• International journal of advanced smart convergence
• /
• v.1 no.2
• /
• pp.30-33
• /
• 2012

This paper propose a new design of fuzzy neural networks based on hard partition to generate the rules of the networks. For this we use hard c-means (HCM) clustering algorithm. The premise part of the rules of the proposed networks is realized with the aid of the hard partition of input space generated by HCM clustering algorithm. The consequence part of the rule is represented by polynomial functions. And the coefficients of the polynomial functions are learned by BP algorithm. The number of the hard partition of input space equals the number of clusters and the individual partitioned spaces indicate the rules of the networks. Due to these characteristics, we may alleviate the problem of the curse of dimensionality. The proposed networks are evaluated with the use of numerical experimentation.

• Proceedings of the Korean Institute of Intelligent Systems Conference
• /
• 2005.04a
• /
• pp.297-300
• /
• 2005

In this study, we proposed genetically optimized self-organizing fuzzy polynomial neural network based on information granulation and evolutionary algorithm (gdSOFPNN), develop a comprehensive design methodology involving mechanisms of genetic optimization. The proposed gdSOFPNN gives rise to a structural Iy and parametrically optimized network through an optimal parameters design available within FPN (viz. the number of input variables, the order of the polynomial, input variables, the number of membership functions, and the apexes of membership function). Here, with the aid of the information granulation, we determine the initial location (apexes) of membership functions and initial values of polynomial function being used in the premised and consequence part of the fuzzy rules respectively. The performance of the proposed gdSOFPNN is quantified through experimentation that exploits standard data already used in fuzzy modeling.

• Earthquakes and Structures
• /
• v.9 no.4
• /
• pp.789-830
• /
• 2015

The recent re-assessment of the seismic hazard in Europe led for many regions of low to moderate seismicity to an increase in the seismic demand. As a consequence, several modern unreinforced masonry (URM) buildings, constructed with reinforced concrete (RC) slabs that provide an efficient rigid diaphragm action, no longer satisfy the seismic design check and have been retrofitted by adding or replacing URM walls with RC walls. Of late, also several new construction projects have been conceived directly as buildings with both RC and URM walls. Despite the widespread use of such construction technique, very little is known about the seismic behaviour of mixed RC-URM wall structures and codes do not provide adequate support to designers. The aim of the paper is therefore to propose a displacement-based design methodology for the design of mixed RC-URM edifices and the retrofit of URM buildings by replacing or adding selected URM walls with RC ones. The article describes also two tools developed for estimating important quantities relevant for the displacement-based design of structures with both RC and URM walls. The tools are (i) a mechanical model based on the shear-flexure interaction between URM and RC walls and (ii) an elastic model for estimating the contribution of the RC slabs to the overturning moment capacity of the system. In the last part of the article the proposed design method is verified through nonlinear dynamic analyses of several case studies. These results show that the proposed design approach has the ability of controlling the displacement profile of the designed structures, avoiding concentration of deformations in one single storey, a typical feature of URM wall structures.

• The Transactions of The Korean Institute of Electrical Engineers
• /
• v.60 no.11
• /
• pp.2157-2164
• /
• 2011

In this paper, we introduce a new category of fuzzy inference system based on Type-2 fuzzy c-means clustering algorithm (T2FCM-based FIS). The premise part of the rules of the proposed model is realized with the aid of the scatter partition of input space generated by Type-2 FCM clustering algorithm. The number of the partition of input space is composed of the number of clusters and the individual partitioned spaces describe the fuzzy rules. Due to these characteristics, we can alleviate the problem of the curse of dimensionality. The consequence part of the rule is represented by polynomial functions with interval sets. To determine the structure and estimate the values of the parameters of Type-2 FCM-based FIS we consider the successive tuning method with generation-based evolution by means of real-coded genetic algorithms. The proposed model is evaluated with the use of numerical experimentation.

• Proceedings of the KSR Conference
• /
• 2008.06a
• /
• pp.2230-2235
• /
• 2008

As a consequence of the standardization process developing in Europe, on April 2005 the new European standard EN 13749 was issued by the European standardization body CEN. The norm EN 13749 standardizes and develops the requirements already present in UIC leaflets for test verifications and define all technical requirements for the acceptance process in order to achieve a complete satisfactory design of the bogie. The aim of the norm is to define the complete design process of new railway bogies. It includes design procedures, assessment methods, verification and manufacturing quality requirements. In this study, fatigue analysis of the bogie frame is investigated comparing different approaches between conventional methodology and simulation results based on the VPD(Virtual Product Development).

