• Journal of the Korea Society for Simulation
• /
• v.20 no.3
• /
• pp.79-88
• /
• 2011

In most existing warships combat simulation system, the tactics of a warship is manipulated by human operators. For this reason, the simulation results are restricted due to the stereotype of human operators. To deal with this, we have employed the genetic algorithm for supporting the evolutionary simulation environment. In which, the tactical decision by human operators is replaced by the human model with a rule-based chromosome for representing tactics so that the population of simulations are created and hundreds of simulation runs are continued on the basis of the genetic algorithm without any human intervention until to find emergent tactics which shows the best performance throughout the simulation. This paper proposes an evolutionary tactics generation methodology for the emergent tactics in many-to-many warship combat simulation. To do this, 3:3 warship combat simulation tests are performed.

• Journal of the HCI Society of Korea
• /
• v.5 no.1
• /
• pp.25-35
• /
• 2010

This paper proposes a method of automatically identifying sentence types in Korean and improving naturalness in sign language generation and speech synthesis using the identified sentence type information. In Korean, sentences are usually categorized into five types: declarative, imperative, propositive, interrogative, and exclamatory. However, it is also known that these types are quite ambiguous to identify in dialogues. In this paper, we present additional morphological and syntactic clues for the sentence type and propose a rule-based procedure for identifying the sentence type using these clues. The experimental results show that our method gives a reasonable performance. We also describe how the sentence type is used to generate non-manual signals in Korean-Korean sign language translation and appropriate intonation in Korean speech synthesis. Since the method of using sentence type information in speech synthesis and sign language generation is not much studied previously, it is anticipated that our method will contribute to research on generating more natural speech and sign language expressions.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.33 no.8A
• /
• pp.846-851
• /
• 2008

With rapid development of communication industry, the kinds of communication service vary. According to the increasing use of radio waves, the intelligent and effective radio monitoring system needs to be developed, which is replaced for previous radio monitoring system. Next-generation intelligent radio monitoring system based on ITU-R, Rule of wireless facilities, and Radio Waves Act is used, and which can accurately and effectively function as effective radio monitoring system through spectrum analysis of channel power, frequency deviation, offset, and an occupied frequency bandwidth(99% or x-dB), about the analog and digital signal in On-Air of V/UHF bandwidth. Main function of the system has an radio quality measurement, unwanted electromagnetic signals (spurious, harmonic) measurement, high-speed spectrum measurement, frequency usage efficiency investigation, illegal radio exploration, working monitoring, In this paper, we proposes radio quality measurement, high-speed spectrum measurement of next-generation intelligent radio monitoring system.

• Proceedings of the Korea Inteligent Information System Society Conference
• /
• 1999.10a
• /
• pp.131-137
• /
• 1999

전문가시스템 개발에 있어서 지식획득 병목현상(knowledge acquisition bottleneck)은 해결해야 할 큰 걸림돌중 하나이다. 지식획득을 위한 여러 과정을 단순화하고 자동화함으로 지식공학자의 작업을 최소화하면서 전문지식을 쉽고 빠르게 획득할 수 있도록 지식획득시스템을 설계·구현한다면 전문가시스템의 대중화는 지금보다 쉽게 이루어질 것이다. 본 연구는 지식 획득시스템 설계와 구현을 위한 연구의 일환으로 기계학습의 한 방법인 PIPPER(Repeated Incremental Pruning to Produce Error Reduction)를 이용하여 규칙을 생성하고 생성된 규칙을 JESS(Justification based Expert System Shell)에서 처리하도록 하였다. 규칙을 생성하기 위한 데이터는 Bohanec이 1997년도에 만든 자동차 평가 데이터베이스(Car Evaluation Database)를 사용하여 실험하였으며, 1700여 개의 레코드에서 약 40개의 규칙이 생성되었고, 생성된 규칙은 지식베이스의 정당성을 위반하지 않으면서 실행되었다.

