• 말소리와 음성과학
• /
• 제3권2호
• /
• pp.71-78
• /
• 2011

In this paper, we propose an approach which constructs classifier ensembles of various channel compensation and feature enhancement methods. CMN and CMVN are used as channel compensation methods. PCA, kernel PCA, greedy kernel PCA, and kernel multimodal discriminant analysis are used as feature enhancement methods. The proposed ensemble system is constructed with the combination of 15 classifiers which include three channel compensation methods (including 'without compensation') and five feature enhancement methods (including 'without enhancement'). Experimental results show that the proposed ensemble system gives highest average speaker identification rate in various environments (channels, noises, and sessions).

• Smart Structures and Systems
• /
• 제4권4호
• /
• pp.465-492
• /
• 2008

Proper pretest planning is a vital component of any successful vibration test on engineering structures. The most important issue in dynamic testing of many engineering structures is arriving at the number and optimal placement of sensors. The sensors must be placed on the structure in such a way that all the important dynamic behaviour of a structural system is captured during the course of the test with sufficient accuracy so that the information can be effectively utilised for structural parameter identification or health monitoring. Several optimal sensor placement (OSP) techniques are proposed in the literature and each of these methods have been evaluated with respect to a specific problem encountered in various engineering disciplines like aerospace, civil, mechanical engineering, etc. In the present work, we propose to perform a detailed characteristic evaluation of some selective popular OSP techniques with respect to their application to practical civil engineering problems. Numerical experiments carried out in the paper on various practical civil engineering structures indicate that effective independence (EFI) method is more consistent when compared to all other sensor placement techniques.

• 한국IT서비스학회지
• /
• 제13권3호
• /
• pp.183-200
• /
• 2014

Online brand communities have become a major component of marketing strategy given that these communities encourage participation and share the culture of Web 2.0 core concepts to Internet users. This study investigated the effects of social capital and knowledge quality on the success of online brand communities. A research model suggests that trust among members and the identification derived from social capital theory and knowledge quality influence individual community participation; knowledge quality also influences brand trust. In turn, community participation and brand trust develop brand loyalty. The model was empirically analyzed using structural equation modeling with data from online brand community members in Korea. The results indicate that identification and knowledge quality significantly affects brand trust and brand loyalty through community participation. This study provides a basis for developing a success model for online brand communities. Also, this study identifies a new role of knowledge quality in an online brand community context.

• 대한전기학회논문지
• /
• 제38권9호
• /
• pp.710-723
• /
• 1989

This paper describes the efforts to develope a PC based parameter identification system for D.C servomotors. A new identification algorithm for the D.C. servomotor parameters is developed. The algorithm is implemented on 16 bit IBM-PC/XT using the C language. The whole identification process of signal generation, measuring and parameter determination is fully automated. To minimize the errors due to the ripple component in the measured armature currents, digital averaging filter is employed. The proposed parameter correction method using the deadzone current and the time to reach the peak current resulted in excellent agreement between the measured current and the current estimated using the model.

• 스마트미디어저널
• /
• 제5권3호
• /
• pp.30-34
• /
• 2016

Nowadays, there are a lot of Korean documents, which often need to be identified in one of printed or handwritten text. Early methods for the identification use structural features, which can be simple and easy to apply to text of a specific font, but its performance depends on the font type and characteristics of the text. Recently, the bag-of-words model has been used for the identification, which can be invariant to changes in font size, distortions or modifications to the text. The method based on bag-of-words model includes three steps: word segmentation using connected component grouping, feature extraction, and finally classification using SVM(Support Vector Machine). In this paper, bag-of-words model based method is proposed using SURF(Speeded Up Robust Feature) for the identification of machine printed and handwritten text in Korean documents. The experiment shows that the proposed method outperforms methods based on structural features.

• 한국원자력학회:학술대회논문집
• /
• 한국원자력학회 2004년도 추계학술발표회 발표논문집
• /
• pp.1165-1166
• /
• 2004

• 디지털융복합연구
• /
• 제6권4호
• /
• pp.25-34
• /
• 2008

This study explores the component factors of innovation brand to build organizational culture of government ministries. A perception of organizational officers on innovation brand is ranked orderly by brand awareness(recognition, discrimination), brand loyalty (identification, ease of memory, meaning diffusion, reaction of customer needs), brand salience, brand knowledge and brand innovation. The results of factor analysis classify the component factors with factor1(brand awareness, brand loyalty) and factor2(brand innovation). This results indicate that the officers definitely recognize the value of innovation brand and brand identity. The brand discrimination and brand loyalty can also positively affect perception on brand innovation.

• 한국복합재료학회:학술대회논문집
• /
• 한국복합재료학회 2000년도 춘계학술발표대회 논문집
• /
• pp.9-14
• /
• 2000

This paper presents the analytical results of local buckling of orthotropic I-shape compression members. Employing the equilibrium approach, the characteristic equation for local buckling of I-shape compression member is derived. Using the derived equation, the minimum buckling coefficients with respect to the ratio of width to thickness for the I-shape column are suggested as a graphical form. In addition, the dominant plate component initiating the local buckling of I-shape column is also identified by using the approximate solution and the results are plotted with dotted line on the minimum bucking coefficient curve.

• 한국해양공학회지
• /
• 제26권4호
• /
• pp.70-76
• /
• 2012

The independent component analysis (ICA) technique is a source identification method that uses statistical independence to separate source signals from measured signals. It has been successfully applied to various fields such as medical care and communication. In this study, the ICA technique was adopted to analyze the vibration source contribution of plate structures. The theory of the ICA technique is introduced and the procedure of the vibration source contribution analysis based on the ICA technique is proposed. To investigate the applicability of the proposed method to plate structures, numerical examples are presented for a rectangular plate under harmonic force excitations. The results show that the proposed method could become an effective tool for the vibration source contribution analysis of a plate structure.

• 한국자원식물학회지
• /
• 제11권2호
• /
• pp.210-216
• /
• 1998

Taxonomic studies in external morphology, principal component analysis and cluster analysis were conducted to understand the intraspecific relationship among three habitats (Jirisan, Odaesan and Ulleungdo) of allium voctorialis var. platyphyllum. External morphology such as bulb color, leaf blade length and width, petiole length, total leaf length, peduncle length, perianth lobe length and width, length of anther and filament were useful characters for identification of poplations in three habitats. The results obtained based on the principal component (Pc) analysis of treated 72 OTUs(included outgroup) were divided into three groups by the PC 1 ,2,3 and the sums of contributions for the total variance were 84.1%(PC1 51.0%, PC2 24.9% and PC3 8.2%, respectively). In cluster analysis by the UPGMA and Ward's methods , there was similarities in the compostion of clustered taxa, and only Ulleungdo population was distinctly identified from population of other two habitats.