• Journal of Information Processing Systems
• /
• v.13 no.5
• /
• pp.1345-1357
• /
• 2017

A prototype selection method chooses a small set of training points from a whole set of class data. As the data size increases, the selected prototypes play a significant role in covering class regions and learning a discriminate rule. This paper discusses the methods for selecting prototypes in a classification framework. We formulate a prototype selection problem into a set covering optimization problem in which the sets are composed with distance metric and predefined classes. The formulation of our problem makes us draw attention only to prototypes per class, not considering the other class points. A training point becomes a prototype by checking the number of neighbors and whether it is preselected. In this setting, we propose a greedy algorithm which chooses the most relevant points for preserving the class dominant regions. The proposed method is simple to implement, does not have parameters to adapt, and achieves better or comparable results on both artificial and real-world problems.

• Journal of the Institute of Electronics and Information Engineers
• /
• v.53 no.3
• /
• pp.59-66
• /
• 2016

This paper presents an empirical evaluation on dimensionality reduction strategies by which dissimilarity-based classifications (DBC) can be implemented efficiently. In DBC, classification is not based on feature measurements of individual objects (a set of attributes), but rather on a suitable dissimilarity measure among the individual objects (pair-wise object comparisons). One problem of DBC is the high dimensionality of the dissimilarity space when a lots of objects are treated. To address this issue, two kinds of solutions have been proposed in the literature: prototype selection (PS)-based methods and dimension reduction (DR)-based methods. In this paper, instead of utilizing the PS-based or DR-based methods, a way of performing DBC in Eigen spaces (ES) is considered and empirically compared. In ES-based DBC, classifications are performed as follows: first, a set of principal eigenvectors is extracted from the training data set using a principal component analysis; second, an Eigen space is expanded using a subset of the extracted and selected Eigen vectors; third, after measuring distances among the projected objects in the Eigen space using $l_p$-norms as the dissimilarity, classification is performed. The experimental results, which are obtained using the nearest neighbor rule with artificial and real-life benchmark data sets, demonstrate that when the dimensionality of the Eigen spaces has been selected appropriately, compared to the PS-based and DR-based methods, the performance of the ES-based DBC can be improved in terms of the classification accuracy.

• KIPS Transactions on Software and Data Engineering
• /
• v.5 no.10
• /
• pp.483-488
• /
• 2016

In this paper, we propose a prototype-based classification learning by using the nearest-neighbor rule. The nearest-neighbor is applied to segment the class area of all the training data with hyperspheres, and a hypersphere must cover the data from the same class. The radius of a hypersphere is computed by the mid point of the two distances to the farthest same class point and the nearest other class point. And we transform the prototype selection problem into a set covering problem in order to determine the smallest set of prototypes that cover all the training data. The proposed prototype selection method is designed by a greedy algorithm and applicable to process a large-scale training set in parallel. The prediction rule is the nearest-neighbor rule and the new training data is the set of prototypes. In experiments, the generalization performance of the proposed method is superior to existing methods.

• Journal of the Korean Society for Precision Engineering
• /
• v.18 no.3
• /
• pp.75-83
• /
• 2001

RIM(Reaction Injection Molding) is a widely used method to manufacture middle-large size outfit-part for a prototype car. The main advantage of RIM is the capability of manufacturing a small number of prototype parts with less cost and lead time than injection molding which is the most popular method to manufacture plastic parts. Generally, epoxy resin and RTV(Room Temperature Vulcanization) silicon are used as mold materials for RIM, and the selection of mold materials is usually depended upon the industrial environment of manufactures and it decides overall mold making process and part quality. This paper suggests a new mold making process by consolidating the advantages of epoxy resin and RTV silicon based RIM mold to enhance the parts quality while reducing the manufacturing cost and time and shows the competitiveness of the suggested process compared with conventional methods.

• Proceedings of the Korean Institute of Building Construction Conference
• /
• 2019.05a
• /
• pp.137-138
• /
• 2019

To overcome the limitation in relation to thermal insulator's selection and installation method that is suitable for exterior insulation and waterproof construction methods, a production basis of thermal insulators of which manufacturing knowhow is held by companies was ensured and future-oriented construction methods to adopt new materials were applied. Performance verification was conducted through performance and mock-up tests of thermal transmittance on the cross sections where the flexible insulators were applied based on the improved prototype and performance data were obtained. To overcome the biggest drawbacks (walking feeling and damage etc.) in the exterior insulation and waterproof construction method, inserting a protective layer between thermal insulator and water-proof layer was proposed, and polypropylene corrugated cardboards.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.12 no.5
• /
• pp.2124-2132
• /
• 2011

The purpose of this research is to design and develop an evaluation system with a view to improving teaching skills in the u-Campus environment. To achieve the purpose, this research analyzed various theories on the effectiveness of teaching and teaching evaluation system, extracting several evaluation factors which are to be included in the system. Based on these evaluation factors, this research developed a prototype by reflecting teaching assessment, coaching, self-reflection, portfolio, supervisor selection, user authority in sharing the portfolio and ubiquitous technology. This prototype differs from the existing evaluation methods in that it can enlarge the extent of supervisors other than professors according to their own selecting and can reduce the burden of assessment task, thus improve their teaching skills. This teaching evaluation system using portfolio and ubiquitous technology will be an innovative alternative to conventional assessment methods and will be of great help to qualitative progress in higher level education.

