• 대한안전경영과학회지
• /
• 제13권3호
• /
• pp.175-182
• /
• 2011

The purpose of this article is to suggest what is the desirable direction of economic relationship between Korea and China. The economic relationship between countries is based on how the present network is. As the economic relationship between countries grows, the network between countries will expand. In the past, the economic relationship between Korea and China is cooperative one from the viewpoint of international division of labor. Korean industries was focused on the value-added and mid-advanced technology products, while Chinese was focused on the labor-intensive products. As the China's economy grows for more than thirty years, there is a great change in China's economic policies and environment. China's industry structure is moving from the labor-intensive industry to technology-oriented industry. China's exports to the global market is increasing very fast, and China's domestic market is also growing. The change in Chinese industries' structure bring about severe competition in the global market. The expanding China's domestic market is also good opportunity as the new market in the world. The change in China's industrial structure needs for Korea to establish the 'New Network" between two countries. Korea has to grab the new opportunities in the China's domestic market and find new cooperative network with the products and industries.

• 제어로봇시스템학회논문지
• /
• 제11권6호
• /
• pp.524-529
• /
• 2005

In this paper, a novel neural network compensation technique for PD like fuzzy controlled robot manipulators is presented. A standard PD-like fuzzy controller is designed and used as a main controller for controlling robot manipulators. A neural network controller is added to the reference trajectories to modify input error space so that the system is robust to any change in system parameter variations. It forms a neural-fuzzy control structure and used to compensate for nonlinear effects. The ultimate goal is same as that of the neuro-fuzzy control structure, but this proposed technique modifies the input error not the fuzzy rules. The proposed scheme is tested to control the position of the 3 degrees-of-freedom rotary robot manipulator. Performances are compared with that of other neural network control structure known as the feedback error learning structure that compensates at the control input level.

• 한국음향학회지
• /
• 제13권4호
• /
• pp.12-19
• /
• 1994

본 논문에서는 음소의 시간 구조 특성만을 다룬 일반적인 TSNN 방법에 음소의 주파수 대역 구조를 포함시킨 신경 회로망을 제안한다. 제안된 신경 회로망에 음소(아, 이, 오, ㅅ, ㅊ, ㅍ, ㄱ, ㅇ, ㄹ, ㅁ)을 학습시켜 인식을 수행한 결과, 시간 인자 특성을 입력으로 음소를 인식한 일반적인 TDNN 방법 과 TSNN 방법보다 본 논문에서 시간과 주파수 인자를 동시에 입력으로 수행한 신경회로망 방법이 약간 더 나은 인식 결과를 보였다.

• 대한전기학회:학술대회논문집
• /
• 대한전기학회 2009년도 제40회 하계학술대회
• /
• pp.1743_1744
• /
• 2009

In this paper, we propose a double network control approach for linear systems. Generally, there are two network control system structures: the direct structure and the hierarchical structure. Here, the hierarchical structure consists of a main controller and a remote controller. The network delay of the structure only appears in the closed loop between the main controller and the remote system. However, the delay can exist between the remote controller and the actuator. Therefore, we design the double network system with delays between the main controller and the remote system, and the remote controller and the actuator. Finally, we carry out simulations on the linear system to illustrate the effectiveness of the proposed control method.

• 대한전기학회:학술대회논문집
• /
• 대한전기학회 1997년도 하계학술대회 논문집 B
• /
• pp.386-389
• /
• 1997

Error-backpropagation has been used in the bulk of Practical applications for neural networks. While an emulator, a multilayered neural network, learns to identify the system's dynamic characteristics. There is, however, no concrete theoretical results about the structure of a plant and the structure of a multilayered neural network and the learning rate. The paper investigates the relation between structure of a plant and a multilayered network and learning rate. Simulation study shows that the plant signal with a short period and a fast sam time is preferable for learning of the network emulator.

• ETRI Journal
• /
• 제35권2호
• /
• pp.207-217
• /
• 2013

This paper introduces the modular cellular neural network (CNN), which is a new CNN structure constructed from nine one-layer modules with intercellular interactions between different modules. The new network is suitable for implementing many image processing operations. Inputting an image into the modules results in nine outputs. The topographic characteristic of the cell interactions allows the outputs to introduce new properties for image processing tasks. The stability of the system is proven and the performance is evaluated in several image processing applications. Experiment results on texture segmentation show the power of the proposed structure. The performance of the structure in a real edge detection application using the Berkeley dataset BSDS300 is also evaluated.

