• 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.

• Structural Engineering and Mechanics
• /
• v.84 no.1
• /
• pp.1-16
• /
• 2022

An efficient and accurate classification method for failure modes of reinforced concrete (RC) columns was proposed based on key characteristic parameters. The weight coefficients of seven characteristic parameters for failure modes of RC columns were determined first based on the support vector machine-recursive feature elimination. Then key characteristic parameters for classifying flexure, flexure-shear and shear failure modes of RC columns were selected respectively. Subsequently, a support vector machine with key characteristic parameters (SVM-K) was proposed to classify three types of failure modes of RC columns. The optimal parameters of SVM-K were determined by using the ten-fold cross-validation and the grid-search algorithm based on 270 sets of available experimental data. Results indicate that the proposed SVM-K has high overall accuracy, recall and precision (e.g., accuracy>95%, recall>90%, precision>90%), which means that the proposed SVM-K has superior performance for classification of failure modes of RC columns. Based on the selected key characteristic parameters for different types of failure modes of RC columns, the accuracy of SVM-K is improved and the decision function of SVM-K is simplified by reducing the dimensions and number of support vectors.

• Physical Therapy Korea
• /
• v.19 no.4
• /
• pp.16-23
• /
• 2012

This study examined the effects of custom-made foot orthotics on the temporal-spatial gait parameters in children with cerebral palsy. Twenty spastic bilateral cerebral palsy (spastic CP) children (11 boys and 9 girls) participated in this study. GAITRite was used to examine the velocity, cadence, step length differential, step length, stride length, stance time, single support time, double support time, base of support, and toe angle while walking with and without foot orthotics. The differences in temporal-spatial parameters were analyzed using paired t-test. The significance level was set at .05. The velocity, cadence, both step lengths, both stride lengths, both bases of support and right toe angle significantly increased when the children with spastic CP with foot orthotics compared to without foot orthotics (p<.05). The step length differential between the two extremities, left stance time and left single support time, significantly decreased with foot orthotics (p<.05). Right stance time, right single support time, both double support times and left toe angle showed little change (p>.05). This study demonstrated that foot orthotics were beneficial for children with spastic CP as a gait assistance tool.

• Journal of Korean Critical Care Nursing
• /
• v.15 no.3
• /
• pp.115-127
• /
• 2022

Purpose : This study aimed to investigate sleep parameters and to identify differences according to respiratory support therapy, sedation, and pain medication in intensive care unit (ICU) patients. Methods : In this observational study, sleep parameters were measured using actigraphy. We observed 45 sleep events in 30 ICU patients receiving respiratory support therapy. We measured the sleep parameters, time, efficiency, and wakefulness after sleep onset (WASO). The differences in sleep parameters according to the respiratory support therapy were analyzed using the Mann-Whitney U test. Results : The average daily sleep time of the participants was 776.66±276.71 minutes, of which more than 60% accounted for daytime sleep. During night sleep, the duration of WASO was 156.93±107.91 minutes, and the frequency of WASO was 26.02±25.82 times. The high flow nasal cannula (HFNC) group had a significantly shorter night sleep time (𝑥²=7.86, p =.049), a greater number of WASO (𝑥²=5.69, p =.128), and a longer WASO duration (𝑥²=8.75, p =.033) than groups of other respiratory therapies. Conclusion : ICU patients on respiratory support therapy experienced sleep disturbances such as disrupted circadian rhythm and sleep fragmentation. Among respiratory support regimens, HFNC was associated with poor sleep parameters, which appears to be associated with the insufficient use of analgesics. The results of this study warrant the development of interventions that can improve sleep in ICU patients receiving respiratory support, including HFNC.

• Transactions of the Korean Society of Mechanical Engineers
• /
• v.12 no.5
• /
• pp.1003-1015
• /
• 1988

Damping information is required to analyse heat exchangers for flow-induced vibration. The most important energy dissipation mechanisms in heat exchanger tubes are related to the dynamic interaction between tube and support. In liquids, squeeze-film damping is dominat. Simple experiments were carried out of a two-span tube with one intermediate support to investigate the effects of tube-support parameters, such as: tube-support thickness, diametral clearance, tube eccentricity, tube span length, location of tube-support, and nature of dynamic interaction between tube and tube-support. The results show that squeeze-film damping is much larger for lateral-type motion than for rocking-type motion at the support. Eccentricity was found to be very important. Diametral clearance, support thickness and frequency are also very relevant. The effects of these parameters on squeeze-film damping are formulated and proposed in a semi-empirical expression.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.17 no.5
• /
• pp.679-683
• /
• 2007

