• Journal of Institute of Control, Robotics and Systems
• /
• v.21 no.6
• /
• pp.518-523
• /
• 2015

This paper proposes a gait phase classifier using a Recurrent Neural Network (RNN). Walking is a type of dynamic system, and as such it seems that the classifier made by using a general feed forward neural network structure is not appropriate. It is known that an RNN is suitable to model a dynamic system. Because the proposed RNN is simple, we use a back propagation algorithm to train the weights of the network. The input data of the RNN is the lower body's joint angles and angular velocities which are acquired by using the lower limb exoskeleton robot, ROBIN-H1. The classifier categorizes a gait cycle as two phases, swing and stance. In the experiment for performance verification, we compared the proposed method and general feed forward neural network based method and showed that the proposed method is superior.

• Journal of Convergence for Information Technology
• /
• v.10 no.7
• /
• pp.1-6
• /
• 2020

A new resource management algorithm is proposed for 5G networks which have a coordinated network architecture. By sharing the contol information among multiple neighbor cells and managing in centralized structure, the propsed algorithm fully utilizes the benefits of network coordination to increase fairness and throughput at the same time. This optimization of network performance is achieved while operating within a tolerable amount of signaling overhead and computational complexity. Simulation results confirm that the proposed scheme improve the network capacity up to 40% for cell edge users and provide network-wise fairness as much as 23% in terms of the well-knwon Jain's Fainess Index.

• The Journal of Korean Association of Computer Education
• /
• v.12 no.2
• /
• pp.77-86
• /
• 2009

Large-scale applications, that needs large-capacity R&D resources and realtime data transmission, have demanded more stable and high-performance network environment than current Internet environments. Recently, global R&D networks have focuses on utilizing Lambda networking technologies and resource reservation systems to be satisfied with various applications' requirements. In this paper, we modify the existing DRS (Dynamic Right-Sizing) model to reflect various advantages in terms of the stability and high-capacity of Lambda network. In addition, we suggest the design methodology of high-performance Lambda network, which can integrate NRPS (Network Resource Provisioning System) into our modified DRS model.

• The Transactions of the Korean Institute of Power Electronics
• /
• v.25 no.1
• /
• pp.6-12
• /
• 2020

In recent years, the demand for the distribution of energy resource has been increasing. However, the output power is limited by the stability of the distribution network. This study proposes an active distribution network that can reconfigure the distribution line using an active phase controller. The conventional distribution network has a fixed structure, whereas the proposed active distribution network has a variable structure. Therefore, the active distribution network can increase the output power of the distribution energy resource and reduce the overload of distribution line facilities. The active phase controller has two operation modes to minimize the circulating current during dynamic reconfiguration. In this study, the voltage and current control algorithms are proposed for the active phase controller. The proposed method for the active phase controller is simulated via PSIM simulation.

• International Journal of Computer Science & Network Security
• /
• v.21 no.2
• /
• pp.77-87
• /
• 2021

In this study, a novel improved second order Radial Basis Function Neural Network based method with excellent scheduling capabilities is used for the dynamic prediction of short and long-term energy required applications. The effectiveness and the reliability of the algorithm are evaluated using training operations with New England-ISO database. The dynamic prediction algorithm is implemented in Matlab and the computation of mean absolute error and mean absolute percent error, and training time for the forecasted load, are determined. The results show the impact of temperature and other input parameters on the accuracy of solar Photovoltaic load forecasting. The mean absolute percent error is found to be between 1% to 3% and the training time is evaluated from 3s to 10s. The results are also compared with the previous studies, which show that this new method predicts short and long-term load better than sigmoidal neural network and bagged regression trees. The forecasted energy is found to be the nearest to the correct values as given by England ISO database, which shows that the method can be used reliably for short and long-term load forecasting of any electrical system.

• Journal of Internet Computing and Services
• /
• v.23 no.5
• /
• pp.17-23
• /
• 2022

Network slicing is a promising paradigm and significant evolution for adjusting the heterogeneous services based on different requirements by placing dynamic virtual network functions (VNF) forwarding graph (VNFFG) and orchestrating service function chaining (SFC) based on criticalities of Quality of Service (QoS) classes. In system architecture, software-defined networks (SDN), network functions virtualization (NFV), and edge computing are used to provide resourceful data view, configurable virtual resources, and control interfaces for developing the modified deep reinforcement learning agent (MDRL-A). In this paper, task requests, tolerable delays, and required resources are differentiated for input state observations to identify the non-critical/critical classes, since each user equipment can execute different QoS application services. We design intelligent slicing for handing the cross-domain resource with MDRL-A in solving network problems and eliminating resource usage. The agent interacts with controllers and orchestrators to manage the flow rule installation and physical resource allocation in NFV infrastructure (NFVI) with the proposed formulation of completion time and criticality criteria. Simulation is conducted in SDN/NFV environment and capturing the QoS performances between conventional and MDRL-A approaches.

• 제어로봇시스템학회:학술대회논문집
• /
• 1997.10a
• /
• pp.215-218
• /
• 1997

A dynamic back-propagation neural network is addressed for adaptive neural control system to approximate non-linear control system rather than static networks. It has the capability to represent the approximation of nonlinear system without mathematical analysis and to carry out the on-line learning algorithm for real time application. The simulated results show fast tracking capability and adaptive response by using dynamic back-propagation neurons.

• Proceedings of the Korean Operations and Management Science Society Conference
• /
• 1996.04a
• /
• pp.570-573
• /
• 1996

The evaluation test for the operation of rotary type surface mounters which consist of the reel axis, the index table and the X-Y table, has been performed by comparing the new method with the old one in only fields. Because the problem seeking for the optimal operation of rotary type surface mounters, is NP complete, it is almost impossible to get the optimal solutions of large problems. This paper deals with a dynamic network modeling, which can reduce the effort, the cost, and the time used for the performance test of rotary type surface mounters.

• Proceedings of the Optical Society of Korea Conference
• /
• 2005.02a
• /
• pp.162-163
• /
• 2005

One of the most important things in EPON(Ethernet Passive Optical Network) is that ONUs(Optical Network Units) have to share a channel in upstream direction. We proposed a new algorithm of Dynamic Bandwidth Allocation using Multiple LLID(Logical Link IDentifier). We show how to allocate bandwidth in Queues for improving performance from Bandwidth using Multiple LLID.

• IE interfaces
• /
• v.14 no.4
• /
• pp.374-384
• /
• 2001

The objective of this paper is to design the dynamic route guidance system(DRGS) and develop a genetic algorithm(GA) for finding the multiple shortest paths in real traffic network. The proposed GA finds a collection of paths between source and destination considering turn-restrictions, U-turn, and P-turn that are genetically evolved until an acceptable solution is reached. This paper also shows the procedure to find the multiple shortest paths in traffic network of Seoul.