Go to the main menu
Skip to content
Go to bottom
REFERENCE LINKING PLATFORM OF KOREA S&T JOURNALS
> Journal Vol & Issue
Journal of Biomedical Engineering Research
Journal Basic Information
Journal DOI :
The Korea Society of Medical and Biological Engineering
Editor in Chief :
Volume & Issues
Volume 37, Issue 3 - Jun 2016
Volume 37, Issue 2 - Apr 2016
Volume 37, Issue 1 - Feb 2016
Selecting the target year
Random Forest Based Abnormal ECG Dichotomization using Linear and Nonlinear Feature Extraction
Kim, Hye-Jin ; Kim, Byeong-Nam ; Jang, Won-Seuk ; Yoo, Sun-K. ;
Journal of Biomedical Engineering Research, volume 37, issue 2, 2016, Pages 61~67
DOI : 10.9718/JBER.2016.37.2.61
This paper presented a method for random forest based the arrhythmia classification using both heart rate (HR) and heart rate variability (HRV) features. We analyzed the MIT-BIH arrhythmia database which contains half-hour ECG recorded from 48 subjects. This study included not only the linear features but also non-linear features for the improvement of classification performance. We classified abnormal ECG using mean_NN (mean of heart rate), SD1/SD2 (geometrical feature of poincare HRV plot), SE (spectral entropy), pNN100 (percentage of a heart rate longer than 100 ms) affecting accurate classification among combined of linear and nonlinear features. We compared our proposed method with Neural Networks to evaluate the accuracy of the algorithm. When we used the features extracted from the HRV as an input variable for classifier, random forest used only the most contributed variable for classification unlike the neural networks. The characteristics of random forest enable the dimensionality reduction of the input variables, increase a efficiency of classifier and can be obtained faster, 11.1% higher accuracy than the neural networks.
Rotational Characteristics of Target Registration Error for Contour-based Registration in Neuronavigation System: A Phantom Study
Park, Hyun-Joon ; Mun, Joung Hwan ; Yoo, Hakje ; Shin, Ki-Young ; Sim, Taeyong ;
Journal of Biomedical Engineering Research, volume 37, issue 2, 2016, Pages 68~74
DOI : 10.9718/JBER.2016.37.2.68
In this study, we investigated the rotational characteristics which were comprised of directionality and linearity of target registration error (TRE) as a study in advance to enhance the accuracy of contour-based registration in neuronavigation. For the experiment, two rigid head phantoms that have different faces with specially designed target frame fixed inside of the phantoms were used. Three-dimensional coordinates of facial surface point cloud and target point of the phantoms were acquired using computed tomography (CT) and 3D scanner. Iterative closest point (ICP) method was used for registration of two different point cloud and the directionality and linearity of TRE in overall head were calculated by using 3D position of targets after registration. As a result, it was represented that TRE had consistent direction in overall head region and was increased in linear fashion as distance from facial surface, but did not show high linearity. These results indicated that it is possible for decrease TRE by controlling orientation of facial surface point cloud acquired from scanner, and the prediction of TRE from surface registration error can decrease the registration accuracy in lesion. In the further studies, we have to develop the contour-based registration method for improvement of accuracy by considering rotational characteristics of TRE.
Mathematical Model for In-Ward Nursing Staffing Optimization Based on Patient Classification System
Kim, Kyoung-Ok ; Park, Mi-Jung ; Lee, In-Kwang ; Park, Kyung-Soon ; Shon, Ho-Sun ; Kim, Kyung-Ah ; Seo, Chang-Jin ; Cha, Eun-Jong ;
Journal of Biomedical Engineering Research, volume 37, issue 2, 2016, Pages 75~83
DOI : 10.9718/JBER.2016.37.2.75
Nursing staffing is of major interest in hospital management, however, no practical method has been developed. The present study proposed a mathematical model based on the patient classification system for nursing staffing optimization. A few characteristic parameters possibly determined experimentally and/or empirically were introduced followed by systematic calculation of the required number of nurses. An essential concept of the model is the unit work load defined as the amount of nursing work performed on single patient per unit time, where the work load is defined as the number of nursing staffs multiplied by the working hours. The unit work load was considered to vary with the patient classification level as well as the working time during a day, both of which were represented by corresponding parameter values. The number of patients for each class and the number of working hours were multiplied to the unit work load, and added up to obtain the total required work load. As the next step, the averaged number of hours that a nurse could provide per day was formulated considering the degree of nursing practice experience into 3 levels. Finally, the appropriate number of nursing staffs was calculated as the total work load divided by the average working hours per nurse. The present technique has a great advantage that the number of nursing staffs to fulfill the required work load is systematically calculated once the characteristic parameters are appropriately determined, leading to instant and fast evaluation. A practical PC program was also developed to apply the present model to nursing practice.
ROI Study for Diffusion Tensor Image with Partial Volume Effect
Choi, Woohyuk ; Yoon, Uicheul ;
Journal of Biomedical Engineering Research, volume 37, issue 2, 2016, Pages 84~89
DOI : 10.9718/JBER.2016.37.2.84
In this study, we proposed ameliorated method for region of interest (ROI) study to improve its accuracy using partial volume effect (PVE). PVE which arose in volumetric images when more than one tissue type occur in a voxel, could be used to reduce an amount of gray matter and cerebrospinal fluid within ROI of diffusion tensor image (DTI). In order to define ROIs, individual b0 image was spatially aligned to the JHU DTI-based atlas using linear and non-linear registration (http://cmrm.med.jhmi.edu/). Fractional anisotropy (FA) and mean diffusivity (MD) maps were estimated by fitting diffusion tensor model to each image voxel, and their mean values were computed within each ROI with PVE threshold. Participants of this study consisted of 20 healthy controls, 27 Alzheimer's disease and 27 normal-pressure hydrocephalus patients. The result showed that the mean FA and MD of each ROI were increased and decreased respectively, but standard deviation was significantly decreased when PVE was applied. In conclusion, the proposed method suggested that PVE was indispensable to improve an accuracy of DTI ROI study.
Load Sharing Ratios Between the Cortex and Centrum in a Lumbar Vertebral Body with aging using Finite Element Method
Lim, JongWan ;
Journal of Biomedical Engineering Research, volume 37, issue 2, 2016, Pages 90~103
DOI : 10.9718/JBER.2016.37.2.90
This research was aimed to analyze load sharing ratios between cortical shell and trabecular bone of a degraded lumbar vertebra with aging, and also evaluate elastic moduli assigned into an FE model, using finite element method. For the better analysis of trabecular bone, effective elastic moduli, that is, nominal elastic moduli divided by the volumetric porosities was used. The elastic moduli of the cortical shell suitable for the trabecular bone were obtained from the equations on the basis of idealized stress-strain relations, including areal porosities. To minimize numerical errors, p-element was used. Using eight parameters that refer to some published papers, the geometry of L3 with a removed posterior part. After the constant compressive displacement was applied, the load sharing ratios were obtained by using both every elastic strain energy and every vertical force between two bones in each 8-volume. As results, 1) according to an increase in age from 20-year to 80-year, load sharing ratios of trabecular bone decreased from 55% to 49%; 2) the maximal ratios of each bone were occurred in the mid-plane of centrums and the endplate of cortical shells, respectively; 3) effective elastic moduli assigned into a porous centrum/cortex were found to be adequate; 4) for load sharing ratios, the difference of two methods showed that the total ratios were almost same within less than 1% but the partial ratios at every depth were more or less different each other.