• Journal of the Korean Institute of Telematics and Electronics B
• /
• v.33B no.2
• /
• pp.140-148
• /
• 1996

This paper proposes a combined feedforward/feedback controller which uses jacobians of neural network. The jacobians are calculated form the neural network that identifies the nonlinear plant, which are used for designing a jacobian controller and for training a neural network controller. Normally, it takes much time to train the neural network controller. Combining the neural and the jacobian controller, it can be a stable controller from the beginning of training phase of neural network, and it can be implemented as a learning-while-functioning controller. Simulated resutls for the proposed controller show its effectiveness and better performances.

• Journal of information and communication convergence engineering
• /
• v.18 no.3
• /
• pp.183-187
• /
• 2020

The general Wi-Fi network connection structure is that a number of IoT (Internet of Things) sensor nodes are directly connected to one AP (Access Point) node. In this structure, the range of the network that can be established within the specified specifications such as the range of signal strength (RSSI) to which the AP node can connect and the maximum connection capacity is limited. To overcome these limitations, multiple middleware bridge technologies for dynamic scalability and load balancing were studied. However, these network expansion technologies have difficulties in terms of the rules and conditions of AP nodes installed during the initial network deployment phase In this paper, an intelligent edge computing IoT device is developed for constructing an intelligent autonomous cluster edge computing network and applying it to real-time road danger context aware and notification system through an intelligent risk situation recognition algorithm.

• Electronics and Telecommunications Trends
• /
• v.4 no.1
• /
• pp.35-43
• /
• 1989

The evolution of telecommunications has raised the profile of many segments of the network that were not previously considered important. Until recently, basic telephony existed with the extension of passive cables without any particular user network interface. In the area of data communications, the introduction of flexible packet switching has allowed the network to evolve in a far more efficient manner. To overcome such separated network problems and business needs of both users and network providers, the integrated narrowband ISDN concept is being developed in most countries for implementation in the public switched telephone network (PSTN). The targets of ISDN, in my opinion, can be explained as follows : To the user, ISDN should provide the services at any time, at any place, through any media. To the business customer using PABX or LAN applications, ISDN should introduce customized services rapidly and also, ISDN should be developed by the modular hardware and software design approach in order for new services to be introduced rapidly and effectively. Software can be also developed by non-expert local staff to cater for adopting new user's service requirements immediately. Finally, ISDN will be able to increase business chances and benefit both users and operating companies.

• Proceedings of the Korean Reliability Society Conference
• /
• 2000.11a
• /
• pp.405-409
• /
• 2000

The flow network is considered to be in a functioning state if it can transmit a maximum flow which is greater than or equal to a specified amount of flow. In this paper we consider the measures of importance of a link in the flow network. We define the structural importance and reliability importance of link when the required amount of flow is given. Also, we present the performance importance of link in a flow network. The performance importance can be used to determine which links should be improved first in order to make the greatest improvement in performance of the network. Numerical examples are presented for illustrative purpose.

• Journal of Fisheries and Marine Sciences Education
• /
• v.26 no.4
• /
• pp.760-768
• /
• 2014

Yet logistics base in China has a refrigerated storage facilities installed areas, the number of those is very limited and is generally insufficient. According to these especial points, a new construction cold chain logistics network design strategy is required from how to use the existing refrigerated warehouses to new issue. For example, however refrigerated storage facility is supplied, can it satisfy all demand of this area? Then does it have optimized location of this area? If future demand expansion, adding that already other refrigerated storage facilities matter? Or, add another refrigerated facilities, optimum cold chain established a network matter? So on. Above problems can be occurred. In order to solve facing many of these issues of distribution network, northeast area in China has been selected as a subject, and we designed a new cold chain distribution network.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.2 no.3
• /
• pp.135-149
• /
• 2008

Traditional attack detection schemes based on packets or flows have very high computational complexity. And, network based anomaly detection schemes can reduce the complexity, but they have a limitation to figure out the pattern of the distributed global scale network attack. In this paper, we propose an efficient and fast method for detecting distributed global-scale network attack symptoms in high-speed backbone networks. The proposed method is implemented at the aggregate traffic level. So, our proposed scheme has much lower computational complexity, and is implemented in very high-speed backbone networks. In addition, the proposed method can detect attack patterns, such as attacks in which the target is a certain host or the backbone infrastructure itself, via collaboration of edge routers on the backbone network. The effectiveness of the proposed method are demonstrated via simulation.

• Journal of Communications and Networks
• /
• v.16 no.6
• /
• pp.645-655
• /
• 2014

Latency, an identified element of Internet protocol (IP) mobility protocol execution, can reduce handover performance in mobile networks. Although the performance can be improved by applying an effective network-based IP mobility scheme in place of the traditional host-based alternatives, the existing inter-domain extensions of network-based IP mobility continue to suffer from an extended handover latency. This paper proposes a new inter-domain network-based IP mobility scheme based on node movement prediction. The proposed scheme accelerates the handover by preparing the future domain of the mobile node in a proactive manner. Analytical and simulation-based evaluations confirm improved performance of the proposed scheme in terms of handover latency and packet loss compared with existing schemes.

• International Journal of Fuzzy Logic and Intelligent Systems
• /
• v.3 no.2
• /
• pp.215-221
• /
• 2003

Generally, we want to be searched the newest as well as some appropriate personalized information from the internet resources. However, it is a complex and repeated procedure to search some appropriate information. Moreover, because the user's interests are changed as time goes, the real time modeling of a user's interests should be necessary. In this paper, I propose PREA system that can search and filter documents that users are interested from the World Wide Web. And then it constructs the user's interest model by a modified spreading neural network. Based on this network, PREA can easily produce some queries to search web documents, and it ranks them. The conventional spreading neural network does not have a visualization function, so that the users could not know how to be configured his or her interest model by the network. To solve this problem, PREA gives a visualization function being shown how to be made his interest user model to many users.

• 제어로봇시스템학회:학술대회논문집
• /
• 2000.10a
• /
• pp.111-111
• /
• 2000

The research of network system, being used to reduce automotive wiring harness, is reaching to the development of by-wire system. It is by-wire system that apply IVN(In-Vehicle-Network) to steering, braking system, and it has the advantage of mass-decreasing, easy to diagnose fault and so on. But until now, many developed device can't satisfied with reliability that system have ever had. So redundancy of each network module, i.e., It is only way to make backup module. This paper researches development of network module and redundancy management of backup module when error occurred for implementation of brake-by-wire system.

• 제어로봇시스템학회:학술대회논문집
• /
• 2000.10a
• /
• pp.196-196
• /
• 2000

This paper describes a lateral guidance system of an autonomous vehicle, using a neural network model of magneto-resistive sensor and magnetic fields. The model equation was compared with experimental sensing data. We found that the experimental result has a negligible difference from the modeling equation result. We verified that the modeling equation can be used in simulations. As the neural network controller acquires magnetic field values(B$\_$x/, B$\_$y/, B$\_$z/) from the three-axis, the controller outputs a steering angle. The controller uses the back-propagation algorithms of neural network. The learning pattern acquisition was obtained using computer simulation, which is more exact than human driving. The simulation program was developed in order to verify the acquisition of the teaming pattern, teaming itself, and the adequacy of the design controller. The performance of the controller can be verified through simulation. The real autonomous electric vehicle using neural network controller verified good results.