• 한국방재학회:학술대회논문집
• /
• 한국방재학회 2008년도 정기총회 및 학술발표대회
• /
• pp.469-472
• /
• 2008

In general, structures in service gradually lose original performance according to time due to initial defects in design and construction, or exposure to unfavorable external conditions such as repeated loading or deteriorating environment, and in extreme cases, may collapse in large disaster. Therefore, in order to maintain the serviceability of structures at optimal level, advanced structure measuring system which can inform optimal time point and method of maintenance is required in addition to accurate prediction of residual life the structure by periodic inspection. To guarantee the safety level of bridge structure and to prevent from disaster, the integration of safety network for bridge structures are needed. Therefore in this study, to enhance the effectiveness of safety network for bridge, the connection methodologies between safety network and pre-installed bridge monitoring system are investigated.

• 전기학회논문지
• /
• 제66권12호
• /
• pp.1772-1781
• /
• 2017

In this study, the design methodology for alleviating the overfitting problem of Polynomial Neural Networks(PNN) is realized with the aid of two kinds techniques such as L2 regularization and Sum of Squared Coefficients (SSC). The PNN is widely used as a kind of mathematical modeling methods such as the identification of linear system by input/output data and the regression analysis modeling method for prediction problem. PNN is an algorithm that obtains preferred network structure by generating consecutive layers as well as nodes by using a multivariate polynomial subexpression. It has much fewer nodes and more flexible adaptability than existing neural network algorithms. However, such algorithms lead to overfitting problems due to noise sensitivity as well as excessive trainning while generation of successive network layers. To alleviate such overfitting problem and also effectively design its ensuing deep network structure, two techniques are introduced. That is we use the two techniques of both SSC(Sum of Squared Coefficients) and $L_2$ regularization for consecutive generation of each layer's nodes as well as each layer in order to construct the deep PNN structure. The technique of $L_2$ regularization is used for the minimum coefficient estimation by adding penalty term to cost function. $L_2$ regularization is a kind of representative methods of reducing the influence of noise by flattening the solution space and also lessening coefficient size. The technique for the SSC is implemented for the minimization of Sum of Squared Coefficients of polynomial instead of using the square of errors. In the sequel, the overfitting problem of the deep PNN structure is stabilized by the proposed method. This study leads to the possibility of deep network structure design as well as big data processing and also the superiority of the network performance through experiments is shown.

• 제어로봇시스템학회논문지
• /
• 제10권5호
• /
• pp.464-474
• /
• 2004

This paper proposes a middleware structure for the module-based personal robot, which can run on heterogeneous network interfaces and provides users easy interface-method regardless of underlying heterogeneous interfaces and convenient exchange of modules. The proposed middleware is divided into three layers of a streaming layer (SL), a network adaptation layer (NAL) and a network interface layer (NIL). The streaming layer manages application transactions using middleware services and provides user a uniform interfaces to the proposed middleware. The network adaptation layer manages a message-routing and provides naming service and it is a core of the proposed middleware. And the network interfaces layer manages dependent parts of heterogeneous network interfaces such as IEEE1394, USB, Ethernet, and CAN (Control Area Network). This paper implements the proposed middleware structure, where 3 types of interfaces of IEEE 1394, USB and Ethernet are used, and measures response times among those interfaces.

• 가정과삶의질연구
• /
• 제15권2호
• /
• pp.45-58
• /
• 1997

In the traditional rural community social relationships among the people are the routes of resources. But as industrialization goes on rural community has changed. I wonder that rural housewives have yet the traditional social network structure. This stud purposed to analyze the structure of social network resource exchange and perception of community resources. Results were as follows: 1. In the rural housewife's social network structure network range and depth were affected by family income age of the youngest and farming time. Network boundary was affected by near environmental variables such as community resources and community level of living. 2. Community resources was the most influential variable in the resource exchanged 3. Perception of community resources was affected by network depth and was not by the resource exchange.