• Communications for Statistical Applications and Methods
• /
• 제28권3호
• /
• pp.267-279
• /
• 2021

A regression with multi-dimensional responses is quite common nowadays in the so-called big data era. In such regression, to relieve the curse of dimension due to high-dimension of responses, the dimension reduction of predictors is essential in analysis. Sufficient dimension reduction provides effective tools for the reduction, but there are few sufficient dimension reduction methodologies for multivariate regression. To fill this gap, we newly propose two fused slice-based inverse regression methods. The proposed approaches are robust to the numbers of clusters or slices and improve the estimation results over existing methods by fusing many kernel matrices. Numerical studies are presented and are compared with existing methods. Real data analysis confirms practical usefulness of the proposed methods.

• 한국의류학회지
• /
• 제16권1호
• /
• pp.73-83
• /
• 1992

This paper examined risk reduction methods utilized by consumers in apparel buying situation in multidimensional conceptual framework, and analyzed the relationships between risk types, consumer demographic variables and preferences of risk reduction methods. Samples of 224 consumers were deliberately selected to include various demographic characteristics such as sex, age, educational level, occupation, income level. The results of the principal axis factor analysis indicated that 26 item risk reduction methods could be summarized into 6 meaningful factors; Marketer-dominated Information Sources Use (MIS), Prepurchase Deliberation / Observation i Dependence on Past Buying Experience (DOE), Independent Information Sources Use (lIS), Interpersonal Information Sources Use (PIS), Brand Loyalty (BL), Label Reading / Guarantee Buying (RG). DOE were used most whereas IIS used least. Correlations of various types of risk perceived with the preference of risk reduction methods were significant especially for positive relationship between psychologi-cal and/or economic risk and DOE, and between social risk and/or fashionability loss and MIS. Results of ANOVA and Duncan test suggested that sex, age, educational level, occupation of consumers can act as ones of determinant variables on making differences in the use of risk reduction methods.

• Communications for Statistical Applications and Methods
• /
• 제29권5호
• /
• pp.615-627
• /
• 2022

Principal Fitted Component (PFC) is a semi-parametric sufficient dimension reduction (SDR) method, which is originally proposed in Cook (2007). According to Cook (2007), the PFC has a connection with other usual non-parametric SDR methods. The connection is limited to sliced inverse regression (Li, 1991) and ordinary least squares. Since there is no direct comparison between the two approaches in various forward regressions up to date, a practical guidance between the two approaches is necessary for usual statistical practitioners. To fill this practical necessity, in this paper, we newly derive a connection of the PFC to covariance methods (Yin and Cook, 2002), which is one of the most popular SDR methods. Also, intensive numerical studies have done closely to examine and compare the estimation performances of the semi- and non-parametric SDR methods for various forward regressions. The founding from the numerical studies are confirmed in a real data example.

• 전기화학회지
• /
• 제10권2호
• /
• pp.73-81
• /
• 2007

This review article considered the electrochemical reduction of uranyl ions on a Pt surface. Specifically, we focussed on the improvement in its reduction current efficiency. First, this article briefly explained the fundamentals of the reduction of uranyl ($UO_2^{2+}$) ions on a Pt surface. Namely, they involved the electrochemical behaviour of uranium species, and electrochemical cell configurations for the reduction of $UO_2^{2+}$ ions. In addition, the effects of adsorbed hydrogen atoms were investigated on the reduction of $UO_2^{2+}$ ions. Finally, this article presented the methods for improving current efficiency of the reduction of $UO_2^{2+}$ ions on a Pt surface. Three different kinds of methods are introduced, which include electrochemical surface treatments of Pt electrode involving hydrogenation and anodisation, the use of catalyst poisons, and formation of thin mercury film on a Pt electrode. Moreover, this article provided some clues about how hydrogenation and catalyst poisons work on the reduction of $UO_2^{2+}$ ions.

• 대한족부족관절학회지
• /
• 제12권1호
• /
• pp.9-13
• /
• 2008

Purpose: Medial capsulorrhaphy is additional hallux reduction method following various hallux reduction procedures and we are going to report author's opinion about several methods of medial capsulorrhaphy. Materials and Methods: We performed three kinds of medial capsulotomy and imbricatory capsulorrhaphy in hallux valgus surgery. Through 8 cadavar study, we compared the easiness of sesamoid reduction and hallux valgus angle reduction. Also, we measured thickness of capsule in various portions. Results: Longitudinal capsule incision and imbrication was useful in sesamoid reduction and vertical procedures was useful in hallux valgus angle reduction. The capsule thickness was measured thickest in dorsal and distal portioin. Conclusion: The methods of medial capsulorrhaphy should be planned preoperatively considering individual hallux deformities. These selected medial capsulorrhaphy can help the reduction of hallux valgus deformity correction and its maintenance.

