• 한국컴퓨터정보학회논문지
• /
• 제8권3호
• /
• pp.113-123
• /
• 2003

본 논문에서는 주식의 종가, 거래량 기술적 지표인 MACD(Moving Average Convergence Divergence) 값과 투자 심리선값을 입력 패턴으로 사용하여 개별 금융지표지수에 대한 매도, 중립 및 매수 시점 예측을 수행하는 신경망 모델이 제안된다. 이 모델은 역전파 알고리즘을 이용한 시계열 예측 기능과 균등다층연산 기능을 갖는다. 학습 데이터의 수가 각 범주들(매도, 중립, 매수)에 균일하게 분포되어 있지 않을 경우 기존의 신경망은 가장 우세한 범주의 예측 정확성만을 향상시키는 문제점을 가지고 있다. 따라서, 본 논문에서는 신경망의 구조, 동작, 학습 알고리즘에 대해 표현한 후 다른 범주의 예측 정확성도 향상시키기 위해 각 범주의 중요성을 이용하여 학습 데이터의 수를 조절하는 균등다층연산 방법을 제안한다. 실험 결과, 균등다층연산 신경망을 이용한 금융지표지수 예측 방법이 기존의 신경망을 이용한 금융지표지수 예측 방법 보다 각 범주에 대해 높은 정확성 비율을 보임을 확인할 수 있었다.

• 한국정보통신학회:학술대회논문집
• /
• 한국해양정보통신학회 2004년도 SMICS 2004 International Symposium on Maritime and Communication Sciences
• /
• pp.1-5
• /
• 2004

In this paper, we propose a novel approach for evolving the architecture of a multi-layer neural network. Our method uses combined ART1 algorithm and Max-Min neural network to self-generate nodes in the hidden layer. We have applied the. proposed method to the problem of recognizing ID number in student identity cards. Experimental results with a real database show that the proposed method has better performance than a conventional neural network.

• 한국지능시스템학회:학술대회논문집
• /
• 한국퍼지및지능시스템학회 2003년도 ISIS 2003
• /
• pp.694-697
• /
• 2003

In this paper, we propose modular network to solve difficult and complex problems that are seldom solved with Multi-Layer Neural Network(MLNN). The structure of Modular Neural Network(MNN) in researched by Jacobs and jordan is selected in this paper. Modular network consists of several Expert Networks(EN) and a Gating Network(CN) which is composed of single-layer neural network(SLNN) or multi-layer neural network. We propose modular network structure using Recurrent Neural Network(RNN), since the state of the whole network at a particular time depends on aggregate of previous states as well as on the current input. Finally, we show excellence of the proposed network compared with modular network.

• 융합보안논문지
• /
• 제13권6호
• /
• pp.77-82
• /
• 2013

최근 네트워크 사용자의 가치 변화와 이용 패턴을 살펴보면, 단순 웹 정보, 단방향 정보습득의 일방적인 데이터 전달에서, 멀티미디어 활용의 증가, 보안 및 개인화의 요구 증대, 자유로운 이동성에 대한 욕구 증가 등의 변화가 생기고 있다. 이러한 욕구의 변화로 인해 개별적으로 제공되는 각각의 서비스는 점차 융합화된 형태의 통합 서비스로 발전하고, 네트워크 또한 각각의 서비스를 위한 개별 망에서 이용자의 다양한 통합 욕구를 실현시켜 주는 지능형 통합망의 형태로 발전할 것으로 전망되며, 관련한 기술의 핵심이 되는 통신망 제어기술 또한 급속히 발전하고 있다. 본 논문에서는 자원의 효율적 사용은 물론 다중 도메인 (multi-domain)환경에서 다계층 (multi-layer)간의 정보 전달을 최소화하고, 최적의 경로선택을 할 수 있는 방법을 제안하였다. 기존의 경로선택에서 각각의 계층에 대한 정보를 이용하여 경로를 선택한 것에 비하여 다계층 구조상에서 다 계층의 정보를 활용하여 경로선택에 대한 다각화를 통한 최적의 경로선택이 수행되도록 제안하였다.

