• Journal of Electrical Engineering and information Science
• /
• v.3 no.3
• /
• pp.355-365
• /
• 1998

The purposes of this study are to propose a network for the characterizing of the input data and to show how to design predictive neural net재가 expert system which doesn't need previous knowledge base. We derived this network from the radial basis function networks(RBFN), and named it as a statistical EBFN. The proposed network can replace the statistical methods for analyzing dynamic relations between target disease and other parameters in medical studies. We compared statistical RBFN with the probabilistic neural network(PNN) and fuzzy logic(FL). And we testified our method in the diabetes prediction and compared our method with the well-known multilayer perceptron(MLP) neural network one, and showed good performance of our network. At last, we developed the diabetes prediction expert system based on the proposed statistical RBFN without previous knowledge base. Not only the applicability of the characterizing of parameters related to diabetes and construction of the diabetes prediction expert system but also wide applicabilities has the proposed statistical RBFN to other similar problems.

• Journal of the Korean Institute of Illuminating and Electrical Installation Engineers
• /
• v.12 no.2
• /
• pp.29-37
• /
• 1998

This paper describes the fault diagnosis based on real-time data of the inverter system for brush less DC motor drive. After identifying all the fault types in the inverter system, a preliminary typical analysis of fault types has been classified into the key fault symptoms. The predicted fault performances are then substantiated by using ACSL(Advanced Continuous Simulation Language), and the simulated results are composed of knowledge-base. The real-time measured data from the inverter system are compared with the simulated knowledge-base through the inference engine of expert system, which have been used to diagnose the fault causes. If some faults may occur in the inverter system, this system will be stopped. And then the expertise of elimination and remedial strategies about the fault causes, will be supplied rapidly to operator who doesn't know well about the inverter drive system.system.

• The Transactions of the Korean Institute of Electrical Engineers A
• /
• v.48 no.11
• /
• pp.1457-1463
• /
• 1999

This paper develops an real-time expert system for the electronic interlocking system. it obtains the higher safety by determining the railway interlocking strategy in order to prevent trains from colliding, and derailing in the viewpoint of veteran expert, considering the situation of station in real-time. The expert system determines the real-time interlocking strategy by confirming the interlocking relationships among signal facilities based on the interlocking knowledge base from input information such as signal, points, and it is implemented as the rule-based system in order to represented accurately and effectively the interlocking relationships. Especially in case of emergency the function which determines the rational route coordinating with IIKBAG on the workstation is designed in order to minimize the spreading effect. It is implemented in C computer language for the purpose of the implementation of the inference engine using the dynamic memory allocation technique, the build and interface of the station structure database. And, the validity of the built expert system is proved by simulating the diversity cases which may occur in the real system for the typical station model.

• Proceedings of the KIEE Conference
• /
• 2004.11b
• /
• pp.122-124
• /
• 2004

Recently, power system is getting larger and more complex. When the complex power system has a problem, it is very difficult even for the experts to find out where the problem is and to make a timely decision by operators. There have been many studies on these problems but the results are not good enough for applying to real power system. Therefore power system operators always had to judge the exact state of power system and had to be preparative for the problems that can occur later. We developed new methods that can be applied to complex power system by dividing the system into small modules. By using 'module' we can combine small modules together to make complex power systems and the knowledge base that is applied to fault diagnosis system. As a result, compared to previously developed diagnosis products, operational time has shortened, and the knowledge base becomes simpler and clearer, which made online usage capable. This system can be used as a complementary measure that helps the operator from making any mistakes.

• Proceedings of the Korean Society for Technology of Plasticity Conference
• /
• 1998.06a
• /
• pp.57-64
• /
• 1998

The purpose of this research is to develop a CAD/CAM system for generation all kind of information such as, total drawing, sub assembly drawing, part drawing, detail drawing, part list, and NC data for machining by CNC lathe, Wire CUT, machining center. Through this study the CAD/CAM System for deep drawing transfer die in mechanical press process has been developed. The developed CAD system can generate the drawing of transfer die in mechanical press. Using these results from CAD system, it can generate the NC data to machine die's elements on the CAD system. This system can reduce design man-hours and human errors. In order to construct the system, it is used to automate the design process using knowledge base system. The developed system is based on the knowledge base system which is involved a lot of expert's technology in the practice field. Using AutoLISP language under the AutoCAD system, CTK customer language of SmartCAM is used as the overall CAD/CAM environment. Results of this system will be provide effective aids to the designer and manufacturer in this field.

• Journal of the Korea institute for structural maintenance and inspection
• /
• v.4 no.2
• /
• pp.175-184
• /
• 2000

The maintenance of tunnels is often neglected since tunnels has tendency to become stable with time. The determination of safety of tunnels is a complicated problem. So the role of experienced engineer in the maintenance is very important and development of an expert system which can perform as these engineers has been needed. In this study, an expert system which can determine the safety of tunnels is developed. The developed knowledge base contains the maintenance procedure which is used in KlSTEC(Korea Infrastructure Safety & Technology Corporation). Field test, laboratory test and nondestructive test methods are considered in this knowledge base. Criteria for each item and integrated diagnosis criteria are implemented in the expert system based on literatures and reports. The expert system includes basic inspection. detail inspection and precision inspection. For precision inspection. it has the capacity to exchange the result from numerical analysis by a commercial program FLAC. To verify the expert system. the proposed procedure was compared with an existing tunnel diagnosis report.

