• Proceedings of the Korean Institute of Intelligent Systems Conference
• /
• 2002.05a
• /
• pp.81-86
• /
• 2002

In current CBR(Case-Based Reasoning) systems, the case adaptation is usually performed by rule-based method that use rules hand-coded by the system developer. So, CBR system designer faces knowledge acquisition bottleneck similar to those found in traditional expert system design. In this thesis, 1 present a model for learning method of case adaptation knowledge using case base. The feature difference of each pair of cases are noted and become the antecedent part of an adaptation rule, the differences between the solutions in the compared cases become the consequent part of the rule. However, the number of rules that can possibly be discovered using a learning algorithm is enormous. The first method for finding cases to compare uses a syntactic measure of the distance between cases. The threshold fur identification of candidates for comparison is fixed th the maximum number of differences between the target and retrived case from all retrievals. The second method is to use similarity metric since the threshold method may not be an accurate measure. I suggest the elimination method of duplicate rules. In the elimination process, a confidence value is assigned to each rule based on its frequency. The learned adaptation rules is applied in riven target Problem. The basic. process involves search for all rules that handle at least one difference followed by a combination process in which complete solutions are built.

• Journal of Biomedical Engineering Research
• /
• v.28 no.6
• /
• pp.768-776
• /
• 2007

A new type of the fluid circulation blood pressure simulator was proposed to enhance the blood pressure simulator used for the development and evaluation of automatic sphygmomanometers. Various pressure waveform of fluid flowing in the pipe was reproduced by operating the proportional control valve after applying a pressure on the fluid in pressurized oil tank. After that, appropriate fluid was supplied by operating the proportional control valve, which enabled to reproduce various pressure wave of the fluid flowing in the tube. To accomplish this work, the mathematical model was carefully reviewed in cooperating with the proposed simulator. After modeling the driving signal as input signal and the pressure in internal tube as output signal, the simulation on system parameters such as internal volume, cross-section of orifice and supply pressure, which are sensitive to dynamic characteristic of system, was accomplished. System parameters affecting the dynamic characteristic were analyzed in the frequency bandwidth and also reflected to the design of the plant. The performance evaluator of fluid dynamic characteristic using proportional control signal was fabricated on the basis of obtained simulation result. An experimental apparatus was set-up and measurements on the dynamic characteristic, nonlinearity, and rising and falling response was carried out to verify the characteristic of the fluid dynamic model. Controller was designed and thereafter, simulation was performed to control the output signal with respect to the reference input in the fluid dynamic model using the proposed proportional control valve. Hybrid controller combined with an proportional controller and feed-forward controller was fabricated after applying a disturbance observer to the control plant. Comparison of the simulations between the conventional proportional controller and the proposed hybrid simulator indicated that even though the former showed good control performance.

• Journal of The Korean Association of Information Education
• /
• v.9 no.1
• /
• pp.113-124
• /
• 2005

In this study, we designed and developed a tool to help teachers select and develop effective performance assessment criteria considering characteristics of individual learners. Using this tool, we can analyze preferences of teachers and characteristics of students for each rubric by exploring the classification and association rules through data mining. Those findings can give us guidelines and insights for the development and the selection of performance assessment criteria. The classification rules found are used for the learner-centered evaluation reflecting learners' interests, capabilities, and circumstances. Association rules found are utilized for analyzing teachers' preference, which enable to reduce time and efforts for the development and selection of rubric. Also, this tool supports creation, change, and selection of teachers' rubric linked with the performance assessment of NEIS(National Education Information System).

• Journal of the Korean Institute of Intelligent Systems
• /
• v.7 no.4
• /
• pp.48-57
• /
• 1997

This paper presents the automatic construction and parameter optimization technique for fuzzy logic controllers using genetic algorithm. In general. the design of fuzzy logic controllers has difficulties in the acq~lisition of expert's knowledge and relies to a great extent on empirical and heuristic knowledge which, in many cases, cannot be objectively justified. So, the performance of the controllers c:an be degraded in the case of plant parameter variations or unpredictable incident which a designer may have ignored, and the parameters of fuzzy logic controllers obtained by expert's control action may not be optirnal. Some of these problems can be resolved by the use of genetic algorithm. The proposed method can tune the parameters of fuzzy logic controllers including scaling factors and determine: the appropriate number of fuzzy rulcs systematically. Finally, we provides the second order dead time plant to evaluate the feasibility and generality of the proposed method. Comparison shows that the proposed method can produce fuzzy logic controllers with higher accuracy and a smaller number of fuzzy rules than manually tuned fuzzy logic controllers.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.24 no.4
• /
• pp.403-411
• /
• 2014

In this paper, an algorithm of extracting the features of home appliances and automatically building a database to identify home appliances is designed and presented. For the verification, a software library supporting this algorithm is implemented and added to an power management system server, which was already implemented to support real-time monitoring of home appliances' power consumption status and controlling their power. The implemented system consists of a system server and clients, each of which measures the power consumed by a home appliance plugged in it and transmits the information to the server in real-time over a wireless network. Through experiments, it is verified that it is possible to identify any home appliance connected to a specific client.

