• Journal of Biomedical Engineering Research
• /
• v.29 no.6
• /
• pp.466-476
• /
• 2008

The more people use ambulatory electrocardiogram(ECG) for arrhythmia detection, the more researchers report the automatic classification algorithms. Most of the previous studies don't consider the un-balanced data distribution. Even in patients, there are much more normal beats than abnormal beats among the data from 24 hours. To solve this problem, the hierarchical classification using 21 features was adopted for arrhythmia abnormal beat detection. The features include R-R intervals and data to describe the morphology of the wave. To validate the algorithm, 44 non-pacemaker recordings from physionet were used. The hierarchical classification model with 2 stages on domain knowledge was constructed. Using our suggested method, we could improve the performance in abnormal beat classification from the conventional multi-class classification method. In conclusion, the domain knowledge based hierarchical classification is useful to the ECG beat classification with unbalanced data distribution.

• Journal of Korea Multimedia Society
• /
• v.9 no.9
• /
• pp.1107-1117
• /
• 2006

In this paper, a load balancing method using ring network structure in the Grid database is proposed. In the Grid database, generally, data is replicated for performance and availability. And, user's request is transferred to node and processed in that node which has target data. But, in such environment, a decline of performance can be occurred because unbalanced workload. A traditional research is proposed to solve unbalanced load problem. However, the Grid database has a number of systems and user's request always changes dynamically. Therefore, a traditional research can not be applied. The proposed method connects each node which has a same replicated data through ing network structure. If workload is overflowed in some node, user's request is transferred to a linked node which has a target data. And, this node stops another request processing until workload is decreased. Then, it changes the link structure through sending a message to a previous node, to stop request forwarding from a previous node. This paper shows a proposed method increases performance than existing research through performance evaluation and is more suitable for a complex and dynamic environment.

• Geomechanics and Engineering
• /
• v.37 no.5
• /
• pp.475-498
• /
• 2024

The prediction of the susceptibility of soil to liquefaction using a limited set of parameters, particularly when dealing with highly unbalanced databases is a challenging problem. The current study focuses on different ensemble learning classification algorithms using highly unbalanced databases of results from in-situ tests; standard penetration test (SPT), shear wave velocity (V_s) test, and cone penetration test (CPT). The input parameters for these datasets consist of earthquake intensity parameters, strong ground motion parameters, and in-situ soil testing parameters. liquefaction index serving as the binary output parameter. After a rigorous comparison with existing literature, extreme gradient boosting (XGBoost), bagging, and random forest (RF) emerge as the most efficient models for liquefaction instance classification across different datasets. Notably, for SPT and V_s-based models, XGBoost exhibits superior performance, followed by Light gradient boosting machine (LightGBM) and Bagging, while for CPT-based models, Bagging ranks highest, followed by Gradient boosting and random forest, with CPT-based models demonstrating lower G_mean(error), rendering them preferable for soil liquefaction susceptibility prediction. Key parameters influencing model performance include internal friction angle of soil (ϕ) and percentage of fines less than 75 µ (F₇₅) for SPT and V_s data and normalized average cone tip resistance (q_c) and peak horizontal ground acceleration (a_max) for CPT data. It was also observed that the addition of V_s measurement to SPT data increased the efficiency of the prediction in comparison to only SPT data. Furthermore, to enhance usability, a graphical user interface (GUI) for seamless classification operations based on provided input parameters was proposed.

• Transactions of the Korean Society of Mechanical Engineers A
• /
• v.40 no.1
• /
• pp.97-102
• /
• 2016

Since vibrations in rotating machinery is a direct cause of performance degradation and failures, it is very important to predict the level of vibrations as well as have a method to lower the vibrations to an acceptable level. However, the changes in balancing during installation and the vibrational modes of the support structure are difficult to predict. This paper presents a method for predicting the unbalanced response of a turbo-compressor supported by active magnetic bearings (AMBs). Transfer functions of the rotor are obtained through system identification using AMBs. These transfer functions contain not only the dynamics of the rotor but also the vibrational modes of the support structure. Using these transfer functions, the unbalanced response is calculated and compared with the run-up data obtained from a compressor prototype. The predictions revealed the effects of the support structure, validating the efficacy of the method.

• Journal of Biomedical Engineering Research
• /
• v.28 no.3
• /
• pp.355-362
• /
• 2007

Diabetes mellitus can cause devastating complications, which often result in disability and death, and diabetic nephropathy is a leading cause of death in people with diabetes. In this study, we tried to predict the onset of diabetic nephropathy from an irregular and unbalanced diabetic dataset. We collected clinical data from 292 patients with type 2 diabetes and performed preprocessing to extract 184 features to resolve the irregularity of the dataset. We compared several feature selection methods, such as ReliefF and sensitivity analysis, to remove redundant features and improve the classification performance. We also compared learning methods with support vector machine, such as equal cost learning and cost-sensitive learning to tackle the unbalanced problem in the dataset. The best classifier with the 39 selected features gave 0.969 of the area under the curve by receiver operation characteristics analysis, which represents that our method can predict diabetic nephropathy with high generalization performance from an irregular and unbalanced dataset, and physicians can benefit from it for predicting diabetic nephropathy.

