• Journal of Korean Society of Industrial and Systems Engineering
• /
• v.45 no.4
• /
• pp.233-239
• /
• 2022

The injection molding process is a process in which thermoplastic resin is heated and made into a fluid state, injected under pressure into the cavity of a mold, and then cooled in the mold to produce a product identical to the shape of the cavity of the mold. It is a process that enables mass production and complex shapes, and various factors such as resin temperature, mold temperature, injection speed, and pressure affect product quality. In the data collected at the manufacturing site, there is a lot of data related to good products, but there is little data related to defective products, resulting in serious data imbalance. In order to efficiently solve this data imbalance, undersampling, oversampling, and composite sampling are usally applied. In this study, oversampling techniques such as random oversampling (ROS), minority class oversampling (SMOTE), ADASYN(Adaptive Synthetic Sampling), etc., which amplify data of the minority class by the majority class, and complex sampling using both undersampling and oversampling, are applied. For composite sampling, SMOTE+ENN and SMOTE+Tomek were used. Artificial neural network techniques is used to predict product quality. Especially, MLP and RNN are applied as artificial neural network techniques, and optimization of various parameters for MLP and RNN is required. In this study, we proposed an SA technique that optimizes the choice of the sampling method, the ratio of minority classes for sampling method, the batch size and the number of hidden layer units for parameters of MLP and RNN. The existing sampling methods and the proposed SA method were compared using accuracy, precision, recall, and F1 Score to prove the superiority of the proposed method.

• The Journal of Churna Manual Medicine for Spine and Nerves
• /
• v.3 no.1
• /
• pp.73-82
• /
• 2008

Objectives : This study was performed to examine the hypothesis that the structural imbalance affect cardiac function and autonomic reflex system and to investigate the possibility of the chiropractic care for cardiovascular system. Methods : 78 of Dong-Guk University students with structural imbalance were recruited for the investigation from March to June 2007. Heart rate variability, Buss and Durkee Hostility inventory(BDHI) and physical examinations to evaluate psoas muscle contracture were performed. Results : Left psoas muscle contracture was associated with decrease of LF/HF ratio(p=0.048). Conclusion : Left side contracture of psoas muscle showed a tendency to decrease sympathetic activity.

• Journal of Korean Medicine for Obesity Research
• /
• v.5 no.1
• /
• pp.141-146
• /
• 2005

It is very important that the ratio of Soft Lean Mass and Body Fat Mass in body composition. Generally we make an effort not only weight reduction but body fat mass reduction, and finally percent body fat is reduced. And we make an effort to reduce of partial obesity. I have one case that improvement of imbalance on the upper and lower part of the body by Oriental Medicine. We have the result that the upper part of the body composition is increased and the lower part of the body composition is decreased.

• PNF and Movement
• /
• v.21 no.2
• /
• pp.231-241
• /
• 2023

Purpose: Weakness of the vastus medialis oblique muscle (VMO), or the imbalance between VMO and vastus lateralis muscle (VL) activity, is one of the most important factors in knee joint problems. Rigid taping techniques, such as patellar inhibition taping and VL inhibition taping, are frequently used in clinical practice to treat knee joint problems. The purpose of this study was to compare the acute effect of three different types of taping (patellar inhibition taping (PIT), distal VL inhibition taping (DVLIT), and proximal VL inhibition taping (PVLIT)) on electromyography (EMG) activity of VMO, VL, and VMO:VL ratio during walking. Methods: Thirty-eight normal healthy subjects (38 males; mean age = 31.00 years) voluntarily participated in this study. EMG was applied to investigate muscle activation during walking. Repeated measures of ANOVA and one-way ANOVA compared the three different conditions (PIT, DVLIT, and PVLIT) for each variable. Results: VMO and VL activation were significantly increased after PTIT application, and VMO and VL activation were significantly decreased after DVLIT and PVLIT application. The VMO:VL ratio increased after the three types of taping application, but there were no significant differences among the three types of taping. Conclusion: Based on the results of this study, PTIT is more effective than DVLIT and PVLIT in increasing the muscle activation of the VMO and VL during walking. Also, DVLIT is more effective for increasing the VMO:VL ratio and has beneficial effects on the imbalance between VMO and VL activity.