Statistical learning theory by Vapnik consists of support vector machine(SVM), support vector regression(SVR), and support vector clustering(SVC) for classification, regression, and clustering respectively. In this algorithms, SVC is good clustering algorithm using support vectors based on Gaussian kernel function. But, similar to SVM and SVR, SVC needs to determine kernel parameters and regularization constant optimally. In general, the parameters have been determined by the arts of researchers and grid search which is demanded computing time heavily. In this paper, we propose a differential evolution based SVC(DESVC) which combines differential evolution into SVC for efficient selection of kernel parameters and regularization constant. To verify improved performance of our DESVC, we make experiments using the data sets from UCI machine learning repository and simulation.

• International Journal of Concrete Structures and Materials
• /
• v.5 no.1
• /
• pp.29-33
• /
• 2011

This article employs Least Square Support Vector Machine (LSSVM) for determination of fracture parameters of concrete: critical stress intensity factor ($K_{Ic}^s$) and the critical crack tip opening displacement ($CTOD_c$). LSSVM that is firmly based on the theory of statistical learning theory uses regression technique. The results are compared with a widely used Artificial Neural Network (ANN) Models of LSSVM have been developed for prediction of $K_{Ic}^s$ and $CTOD_c$, and then a sensitivity analysis has been performed to investigate the importance of the input parameters. Equations have been also developed for determination of $K_{Ic}^s$ and $CTOD_c$. The developed LSSVM also gives error bar. The results show that the developed model of LSSVM is very predictable in order to determine fracture parameters of concrete.

• PNF and Movement
• /
• v.17 no.1
• /
• pp.111-118
• /
• 2019

Purpose: This study aimed to investigate the correlation between trunk stabilization muscle activation and the parameters of gait analysis in healthy individuals. Methods: Thirty healthy adults (15 male, 15 female) with no history of lower back pain (LBP) or current musculoskeletal and neurological injuries were studied. Trunk stabilization muscle activation (e.g., external oblique, internal oblique, transverse abdominis, erector spinae) were assessed using surface electromyography. To analyze gait, we measured temporal parameters (e.g., gait velocity, single support phase, double support phase, swing phase, and stance phase) and a spatial parameter (e.g., H-H base of support). Results: A statistically significant correlation was found between the internal oblique, transverse abdominis, and erector spinae muscle activity and gait velocity, single support phase, double support phase, swing phase, and stance phase. No statistically significant correlation was found between the external oblique muscle activity and the gait velocity, single support phase, double support phase, swing phase, and stance phase. No statistically significant correlation was found between the external oblique, internal oblique, transverse abdominis, and erector spinae muscle activity and the spatial parameter. Conclusion: This study demonstrated that a relationship exists between trunk stabilization muscle activation and temporal parameter (i.e., gait velocity, single support phase, double support phase, swing phase, and stance phase) during gait analysis. Therefore, the trunk's stabilizer muscles play an important role in the gait of healthy individuals.

• The Transactions of the Korean Institute of Power Electronics
• /
• v.10 no.5
• /
• pp.468-480
• /
• 2005

The overall performance of AC servo system is greatly affected the uncertainties of unpredictable mechanical parameter variations and external load disturbances. To overcome this problem, it is necessary to know different parameters and load disturbances subjected to position/speed control. This paper proposes an on-line identification method of mechanical parameters/load disturbances for AC servo system using support vector regression(SVR). The experimental results demonstrate that the proposed SVR algorithm is appropriate for control of unknown servo systems even with time-varying/nonlinear parameters.

• Proceedings of the KSR Conference
• /
• 2004.06a
• /
• pp.1065-1070
• /
• 2004

When the track designer analyze the track structure uses many known & unknown parameters. Unknown parameters, equivalent rail support spring factor, unit rail support spring factor, track damping coefficient, should be assumed. Known parameters are section properties (area, section factor, etc), material properties(modulus of elasticity, mass, etc) and track conditions(wheel load, loading conditions, gauge, etc.). In the assumption of track design parameters, some parameters can be overestimated or under estimated. The purpose of this study is to verify design parameters used in track design, in the way of experimental measurements. Data of displacements, banding stresses, loads, accelerations are measurable at track site. From these data, unknown parameters are derived. Compare these assumed and derived parameters, estimate the entire track stability.