• Journal of the Korean Home Economics Association
• /
• v.17 no.3
• /
• pp.23-34
• /
• 1979

Adequate intake of nutrients exert a profound influence on the physical and spiritual development of children. Thus, it is important to children and their mothers about nutrition and selection of nutritious foods. In order to underline the importance of nutrition for children, this study investigated and analyzed food habits of children expecially those in preschool ages, to obtain basic data to develop effective educational materials related to nutrition. dietary habits of 61 boys and 44 girls in the average age of six were surveyed through their mothers. Results therefrom are as follows : 1. Only 17 per cent of the mothers questioned replied that they considered the balance of diet in preparing meals, while 58.1% of the mothers gave precedence to the liking of their family . The lower the educational level of a mother , the higher her stress on the food preference of her family. 2. Seventy six of the mothers said they understand the basic food group , but only one mother displayed an accurate knowledge about it. 3. As for between meal eating , 82.9% took fruits, 68.6% milk, 35.2 bread, and 33.3% cookies. 4. Problems with food habits of children were : Unbalanced diet for 43.8% of children ,eating of snacks at irregular intervals for 26.7% and TV impact for 5.7%. 5. Children's food habits are greatly influenced by their parents, In the case of animal liver, 32.1 % of the children surveyed do not like to eat it, while 35.8% have never tasted it . 27.9% of children also do not like to eat cereals. Children's likes and dislikes with regarded to foods were influenced greatly by their parents. Thus, it is urgent to educate mothers about balanced diet and basic food group. Children will have to be taught to understand unfavorable effects of unbalanced diet so that they may correct their unsound food habits. This study also indicated the need for developing new cooking methods for those food items which are very liked by children to be a major cause of their unbalanced dietary habits.

• Proceedings of the Korea Concrete Institute Conference
• /
• 2008.04a
• /
• pp.1-4
• /
• 2008

Flat plate slab has been widely used in high rise building for its remarkable advantages. However, Flat plate structures under lateral load are susceptible to punching shear of the slab-column connection. Exterior slab-column connections has an unsymmetrical critical section for eccentric shear of which perimeter is less than that of interior connection, and hence, around the connection, unbalanced moment and eccentric shear are developed by both gravity load and lateral loads. Therefore, exterior connections is susceptible to punching shear failure. For that reason, this study compare ACI 318-05 to CEB-FIP MC 90 that is based on experiment results and existing data of flat plate exterior connections. This study shows that compared to CEB-FIP MC 90 is more exact about eccentric shear stress, unbalanced moment and Both of all are not suitable in large column aspect ratio. Considering gravity shear ratio, These are suitable but design condition only consider gravity shear ratio. So these should be considered differences from change of design condition

• Journal of Industrial Convergence
• /
• v.19 no.5
• /
• pp.1-11
• /
• 2021

Prior research regarding the macro patterns of industry convergence has focused on the inter-industry patent network and cross-industry movements of products or services. This article provides a novel approach, according to which human resources embodying explicit and implicit knowledge and technologies are important media driving industry convergence. Drawing on GOMS data (2015-2019) and using information of university graduates' academic majors and their occupations, this article proposes an analytic strategy by which to understand the macro patterns and structural features of industry convergence. Specifically, we build unbalanced bipartite networks of major-industry (occupation) relations, and construct the measures of the industry's niche width and the measure of the average degree of convergence of majors that each industry is linked to. By crossing the two measures, we identify four groups of industries(occupations); specialist, generalist, partial convergence, and full convergence. The convergence group is composed of industries (occupations) that acquire human resources from a number of academic majors each of which plays a role of glue connecting several local industries.

• Journal of Information Processing Systems
• /
• v.16 no.4
• /
• pp.870-881
• /
• 2020

Because SCADA monitoring data of wind turbines are large and fast changing, the unbalanced proportion of data in various working conditions makes it difficult to process fault feature data. The existing methods mainly introduce new and non-repeating instances by interpolating adjacent minority samples. In order to overcome the shortcomings of these methods which does not consider boundary conditions in balancing data, an improved over-sampling balancing algorithm SC-SMOTE (safe circle synthetic minority oversampling technology) is proposed to optimize data sets. Then, for the balanced data sets, a fault diagnosis method based on improved k-nearest neighbors (kNN) classification for wind turbine blade icing is adopted. Compared with the SMOTE algorithm, the experimental results show that the method is effective in the diagnosis of fan blade icing fault and improves the accuracy of diagnosis.

• The Journal of the Korea Contents Association
• /
• v.19 no.12
• /
• pp.647-659
• /
• 2019

The purpose of this study was to investigate the influence of children's elementary school entrance to working conditions of employed mothers. The data from 4th to 8th wave of Panel Study on Korean Children (PSKC) were used for analysis. Specifically, we examined changes in wages, working hours and regular employment of employed mothers after their children entered elementary schools. We adopted Heck selection model for unbalanced panel data after controlling sample selection bias, and compare results of analysis for unbalanced and balanced panel data. The results showed that children's elementary school entrance reduces employed mothers' wage, working hours and regular employment. These results indicate that mother tend to leave regular job and could not entry into decent job when their children are in elementary school.