• Communications for Statistical Applications and Methods
• /
• v.30 no.3
• /
• pp.245-258
• /
• 2023

This study proposes a modification to the objective function of the support vector machine for the linearly non-separable case of a binary classifier y_i ∈ {-1, 1}. The modification takes into account the position of each data item x_i from its corresponding class centroid. The resulting optimization function involves the centroid mean vector, and the spread of data besides the support vectors, which should be minimized by the choice of hyper-plane β. Theoretical assumptions have been tested to derive an optimal separable hyperplane that yields the minimal misclassification rate. The proposed method has been evaluated using simulation studies and real-life COVID-19 patient outcome hospitalization data. Results show that the proposed method performs better than the classical linear SVM classifier as the sample size increases and is preferred in the presence of correlations among predictors as well as among extreme values.

• Korean Journal of Child Studies
• /
• v.37 no.2
• /
• pp.157-168
• /
• 2016

Objective: This study examined the facotrs influencing the relationship of adolescents with non-custodial parent. Specifically, this study focused on the comparative influence of the family function as a factor controlling other factors such as socio-demographic characteristics, beliefs about parental divorce, and social support. Methods: Data were collected from 322 adolescents from divorced families using a structured questionnaire. SPSS 22.0, descriptive statistical analysis, correlation analysis, and hierarchical multiple regression were performed to analyze the data. Results and Conclusion: The results revealed that beliefs about parental divorce, social support, and family function affected the relationship with non-custodial parent. After controlling the influence of other factors, family function was found to have a significant influence on the relationship with non-custodial parents. Based on the results, practical suggestions were provided to enhance the relationship between adolescents and non-custodial parents.

• The Transactions of the Korea Information Processing Society
• /
• v.7 no.6
• /
• pp.1867-1873
• /
• 2000

Function approximation from a set of input-output pairs has numerous applications in scientific and engineering areas. Support vector machine (SVM) is a new and very promising classification, regression and function approximation technique developed by Vapnik and his group at AT&TG Bell Laboratories. However, it has failed to establish itself as common machine learning tool. This is partly due to the fact that this is not easy to implement, and its standard implementation requires the use of optimization package for quadratic programming (QP). In this appear we present simple iterative Kernel Adatron (KA) algorithm for function approximation and compare it with standard SVM algorithm using QP.

• Journal of Electrical Engineering and information Science
• /
• v.2 no.3
• /
• pp.41-50
• /
• 1997

In this paper, we describe the design, implementation and evaluation for a multimedia conferencing system with intramedia and intermedia synchronization support between audio and video. The synchronization mechanism proposed here is capable of dynamically adapting to various network conditions thus providing an optimized QoS. In realizing the system based on this mechanism, NeVoT on Mbone is used for audio and VIC for video. Furthermore a synchromization controller is designed and realized with a unique process in supporting intermedia synchronization. Each media agents handling its media stream are modified with intramedia synchronization function. And a communicative function between media agents and synchronization controller is added as well for intermedia synchronization function. Each media agents function reports its buffering status to the synchronization control process which in turn send out optimized buffering delay value thus supporting intermedia synchronization. The realized system is configured and tested on Ethernet and ATM network where performance measurements were performed and its effective synchronization support has been assured.

• Journal of the Korean Data and Information Science Society
• /
• v.26 no.6
• /
• pp.1537-1545
• /
• 2015

Support vector quantile regression (SVQR) can be obtained by applying support vector machine with a check function instead of an e-insensitive loss function into the quantile regression, which still requires to solve a quadratic program (QP) problem which is time and memory expensive. In this paper we propose an SVQR whose objective function is composed of an asymmetric quadratic loss function. The proposed method overcomes the weak point of the SVQR with the check function. We use the iterative procedure to solve the objective problem. Furthermore, we introduce the generalized cross validation function to select the hyper-parameters which affect the performance of SVQR. Experimental results are then presented, which illustrate the performance of proposed SVQR.

• International Journal of Fuzzy Logic and Intelligent Systems
• /
• v.8 no.3
• /
• pp.196-201
• /
• 2008

Statistical learning theory has three analytical tools which are support vector machine, support vector regression, and support vector clustering for classification, regression, and clustering respectively. In general, their performances are good because they are constructed by convex optimization. But, there are some problems in the methods. One of the problems is the subjective determination of the parameters for kernel function and regularization by the arts of researchers. Also, the results of the learning machines are depended on the selected parameters. In this paper, we propose an efficient method for objective determination of the parameters of support vector clustering which is the clustering method of statistical learning theory. Using evolutionary algorithm and bootstrap method, we select the parameters of kernel function and regularization constant objectively. To verify improved performances of proposed research, we compare our method with established learning algorithms using the data sets form ucr machine learning repository and synthetic data.

• Journal of Korean Academy of Nursing
• /
• v.29 no.3
• /
• pp.639-655
• /
• 1999

An explanatory design was employed to identify the relationship of physical, emotional & social readjustment and social support of post hospitalized stroke patients and their caregivers. A convenient sample of 254 patients who given follow-up care at the outpatient department after discharge and 225 caregivers were recruited. Mental Status Questionnaire (MSQ), Social Support Inventory Stroke Survivors (SSISS), Illness intrusiveness(II), Instument Activity of Daily Living(IADL), Center of Epidemilogic Studies-Depression(CES-D), social activity and caregiver burden were used for measurement in this study. Results showed patient's physical level measured by IADL and psychological level measured by depression were high. But social activity was low. Cognitive function, depression & social activity were not significantly different by the posthospitalized period, but IADL was. The source of professional support was mostly the physician at the outpatient department. The family support was found significantly related to patient's depression & social activity and caregiver's subjective burden. Professional support was found significantly related to patient's IADL & depression. Illness intrusiveness as a mediating variable was a sig nificantly predicting power on patient's IADL & depression. The path analysis was used to identify the variables to predict the physical, emotional, and social status of patients. As a result, patient's age, cognitive function, illness intursiveness and professional support significantly predicted the level of IADL ; patient's cognitive function, illness intrusiveness and family support significantly predicted the level of depression ; and patient's age and family support significantly predicted the level of social activity of posthospitalized stroke patients. Based upon these results, the rehabilitation programs to reduce the illness intrusiveness and improve cognitive funtion were recommended for the readjustment of the stroke patients. This model of the readjustment of the posthospitalized stroke patients is recommended as the framework for care of the stroke patients.

• Journal of the Korean Data and Information Science Society
• /
• v.14 no.1
• /
• pp.67-74
• /
• 2003

Median regression analysis has robustness properties which make it an attractive alternative to regression based on the mean. Support vector machine (SVM) is used widely in real-world regression tasks. In this paper, we propose a new SV median regression based on check function. And we illustrate how this proposed SVM performs and compare this with the SVM based on absolute deviation loss function.

• Journal of applied mathematics & informatics
• /
• v.15 no.1_2
• /
• pp.211-225
• /
• 2004

A mixed type dual to a programming problem containing support functions in a objective as well as constraint functions is formulated and various duality results are validated under generalized convexity and invexity conditions. Several known results are deducted as special cases.

• Journal of the Korean Data and Information Science Society
• /
• v.15 no.2
• /
• pp.507-513
• /
• 2004

Least-squares support vector machine (LS-SVM) has been very successful in pattern recognition and function estimation problems for crisp data. In this paper, we propose LS-SVM approach to evaluating fuzzy regression model with multiple crisp inputs and a Gaussian fuzzy output. The proposed algorithm here is model-free method in the sense that we do not need assume the underlying model function. Experimental result is then presented which indicate the performance of this algorithm.