• Annual Conference on Human and Language Technology
• /
• 2019.10a
• /
• pp.185-189
• /
• 2019

관계추출기의 학습을 위해서는 많은 학습 데이터가 필요한데, 사람이 모으게 되면 많은 비용이 필요하여 원격 지도 학습을 이용한 데이터 수집이 많은 연구에서 사용되고 있다. 원격 지도 학습은 지식베이스를 기반으로 학습 데이터를 자동으로 만들어 내는 방식이기에 비용이 거의 들지 않지만, 지식베이스의 질과 양에 영향을 받는다. 본 연구는 원격 지도 학습을 기본으로 관계추출기의 성능을 향상 시키고, 지식베이스를 확장하는 방안으로 반복학습을 제안한다. 실험을 적은 비용으로 빠르게 진행하기 위해 반복학습을 자동화 하는 시스템을 설계하여 실험을 하였고, 이 시스템으로 관계추출기의 성능이 향상 될 수 있는 가능성을 보였으며, 반복학습을 통한 지식베이스의 확장 방안을 제시한다.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2008.11a
• /
• pp.52-55
• /
• 2008

The paper aims at showing the subsumption relations of the Wordnet can be captured automatically from a dynamic encyclopedia such as Wikipedia with a meaningful precision. The idea behind the proposal is that a knowledge base in the form of Wordnet can be dynamically obtained and maintained accordingly to the online dictionaries so that the scalability of knowledge base construction may be achieved to some degree. To show the plausibility of dynamic ISA construction, we have tested how well the ISA relations among the 100 technology terms selected from the Wordnet can be saved from the ISA construction by the wiki definitions of the selected terms. As a result the wiki definition led to the ISA relations of the Wordnet with the precision of 80%.

• Journal of Intelligence and Information Systems
• /
• v.17 no.3
• /
• pp.43-61
• /
• 2011

In this research, we propose a dynamic decision making using social context based on ontology. Dynamic adaptation is adopted for the high qualified decision making, which is defined as creation of proper information using contexts depending on decision maker's state of affairs in ubiquitous computing environment. Thereby, the context for the dynamic adaptation is classified as a static, dynamic and social context. Static context contains personal explicit information like demographic data. Dynamic context like weather or traffic information is provided by external information service provider. Finally, social context implies much more implicit knowledge such as social relationship than the other two-type context, but it is not easy to extract any implied tacit knowledge as well as generalized rules from the information. So, it was not easy for the social context to apply into dynamic adaptation. In this light, we tried the social context into the dynamic adaptation to generate context-appropriate personalized information. It is necessary to build modeling methodology to adopt dynamic adaptation using the context. The proposed context modeling used ontology and cases which are best to represent tacit and unstructured knowledge such as social context. Case-based reasoning and constraint satisfaction problem is applied into the dynamic decision making system for the dynamic adaption. Case-based reasoning is used case to represent the context including social, dynamic and static and to extract personalized knowledge from the personalized case-base. Constraint satisfaction problem is used when the selected case through the case-based reasoning needs dynamic adaptation, since it is usual to adapt the selected case because context can be changed timely according to environment status. The case-base reasoning adopts problem context for effective representation of static, dynamic and social context, which use a case structure with index and solution and problem ontology of decision maker. The case is stored in case-base as a repository of a decision maker's personal experience and knowledge. The constraint satisfaction problem use solution ontology which is extracted from collective intelligence which is generalized from solutions of decision makers. The solution ontology is retrieved to find proper solution depending on the decision maker's context when it is necessary. At the same time, dynamic adaptation is applied to adapt the selected case using solution ontology. The decision making process is comprised of following steps. First, whenever the system aware new context, the system converses the context into problem context ontology with case structure. Any context is defined by a case with a formal knowledge representation structure. Thereby, social context as implicit knowledge is also represented a formal form like a case. In addition, for the context modeling, ontology is also adopted. Second, we select a proper case as a decision making solution from decision maker's personal case-base. We convince that the selected case should be the best case depending on context related to decision maker's current status as well as decision maker's requirements. However, it is possible to change the environment and context around the decision maker and it is necessary to adapt the selected case. Third, if the selected case is not available or the decision maker doesn't satisfy according to the newly arrived context, then constraint satisfaction problem and solution ontology is applied to derive new solution for the decision maker. The constraint satisfaction problem uses to the previously selected case to adopt and solution ontology. The verification of the proposed methodology is processed by searching a meeting place according to the decision maker's requirements and context, the extracted solution shows the satisfaction depending on meeting purpose.

• KIISE Transactions on Computing Practices
• /
• v.21 no.12
• /
• pp.774-779
• /
• 2015

In this paper, we present the design and implementation of a large-scale qualitative spatial reasoner using Apache Spark, an in-memory high speed cluster computing environment, which is effective for sequencing and iterating component reasoning jobs. The proposed reasoner can not only check the integrity of a large-scale spatial knowledge base representing topological and directional relationships between spatial objects, but also expand the given knowledge base by deriving new facts in highly efficient ways. In general, qualitative reasoning on topological and directional relationships between spatial objects includes a number of composition operations on every possible pair of disjunctive relations. The proposed reasoner enhances computational efficiency by determining the minimal set of disjunctive relations for spatial reasoning and then reducing the size of the composition table to include only that set. Additionally, in order to improve performance, the proposed reasoner is designed to minimize disk I/Os during distributed reasoning jobs, which are performed on a Hadoop cluster system. In experiments with both artificial and real spatial knowledge bases, the proposed Spark-based spatial reasoner showed higher performance than the existing MapReduce-based one.