• Structural Engineering and Mechanics
• /
• v.46 no.3
• /
• pp.371-385
• /
• 2013

Vibration isolators and anti-vibration mounts are ideal, for example, in creating floating floors for gymnasiums, or performance spaces. However, it is well-known that there are great difficulties on isolating vibration transmission in structural steel components, especially steel floors. Besides, the selection of inertia blocks, which are usually used by engineers as an effective vibration control measure, is usually based on crude methods or the experience of the engineers. Thus, no simple method or indices have been available for assessing the effect of inertia blocks on vibration isolation or stability of vibratory systems. Thus, the aims of this research are to provide further background description using a FE model and present and implement a modal approach, that was validated experimentally, the latter assisting in providing improved understanding of the vibration transmission phenomenon in steel buildings excited by a velocity-source type of excitation. A better visualization of the mean-square velocity distribution in the frequency domain is presented using the concept of modal expansion. Finally, the variation of the mean-square velocity with frequency, whilst varying mass and/or stiffness of the coupled system, is presented.

• Journal of Power Electronics
• /
• v.19 no.4
• /
• pp.922-933
• /
• 2019

The arm inductance (AI) of a modular multilevel converter (MMC) affects both the fault and circulating current magnitudes. In addition, it has an impact on the inverter efficiency and harmonic content. In this study, the AI of a three-phase MMC is optimized in a novel way in terms of DC voltage utilization, harmonics and efficiency. This MMC has 10 submodules (SM) per arm and the power circuit topology of the SM is a half-bridge. The optimum AI is adopted and verified in an MMC that has 100 SMs per arm. Then the phase shift (PS) and phase disposition (PD) pulse width modulation (PWM) methods are investigated for better DC voltage utilization, efficiency and harmonics. It is found that similar performances are obtained for both modulation techniques in terms of DC voltage utilization. However, the total harmonic distortion (THD) of the PS-PWM is found to be 0.02%, which is slightly lower than the THD of the PD-PWM at 0.16%. In efficiency calculations, the switching and conduction losses for all of the semiconductor are considered separately and the minimum efficiency of the 100-SM based MMC is found to be 99.62% for the PS-PWM and 99.64% for the PD-PWM with the optimal value of the AI. Simulation results are verified with an experimental prototype of a 6-SM based MMC.

• Journal of the Korea Institute of Military Science and Technology
• /
• v.14 no.4
• /
• pp.732-739
• /
• 2011

A fuel cell/secondary battery hybrid power generation system could extend well beyond the efficiency and interoperability of the conventional diesel generator. The suggested power source system consists of 2.3 kW class PEMFC, 100 Ah lithium polymer battery, and two DC/DC converters by serial connection type. It was known that interoperability of sub-systems is the key factor for stable and optimal control of the hybrid power generation system. The modeling and simulation methods have been proposed to reduce the number of configurations and performance tests for components selection and select the optimized control condition of the power generation system. The control model for power source system is implemented based on the empirical formulation and carried out in the Matlab/Simulink environment. The results show that the simulation can be used to establish the algorism of prototype and increase the durability of the power source system.

• Smart Media Journal
• /
• v.9 no.4
• /
• pp.66-72
• /
• 2020

As the online education market expands, educational contents with various presentation methods are being developed and released. In addition, it is imperative to develop content that reflects the usability and user environment of users who use this educational content. However, for qualitative growth of contents that will support quantitative expansion of markets, existing model analysis methods are urgently needed at a time when development direction of newly developed contents is secured. In this process of content development, a typical model for setting development goals is needed, as the rules of the prototype affect the entire development process and the final development outcome. It can also provide a positive benefit that screens the issue of performance dualization between processes due to the absence of communication between a single entity or between a number of entities. In the case of AR-based educational content which is effective to secure data necessary for development by securing samples of similar categories because there are not enough ready-made samples released. Therefore, a big data statistical analysis service is needed that can easily collect data and make decisions using big data. In this paper, we would like to design analysis services that enable the selection and detection of intuitive multidimensional factors and attributes, and propose big data-based statistical analysis services that can assist cooperative activities within an organization or among many companies.