• The Transactions of The Korean Institute of Electrical Engineers
• /
• v.63 no.4
• /
• pp.534-540
• /
• 2014

In this paper, we propose a fuzzy combined Polynomial Neural Network(PNN) for pattern classification. The fuzzy combined PNN comes from the generic TSK fuzzy model with several linear polynomial as the consequent part and is the expanded version of the fuzzy model. The proposed pattern classifier has the polynomial neural networks as the consequent part, instead of the general linear polynomial. PNNs are implemented by stacking the simple polynomials dynamically. To implement one layer of PNNs, the various types of simple polynomials are used so that PNNs have flexibility and versatility. Although the structural complexity of the implemented PNNs is high, the PNNs become a high order-multi input polynomial finally. To estimate the coefficients of a polynomial neuron, The weighted linear discriminant analysis. The output of fuzzy rule system with PNNs as the consequent part is the linear combination of the output of several PNNs. To evaluate the classification ability of the proposed pattern classifier, we make some experiments with several machine learning data sets.

• English Language & Literature Teaching
• /
• v.18 no.1
• /
• pp.23-43
• /
• 2012

This study investigates the effects of three different types of instruction, namely form-based, comprehension-based, and production-based on the development of Korean university students' (n=137) comprehension and production of English relative clauses (RCs). The extent of improvements was analyzed by administering pre-and post-tests consisting of two comprehension tests (selecting the right form of RCs and the right picture descriptions) and one production test (combining two sentences). Findings of this study suggest that all three types of instruction increased participants' comprehension and productions of RCs. However, there appeared differential effects by the instruction type. It was found production-based instruction was most effective in promoting comprehension, followed by comprehension-based instruction. Comprehension-based instruction worked best with the development of production, suggesting that the effects of comprehension training did not only work for increasing comprehension skills, but also transfer to production skills. The type or level of tasks employed for each instruction appeared to play an important role in causing such results. Form-based instruction displayed the lowest improvements in both comprehension and production of RCs. A sentence-combination task employed for form-based instruction appear to result in mere explicit rule explanations without chances to notice rules in context or use their knowledge in practice.

• Journal of the Korean Society for information Management
• /
• v.22 no.4 s.58
• /
• pp.97-109
• /
• 2005

To build the consistency among different metadata systems and to increase the interoperability of that systems even among different domains, naming rules and glossaries for the data elements are necessary. This study provides discussion of naming and identification of the data element concept, data element, conceptual domain, value domain, and its meta model. This study also describes example naming conventions based on ontology derived from the combination with object, properties, and representation of data elements. The naming principles and rules described in this study use I-R analysis, DC metadata set, and SHOE 1.0 as an example of the scientific documents. This study would be a guideline to build the naming rules of metadata based on ontology in various domains.

• Proceedings of the Korean Society of Agricultural Engineers Conference
• /
• 2001.10a
• /
• pp.156-161
• /
• 2001

Currently, agricultural facilities are evaluated using either basic inspections or detailed analysis. However, conventional analyses as well as methods based on fuzzy logic and rule of thumb have not been very successful in providing a clear relationship between rating and real state of agricultural facilities, because they can't provide exactly acceptable reliability of degraded structures with manager or supervisor. Therefore, in this stage, we must define probabilistic variables for representing degradation of structures being given damages during a survival time. This paper describes the application of neural network system in developing the relation between subjective ratings and parameters of agricultural reservoir as well as that between subjective and analytical ratings. It is shown that neural networks can be trained and used successfully in estimating a rating based on several parameters. The specific application problem for agricultural reservoir in the rural area of Korea is presented and database is constructed to maintain training data set, the information of inspection and facilities. This study showed that a successful training of a neural network could be useful, especially if the input data set for target problem contains parameters with a diverse combination of inter-correlation coefficients. And the networks had a prediction rating of about $^{\ast}^{\ast}^{\ast}%$. The neural network system is expected to show high performance fairly in estimate than statistical method to use equation that is consisted of very lowly interrelated variables.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.41 no.7
• /
• pp.768-774
• /
• 2016

This paper deals with a method to recommend the combination of items as a group according to similarity to handle application area such as fashion and cooking, while the previous methods recommend single item such as a book, music or movie. Collaborative filtering is a method to recommend an item selected by users with similar tendency based on similarity between users. In this paper, the proposed method generates a set of frequent items based on collaborative filtering and association rules and recommends a group by similarity between groups. To show the validity of the proposed method, experiments are performed with purchase data collected from e-commerce for four months.