• Proceedings of the Earthquake Engineering Society of Korea Conference
• /
• 1998.10a
• /
• pp.57-64
• /
• 1998

This paper presents the cyclic seismic performance of slip-critically designed, high-strength bolted-beam splice in steel moment frame. Before the moment connection reaching its plastic strength, unexpected premature slippage occurred at the slip-critically designed beam splice during the test. The experimentally observed frictional coefficients were as low as about 50% to 60% of nominal (code) value. Nevertheless, the bearing type behavior mobilized after the slippage transferred the increasing cyclic loads successfully, i.e., the consequence of slippage into bearing was not catastrophic to the connection behavior. The test result seems to indicate that the traditional beam splice design basing upon (bolt-hole deducted) effective flange area criterion may not be sufficient in developing the plastic strength of moment connections under severe earthquake loading. New procedure for achieving slip-critical beam splice design is proposed based on capacity design concept.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.14 no.10
• /
• pp.4719-4725
• /
• 2013

In this paper, we propose that a model based design for an electric motor cycle system using Automotive Simulation Models. Before prototyping a realistic electric motorcycle, a reliable simulation program is required to test the capacities of the power sources and optimize the parameters of an electric motorcycle. In the past, The research of electric motorcycle was conducted at macro rather than micro level. However, this research suggests the detailed analysis method of specific key components. This paper can get a good error ratio, 2.3%, as a consequence of the interpretation of experiment and simulation. With the analysis of specific electric motorcycle, it is able to analyze design factor and improve accuracy of electric motorcycle interpretation. Also, this research suggests the effective way to get fail safety so that it can solve the fail which can be encountered in electric motorcycle.

• Journal of Distribution Science
• /
• v.20 no.11
• /
• pp.99-108
• /
• 2022

Purpose: The wide distribution of smartphones has changed life and user behavior. This phenomenon has both advantages and disadvantages for users. As smartphones become a part of our daily lives, smartphone addiction has recently become a social issue in many countries. This study explores factors that affect smartphone addiction and the consequences of addictive behaviors. Research design, data and methodology: Our model hypothesizes that four key factors determine addictive behavior: flow, enjoyment, preference for online social life, and escape reality. Commitment and compulsive use are mediating variables that connect key drivers and addictive results. Based on the SEM (structural equation model) analysis of 497 survey responses, these four driving factors each have a significant effect on the compulsive use of smartphones directly or indirectly; the compulsive use of smartphones directly influences the three results Results: We conducted a reliability and validity analysis, and the results were successful. In the hypothesis test, every path is accepted as expected at the significance level of 0.05. Conclusions: Among the four driving factors, escape reality is the vital factor influencing smartphone addiction and its consequences. And anxiety is the number one consequence influenced by the compulsive use of smartphones.

• Journal of the Society of Naval Architects of Korea
• /
• v.55 no.3
• /
• pp.215-221
• /
• 2018

The structural design of offshore installations against explosions has been required to protect vital areas (e.g. control room, worker's area etc.) and minimize the damage from explosion accidents. Because the explosion accident will not only result in significant casualties and economic losses, but also cause serious pollution and damage to surrounding environment and coastal marine ecosystems. Over the past two decades, an incredible efforts was made to develop reliable methods to reduce and manage the explosion risk. Among the methods Quantitative Risk Assessment and Management (QRA&M) is the one of cutting-edge technologies. The explosion risk can be quantitatively assessed by the product of explosion frequency based on probability calculation and consequence analyzed using computer simulations, namely Computational Fluid Dynamics (CFD) and Finite Element Analysis (FEA). However to obtain reliable consequence analysis results by CFD and FEA, uncertainties associate with modeling and simulation are needed to be identified and validated by comparison with experimental data. Therefore, large-scaled explosion test procedure is developed in this study. And developed test procedure can be helpful to obtain precious test data for the validation of consequence analysis using computer simulations, and subsequently allow better assessment and management of explosion risks.

• International Journal of Control, Automation, and Systems
• /
• v.1 no.3
• /
• pp.321-331
• /
• 2003

Experimental software datasets describing software projects in terms of their complexity and development time have been the subject of intensive modeling. A number of various modeling methodologies and modeling designs have been proposed including such approaches as neural networks, fuzzy, and fuzzy neural network models. In this study, we introduce the concept of the Rule-based fuzzy polynomial neural networks (RFPNN) as a hybrid modeling architecture and discuss its comprehensive design methodology. The development of the RFPNN dwells on the technologies of Computational Intelligence (CI), namely fuzzy sets, neural networks, and genetic algorithms. The architecture of the RFPNN results from a synergistic usage of RFNN and PNN. RFNN contribute to the formation of the premise part of the rule-based structure of the RFPNN. The consequence part of the RFPNN is designed using PNN. We discuss two kinds of RFPNN architectures and propose a comprehensive learning algorithm. In particular, it is shown that this network exhibits a dynamic structure. The experimental results include well-known software data such as the NASA dataset concerning software cost estimation and the one describing software modules of the Medical Imaging System (MIS).