• Geophysics and Geophysical Exploration
• /
• v.23 no.3
• /
• pp.131-140
• /
• 2020

In training a classification model using machine learning, the acquisition of training data is a very important stage, because the amount and quality of the training data greatly influence the model performance. However, when the cost of obtaining data is so high that it is difficult to build ideal training data, the number of samples for each class may be acquired very differently, and a serious data-imbalance problem can occur. If such a problem occurs in the training data, all classes are not trained equally, and classes containing relatively few data will have significantly lower recall values. Additionally, the reliability of evaluation indices such as accuracy and precision will be reduced. Therefore, this study sought to overcome the problem of data imbalance in two stages. First, we introduced weighted accuracy and weighted precision as new evaluation indices that can take into account a data-imbalance ratio by modifying conventional measures of accuracy and precision. Next, oversampling was performed to balance weighted precision and recall among classes. We verified the algorithm by applying it to the problem of facies classification. As a result, the imbalance between majority and minority classes was greatly mitigated, and the boundaries between classes could be more clearly identified.

• Journal of Nutrition and Health
• /
• v.38 no.7
• /
• pp.521-532
• /
• 2005

The prevalence of atopic dermatitis (AD) continues to rise in industrialized countries related to Western lifestyle, including dietary habits, especially imbalance of intake of dietary fatty acids. The purpose of this study was to evaluate the dietary fatty acids and the assess the blood fatty acid composition and immune parameters in AD patients. AD (n = 50) patients and gender ${\cdot}$ age matched healthy controls (HC) were studied in case-control clinical trail. Current fatty acids intake status was determined by 3-day food record method. Blood sample were collected from 30 subjects in each group and blood fatty acid composition and immune parameters were analysed. AD patients consumed less PUFA and their n-6/n-3 PUFA ratio was higher than that of HC. Both the ratios of PUFA and MUFA were positively correlated with SCORAD in AD patients (p < 0.05). In the AD patients, there were abnormalities in the fatty acid composition of the RBC and WBC, SFA being significantly high and most n-3 PUFA being significantly low. Moreover, both the ratios of EPA and DHA in WBC were negatively correlated with dietary n-6/n-3 PUFA ratio in AD patients (p < 0.05). Serum total IgE and IL-4 levels of AD patients increased significantly compared with the levels of HC (p < 0.01). Ratios of monocyte and eosinophil in WBC of AD patients increased significantly compared with the levels of HC including total WBC count (p < 0.01), and ratios of Iymphocyte and basophil in WBC of AD patients decreased significantly compared with the levels of HC (p < 0.05). Moreover, the ratios of eosinophil in WBC were positively correlated with dietary P/M ratio (p < 0.05), and the ratios of monocyte in WBC were positively correlated with n-6/n-3 PUFA ratio (p < 0.05) in AD patients. This results indicated that AD patients had significantly high intake of dietary n-6/n-3 PUFA compared with HC. Imbalance of intake of dietary fatty acids affected fatty acid compositions in the RBC and WBC, and these lead to immune imbalance and grow worse of AD.

• The Journal of the Korea Contents Association
• /
• v.18 no.8
• /
• pp.525-535
• /
• 2018

If the frequency of a particular class is excessively higher than the frequency of other classes in the classification problem, data imbalance problems occur, which make machine learning distorted. Corporate bankruptcy prediction often suffers from data imbalance problems since the ratio of insolvent companies is generally very low, whereas the ratio of solvent companies is very high. To mitigate these problems, it is required to apply a proper sampling technique. Until now, oversampling techniques which adjust the class distribution of a data set by sampling minor class with replacement have popularly been used. However, they are a risk of overfitting. Under this background, this study proposes ROSE(Random Over Sampling Examples) technique which is proposed by Menardi and Torelli in 2014 for the effective corporate bankruptcy prediction. The ROSE technique creates new learning samples by synthesizing the samples for learning, so it leads to better prediction accuracy of the classifiers while avoiding the risk of overfitting. Specifically, our study proposes to combine the ROSE method with SVM(support vector machine), which is known as the best binary classifier. We applied the proposed method to a real-world bankruptcy prediction case of a Korean major bank, and compared its performance with other sampling techniques. Experimental results showed that ROSE contributed to the improvement of the prediction accuracy of SVM in bankruptcy prediction compared to other techniques, with statistical significance. These results shed a light on the fact that ROSE can be a good alternative for resolving data imbalance problems of the prediction problems in social science area other than bankruptcy prediction.

