• Journal of Korean Society for Atmospheric Environment
• /
• v.32 no.5
• /
• pp.513-525
• /
• 2016

To propose an effective ensemble methods in predicting $PM_{10}$ concentration, six experiments were designed by different ensemble average methods (e.g., non-weighted, single weighted, and cluster weighted methods). The single weighted method was calculated the weighted value using both multiple regression analysis and singular value decomposition and the cluster weighted method was estimated the weighted value based on temperature, relative humidity, and wind component using multiple regression analysis. The effects of ensemble average methods were significantly better in weighted average than non-weight. The results of ensemble experiments using weighted average methods were distinguished according to methods calculating the weighted value. The single weighted average method using multiple regression analysis showed the highest accuracy for hourly $PM_{10}$ concentration, and the cluster weighted average method based on relative humidity showed the highest accuracy for daily mean $PM_{10}$ concentration. However, the result of ensemble spread analysis showed better reliability in the single weighted average method than the cluster weighted average method based on relative humidity. Thus, the single weighted average method was the most effective method in this study case.

• The Proceeding of the Korean Institute of Electromagnetic Engineering and Science
• /
• v.17 no.3 s.59
• /
• pp.63-73
• /
• 2006

Auctions have been traditionally used to find the current price of goods when little is known about their true value. A special auction methodology, called a 'simultaneous multiple round auction', is available to auction radiofrequency spectrum where all lots are simultaneously on of for over multiple rounds of bidding. This type of auction is especially useful when there are lots that are of essentially equal value and substitutable, except that different bidders may prefer different combinations of lots. By using multiple rounds, a bidder has the opportunity to gather information concerning the value of individual lots and can change strategy by shifting the bidding to another preferred combination if one combination becomes too expensive. Information is released in three main ways during an auction: Bidder Status; High Bids; and Bandwidth Value.

• Applied Biological Chemistry
• /
• v.45 no.1
• /
• pp.18-24
• /
• 2002

This study was conducted to find out optimum conditions for kanjang fermented with barley bran. The correlation between taste components and sensory evaluation score was analyzed with stepwise multiple regression analysis. It was revealed that the taste of kanjang was explained with the mix of free amino acids, free sugars and organic acids. The highest multiple correlation coefficient was obtained from absolute value transformed with logarithm. Thus, stepwise multiple regression analysis was conducted with absolute value transformed with logarithm, for which F-value was highest and standard error of estimation was lowest among the multiple regression models transformed with six variables. The stepwise multiple regression analysis showed that the taste components which most contribute to the quality of taste of kanjang fermented with barley bran was salty taste component followed by palatable taste component, and bitter taste component.

• Korean Journal of Mathematics
• /
• v.23 no.4
• /
• pp.665-732
• /
• 2015

Existence results for multiple positive solutions of two classes of boundary value problems for bilateral difference systems are established by using a fixed point theorem under convenient assumptions. It is the purpose of this paper to show that the approach to get positive solutions of boundary value problems of finite difference equations by using multi-fixed-point theorems can be extended to treat the bilateral difference systems with one-dimensional Laplacians. As an application, the sufficient conditions are established for finding multiple positive homoclinic solutions of a bilateral difference system. The methods used in this paper may be useful for numerical simulation. An example is presented to illustrate the main theorems. Further studies are proposed at the end of the paper.

• Proceedings of the KIEE Conference
• /
• 2004.07d
• /
• pp.2559-2561
• /
• 2004

This paper proposes the new signal-to-noise ratio(SNR) that is different from the conventional signal-to-noise ratio (SNR) in direct-sequence code-division multiple-access communication system employing offset quadrature phase-shift keying(OQPSK) and using a chip waveform. The conventional SNR value is so different from a real SNR value. Therefore, we propose a new SNR equation approximated to real SNR. The multiple-access interference(MAI) in DS-CDMA communication system has an effect on SNR performance and MAI is concerned with the correlation functions of the chip waveform. For this reason, we considered all possible correlations of chip waveforms. In conclusion, the SNR value of proposed method is enclosed to the real SNR value.

• Analytical Science and Technology
• /
• v.15 no.6
• /
• pp.580-583
• /
• 2002

New approach is developed employing the overall uncertainty obtained from multiple measurements to evaluate the statistical significance for the difference between a given reference value and its measured value determined in a lab. The overall uncertainty is determined by separate combinations of the uncertainties arising from systematic and random effects. It is shown that the uncertainty term in regular t-test can be underestimated by n measurements.

• Journal of Information Processing Systems
• /
• v.17 no.6
• /
• pp.1083-1096
• /
• 2021

Compressed sensing-based matching pursuit algorithms can estimate the sparse channel of massive multiple input multiple-output systems with short pilot sequences. Although they have the advantages of low computational complexity and low pilot overhead, their accuracy remains insufficient. Simply multiplying the weight value and the estimated channel obtained in different iterations can only improve the accuracy of channel estimation under conditions of low signal-to-noise ratio (SNR), whereas it degrades accuracy under conditions of high SNR. To address this issue, an improved weighted matching pursuit algorithm is proposed, which obtains a suitable weight value u_op by training the channel data. The step of the weight value increasing with successive iterations is calculated according to the sparsity of the channel and u_op. Adjusting the weight value adaptively over the iterations can further improve the accuracy of estimation. The results of simulations conducted to evaluate the proposed algorithm show that it exhibits improved performance in terms of accuracy compared to previous methods under conditions of both high and low SNR.

• International conference on construction engineering and project management
• /
• 2009.05a
• /
• pp.1503-1508
• /
• 2009

The paradigm of urban generation does not lie in physical development/maintenance such as urban redevelopment any more. The paradigm is shifting to balanced activation of administration / management functions including central commerce/business functions, broad culture/tourism functions, international functions and adequate level of residence functions. The urban regeneration project aims to restore functions of cities by physical/environmental, living/cultural and industrial/economical regeneration and is managed differently from existing projects in that it includes multiple sub-projects in it. The overall projects management should be by managing the value sought by the urban regeneration project and multiple other sub-projects. The objective of this study is to present various methods of value management in order to avoid conflicts between various objectives within the said project. It aims to provide the value management methods for decision making by understanding correlatedness between values of various projects and prioritizing them.

• Journal of the Korean Operations Research and Management Science Society
• /
• v.37 no.3
• /
• pp.13-21
• /
• 2012

In this note, a recent work in Won (2011) which investigates properties of the newsvendor model under progressive multiple discounts is revisited and a complete proof is provided for the conjecture on the consistent advantage of progressive multiple discounts over no-discounts in terms of the expected profit. The proof considers the generalized newsvendor model under progressive multiple discounts extended with positive shortage cost and salvage value which have not been considered in the previous newsvendor models under progressive multiple discounts. Without relying on derivatives, we prove that the expected profit under progressive multiple discounts are consistently greater than or equal to the one under no-discounts for every order quantity as far as her multiple discounts do not decrease customer demand, and therefore, the optimal expected profit under progressive multiple discounts is always greater than or equal to the one under no-discounts. As by-products from the proof, some interesting features of the generalized newsvendor model under progressive multiple discounts are revealed.

• Journal of applied mathematics & informatics
• /
• v.28 no.3_4
• /
• pp.837-844
• /
• 2010

In this paper, a class of initial value problem of hyperbolic equations for fourth order with multiple characteristics is considered and can be solved analytically by variable transforms. Also, similar to Goursat's problem we present a direct integration technique for finding a new solutions of an inhomogeneous hyperbolic equation of fourth order such that the attached conditions are given on its multiple characteristics.