• 제어로봇시스템학회:학술대회논문집
• /
• 1989.10a
• /
• pp.296-301
• /
• 1989

As a cornerstone of assembly automation, the automatic part feeders are used to feed the various kind of the parts to the assembly workstation in the desired order and fashion. In this paper, EXPERT SYSTEM consisting of the data base for the feeding functions and part properties plus the rule base for the selection of feeder types is developed. The symbolic data of the part properties are used as basic factors in the selection rule of the suitable feeder types.

• Proceedings of the Korean Institute of Intelligent Systems Conference
• /
• 1996.10a
• /
• pp.162-165
• /
• 1996

In this paper, we proposed an optimization method of the membership function and the numbers of fuzzy rule base for the stabilization controller of the inverted pendulum system by genetic algorithm(GAs). Conventional methods to these problems need to an expert knowledge or human experience. The proposed genetic algorithm method will tune automatically the input-output membership parameters and will optimize their rule-base.

• Proceedings of the KIEE Conference
• /
• 2007.11b
• /
• pp.255-257
• /
• 2007

Korea electricity market consists of two payment systems, capacity and energy. Capacity payments are given to the generators according to its hourly availability considering hourly and seasonal weighting factors. Energy payments are settled at the marginal generation cost based on generator variable cost. In 2007, base load energy market is closed and single capacity payment system is begun to apply in electricity market. In this revised market rule, energy price cap for base load generators is newly introduced. We analyze impact of market rule revision in 2007 on base load generators and suggest improvement scheme to enforce market system in this study.

• Proceedings of the Korean Society of Precision Engineering Conference
• /
• 1997.04a
• /
• pp.724-728
• /
• 1997

A CAD system of grid element for vacuum fluorescent disply has been developed. In order to reduce design man-houre and human erros, it is used to automate the design process using a knowledge base system. In the case of VFD product design, the most important consideration is the short-life cycle. So the development of CAD system for VFD product is needed. The developed system is based on the knowledge base system which is involved in a lot of expert's technology in the practice field. Using C-language under the HP-UNIX system, CIS customer language of the EXCESS CAD/CAM is used as the overall CAD environment. Results of this system will provide effective aids to the designer in this field

• Proceedings of the Korean Society for Noise and Vibration Engineering Conference
• /
• 2001.11b
• /
• pp.633-639
• /
• 2001

This paper proposes a knowledge-based expert system. which is assembled into hardware organized with sensor module. AID converter, USB. data acquisition PC and software composed of monitoring and diagnosis module combined with a frame-based method using Sohre's chart and a rule-based method. Vibration signals using various sensors are acquired by AID converter. transferred into PC and processed to obtain a continuous monitoring of the machine status displayed into several plots. Through combining frame-base which covers wide vibration causes with rule-base which gives relatively specified diagnosis results, high accuracy of fault diagnosis can be guaranteed and knowledge base can be easily extended by adding new causes or symptoms. Some examples using experimental data show the good feasibility of the proposed algorithm for condition monitoring and diagnosis of industrial rotating machinery.

• Journal of Korean Ophthalmic Optics Society
• /
• v.5 no.2
• /
• pp.27-31
• /
• 2000

As the functional test of cornea. The clinical value of keratometric information was important for assessment the curvature of the cornea, the quality of the corneal surface, the stability of the corneal curvature, and the direction of the corneal astigmatism. This study was performed the comparative analysis of male and female of adult on the base curve, power and astigmatism of the Cornea. On the corneal base curve, the male right eye was 7.656 mm in vertical and 7.966 mm in horizontal. But, the male left cornea was 7.714 mm in vertical base curve and 8.026 mm in horizontal base curve. On the other hand, the female right eye cornea was 7.559 mm in vertical base curve and 7.695 mm in horizontal base curve. But, the female left eye cornea was 7.444 mm in vertical base curve and 7.742 mm in horizontal base curve. On the corneal diopter power, the male right eye was 44.063 diopter in vertical and 43.738 diopter in horizontal. But the male left eye was 44.046 diopter in vertical and 42.304 diopter in horizontal. On the other hand, the female right eye was 44.082 diopter in vertical and 43.77 diopter in horizontal. But, the female left eye was 44.347 diopter in vertical and 43.495 diopter in horizontal. According to the corneal astigmatism axis. The male right eye have 89.9% positive for with the - rule astigmatism, and 8.1 % positive for against - the - rule astigmatism. But, he male left eye have 91.89% positive for with - the - rule astigmatism, and 8.11 % positive for against - the - rule astigmatism. On the other hand, The female right eye have 76.92% positive for with - the - rule astigmatism, and 23.08 % positive for against - the - rule astigmatism. But, the female left have 80.76 % positive for with - the - rule astigmatism, and 17.31 % positive for against - the - rule as tigmatism. The diopter power of corneal astigmatism have 25.57% positive for behind 1 diopter, 44.89% positive for 1 diopter, 18.18% positive for 2 diopter, 5.11% positive for 3 diopter and 6.25% positive for over 4 diopter.