• 제어로봇시스템학회논문지
• /
• 제9권12호
• /
• pp.1048-1054
• /
• 2003

In laser surface hardening processes, the geometrical parameters such as the depth and the width of a hardened layer can be utilized to assess the hardened layer quality. However, accurate monitoring of the geometrical parameters for on-line process control as well as for on-line quality evaluation is very difficult because the hardened layer is formed beneath a material surface and is not visible. Therefore, temperature monitoring of a point of specimen surface has most frequently been used as a process monitoring method. But, a hardened layer depends on the temperature distribution and the thermal history of a specimen during laser surface hardening processing. So, this paper describes the estimation results of the geometric parameters using multi-point surface temperature monitoring. A series of hardening experiments were performed to find the relationships between the geometric parameters and the measured temperature. Estimation results using a neural network show the enhanced effectiveness of multi-point surface temperature monitoring compared to one-point monitoring.

• 전자공학회논문지B
• /
• 제29B권1호
• /
• pp.58-66
• /
• 1992

This paper proposes a neuro-controller for position control of one-link flexible robot arm. Basically the controller consists of a multi-layer neural network and a conventional PD controller. Two controller are parallelly connected. Neural network is traind by the conventional error back propagation learning rules. During learning period, the weights of neural network are adjusted to minimize the position error between the desired hub angle and the actual one. Finally the effectiveness of the proposed approach will be demonstrated by computer simulation.

• 한국군사과학기술학회지
• /
• 제21권4호
• /
• pp.497-507
• /
• 2018

Tactical networks are evolving into an All-IP based network for network centric warfare(NCW). Owing to the flexibility of IP based network, various military data applications including real-time and multi-media services are being integrated in tactical networks. Because each application has diverse Quality-of-service(QoS) requirements, it is crucial to develop a QoS provisioning method for guaranteeing QoS requirements efficiently. Conventionally, differentiated services(DiffServ) have been used to provide a different level of QoS for traffic flows. However, DiffServ is not designed to guarantee a specific requirement of QoS such as delay, loss, and bandwidth. Therefore, it is not suitable for military applications with a tight bound of QoS requirements. In this paper, we propose a multi-layer network virtualization scheme that allocates traffic flows having different QoS requirements to multiple virtual networks, which are constructed to support different QoS policies such as virtual network functions(VNFs), routing, queueing/active queue management(AQM), and physical layer policy. The experiment results indicate that the proposed scheme achieves lower delays and losses through multiple virtual networks having differentiated QoS policies in comparison with conventional networks.

• Journal of information and communication convergence engineering
• /
• 제9권5호
• /
• pp.523-529
• /
• 2011

In this paper an inter-layer protocol, referred to as a Multi-Network Selector (MNS) is proposed for multiband maritime networks. A MNS is located between the data-link layer and the network layer and performs vertical handover when a ship moves another radio network. In order to provide seamless data transfer to different radio networks, the MNS uses received signal strength (RSS) and ship's location information as decision parameters for vertical handover, which can avoid ping-pong effect and reduces handover latency. In addition, we present related issues in order to implement the MNS for a multiband maritime network.

• 한국산업융합학회 논문집
• /
• 제16권3호
• /
• pp.61-68
• /
• 2013

Long-term runoff model can be used to establish the effective plan of water reources allocation and the determination of the storage capacity of reservoir. So this study aims at the development of monthly runoff model using artificial neural network technique. For this, it was selected multi-layer neural network(MLN) and radial basis function neural network(RFN) model. In this study, it was applied model to analysis monthly runoff process at the Wi stream basin in Nakdong river which is representative experimental river basin of IHP. For this, multi-layer neural network model tried to construct input 3, hidden 7, and output 1 for each number of layer. As the result of analysis of monthly runoff process using models connected with artificial neural network technique, it showed that these models were effective in the simulation of monthly runoff.

• 전자공학회논문지B
• /
• 제31B권8호
• /
• pp.211-218
• /
• 1994

In this paper we develope a hybrid learning rule to improve the robustness of multi-layer Perceptions. In most neural networks the activation of a neuron is deternined by a nonlinear transformation of the weighted sum of inputs to the neurons. Investigating the behaviour of activations of hidden layer neurons a new learning algorithm is developed for improved robustness for multi-layer Perceptrons. Unlike other methods which reduce the network complexity by putting restrictions on synaptic weights our method based on error-backpropagation increases the complexity of the underlying proplem by imposing it saturation requirement on hidden layer neurons. We also found that the additional gradient-descent term for the requirement corresponds to the Hebbian rule and our algorithm incorporates the Hebbian learning rule into the error back-propagation rule. Computer simulation demonstrates fast learning convergence as well as improved robustness for classification and hetero-association of patterns.