• Proceedings of the KIEE Conference
• /
• 2006.10c
• /
• pp.282-284
• /
• 2006

Generally PI controller is used to control the speed of an induction motor. It has the good performance of speed control in case of adjusting the control parameters. But it occurred the problem to change the control parameters in the change of operation condition. In order to solve this problem, Fuzzy control or Artificial neural network is introduced in the speed control of an induction motor. However, Fuzzy control have the problems as the difficulties to change the membership function and fuzzy rule and the remaining error. Also Neural network has the problem as the difficulties to analyze the behavior of inner part. Therefore, the study on the combination of two controller is proceeded. In this paper, Speed controller of an induction motor based fuzzy-neural network is proposed and the speed control of an induction motor is performed using the proposed controller. Through the experiment, the fast response and good stability of the proposed speed controller is proved.

• Journal of the Korean Society for Railway
• /
• v.13 no.1
• /
• pp.51-57
• /
• 2010

The aerodynamic drag of ultra high-speed train in evacuated tube have been calculated using computational fluid dynamics and the variation of aerodynamic drag for the change of major system parameter of tube-vehicle system such as the train speed, air density, and the tunnel diameter. The aerodynamic drag in the tube increases with increasing train speed, however, the ratio of drag increase in tube is larger than that on the open field, the V square rule. The aerodynamic drag decreases with increasing tunnel diameter and increasing air density, and the drag increasing for air density is almost linear just like that on open field. For some combination of the parameters, the trend of aerodynamic drag of train showed irregularity.

• Journal of the Earthquake Engineering Society of Korea
• /
• v.24 no.3
• /
• pp.129-139
• /
• 2020

An approximate analysis method is proposed to predict the dynamic amplification of shear forces in ordinary reinforced concrete shear walls as a preliminary study. First, a seismic design for three groups of ordinary reinforced concrete shear walls higher than 60 m was created on the basis of nonlinear dynamic analysis. Causes for the dynamic amplification effect of shear forces were investigated through a detailed evaluation of the nonlinear dynamic analysis result. A new modal combination rule was proposed on the basis of that observation, in which fundamental mode response and combined higher mode response were summed directly. The fundamental mode response was approximated by nonlinear static analysis result, while higher mode response was computed using response spectrum analysis for equivalent linear structural models with the effective stiffness based on the nonlinear dynamic analysis result. The proposed approximate analysis generally predicted vertical distribution of story shear and shear forces of individual walls from the nonlinear dynamic analysis with comparable accuracy.

• Coupled systems mechanics
• /
• v.5 no.2
• /
• pp.101-126
• /
• 2016

Seismic structural fragility constitutes an important step for performance based seismic design. Lateral load-resisting structural members are often analyzed under one component base excitation, while the effect of bi-directional shaking is accounted per simplified rules. Fragility curves are constructed herein under real bi-directional excitation by a simple extension of the conventional Incremental Dynamic Analysis (IDA) under uni-directional shaking. Simple SODF systems, parametrically adjusted to different periods, are examined under a set of near-fault and far-fault excitations. Consideration of bi-directional interaction appears important for stiff systems. Further, the study indicates that the peak ground accelertaion, velocity and displacement (PGA, PGV and PGD) of accelerogram are relatively stable and efficient intensity measures for short, medium and long period systems respectively. '30%' combination rule seems to reasonably predict the fragility under bi-directional shaking at least for first mode dominated systems dealt herein up to a limit state of damage control.

• Geomechanics and Engineering
• /
• v.15 no.1
• /
• pp.621-630
• /
• 2018

In the note a comprehensive and optimal passive-active mode for describing the limit failure of circular shallow tunnel with settlement is put forward to predict the catastrophic stability during the geotechnical construction. Since the surrounding soil mass around tunnel roof is not homogeneous, with tools of variation calculus, several different curve functions which depict several failure shapes in different soil layers are obtained using virtual work formulae. By making reference to the simple-form of Power-law failure criteria based on numerous experiments, a numerical procedure with consideration of combination of upper bound theorem and stochastic medium theory is applied to the optimal analysis of shallow-buried tunnel failure. With help of functional catastrophe theory, this work presented a more accurate and optimal failure profile compared with previous work. Lastly the note discusses different effects of parameters in new yield rule and soil mechanical coefficients on failure mechanisms. The scope of failure block becomes smaller with increase of the parameter A and the range of failure soil mass tends to decrease with decrease of unit weight of the soil and tunnel radius, which verifies the geomechanics and practical case in engineering.