• Journal of Information Processing Systems
• /
• v.5 no.2
• /
• pp.41-68
• /
• 2009

Face recognition presents a challenging problem in the field of image analysis and computer vision, and as such has received a great deal of attention over the last few years because of its many applications in various domains. Face recognition techniques can be broadly divided into three categories based on the face data acquisition methodology: methods that operate on intensity images; those that deal with video sequences; and those that require other sensory data such as 3D information or infra-red imagery. In this paper, an overview of some of the well-known methods in each of these categories is provided and some of the benefits and drawbacks of the schemes mentioned therein are examined. Furthermore, a discussion outlining the incentive for using face recognition, the applications of this technology, and some of the difficulties plaguing current systems with regard to this task has also been provided. This paper also mentions some of the most recent algorithms developed for this purpose and attempts to give an idea of the state of the art of face recognition technology.

• Proceedings of the KWS Conference
• /
• 2002.10a
• /
• pp.82-88
• /
• 2002

Simulation systems allow a close inspection of the relation between welding parameters and the resulting weld seam. These systems are very useful in education of weld staff as well as production and planning. In training the influence of variations of parameters can be investigated without the need for real welding experiments. In the design phase requirements of the welding process can be taken into account without several iteration cycles. By estimating a good parameter set for the given welding task the set up phase for a new production cycle can be reduced

• Transactions on Control, Automation and Systems Engineering
• /
• v.3 no.3
• /
• pp.170-175
• /
• 2001

Q-learning is a kind of reinforcement learning where the agent solves the given task based on rewards received from the environment. Most research done in the field of Q-learning has focused on discrete domains, although the environment with which the agent must interact is generally continuous. Thus we need to devise some methods that enable Q-learning to be applicable to the continuous problem domain. In this paper, an extended fuzzy rule is proposed so that it can incorporate Q-learning. The interpolation technique, which is widely used in memory-based learning, is adopted to represent the appropriate Q value for current state and action pair in each extended fuzzy rule. The resulting structure based on the fuzzy inference system has the capability of solving the continuous state about the environment. The effectiveness of the proposed structure is shown through simulation on the cart-pole system.

• Transactions on Control, Automation and Systems Engineering
• /
• v.1 no.2
• /
• pp.147-152
• /
• 1999

It is an interesting area in the field of artifical intelligence to find an analytic model of cooperative structure for multiagent system accomplishing a given task. Usually it is difficult to design controllers for multi-agent systems without a comprehensive knowledge about the system. One of the way to overcome this limitation is to implement an evolutionary approach to design the controllers. This paper introduces the use of a genetic algorithm to discover a fuzzy logic controller with rules that govern emergent agents solving a pursuit problem in a continuous world. Simulation results indicate that, given the complexity of the problem, an evolutionary approach to find the fuzzy logic controller seems to be promising.

• Proceeding of Spring/Autumn Annual Conference of KHA
• /
• 2008.11a
• /
• pp.448-451
• /
• 2008

This study is under doing to suggest application manual using assembling reference plane design & standard finish material basis upon material classification code as a tool of a linkage between building design and construction standarization in order to enlarge the applicability of house building material that is produced by the module plant. We can say the goal of building standardization intend not only the improvement of construction productibility but also guarantee of subsequent performance through automatization basis upon informationalization of building design. For a etabilishing of this condition, it is neccessary to link the standardization's result of material--design--construction field. According to this neccessity, we are going to suggest information factor that can make relative business manager easily approach to the standardization practical task.

• Physical Therapy Korea
• /
• v.10 no.1
• /
• pp.97-108
• /
• 2003

Slipping during various kinds of movement often leads to potentially dangerous incidents of falling. The purpose of this paper was to review some of the research performed in the field including such topics as rating scales for balance, kinematics and kinetics of slipping, adaptation to slippery conditions, postural and balance control, and protective movement during falling. Controlling slipping and fall injuries requires a multifaceted approach. Environmental conditions (state of floor surface, tidiness, lighting, etc), work task (walking, carrying, pushing, lifting, etc), and human behavior (anticipation of hazards, adaptation to risks, risk taking, etc) must be accounted for in the assessment of slip and fall-related risks. Future directions of research must deal with modeling of basic tribophysical, biomechanical, and postural control process involved in slipping and falling.

• Journal of Advanced Marine Engineering and Technology
• /
• v.38 no.8
• /
• pp.1000-1003
• /
• 2014

There are 70 vertical and 70 horizontal correctors for Pohang Light Source. Until mid of 2000, power supplies for these correctors were based on 1990's technology, so the global orbit feedback system was not possible with poor 12 bit resolution. A new task force team was assembled to develop new power supplies with BESSY type DAC cards. After the project, two vertical correctors in each lattice were connected with new power supplies, and the global orbit feedback was available within the accuracy of 5 microns. However, this replacement was not enough to satisfy the beam stability requirement of 2 microns for PLS. We have launched another power supply design based on all digital technology. This attempt was completed within a year, and 80 units were assembled in house. Currently, the global orbit feedback system is running successfully with new digital power supplies and the compensation of chamber motion due to the thermal load by using digital displacement transducers attached on each BPMs.

• Journal of IKEEE
• /
• v.11 no.4
• /
• pp.297-306
• /
• 2007

A sensor network is composed of a large number of sensor nodes that are densely deployed in a field. Each sensor performs a sensing task for detection specific events. After detecting this event, location information of the sensor node is very important. Range-based scheme of the proposed approaches typically achieve high accuracy on either node-to-node distances or angles, but this scheme have a drawback because all sensor nodes have the special hardware. On the other hand, range-free scheme provides economic advantage because of no needed hardware even if that leads to coarse positioning accuracy. In this paper, we propose a range-free localization algorithm without range information in wireless sensor networks. This is a range-free approach and uses a small number of anchor nodes and known sensor nodes. This paper develops a localization mechanism using the geometry conjecture (perpendicular bisector of a chord). The conjecture states that a perpendicular bisector of a chord passes through the center of the circle.

• Journal of the Korean Society for Precision Engineering
• /
• v.30 no.4
• /
• pp.375-382
• /
• 2013

Down through the years, human needs and desires have required a robot system to work at hazardous environments instead. Current painting task is costly and laborious, and it exposes workers to significant health and safety risks. Automation system offers potential improvement in this area and is especially well suited to the outer-wall painting tasks in concrete structures. This paper introduces the result of gondola-type building management robot(G-BMR) platform and mechanism for moving/tasking on building outer-wall for the outer-wall painting. Its technical and economic feasibility are conducted, and it is concluded that developing G-BMR is physically and economically feasible in this research. And we discuss about the future of G-BMR and automation in construction field.

• Journal of Electrical Engineering and Technology
• /
• v.8 no.3
• /
• pp.559-564
• /
• 2013

In this paper a new hybrid forecast method composed of wavelet transform and neural network is proposed to forecast the wind speed more accurately. In the field of wind energy research, accurate forecast of wind speed is a challenging task. This will influence the power system scheduling and the dynamic control of wind turbine. The wind data used here is measured at 15 minute time intervals. The performance is evaluated based on the metrics, namely, mean square error, mean absolute error, sum squared error of the proposed model and compared with the back propagation model. Simulation studies are carried out and it is reported that the proposed model outperforms the compared model based on the metrics used and conclusions were drawn appropriately.