backpropagation, the Baba's MROM, and the Sun's method with randomized initial point settings. The results of adaptive adjusting of the training parameters show that the proposed method further improves the convergence speed about 20% in training.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.9 no.1
• /
• pp.1-19
• /
• 2015

With the recent popularity of smart terminals, the demand for high-data-rate transmission is growing rapidly, which brings a new challenge for the traditional cellular networks. Both device-to-device (D2D) communication and small cells are effective to improve the transmission efficiency of local communication. In this paper, we apply D2D communication into a small cell network system (SNets) and study about the optimization problem of resource allocation for D2D communication. The optimization problem includes system scheduling and resource allocation, which is exponentially complex and the optimal solution is infeasible to achieve. Therefore, in this paper, the optimization problem is decomposed into several smaller problems and a hierarchical scheme is proposed to obtain the solution. The proposed hierarchical scheme consists of three steps: D2D communication groups formation, the estimation of sub-channels needed by each D2D communication group and specific resource allocation. From numerical simulation results, we find that the proposed resource allocation scheme is effective in improving the spectral efficiency and reducing the outage probability of D2D communication.

• Journal of the Institute of Electronics and Information Engineers
• /
• v.52 no.3
• /
• pp.19-24
• /
• 2015

We introduce an optimization of the number of base station antennas in massive multiple-input multiple-output (MIMO) wireless powered communication network (WPCN). We use channel hardening property of massive MIMO system to approximate channel gain in terms of the number of base station antennas. Then, we find an optimal solution by partial differential and obtain a closed form solution by using Lambert-W function. The simulation results show that the approximation and the method of solving the optimization problem are reasonable, and the optimal solution of proposed scheme is almost identical to the optimal number of base station antennas by the exhaustive search method.

• Journal of Forest and Environmental Science
• /
• v.32 no.2
• /
• pp.173-181
• /
• 2016

This study designed a model of the efficient production schemes and raw materials transportation optimization of current South Korean's simple and monolithic distribution system of wood to build a SCM (supply chain management) as a basic level to establish a distribution of future by pellet production of raw materials costs and reduce transport costs, and specifically to forest of pallet to contribute to revitalizing the market. The result of each transportation costs after building the best transportation network from raw material supply area to demand area applying transport law was 964,600 thousands Won from 6 supply areas to 7 demand areas. And the result of each model's analysis to get the pellet's efficient production through production cost reduction showed that it reduced from 325,701 Won/t to 240,106 Won/t, results of existing efficient pellet for the production model 8,233 tons over 20,000 tons annual production capacity from the size of the expanded production capacity when the expansion. However, when the production size expanded to 50,000 Tons of the production, the effect was very small even though production cost decreased.

• Journal of the Korea Computer Industry Society
• /
• v.7 no.3
• /
• pp.145-154
• /
• 2006

This paper improves algorithms of Speculative Partial Redundancy Elimination(SPRE) proposed by Knoop et al. Improving SPRE algorithm performs the execution speed optimization based on the information of the execution frequency from profiling and the memory space optimization. The first purpose of presented algorithm is to reduce in space requirements and the second purpose is to de crease the execution time. Since too much weight on execution speed optimization may cause the explosion of the memory space, it is important to consider the size of memory. This fact can be a big advantage in the embedded system which concerns the required memory size more than the execution speed In this paper we implemented the min-cut algorithm, and this algorithm used the control flow graph is constructed with network and partitioned.