• Proceedings of the Korean Institute of Electrical and Electronic Material Engineers Conference
• /
• 2001.11b
• /
• pp.46-51
• /
• 2001

For Fast Real-time Recognition of Nonlinear Error Data, a new Neural Network algorithm which recognized the map in real time is proposed. The proposed neural network technique is the real time computation method through the inter-node diffusion, In the network, a node corresponds to a state in the quantized input space. Each node is composed of a processing unit and fixed weights from its neighbor nodes as well as its input terminal. The most reliable algorithm derived for real time recognition of map, is a dynamic programming based algorithm based on sequence matching techniques that would process the data as it arrives and could therefore provide continuously updated neighbor information estimates. Through several simulation experiments, real time reconstruction of the nonlinear map information is processed,

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2002.11a
• /
• pp.770-774
• /
• 2002

Recently, most of the embedded system have the function of multimedia information processing and network connecting. This make the overall system more complicated and need a new approach. Moreover the embedded system must be real-time system, which are different with Linux is constructed and the kernel is redesigned on the strong-arm board in order to make the real-time embedded web-server system.

• Proceedings of the Korean Institute of Electrical and Electronic Material Engineers Conference
• /
• 2001.11a
• /
• pp.46-51
• /
• 2001

For Fast Real-time Recognition of Nonlinear Error Data, a new Neural Network algorithm which recognized the map in real time is proposed. The proposed neural network technique is the real time computation method through the inter-node diffusion. In the network, a node corresponds to a state in the quantized input space. Each node is composed of a processing unit and fixed weights from its neighbor nodes as well as its input terminal. The most reliable algorithm derived for real time recognition of map, is a dynamic programming based algorithm based on sequence matching techniques that would process the data as it arrives and could therefore provide continuously updated neighbor information estimates. Through several simulation experiments, real time reconstruction of the nonlinear map information is processed.

• Proceedings of the KIEE Conference
• /
• 1995.11a
• /
• pp.534-538
• /
• 1995

In this paper, a realization of a real-time train information system(TIS) is discussed. The requirements of TIS which satisfy real-time constraints are analyzed in view of data transfer. For efficient data communication in TIS, a new network system is suggested and its real-time characteristics are analyzed and compared with the standard network system. A local unit is designed based on VMEbus system.

• The Transactions of the Korean Institute of Electrical Engineers D
• /
• v.52 no.11
• /
• pp.644-649
• /
• 2003

This study develops an analytical model for the delay analysis of real-time data in the token-passing service of Foundation Fieldbus(FF). Using the analytical model, this study proposes a network design scheme of FF Two design criteria are introduced in this study; one is the average delay of real-time data, and the other is the maximum allowable delay of real-time data. The network design scheme determines the network parameters that satisfies the performance requirements given by these design criteria.

• Proceedings of the KIEE Conference
• /
• 2003.11c
• /
• pp.797-801
• /
• 2003

In this paper, a real-time communication method using a PICNET-NP (Plant Instrumentation and Control Network for Nuclear Power plant) is proposed with an analysis of the control network requirements of DCS (Distributed Control System) in nuclear power plants. The method satisfies deadline in case of worst data traffics by considering aperiodic and periodic real-time data and others.

• 제어로봇시스템학회:학술대회논문집
• /
• 2001.10a
• /
• pp.133.3-133
• /
• 2001

This paper analyses the real-time performance of Ethernet based intranet whether it is applicable to the real-time network. Unpredictability of transmission delay by collision-delay-retransmission mechanism in CAMA/CD(Carrier Sense Multiple Access with Collision Detect) of Ethernet is the major reason making hard to apply to real-time system. Both retransmission mechanism of TCP(Transmission Control Protocol) for reliability and sliding windows algorithm for high utilization make hard to predict transmission delay. Because real-time control network require fast responsibility and bustle of short-periodic messages, global-clock for collision avoidance and UDP(User Datagram Protocol) for high utilization of network are used. The mathematical models for time-delay that can be occured between ...

• 제어로봇시스템학회:학술대회논문집
• /
• 2000.10a
• /
• pp.58-58
• /
• 2000

As many sensors and actuators are used in various automated systems, the application of network system to real-time distributed control is gaining acceptance in many industries. In order to take advantages of the network technique. however, network implementation should be carefully designed to satisfy real-time constraints and to consider network delays. This paper presents the implementation of feedback control system in Profibus-DP. Profibus-DP is a type of fieldbus protocols that are specifically designed to interconnect simple devices with fast I/O data exchange. As feedback control in profibus-DP is implemented, Network delays is found with influence of system performance. We analyze network delays in Profibus-DP into 3 reasons - dead time in Profibus interface, protocol delay, delay by asynchronization. In order to compensate the network delays, we introduce control algorithms with time delay concept. The results show that network delay can be compensated.

• Journal of the Korean Society of Systems Engineering
• /
• v.13 no.2
• /
• pp.9-17
• /
• 2017

Concept development of a real-time Field Programmable Gate Array (FPGA)-based switched Ethernet data communication network for the Man-Machine Interface System (MMIS) is presented in this paper. The proposed design discussed in this research is based on the systems engineering (SE) approach. The design methodology is effectively developed by defining the concept development stage of the life-cycle model consisting of three successive phases, which are developed and discussed: needs analysis; concept exploration; and concept definition. This life-cycle model is used to develop an FPGA-based time-triggered Ethernet (TTE) switched data communication network for the non-safety division of MMIS system to provide real-time data transfer from the safety control systems to the non-safety division of MMIS and between the non-safety systems including control, monitoring, and information display systems. The original IEEE standard 802.3 Ethernet networks were not typically designed or implemented for providing real-time data transmission, however implementing a network that provides both real-time and on-demand data transmission is achievable using the real-time Ethernet technology. To develop the design effectively, context diagrams are implied. Conformance to the stakeholders needs, system requirements, and relevant codes and standards together with utilizing the TTE technology are used to analyze, synthesize, and develop the MMIS non-safety data communication network of the APR1400 nuclear power plant.

• KIPS Transactions on Computer and Communication Systems
• /
• v.12 no.2
• /
• pp.53-60
• /
• 2023

Recently, the demand and traffic volume for various multimedia contents are rapidly increasing through real-time streaming platforms. In this paper, we predict real-time streaming traffic to improve the quality of service (QoS). Statistical models have been used to predict network traffic. However, since real-time streaming traffic changes dynamically, we used recurrent neural network-based deep learning models rather than a statistical model. Therefore, after the collection and preprocessing for real-time streaming data, we exploit vanilla RNN, LSTM, GRU, Bi-LSTM, and Bi-GRU models to predict real-time streaming traffic. In evaluation, the training time and accuracy of each model are measured and compared.