• Proceedings of the Korea Water Resources Association Conference
• /
• 2019.05a
• /
• pp.58-58
• /
• 2019

최근 기계학습기법에 대한 활발한 연구로 인하여 많은 기계학습기법들이 개발되었다. 이러한 최신기계학습기법은 기존에 사용되어온 기계학습기법과 경험식들보다 자연현상을 예측하고 재현하는데 높은 성능을 보이는 것으로 알려져 있다. 레이더 자료를 이용한 강우추정 기법으로는 ZR관계식이 널리 사용되고 있다. 이상적인 조건에서는 ZR 관계식을 이용한 레이더 강우추정이 양호한 성능을 보이나, 실제 레이더 자료를 이용한 강우추정은 이상적인 환경이 아닌 경우가 매우 많다. 이런 ZR관계식의 한계점을 보완하기 위한 방법으로 기계학습기법을 이용한 레이더 강우추정 기법들이 개발되었으나, 현재 한국의 레이더 자료를 대상으로 해서는 많은 연구가 진행되어 오지 않고 있다. 레이더 자료를 이용한 강우추정의 정확도 향상을 위해서는 최신 기계학습기법들의 레이더 강우추정 기법에 대한 적용가능성을 평가해 볼 필요성이 있다. 본 연구에서는 random forest, stochastic gradient boosted model, extreme learning machine의 강우 레이더 강우추정 기법으로의 적용성을 평가하였다. 강우추정 기법 개발 및 성능 비교를 위해서 2018년 광덕산 이중편파 레이더 자료를 이용하였다. 다양한 이중편파 매개변수 조합을 레이더 강우추정 기법의 입력변수로 적용하였다. 기존 연구의 사용되어 온 ZR관계식의 매개변수를 또한 강우사상과 이중편파 매개변수 조합을 이용하여 추정하였다. 기계학습을 적용한 레이더 강우추정 기법이 ZR관계식보다 상관계수와 제곱근오차를 기준으로 높은 강우추정 정확도를 보였다. 특히 개발된 강우추정 기법은 호우사상에서 높은 정확도를 보이는 것을 확인 할 수 있었다. 적용된 기계학습 기법 중에서는extreme learning machine이 레이더 강우추정기법 개발에 가장 적합한 것으로 나타났다.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.10 no.6
• /
• pp.1032-1037
• /
• 2006

The channel is one of the precious and limited resources in wireless networks. There are many researches on the channel management. Recently, the optimization problem of guard channels has been an important issue. In this paper, we propose an intelligent channel management technique based on the neural networks. An SRN channel allocation model is developed to generate the learning data for the neural networks and the performance analysis of system. In the proposed technique, the neural network is trained to generate optimal guard channel number g, using backpropagation supervised learning algorithm. The optimal g is computed using the neural network and compared to the g computed by the SRM model. The numerical results show that the difference between the value of 8 by backpropagation and that value by SRM model is ignorable.

• Journal of the Korean Society for Precision Engineering
• /
• v.11 no.4
• /
• pp.138-147
• /
• 1994

Performance management of computer networks is intended to improve a given network performance in order for more efficient information exchange between subsystems of an integrated large-scale system. Improtance of performance management is growing as many function of the large- scale system depend on the quality of communication services provided by the network. The role of performance management is to manipulate the adjustable protocol parameters on line so that the network can adapt itself to a dynamic environment. This can be divided into two subtasks : performance evaluation to find how changes in protocol parameters affect the network performance and decision making to detemine the magnitude and direction of parameter adjustment. This paper is the second part of the two papers focusing on conceptual design, development, and evaluation of performance management for token bus networks. This paper specifically deals with the task of decision making which utilizes the principles of stochastic optimization and learning automata. The developed algorithm can adjuxt four timer settings of a token bus protocol based on the result of performance evaluation. The overall performance management has been evaluated for its efficacy on a network testbed.

• Structural Engineering and Mechanics
• /
• v.83 no.4
• /
• pp.537-549
• /
• 2022

In this paper, a novel multi-feature model predictive control (MPC) framework with real-time and adaptive performances is proposed for intelligent structural control in which some drawbacks of the algorithm including, complex control rule and non-optimality, are alleviated. Hence, Linear Programming (LP) is utilized to simplify the resulted control rule. Afterward, the Whale Optimization Algorithm (WOA) is applied to the optimal and adaptive tuning of the LP weights independently at each time step. The stochastic control rule is also achieved using Kalman Filter (KF) to handle noisy measurements. The Extreme Learning Machine (ELM) is then adopted to develop a data-driven and real-time control algorithm. The efficiency of the developed algorithm is then demonstrated by numerical simulation of a twenty-story high-rise benchmark building subjected to earthquake excitations. The competency of the proposed method is proven from the aspects of optimality, stochasticity, and adaptivity compared to the KF-based MPC (KMPC) and constrained MPC (CMPC) algorithms in vibration suppression of building structures. The average value for performance indices in the near-field and far-field (El earthquakes demonstrates a reduction up to 38.3% and 32.5% compared with KMPC and CMPC, respectively.