• The Korean Journal of Applied Statistics
• /
• v.37 no.5
• /
• pp.615-629
• /
• 2024

In the field of big data mining, the challenge of imbalanced classification problem has been actively researched for decades. While imbalanced data issues manifest in various forms, past research mainly focused on addressing sample size imbalance between classes. However, recent studies have revealed that rather than the imbalance in sample size alone, the degradation of classification performance significantly worsens when the class overlap is combined. In response, this study introduces GC-Forest (GIR-based canonical forest), an effective ensemble classification method that utilizes weighted resampling technique considering the degrees of overlap between classes. This method measures the imbalance ratio in terms of class overlap at each stage of ensemble and balances the classes by increasing the representativeness of the minority class. Additionally, to improve overall classification performance, the GC-Forest method adopts the canonical forest method as an ensemble classifier, which is designed to enhance both the performance and diversity of individual classifiers. The performance of the proposed method was compared and verified through experiments using 14 different types of real imbalanced data. GC-Forest showed very competitive classification performance in terms of AUC, PR-AUC, G-mean, and F1-score compared to 7 other ensemble methods.

• Journal of Acupuncture Research
• /
• v.25 no.6
• /
• pp.109-116
• /
• 2008

Objectives : This study investigated the effect of imbalance of autonomic nerve system on the idiopathic facial palsy by the comparison Heart Rate Variability results of Facial palsy group and healthy control group, and to clarify correlation between House-Brackmann Grade and Heart Rate Variability results. Methods : 119 idiopathic facial palsy patients and 88 health subjects who underwent HRV test were retrospectively reviewed based on medical records. We compared between the HRV results of facial palsy group and that of normal control group, and also compared the HRV results of facial palsy subgroup classified by House-Brackmann Grade. Results 1. All HRV results－Mean Heart Rat(MHRT), Standard Deviation of all the Normal RR intervals(SDNN), Total Power(TP), Very Low Frequency(VLF), Low Frequency(LF), High Frequency(HF), ratio betwween the Low Frequency and High Frequency power(LF/HF ratio) of facial palsy group are decreased compared to that of normal control group, especially SDNN, TP, VLF, LF, LF/HF ratio showed significant difference(p<0.05). 2. HRV results showed no significant correlation in House-Brackmann Grade. Conclusions : This study showed that lower HRV results of facial palsy group than normal control group and suggests that imbalance of autonomic nerve system related with facial palsy. HRV could be a objective tool to reflect condition of idiopathic facial palsy patients.

• Information Systems Review
• /
• v.24 no.4
• /
• pp.23-40
• /
• 2022

Although Support Vector Machine(SVM) has been used in various fields such as bankruptcy prediction model, the hyperplane learned by SVM in class imbalance problem can be severely skewed toward minority class and has a negative impact on performance because the area of majority class is expanded while the area of minority class is invaded. This study proposed optimized uneven margin SVM(OPT-UMSVM) combining threshold moving or post scaling method with UMSVM to cope with the limitation of the traditional even margin SVM(EMSVM) in class imbalance problem. OPT-UMSVM readjusted the skewed hyperplane to the majority class and had better generation ability than EMSVM improving the sensitivity of minority class and calculating the optimized performance. To validate OPT-UMSVM, 10-fold cross validations were performed on five sub-datasets with different imbalance ratio values. Empirical results showed two main findings. First, UMSVM had a weak effect on improving the performance of EMSVM in balanced datasets, but it greatly outperformed EMSVM in severely imbalanced datasets. Second, compared to EMSVM and conventional UMSVM, OPT-UMSVM had better performance in both balanced and imbalanced datasets and showed a significant difference performance especially in severely imbalanced datasets.