• Journal of Korean Institute of Industrial Engineers
• /
• v.20 no.3
• /
• pp.35-53
• /
• 1994

Orthographic views ore traditionally used for engineering drawings. This paper presents a methodology for 3D parametric design using orthographic views. The parametric design technique, which is used to design 2D orthographic views, is based on production rules. In the production rule-base, several view interrelation rules and over 50 geometric rules are included. An efficient algorithm is also developed to expedite the reasoning process. For 3D object construction from orthographic views, the approach known as bottom-up geometrical approach is used. The approach consists of 4 steps : 1) generation of wire-frame, 2) construction of face from wire frame, 3) formation of 3D subobjects from faces, and 4) construction of final 3D objects. Curvilinear solids as well as planar solids can be constructed. A method of converting existing 2D CAD data to parametric 3D CAD data is also presented.

• Proceedings of the KSPS conference
• /
• 2002.11a
• /
• pp.41-44
• /
• 2002

This paper is related to the enhancement of speech recognition rate using enhanced pronunciation dictionary. Modern large vocabulary, continuous speech recognition systems have pronunciation dictionaries. A pronunciation dictionary provides pronunciation information for each word in the vocabulary in phonemic units, which are modeled in detail by the acoustic models. But in most speech recognition system based on Hidden Markov Model, actual pronunciation variations are disregarded. Without the pronunciation variations in the speech recognition system, the phonetic transcriptions in the dictionary do not match the actual occurrences in the database. In this paper, we proposed the unvoiced rule of semivowel in allophone rules to pronunciation dictionary. Experimental results on speech recognition system give higher performance than existing pronunciation dictionaries.

• Proceedings of the Korean Society for Technology of Plasticity Conference
• /
• 1992.03a
• /
• pp.177-200
• /
• 1992

A thermo-viscoplastic finite element program was developed to analyze the compression molding of SMC process. Deformation of the material was modelled by using the flow-rule. Heat balance during the process was coupled to the deformation. In the cure study, a kinetic model was adopted to describe the cure behavior. The numerical kinetic model was integrated with the thermo-viscoplastic numerical analysis by adding heat generation due to the chemical reaction of the workpiece in the heat transfer analysis. The integrated finite element program can simulate a whole sequential molding process including deformation, heat transfer, and chemical reaction. A practical SMC molding process with T-shaped substructure was simulated. The simulated results showed good agreements with experiments.

• The Transactions of The Korean Institute of Electrical Engineers
• /
• v.58 no.4
• /
• pp.840-848
• /
• 2009

This paper proposes a new multi-start scheme that generates guided random bits in selecting initial search points for global optimization with univariate dynamic encoding algorithm for searches (uDEAS). The proposed method counts the number of 1 in each bit position from all the previously generated initial search matrices and, based on this information, generates 0 in proportion with the probability of selecting 1. This rule is simple and effective for improving diversity of initial search points. The performance improvement of the proposed multi-start is validated through implementation in uDEAS and function optimization experiments.

• Proceedings of the KIEE Conference
• /
• 2008.11a
• /
• pp.74-76
• /
• 2008

The power expansion planning is large and capital intensive capacity planning. In the past the expansion planning was established with the proper supply reliability in order to minimize social cost. However, the planning not used cost minimizing objective function in the power markets with many market participants. This paper proposed the power expansion planning process in the power markets. This system is composed of Regulator and GENCO's model. Regulator model used multi-criteria decision making rule. GENCO model is very complex problem. Thus, this system transacted the part by several scenario assuming GENCO model.

• The Transactions of The Korean Institute of Electrical Engineers
• /
• v.63 no.7
• /
• pp.916-923
• /
• 2014

This paper proposes a low-cost switched-mode rectifier (SMR) for a small-scale wind turbine with a permanent magnet synchronous generator (PMSG) system. Also, a sensorless Fuzzy MPPT control is realized by the proposed system. In the PMSG system with the SMR, the synchronous impedance can be replaced as the input inductor of a boost converter. Moreover, the sensorless MPPT control using the Fuzzy technique is carried out by the duty-ratio regulation of the SMR. The relation between the generating power and the duty-ratio is ruled by the chain rule. The wind turbine model is implemented by the squirrel cage induction motor and generated the variable torque when the generator speed is varied. To verify the performance of the proposed system, simulation and experimental results are executed.