• 신재생에너지
• /
• 제16권2호
• /
• pp.1-13
• /
• 2020

The reduction of noise from wind turbines has been studied using various methods. Some examples include controlling wind turbine blades, designing low-noise-emitting wind turbine blades, and using trailing-edge serrations. Among these methods, serration is considered an effective noise reduction method. Various studies have aimed to understand the effects of trailing-edge serration parameters. Most studies, however, have focused on fixed-wing concepts, and few have analyzed noise reduction or developed a prediction method for rotor-type blades. Herein, a noise prediction method, composed of two noise prediction methods for a wind turbine with trailing-edge serrations, is proposed. From the flow information obtained by an in-house program (WINFAS), the noise from non-serrated blades is calculated by turbulent ingestion noise and airfoil self-noise prediction methods. The degree of noise reduction caused by the trailing-edge serrations is predicted in the frequency domain by Lyu's method. The amount of noise reduction is subtracted from the predicted result of the non-serrated blade and the total reduction of the noise from the rotor blades is calculated.

• Industrial Engineering and Management Systems
• /
• 제13권4호
• /
• pp.454-462
• /
• 2014

Retention of possible churning customer is one of the most important issues in customer relationship management, so companies try to predict churn customers using their large-scale high-dimensional data. This study focuses on dealing with large data sets by reducing the dimensionality. By using six different dimension reduction methods-Principal Component Analysis (PCA), factor analysis (FA), locally linear embedding (LLE), local tangent space alignment (LTSA), locally preserving projections (LPP), and deep auto-encoder-our experiments apply each dimension reduction method to the training data, build a classification model using the mapped data and then measure the performance using hit rate to compare the dimension reduction methods. In the result, PCA shows good performance despite its simplicity, and the deep auto-encoder gives the best overall performance. These results can be explained by the characteristics of the churn prediction data that is highly correlated and overlapped over the classes. We also proposed a simple out-of-sample extension method for the nonlinear dimension reduction methods, LLE and LTSA, utilizing the characteristic of the data.

• 한국물환경학회지
• /
• 제24권3호
• /
• pp.297-305
• /
• 2008

It is necessary to select proper reduction methods and to calculate reasonably reduction amount for making good practice of the reduction scheme. Moreover, it is suggested that the reduction amount have to be distributed properly during the planning period. In other words, it has not to be concentrated on the specific year (especially final year of the planning period). The reason why, if the reduction amount concentrate on the final year of the planning period, allotment loading amount could not be achieved in some cases (e.g., insufficiency of budget, extension of construction duration). Even though much of the budget have been supported from national treasury (about 50%), it is thought the role of the local government must be strengthened gradually.

• 한국염색가공학회지
• /
• 제13권4호
• /
• pp.234-240
• /
• 2001

In order to improve the washing fastness of dyed polyester artificial suede fabric, it was dyed by using auto and anthraguinone type disperse dyes and treated with 3 different reduction clearing methods. The reduction clearing methods used in this study were normal alkaline reduction clearing, $N_2$ gas replacement method, and ultrasonic treatment during normal reduction clearing. The results were as followings ; The washing fastness property of dyed polyester artificial suede fabric was slightly improved by reduction clearing with $N_2$ gas replacement or with ultrasonic treatment comparing with normal alkaline reduction clearing. It was found that the use of $N_2$ gas replacement or ultrasonic treatment during reduction clearing eave effective removal of unfixed dyes on the fiber surface. We also obtained that the azo type disperse dye on polyester artificial fabric suede fabric showed higher wash fastness than anthraquinone type disperse dye.

• 음성과학
• /
• 제11권1호
• /
• pp.43-52
• /
• 2004

This paper concerns an effective dual-channel noise reduction method to increase the performance of speech recognition in a car environment. While various single channel methods have already been developed and dual-channel methods have been studied somewhat, their effectiveness in real environments, such as in cars, has not yet been formally proven in terms of achieving acceptable performance level. Our aim is to remedy the low performance of the single and dual-channel noise reduction methods. This paper proposes an effective dual-channel noise reduction method based on a high-pass filter and front-end processing of the eigendecomposition method. We experimented with a real multi-channel car database and compared the results with respect to the microphones arrangements. From the analysis and results, we show that the enhanced eigendecomposition method combined with high-pass filter indeed significantly improve the speech recognition performance under a dual-channel environment.