• Proceedings of the Korean Institute of Intelligent Systems Conference
• /
• 2005.11a
• /
• pp.271-275
• /
• 2005

In this research, we propose a Unified Fuzzy rule-based knowledge Inference Systems UFIS) to help the expert in cosmetic brand detection. Users' preferred cosmetic product detection is very important in the level of CRM. To this Purpose, many corporations trying to develop an efficient data mining tool. In this study, we develop a prototype fuzzy rule detection and inference system. The framework used in this development is mainly based on two different mechanisms such as fuzzy rule extraction and RDB (Relational DB)-based fuzzy rule inference. First, fuzzy clustering and fuzzy rule extraction deal with the presence of the knowledge in data base and its value is presented with a value between $0\∼1$. Second, RDB and SQL(Structured Query Language)-based fuzzy rule inference mechanism provide more flexibility in knowledge management than conventional non-fuzzy value-based KMS(Knowledge Management Systems)

• International Journal of Fuzzy Logic and Intelligent Systems
• /
• v.5 no.4
• /
• pp.353-359
• /
• 2005

In this research, we propose a Unified Fuzzy rule-based knowledge Inference Systems (UFIS) to help the expert in cosmetic brand detection. Users' preferred cosmetic product detection is very important in the level of CRM. To this purpose, many corporations trying to develop an efficient data mining tool. In this study, we develop a prototype fuzzy rule detection and inference system. The framework used in this development is mainly based on two different mechanisms such as fuzzy rule extraction and RDB (Relational DB)-based fuzzy rule inference. First, fuzzy clustering and fuzzy rule extraction deal with the presence of the knowledge in data base and its value is presented with a value between 0 -1. Second, RDB and SQL (Structured Query Language)-based fuzzy rule inference mechanism provide more flexibility in knowledge management than conventional non-fuzzy value-based KMS (Knowledge Management Systems).

• International journal of advanced smart convergence
• /
• v.8 no.2
• /
• pp.94-101
• /
• 2019

Building a stable knowledge base is an important issue in the application of knowledge engineering. In this paper, we present an algorithm for detecting and locating discrepancies in the line of the reasoning process especially when discrepancies occur on belief values. This includes backtracking the rule firing from a goal node of the rule network. Retracting a belief function allows the current belief state to move back to another belief state without the rule firing. It also gives an estimate, called contribution measure, of how much the rule has an impact on the current belief state. Examining the measure leads the expert to locate the possible cause of problem in the rule. For non-monotonic reasoning, the belief retraction method moves the belief state back to the previous state. A tracing algorithm is presented to identify and locate the cause of problem. This also gives repair suggestions for rule refinement.

• Journal of Industrial Technology
• /
• v.31 no.B
• /
• pp.37-43
• /
• 2011

In pattern analysis, dimensionality reduction and reasonable identification rule generation are very important parts. This paper performed effectively the dimensionality reduction by grouping the sensors of which the measured patterns are similar each other, where genetic algorithms were used for combination optimization. To identify the gas type, this paper constructed the hierarchically identifiable rule base with two frames by using rough set theory. The first frame is to accept measurement characteristics of each sensor and the other one is to reflect the identification patterns of each group. Thus, the proposed methods was able to accomplish effectively dimensionality reduction as well as accurate gas identification. In simulation, this paper demonstrated the effectiveness of the proposed methods by identifying five types of gases.