• 제어로봇시스템학회:학술대회논문집
• /
• 2001.10a
• /
• pp.41.5-41
• /
• 2001

A novel method is introduced for determining the weights of a regularization network which approximates one-to-many mapping. A conventional neural network will converges to the average value when outputs are multiple for one input. The capability of proposed network is demonstrated by an example of learning inverse mapping.

• 제어로봇시스템학회:학술대회논문집
• /
• 2001.10a
• /
• pp.49.4-49
• /
• 2001

Digit recognition based on backpropagation neural networks, as an important application of pattern recognition, was attracted much attention. Although it has the advantages of parallel calculation, high error-tolerance, and learning capability, better recognition effects can only be achieved with some specific fixed format input of the digit image. Therefore, digit image preprocessing ability directly affects the accuracy of recognition. Here using Matlab software, the digit image was enhanced by resizing and neutral-rotating the extracted digit image, which improved the digit recognition capability of the backpropagation neural network under practical conditions. This method may also be helpful for recognition of other patterns with backpropagation neural networks.

• Convergence Security Journal
• /
• v.6 no.2
• /
• pp.91-99
• /
• 2006

As the speed of network has fastened and the Internet has became common, an ill-intentioned aggression, such as worm and E-mail virus rapidly increased. So that there too many defenses created the recent Intrusion detection system as well as the Intrusion Prevention Systems to defense the malicious aggression to the network. Also as the form of malicious aggression has changed, at the same time the method of defense has changed. There is "snort" the most representive method of defense and its Rules file increases due to the change of aggression form. This causes decline of capability for detection. This paper suggest, design, and realize the structure for the improvement of processing capability by separating the files of Snort Rule according to o/s. This system show more improvement of the processing capability than the existing composion.

• Journal of Korean Society for Atmospheric Environment
• /
• v.23 no.5
• /
• pp.526-538
• /
• 2007

Since air quality monitoring data sets are important base for developing of air quality management strategies including policy making and policy performance assessment, the environmental protection authorities need to organize and operate monitoring network properly. Air quality monitoring network of Busan, consisting of 18 stations, was allocated under unscientific and irrational principles. Thus the current state of air quality monitoring networks was reassessed the effect and appropriateness of monitoring objectives such as population protection and sources surveillance. In the process of the reassessment, a GIS-based decision support system was constructed and used to simulate air quality over complex terrain and to conduct optimization analysis for air quality monitoring network with multi-objective. The maximization of protection capability for population appears to be the most effective and principal objective among various objectives. The relocation of current monitoring stations through optimization analysis of multi-objective appears to be better than the network building for maximization of population protection capability. The decision support system developed in this study on the basis of GIS-based database appear to be useful for the environmental protection authorities to plan and manage air quality monitoring network over complex terrain.

• The KIPS Transactions:PartB
• /
• v.14B no.5
• /
• pp.377-382
• /
• 2007

This paper proposes a training algorithm for global optimization of the parameters of radial basis function networks. Since conventional training algorithms usually perform only local optimization, the performance of the network is limited and the final network significantly depends on the initial network parameters. The proposed hybrid simulated annealing algorithm performs global optimization of the network parameters by combining global search capability of simulated annealing and local optimization capability of gradient-based algorithms. Via experiments for function approximation problems, we demonstrate that the proposed algorithm can find networks showing better training and test performance and reduce effects of the initial network parameters on the final results.

• Convergence Security Journal
• /
• v.24 no.2
• /
• pp.175-180
• /
• 2024

Future warfare is evolving with advanced science and technology, introducing a variety of unmanned and manned combat systems. These systems generate and exchange massive amounts of information, challenging current tactical communication systems as a foundation for future communication infrastructure. To analyze the information distribution capability of the Army TIGER corps, this paper examines four scenarios: standalone ground network operation, integrated network operation, load distribution, and error recovery. Utilizing M&S results, we highlight the potential of a multilayer integrated command and control network, incorporating ground, air, and space networks, to enhance the reliability and stability of the overall communication network.

• Management & Information Systems Review
• /
• v.2
• /
• pp.335-354
• /
• 1998

In this study I construct CAN(Controller Area Network) for automobiles similar to LAN(Local Area Network) and build communication modules in the major part of an automobile to link several sub-systems. Since each station replaces the communication function of sub-systems and has various types of sensor, actuator, controller, and switch, every information about automobile's status is obtained from the network. The manufactured system showed a superior capability. The following is the contents of study. 1. The definition of communication packet through the analysis of CAN protocol. 2. The Design of modules using micro-controller 80C196CA. 3. The Network configuration.

• Proceedings of the Korean Operations and Management Science Society Conference
• /
• 1993.10a
• /
• pp.212-226
• /
• 1993

The self-reliance of NSSS System Design is required not only the design capability to perform the system design but also the management capability to control the resource and time for the Project effectively. The purpose of this study is to develop the simplified standard Logic Network that is scheduled on the time and resource using the PERT/CPM method. That is mainly focused on Ulchin 3&4 Project. We prepare the management tool of NSSS System Design project. And we can utilize it as a reference tool for the similar project which are complex and long term in a next project.

• Proceedings of the KIPE Conference
• /
• 2017.11a
• /
• pp.111-112
• /
• 2017

This paper presents a novel three-port converter for the OnBoard Charger of Electric Vehicles by using an impedance control network. The proposed concept is suitable for charging a main battery and an auxiliary battery of an electric vehicle at the same time due to its power handling capability of the converter without additional switches. The power flow is managed by the phase angle (${\Theta}$) between the ports whereas voltage at each port is controlled by the asymmetric duty cycle and the phase shift (${\Phi}$) between the inverter lags controlled by the impedance control network. The proposed system has a capability of achieving zero voltage switching (ZVS) and zero current switching (ZCS) at all the switches over the wide range of input voltage, output voltage and output power. The feasibility of the proposed system is verified by the PSIM simulation.

• Journal of Power Electronics
• /
• v.16 no.5
• /
• pp.1716-1724
• /
• 2016

This paper proposes both an active-switched quasi-Z-source inverter (AS-qZSI) and an extended active-switched qZSI (EAS-qZSI), which are based on the classic qZSI. The proposed AS-qZSI adds only one active switch and one diode to the classic qZSI for increasing the voltage boost capability. Compared with other topologies based on the switched-inductor/capacitor qZSI, the proposed AS-qZSI requires fewer passive components in the impedance network under the same boost capability. Additionally, the proposed EAS-qZSI is designed by adding one inductor and three diodes to the AS-qZSI, which offers enhanced boost capability and lower voltage stress across the switches. The performances of the two proposed topologies are verified by simulation and experimental results obtained from a prototype with a 32-bit DSP built in a laboratory.