• Journal of the Korean Data and Information Science Society
• /
• v.28 no.5
• /
• pp.1125-1132
• /
• 2017

In a situation where the severity and frequency of drought events getting stronger and higher, many studies related to drought forecast have been conducted to improve the drought forecast accuracy. However it is difficult to predict drought events using a single model because of nonlinear and complicated characteristics of temporal behavior of drought events. In this study, in order to overcome the shortcomings of the single model approach, we first build various single models capable to explain the relationship between the meteorological drought index, Standardized Precipitation Index (SPI), and other independent variables such as world climate indices. Then, we developed a combined models using Stochastic Gradient Descent method among Ensemble Learnings.

• Journal of Korean Society of Steel Construction
• /
• v.17 no.6 s.79
• /
• pp.661-672
• /
• 2005

For the efficient stochastic optimization of steel structures for which a large number of analyses is required, artificial neural networks,which have emerged as a powerful tool that could have been used to replace time-consuming procedures in many scientific or engineering applications, are applied. They are utilized for the solution of the equilibrium equations resulting from the application of the finite element method in connection with the reanalysis type of problem, for which a large number of finite element analyses are required in this study. As such, the use of artificial neural networks to predict finite element analysis outputs simplifies and facilitates the performance of the stochastic optimal design of structural systems where a trained neural network is used to replace the structural reanalysis phase. Moreover, to improve efficiency of used artificial neural networks, genetic algorithm is utilized. The stochastic optimizer used in this study is an algorithm based on the evolution theory. The efficiency of the proposed procedure is examined in problems with both volume (weight) functions and real-world cost functions

• 제어로봇시스템학회:학술대회논문집
• /
• 1996.10b
• /
• pp.466-469
• /
• 1996

In this paper, we present the global minimization condition by an informal analysis of the Langevine competitive learning neural network. From the viewpoint of the stochastic process, it is important that competitive learning guarantees an optimal solution for pattern recognition. By analysis of the Fokker-Plank equation for the proposed neural network, we show that if an energy function has a special pseudo-convexity, Langevine competitive learning can find the global minima. Experimental results for pattern recognition of handwritten numeral data indicate the superiority of the proposed algorithm.

• Proceedings of the Korean Institute of Intelligent Systems Conference
• /
• 1998.03a
• /
• pp.81-84
• /
• 1998

Genetic Algorithms (GAs) are stochastic algorithms whose search methods model some natural phenomena. The procedure of GAs may be divided into two sub-procedures : Operation and Selection. Chromosomes can produce new offspring by means of operation, and the fitter chromosomes can produce more offspring than the less fit ones by means of selection. However, operation which is executed randomly and has some limits to its execution can not guarantee to produce fitter chromosomes. Thus, we propose a method which gives a directional information to the genetic operator by reinforcement learning. It can be achived by using neural networks to apply reinforcement learning to the genetic operator. We use the amount of fitness change which can be considered as reinforcement signal to calcualte the error terms for the output units. Then the weights are updated using backpropagtion algorithm. The performance improvement of GAs using reinforcement learning can be measured by applying the pr posed method to GA-hard problem.

• Proceedings of the KIEE Conference
• /
• 1996.07b
• /
• pp.1344-1346
• /
• 1996

In this paper, we discuss an informal analysis of diffusion, global optimization properties of Langevine competitive learning neural network. In the view of the stochastic process, it is important that competitive learning gurantee an optimal solution for pattern recognition. We show that the binary reinforcement function in Langevine competitive learning is a brownian motion as Gaussian process, and construct the Fokker-Plank equation for the proposed neural network. Finally, we show that the informal analysis of the proposed algorithm has a possiblity of globally optimal. solution with the proper initial condition.

• The Journal of Korea Robotics Society
• /
• v.17 no.1
• /
• pp.40-47
• /
• 2022

A reward function suitable for a task is required to manipulate objects through reinforcement learning. However, it is difficult to design the reward function if the ample information of the objects cannot be obtained. In this study, a demonstration-based object manipulation algorithm called stochastic exploration guided by demonstration (SEGD) is proposed to solve the design problem of the reward function. SEGD is a reinforcement learning algorithm in which a sparse reward explorer (SRE) and an interpolated policy using demonstration (IPD) are added to soft actor-critic (SAC). SRE ensures the training of the critic of SAC by collecting prior data and IPD limits the exploration space by making SEGD's action similar to the expert's action. Through these two algorithms, the SEGD can learn only with the sparse reward of the task without designing the reward function. In order to verify the SEGD, experiments were conducted for three tasks. SEGD showed its effectiveness by showing success rates of more than 96.5% in these experiments.