• Journal of Korea Society of Industrial Information Systems
• /
• v.17 no.1
• /
• pp.63-71
• /
• 2012

Most of sensor networks are difficult to be debugged, verified, and upgraded once they are deployed in the fields, for they are usually deployed in real world and large scale. Therefore, before deploying the sensor networks, we should test and verify them sufficiently in realistic testbeds. However, since we need to control physical environments which interact with sensor networks, it takes much of time and cost to test and verify sensor networks at the level of resource-constrained sensor nodes in such environments. This paper proposes an efficient software framework for evaluating and verifying sensor networks in the view points of network and application operations (i.e., accuracy of sensing algorithms). Applying the proposed software framework to the development of a simulator for a smart parking application based on wireless sensor network, this paper verifies the feasibility of the proposed framework.

• Journal of IKEEE
• /
• v.15 no.3
• /
• pp.227-234
• /
• 2011

The Interest in robotics has been steadily increasing in recent times both in Korea as well as abroad. Research on robots for new and diverse fields is ongoing. This study discusses the current research and development on robot actuator, which are used to control the joints of robots, and focuses on developing more efficient technology for joint control, as compared with the current technologies. It also aims to find means to apply the abovementioned technology to diverse industrial fields. We found that easy and effective control of actuators could be achieved by using ZigBee sensor networks, which were widely being used on wireless communications. Throughout the experiments it is proved that the developed wireless actuator could be used for easy control of various robot joints. This technology can be effectively applied to develop two-legged robots that will be able to walk like human, or even quadruped and hexapod robots. It can also be applied to motors used in industry. In this study, we develop an extremely minimized ZigBee sensor network module that can be used to control various servo motors with low power consumption even if it is long distances. We realized effective wireless control by optimizing the ZigBee antenna, and were able to quickly check the status of relevant Tree node through mutual communication between the servo motors composing the ZigBee sensor network and the main server control modules. The developed Servo Motor with ZigBee sensor network modules can be applied in both robotics as well as for home or factory automation.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.11 no.10
• /
• pp.3935-3941
• /
• 2010

With the advent of high-speed communications networks, many authentication and access control systems are being introduced to combat network security issues like system hacking. But the fact is that the security systems for protecting information used in these networks are themselves weak. In response to the mounting demands of existing users, there is a clear need for a new authentication system that provides both safety and reliability. This research presents an authentication method with excellent access authorization (explicit and implicit authentication) and safety performance, demonstrated through its use in online networks.

• Proceedings of the KAIS Fall Conference
• /
• 2006.05a
• /
• pp.316-319
• /
• 2006

Connectionist networks, also called neural networks, have been broadly applied to solve many different problems since McCulloch and Pitts had shown mathematically their information processing ability in 1943. In this thesis, we present a genetic neuro-control scheme for nonlinear systems. Our method is different from those using supervised learning algorithms, such as the backpropagation (BP) algorithm, that needs training information in each step. The contributions of this thesis are the new approach to constructing neural network architecture and its training.

• ETRI Journal
• /
• v.37 no.5
• /
• pp.917-921
• /
• 2015

We consider a multiserver system with two classes of customers with preemption, which is a widely used system in the analysis of cognitive radio networks. It is known that the optimal admission control for this system is of threshold type. We express the expected total discounted profit using the total number of customers, thus reducing the stochastic optimization problem with a two-dimensional state space to a problem with a one-dimensional birth-and-death structure. An efficient algorithm is proposed for the calculation of the expected total discounted profit.

• Proceedings of the KAIS Fall Conference
• /
• 2008.05a
• /
• pp.152-156
• /
• 2008

We consider the problem of constructing observers for nonlinear systems with unknown inputs. Connectionist networks, also called neural networks, have been broadly applied to solve many different problems since McCulloch and Pitts had shown mathematically their information processing ability in 1943. In this thesis, we present a genetic neuro-control scheme for nonlinear systems. Our method is different from those using supervised learning algorithms, such as the backpropagation (BP) algorithm, that needs training information in each step. The contributions of this thesis are the new approach to constructing neural network architecture and its training.

• Smart Structures and Systems
• /
• v.23 no.4
• /
• pp.393-403
• /
• 2019

Applying more features gives us better accuracy in modeling; however, increasing the inputs causes the curse of dimensions. In this paper, a new structure has been proposed for fault detecting and identifying (FDI) of high-dimensional systems. This structure consist of two structure. The first part includes Auto-Encoders (AE) as Deep Neural Networks (DNNs) to produce feature engineering process and summarize the features. The second part consists of the Local Model Networks (LMNs) with LOcally LInear MOdel Tree (LOLIMOT) algorithm to model outputs (multiple models). The fault detection is based on these multiple models. Hence the residuals generated by comparing the system output and multiple models have been used to alarm the faults. To show the effectiveness of the proposed structure, it is tested on single-shaft industrial gas turbine prototype model. Finally, a brief comparison between the simulated results and several related works is presented and the well performance of the proposed structure has been illustrated.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.39B no.5
• /
• pp.291-295
• /
• 2014

This paper presents the implementation of industrial wireless network for real-time control system and the performance evaluation on the implemented system. We propose the hybrid network architecture of wired EtherCAT and wireless 802.15.4e. For performance evaluation, we use the reference model of inverse pendulum system. Through the performance evaluation on our testbed system, it is verified that our proposed system can be applied to industrial real-time control system.

• Journal of Korean Society of Industrial and Systems Engineering
• /
• v.24 no.66
• /
• pp.19-26
• /
• 2001

I propose the control chart pattern to provide a more comprehensive scheme for detecting process X and R shifts using individual observations in start-up process. It is important to automate the identification of special disturbances to facilitate real-time manufacturing. This papers formulates X-R charts for interpretation by artificial neural networks. In this papers, which uses the backpropagation algorithm, two samples are fed into the trained neural network to provide outputs ranging from 0 to 1. Simulation results sow that the performance of the proposed control chart using the neural network(NNCC) is quite promising. Using these NN charts, guidelines are given for detecting and classifying process X and R shifts.

• Proceedings of the KIEE Conference
• /
• 2007.11b
• /
• pp.46-47
• /
• 2007

SCADA (Supervisory Control and Data Acquisition) system has been used fur remote measurement and control on the critical infrastructures as well as modem industrial facilities. As cyber attacks increase on communication networks. SCADA network has been also exposed to cyber security problems. Especially, SCADA systems of energy industry such as electric power, gas and oil are vulnerable to targeted cyber attack and terrorism. Recently, many research efforts to solve the problems have made progress on SCADA network security. In this paper, we introduce recent security issue of SCADA network and propose the application of encryption method to Korea SCADA network.