• 산업기술연구
• /
• 제24권A호
• /
• pp.99-107
• /
• 2004

This paper considers reinforcement learning control with the self-organizing map. Reinforcement learning uses the observable states of objective system and signals from interaction of the system and the environments as input data. For fast learning in neural network training, it is necessary to reduce learning data. In this paper, we use the self-organizing map to parition the observable states. Partitioning states reduces the number of learning data which is used for training neural networks. And neural dynamic programming design method is used for the controller. For evaluating the designed reinforcement learning controller, an inverted pendulum of the cart system is simulated. The designed controller is composed of serial connection of self-organizing map and two Multi-layer Feed-Forward Neural Networks.

• 한국경영과학회:학술대회논문집
• /
• 대한산업공학회/한국경영과학회 2006년도 춘계공동학술대회 논문집
• /
• pp.1221-1226
• /
• 2006

The use of Artificial Neural Networks (ANN) has received increasing attention in the analysis and prediction of financial time series. Stationarity of the observed financial time series is the basic underlying assumption in the practical application of ANN on financial time series. In this paper, we will investigate whether it is feasible to relax the stationarity condition to non-stationary time series. Our result discusses the range of complexities caused by non-stationary behavior and finds that overfitting by ANN could be useful in the analysis of such non-stationary complex financial time series.

• 한국산업정보학회:학술대회논문집
• /
• 한국산업정보학회 2008년도 추계 공동 국제학술대회
• /
• pp.445-448
• /
• 2008

The key establishment between nodes is one of the most important issues to secure the communication in wireless sensor networks. Some researcher used the probabilistic key sharing scheme with a pre-shared key pool to reduce the number of keys and the key disclosure possibility. However, there is a potential possibility that some nodes do not have a common share in the key pool. The purpose of this paper is to devise a peer to peer key sharing protocol (PPKP) based on Quorum system and Diffie-Hellman key exchange scheme (DHS). The PPKP establishes a session key by creating a shared key using the DHS and then scrambles it based on Quorum system to secure that. The protocol reduces the number of necessary keys than the previous schemes and could solve the non-common key sharing possibility problem in the probabilistic schemes.

• 산업공학
• /
• 제16권spc호
• /
• pp.28-32
• /
• 2003

In this paper, the fuzzy group method data handling-type(GMDH) neural networks and their application to the forecasting of mobile communication system are described. At present, GMDH family of modeling algorithms discovers the structure of empirical models and it gives only the way to get the most accurate identification and demand forecasts in case of noised and short input sampling. In distinction to neural networks, the results are explicit mathematical models, obtained in a relative short time. In this paper, an adaptive learning network is proposed as a kind of neuro-fuzzy GMDH. The proposed method can be reinterpreted as a multi-stage fuzzy decision rule which is called as the neuro-fuzzy GMDH. The GMDH-type neural networks have several advantages compared with conventional multi-layered GMDH models. Therefore, many types of nonlinear systems can be automatically modeled by using the neuro-fuzzy GMDH. The computer program is developed and successful applications are shown in the field of estimating problem of mobile communication with the number of factors considered.

• 대한산업공학회지
• /
• 제22권3호
• /
• pp.427-440
• /
• 1996

Constraint networks are a major approach to knowledge representation in Concurrent Engineering (CE) systems. The networks model various factors in CE as constraints linked by shared variables. Many systems have been developed to assist constraint network processing. While these systems can be useful, their underlying assumption that a solution must simultaneously satisfy all the constraints is often unrealistic and hard to achieve. Proposed in this paper is a hierarchical representation of constraint networks using priorities, namely Prioritized Constraint Network (PCN). A mechanism to propagate priorities is developed, and a new satisfiability definition taking into account the priorities is described. Strength of constraint supporters can be derived from the propagated priorities. Several properties useful for investigating PCN's and finding effective solving strategies ore developed.

• 대한산업공학회지
• /
• 제23권2호
• /
• pp.371-383
• /
• 1997

This paper propose a fuzzy regression method using fuzzy neural networks when a membership value is attached to each input-output pair. First, a method of linear fuzzy regression analysis is described by interpreting the reliability of each input-output pair as its membership values. Next, an architecture of fuzzy neural networks with fuzzy weights and fuzzy biases is shown. The fuzzy neural network maps a crisp input vector to a fuzzy output. A cost function is defined using the fuzzy output from the fuzzy neural network and the corresponding target output with a membership value. A learning algorithm is derived from the cost function. The derived learning algorithm trains the fuzzy neural network so that the level set of the fuzzy output includes the target output. Last, the proposed method is illustrated by computer simulations on numerical examples.

• 산업기술연구
• /
• 제27권B호
• /
• pp.43-51
• /
• 2007

In mobile multi-hop wireless networks, the authentication between a base station and a mobile multi-hop node, between multi-hop nodes, and between user a station and a multi-hop node is needed for the reliable and secure network operation. In this paper, we survey various authentication schemes which can be considered to be adopted in mobile multi-hop wireless networks and propose a concept of novel mutual authentication scheme applicable to mobile multi-hop network architecture. The scheme should resolve the initial trust gain problem of a multi-hop node at its entry to the network, the problem of rogue mobile multi-hop node and the problem of hop-by-hop authentication between multi-hop nodes. Effectively, the scheme is a hybrid scheme of the distributed authentication method and the centralized authentication method which are considered to be deployed in the wireless ad-hoc network and the wireless network connected to wired authentication servers, respectively.

• 한국산업정보학회논문지
• /
• 제4권2호
• /
• pp.7-13
• /
• 1999

본 연구에서는 주어진 입출력 데이터에 신뢰도를 나타내는 소속함수 값이 붙여진 경우에 대하여 유효한 퍼지 신경망을 제안한다. 먼저, 퍼지수 연결강도와 퍼지수 임계치를 가진 퍼지 신경망의 구조를 나타낸다. 코스트 함수는 퍼지 신경망으로부터의 출력치와 소속함수 값을 가진 목표 출력치를 이용하여 정의되고, 퍼지 신경망의 학습 알고리즘은 정의된 코스트 함수로부터 도출된다. 마지막으로 도출된 학습 알고리즘을 이용하여 사출성형 품질의 목측 평가치 해석에 적용하고 그 유효성을 나타낸다.

• Industrial Engineering and Management Systems
• /
• 제9권4호
• /
• pp.339-347
• /
• 2010

Simple-closed expressions for approximate calculation of quality of service (QoS) metrics of isolated cell of wireless networks with either finite or infinite queues of both new and handover calls are developed. It is assumed that both kinds of calls might leave the system without receiving service if their waiting times exceed some threshold value. For the models with infinite queues of heterogeneous calls easily checkable ergodicity conditions are proposed. The high accuracy of the developed approximation formulas is shown. Results of numerical experiments are given.

• Journal of the Korean Society for Industrial and Applied Mathematics
• /
• 제24권4호
• /
• pp.331-350
• /
• 2020

Exploding gradient is a widely known problem in training recurrent neural networks. The explosion problem has often been coped with cutting off the gradient norm by some fixed value. However, this strategy, commonly referred to norm clipping, is an ad hoc approach to attenuate the explosion. In this research, we opt to view the problem from a different perspective, the discrete-time optimal control with infinite horizon for a better understanding of the problem. Through this perspective, we fathom the region at which gradient explosion occurs. Based on the analysis, we introduce a gradient-explosion-free algorithm that keeps the training process away from the region. Numerical tests show that this algorithm is at least three times faster than the clipping strategy.