• Title, Summary, Keyword: support function

Search Result 2,274, Processing Time 0.046 seconds

Support vector quantile regression ensemble with bagging

  • Shim, Jooyong;Hwang, Changha
    • Journal of the Korean Data and Information Science Society
    • /
    • v.25 no.3
    • /
    • pp.677-684
    • /
    • 2014
  • Support vector quantile regression (SVQR) is capable of providing more complete description of the linear and nonlinear relationships among random variables. To improve the estimation performance of SVQR we propose to use SVQR ensemble with bagging (bootstrap aggregating), in which SVQRs are trained independently using the training data sets sampled randomly via a bootstrap method. Then, they are aggregated to obtain the estimator of the quantile regression function using the penalized objective function composed of check functions. Experimental results are then presented, which illustrate the performance of SVQR ensemble with bagging.

Cognitive Function, Depression, Social Support, and Self-Care in Elderly with Hypertension (노인 고혈압 환자의 인지기능, 우울, 사회적 지지 및 자가간호에 관한 연구)

  • Kim, Ok-Soo;Jeon, Hae-Ok
    • Korean Journal of Adult Nursing
    • /
    • v.20 no.5
    • /
    • pp.675-684
    • /
    • 2008
  • Purpose: The purpose of this study was to examine the relationship among cognitive function, depression, social support, and self-care in elderly with hypertension. Methods: The subjects were 132 elderly with hypertension living in Seoul, Korea. Data were collected through face-to-face interviews using the Korean version of Mini-Mental State Examination(MMSE-K), Short form geriatric depression scale, social support questionnaire 6, and hypertension self-care scale. Results: Thirty-four percent of the subjects had questionable dementia and forty-two percent of the subjects were depressed. Means for social support were 2.40 for network size and 4.07 for satisfaction. The mean score of hypertension self-care was 60.34, indicating that the subjects took care of themselves moderately well. Cognitive function was negatively related to depression. Social support network and satisfaction were negatively related to depression. Self-care was negatively related to social support network. Conclusion: Programs are needed for elderly with hypertension to improve their cognitive function, depression, and social support. Also further studies are needed to confirm the factors related to self-care in the elderly with hypertension.

  • PDF

The Effect of Social Support of Parents of children with Disabilities on Family Function : Mediating effect of disability (장애 아동 부모의 사회적지지가 가족기능에 미치는 영향: 장애수용의 매개효과와 경제적 안정감의 조절효과)

  • Mun, Jong-Hyeok
    • Journal of the Korea Academia-Industrial cooperation Society
    • /
    • v.20 no.6
    • /
    • pp.421-429
    • /
    • 2019
  • This study seeks to discuss the effects of social support, acceptance of disability, and the sense of economic stability on the part of parents of children with developmental disabilities who are receiving treatment and training at a child development center has on family function. A survey was given to 252 parents of children who were using the child development center in S city. In the relationship between social support and family function, the mediating effects of the disability acceptance and the social support, the disability acceptance and the family function were used to verify the adjustment effect of the economic stability. The results of this study are as follows. First, as a result of checking the moderating effect of economic stabilization, social support, family function, disability acceptance and family function did not show any effect on economic stability. Second, as a result of verifying whether the relationship between social support and family function is mediated by disability acceptance, disability acceptance partially mediated the relationship between social support and family function. This study is significant in that it provided basic data for the development of a program to help children with developmental disabilities function properly.

Quality of Life among Breast Cancer Patients Undergoing Treatment in National Cancer Centers in Nepal

  • Manandhar, Sajani;Shrestha, Deepak Sundar;Taechaboonsermsk, Pimsurang;Siri, Sukhontha;Suparp, Jarueyporn
    • Asian Pacific Journal of Cancer Prevention
    • /
    • v.15 no.22
    • /
    • pp.9753-9757
    • /
    • 2014
  • Purpose: To study the quality of life and to identify associated factors among breast cancer patients undergoing treatment in national cancer centers in Nepal. Materials and Methods: One hundred breast cancer patients were selected and interviewed using a structured questionnaire. European Organization of Research and Treatment of Cancer EORTC-QLQ-C30 and EORTC-QLQ-BR23 were used to assess quality of life and modified Medical Outcome Study -Social Support survey(mMOS-SS) was used to assess social support. Only multi-item scales of EORTC C30 and BR23 were analyzed for relationships. Independent sample T-tests and ANOVA were applied to analyze differences in mean scores. Results: The score of global health status/quality of life (GHS/GQoL) was marginally above average (mean=52.8). The worst performed scales in C-30 were emotional and social function while best performed scales were physical and role function. In BR-23, most of the patients fell into the problematic group regarding sexual function and enjoyment. Almost 90% had financial difficulties. Symptom scales did not demonstrate many problems. Older individuals, patients with stage I breast cancer and thosewith good social support were found to have good GHS/GQoL. Of all the influencing factors, social support was established to have strong statistical associations with most of the functional scales: GHS/GQoL (0.003), emotional function (<0.001), cognitive function (0.020), social function (<0.001) and body image function (0.011). Body image was significantly associated with most of the influencing factors: monthly family income (0.003), type of treatment (<0.001), type of surgery (<0.001), stage of cancer (0.017) and social support (0.011). Conclusions: Strategies to improve social support of the patients undergoing treatment should be given priority and financial difficulties faced by breast cancer patients should be well addressed from a policy making level by initiating health financing system.