• Transactions of the Korean hydrogen and new energy society
• /
• v.13 no.4
• /
• pp.270-278
• /
• 2002

Mg and Mg alloys are attractive hydrogen storage materials because of their lightweight and high absorption capacity. Their range of applications could be further extended if their hydrogenation properties and degradation behavior could be improved, The main emphasis of this study was to find an economic manufacturing method for Mg-Ti-Ni-H systems, and to investigate their hydrogenation properties, In order to examine hydrogenation behavior, a Sieverts type automatic pressure-composition-isotherm(PCI) apparatus was used and the experiments were performed at 423, 473, 523, 573, 623 and 673K. The results of thermogravimetric analysis(TGA) reveal that the absorbed hydrogen contents are around 2.5 wt% for ($Mg_9Ti_1$)-10 wt% Ni. With increased Ni content, the absorbed hydrogen content decreases to 1.7 wt%, whereas the dehydriding starting temperatures are lowered by some 70-100K. The results of PCI on ($Mg_9Ti_1$)-20 wt% Ni show that its hydrogen capacity is around 5.3 wt% and its reversible capacity and plateau pressure are also excellent at 523K and 573K. In addition, the reaction enthalpy, $\Delta$HD.plateau, is $30.6{\pm}5.7kJ/molH_2$.

• KSCE Journal of Civil and Environmental Engineering Research
• /
• v.34 no.1
• /
• pp.273-283
• /
• 2014

With the introduction of COBie (Construction Operation Building Exchange) in BIM technology enabling an automatic transfer of design and construction information to operation and management (O&M) phase, the BIM centric O&M management system development process has been tested on the subject of architectural types of building. However, for now, there is a need to investigate the technical feasibility of COBie application to civil structures including industrial facilities. This study takes both "O&M Guideline for Public Wastewater Treatment Plant" and a real wastewater treatment plant into account for the purpose, in which the latter is intended to supplement the result of the first. The findings are three-folds: (1) COBie, as an asset modeling, is not sufficient enough to encompass commissioning data, (2) more relevant IFC development and family library build-up useful to modeling wastewater treatment plant is imperative, and (3) well-planned coordination and organization of COBie data-set in line with O&M practice will enhance the feasibility of the COBie in industrial facilities. The result could be used for a basis study for COBie application, particularly in industrial facilities.

• Transactions of the Korean Society of Mechanical Engineers A
• /
• v.39 no.3
• /
• pp.337-345
• /
• 2015

High machining technology is needed for manufacturing jet engines for use in aircrafts. To reduce errors in the jet engine machining process, the machining companies of aircraft engines have introduced the CAM (computer-aided manufacturing) technology. However, to create a CAM model, the operator must manually conduct machining operations based on a CAD (computer-aided design) model, which can take several days or weeks. To solve this problem, this study proposes a method for automatically generating a CAM model for machining holes in the parts, using a CAD model. In this method, the features of the hole are recognized from the CAD model and translated into machining operations to be used with the CATIA program. Additionally, a prototype system was implemented and the proposed method was experimentally verified.

• Journal of Korea Society of Digital Industry and Information Management
• /
• v.10 no.2
• /
• pp.61-73
• /
• 2014

An automatic vehicle location tracing system is to build GIS server and on transmission for providing service in various ways by collecting a GPS location information from each vehicle. It is to save GPS data from OBU built-in on the vehicle and transmit the GPS data using the RSU on the roadside and WAVE communication technology. The collected data from the RSU is transmitted to the GIS server and stored in DB(database) and based on the GPS data that was collected from the each vehicle the system is to provide user service to suit the applications so it is to provide various services between RSU and OBU. In this paper, by implementing a multi-session process between the RM and the RMA a variety of services between RSU and OBU are provided. In addition, the system is designed and implemented using GPS to provide a variety of services, for the services provided from each RMA by configuring them as an independent session so it enables a variety of services implemented from one of RSU. With the result of the comparative analysis on the multi-session processing and single-session processing it shows that the differenes of them are minor in repect of the data loss rate and the data transfer rate but various services can be provided.

• Transactions of the Korean Society of Automotive Engineers
• /
• v.20 no.3
• /
• pp.119-125
• /
• 2012

Caliper intergrated Electric Parking Brake (EPB) is an automatic parking brake system, attached to rear caliper. Because EPB uses luxury vehicles recently, the drivers of vehicles are sensitive to the EPB noise. EPB is operated by the motor and gear, so noise is generated by motor and gear. In order to reduce noise, One of EPB manufacturers uses helical gear and changes the shape of EPB housing. But these methods are not optimized for reduction of interior noise. There are many noise transfer paths into vehicle interior and it is difficult to identify the noise sources. Therefore, in this study, we performed contribution analysis and modal testing in the vehicle system. It is possible to distinguish between air-borne noise and structure-borne noise in the vehicle interior noise by comparing interior noise peak with resonance mode map.