• 복식
• /
• 제53권8호
• /
• pp.81-89
• /
• 2003

This study is to consider both the eastern and western concepts of colors focusing on the five colors(Blue, Red, Yellow, White, Black) derived from the principles of Yang and the Five Elements, which are the traditional philosophy of the East and to analyze the modern fashion on the basis of the theoretical background. This study is summarized in the following. The eastern color concept has been formed by the influence of the principles of Yin and Yang and the Five Elements, which explain the generation and extinction of the universe. When it comes to the five colors, the symbolism of the east and west has much in common relatively. Concerning the rule of the five colors match, both the rules of the east and west are highly similar with each other. As mentioned above, the study shows that the five colors concepts and match rules between the east and west have much in common. There is a high possibility to connect the compatibility and incompatibility of the eastern five colors with scientific western theory of color harmony.

• 한국기계가공학회지
• /
• 제4권3호
• /
• pp.57-62
• /
• 2005

Neural networks, which have learning and self-organizing abilities, can be advantageously used in the pattern recognition. Neural network techniques have been widely used in monitoring and diagnosis, and compare favourable with traditional statistical pattern recognition algorithms, heuristic rule-based approaches, and fuzzy logic approaches. In this study the fault diagnosis of the face-milling using the artificial neural network was investigated. After training, the sample which measure load current was monitored by constant output results.

• 제어로봇시스템학회:학술대회논문집
• /
• 제어로봇시스템학회 2000년도 제15차 학술회의논문집
• /
• pp.140-140
• /
• 2000

Traditional genetic algorithms, though robust, are generally not the most successful optimization algorithm on any particular domain. Hybridizing a genetic algorithm with other algorithms can produce better performance than both the genetic algorithm and the other algorithms. In this paper, we use random process and simulated annealing instead of mutation operator in order to get well tuned fuzzy rules. The key of this approach is to adjust both the width and the center of membership functions so that the tuned rule-based fuzzy controller can generate the desired performance. The effectiveness of the proposed algorithm is verified by computer simulation.

• 말소리와 음성과학
• /
• 제1권3호
• /
• pp.155-163
• /
• 2009

This paper introduces an automatic voice classification system for the diagnosis of individual constitution based on Sasang Constitutional Medicine (SCM) in Traditional Korean Medicine (TKM). For the developing of this algorithm, we used the voices of 473 speakers and extracted a total of 144 speech features from the speech data consisting of five sustained vowels and one sentence. The classification system, based on a rule-based algorithm that is derived from a non parametric statistical method, presents binary negative decisions. In conclusion, 55.7% of the speech data were diagnosed by this system, of which 72.8% were correct negative decisions.

• 한국지능시스템학회:학술대회논문집
• /
• 한국퍼지및지능시스템학회 1996년도 추계학술대회 학술발표 논문집
• /
• pp.243-248
• /
• 1996

In this paper, a general neural-network-based connectionist model, called Fuzzy Neural Network(FNN), is proposed for the realization of a fuzzy logic control system. The proposed FNN is a feedforward multi-layered network which integrates the basic elements and functions of a traditional fuzzy logic controller into a connectionist structure which has distributed learning abilities. Such FNN can be constructed from training examples by learning rule, and the connectionist structure can be trained to develop fuzzy logic rules and find optimal input/output membership functions. Computer simulation examples will be presented to illustrate the performance and applicability of the proposed FNN, and their associated learning algorithms.

• 대한용접접합학회:학술대회논문집
• /
• 대한용접접합학회 2005년도 춘계학술발표대회 개요집
• /
• pp.112-114
• /
• 2005

Direct nonlinear finite element analysis was carried out using nonlinear kinematic hardening model which was calibrated based on the experimentally determined material properties to obtain notch stress-strain state under cyclic load. By comparing numerical results and experimental data, conclusion was made on how well analysis results match physical phenomenon. Also, suggestion was made on what material curve should be used in conjunction with traditional Neuber/Glinka's rule to take into account the effect of material heterogeneity in its application to welded joint.

• 제어로봇시스템학회논문지
• /
• 제7권2호
• /
• pp.131-137
• /
• 2001

Traditional genetic algorithms, though robust, are generally not the most successful optimization algorithm on only particular domian. Hybridizing a genetic algorithm with other algorithms can produce better performance than both the genetic algorithm and the other algorithms. This paper describes the application of random signal-based learning to a genetic algorithm in order to get well tuned fuzzy rules. The key of tis approach is to adjust both the width and the center of membership functions so that the tuned rule-based fuzzy controller can generate the desired performance. The effectiveness of the proposed algorithm is verified by computer simulation.

• 혜화의학회지
• /
• 제9권1호
• /
• pp.647-660
• /
• 2000

As above, it described Dr.Tanaka's Spiral Balance Theory and studied the theoretical background and the special meridian circulation system, diagnostics and treatments. Though the considered the rule of the tenseness of the body as muscle movement theory, it corresponds with tradtional meridians theory in oriental medicine. If we study and develop the traditional meridians circulaition system more, we can expect clinical development applying to any theories in the field of oriential medicine such as acupuncture therapy, moxa therapy and chiropractc therapy. etc, as well as tapaing therapy, electronic stimulation therapy and exercising therapy.

• 접착 및 계면
• /
• 제3권1호
• /
• pp.43-51
• /
• 2002

Advanced adhesive technologies and demanding applications of adhesive joints can no longer be developed successfully by the traditional "trial and error" approach. Appropriate technical solutions require reference to a reliable basis of well-established scientific knowledge about the elementary mechanisms of adhesion (i.e. the 'fundamental adhesion') as they are responsible for the capability of the compound w transmit mechanical force between the adhesive and the substrate surface (i.e. the 'practical adhesion'). Adhesion mechanisms also influence the formation of polymer structure in the adhesive and the resulting macromolecular dynamics in the interphase that is formed in the adhesive near to the substrate. These manifold molecular factors rule the macroscopic behaviour of an adhesive bond line in terms of mechanical and other physical properties as well as in terms of durability. This paper reviews the level of refinement that understanding of fundamental adhesion has achieved up to now.

• 한국정보시스템학회지:정보시스템연구
• /
• 제14권3호
• /
• pp.37-47
• /
• 2005

Mining of association rules is to find associations among data items that appear together in some transactions or business activities. As of today, algorithms for association rule mining, as well as for other data mining tasks, are mostly applied to relational databases. As XML being adopted as the universal format for data storage and exchange, mining associations from XML data becomes an area of attention for researchers and developers. The challenge is that the semi-structured data format in XML is not directly suitable for traditional data mining algorithms and tools. In this paper we present an encoding method to encode XML tree-nodes. This method is used to store the XML data in Value Table and Transaction Table that can be easily accessed via indexing. The hierarchical relationship in the original XML tree structure is embedded in the encoding. We applied this method to association rules mining of XML data that may have missing data.