SVC with Modified Hinge Loss Function

  • Lee, Sang-Bock
    • Journal of the Korean Data and Information Science Society
    • /
    • v.17 no.3
    • /
    • pp.905-912
    • /
    • 2006
  • Support vector classification(SVC) provides more complete description of the linear and nonlinear relationships between input vectors and classifiers. In this paper we propose to solve the optimization problem of SVC with a modified hinge loss function, which enables to use an iterative reweighted least squares(IRWLS) procedure. We also introduce the approximate cross validation function to select the hyperparameters which affect the performance of SVC. Experimental results are then presented which illustrate the performance of the proposed procedure for classification.

  • PDF

A Study on the Types of Social Networks of Housewives in Urban Nuclear Families (가족의 사회관계망 유형화 연구 - 도시 핵가족 주부를 중심으로 -)

  • 원효종;옥선화
    • Journal of Korean Home Management Association
    • /
    • v.20 no.4
    • /
    • pp.149-164
    • /
    • 2002
  • The purpose of this study was to identify the types of social networks of urban housewives according to different network composition patterns and to analyze the structural and functional characteristics of identified types. The data used in this study were collected from 589 full-time housewives residing in Taejeon city. The major findings are as follows: 1) The social networks of housewives in urban nuclear families were classified into eight types: the kin network, the non-kin network, the kin-centered network, the friend-centered network, the neighbor-centered network, the associate-centered network, the parallel network, and the decentralized network. 2) The structual characteristics (size, density, homogeneity, duration, proximity, frequency, closeness, direction) varied according to the type. The kin network type and the non-kin network type showed extreme degrees in network characteristics. The parallel network type and the decentralized network type showed an average level of network characteristics. The kin-, friend-, neighbor-, and the associate-centered types showed network characteristics of an intermediate level between the single-category types and the decentralized type. 3) The average levels of function of social network types were different in only two(service support, interference) of the six function areas(emotional support, service support, material support, information support, social companionship support, interference). The average level of service support by the non-kin network type was higher than other types. The average level of interference by the kin-centered network type was higher than other types, and that of the neighbor-centered network type was lower than other types. On the other hand, the total amount of function performance of social network types was different in all function areas. The total amount of social support given by the decentralized network type was greater than the other types. The total amount of interference given by the non-kin network type was smaller than the other types.

Support vector quantile regression for longitudinal data

  • Hwang, Chang-Ha
    • Journal of the Korean Data and Information Science Society
    • /
    • v.21 no.2
    • /
    • pp.309-316
    • /
    • 2010
  • Support vector quantile regression (SVQR) is capable of providing more complete description of the linear and nonlinear relationships among response and input variables. In this paper we propose a weighted SVQR for the longitudinal data. Furthermore, we introduce the generalized approximate cross validation function to select the hyperparameters which affect the performance of SVQR. Experimental results are the presented, which illustrate the performance of the proposed SVQR.

Multiclass Support Vector Machines with SCAD

  • Jung, Kang-Mo
    • Communications for Statistical Applications and Methods
    • /
    • v.19 no.5
    • /
    • pp.655-662
    • /
    • 2012
  • Classification is an important research field in pattern recognition with high-dimensional predictors. The support vector machine(SVM) is a penalized feature selector and classifier. It is based on the hinge loss function, the non-convex penalty function, and the smoothly clipped absolute deviation(SCAD) suggested by Fan and Li (2001). We developed the algorithm for the multiclass SVM with the SCAD penalty function using the local quadratic approximation. For multiclass problems we compared the performance of the SVM with the $L_1$, $L_2$ penalty functions and the developed method.

- Development of Design Support Methodology Using Product Function Analysis - (제품기능분석을 이용한 설계지원 방법론 개발)

  • 김형준;이내형;서광규
    • Journal of the Korea Safety Management and Science
    • /
    • v.5 no.2
    • /
    • pp.111-127
    • /
    • 2003
  • In this paper, a new method of product function analysis is presented to categorize various design information generated in product development processes. In order to improve product functions, designers must understand unit functions and modified parts of products. The product function analysis (PFA) is based on the designer's understanding of product functions. The proposed PFA provides the methodology to classify the various functions systematically and understand the relation between functions easily. Using this approach, efficient design support system can be developed and used for designers to support decision-making with design knowledge.

Modeling of Plasma Process Using Support Vector Machine (Support Vector Machine을 이용한 플라즈마 공정 모델링)

  • Kim, Min-Jae;Kim, Byung-Whan
    • Proceedings of the KIEE Conference
    • /
    • /
    • pp.211-213
    • /
    • 2006
  • In this study, plasma etching process was modeled by using support vector machine (SVM). The data used in modeling were collected from the etching of silica thin films in inductively coupled plasma. For training and testing neural network, 9 and 6 experiments were used respectively. The performance of SVM was evaluated as a function of kernel type and function type. For the kernel type, Epsilon-SVR and Nu-SVR were included. For the function type, linear, polynomial, and radial basis function (RBF) were included. The performance of SVM was optimized first in terms of kernel type, then as a function of function type. Five film characteristics were modeled by using SVM and the optimized models were compared to statistical regression models. The comparison revealed that statistical regression models yielded better predictions than SVM.

  • PDF