• Journal of the Korea Society of Computer and Information
• /
• v.20 no.1
• /
• pp.197-206
• /
• 2015

Defect severity that is a measure of the impact caused by the defect plays an important role in software quality activities because not all software defects are equal. Earlier studies have concentrated on defining defect severity levels, but there have almost never been trials of measuring module severity. In this paper, first, we define a defect severity metric in the form of an exponential function using the characteristics that defect severity values increase much faster than severity levels. Then we define a new metrics set for software module severity using the number of defects in a module and their defect severity metric values. In order to show the applicability of the proposed metrics, we performed an analytical validation using Weyuker's properties and experimental validation using NASA open data sets. The results show that ms is very useful for measuring the module severity and msd can be used to compare different systems in terms of module severity.

• Journal of the Korea Society of Computer and Information
• /
• v.21 no.4
• /
• pp.73-80
• /
• 2016

Most fault prediction models have class imbalance problems because training data usually contains much more non-fault class modules than fault class ones. This imbalanced distribution makes it difficult for the models to learn the minor class module data. Data imbalance is much higher when severity-based fault prediction is used. This is because high severity fault modules is a smaller subset of the fault modules. In this paper, we propose severity-based models to solve these problems using the three sampling methods, Resample, SpreadSubSample and SMOTE. Empirical results show that Resample method has typical over-fit problems, and SpreadSubSample method cannot enhance the prediction performance of the models. Unlike two methods, SMOTE method shows good performance in terms of AUC and FNR values. Especially J48 decision tree model using SMOTE outperforms other prediction models.

• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.18 no.3
• /
• pp.151-157
• /
• 2018

Most previous studies of software fault prediction have focused on supervised learning models for binary classification that determines whether an input module has faults or not. However, binary classification model determines only the presence or absence of faults in the module without considering the complex characteristics of the fault, and supervised model has the limitation that it requires a training data set that most development groups do not have. To solve these two problems, this paper proposes severity-based ternary classification model using unsupervised learning algorithms, and experimental results show that the proposed model has comparable performance to the supervised models.

• Transactions of the Korean Society of Automotive Engineers
• /
• v.19 no.6
• /
• pp.61-67
• /
• 2011

The cooling module needs enough space (or distance) from hood to absorb the energy from any pedestrian collision. Downsized cooling module for pedestrian protection is important to reduce the severity of pedestrian injury. When a vehicle collision happens, the downsized cooling module is required to reduce the risk of injury to the upper legs of adults and the heads of children. In this study, the performance of cooling module to cool the engine was investigated under 25% height reduction. The heat dissipation and pressure drop characteristics have been experimentally studied with the variation of coolant flow rate, air inlet velocity and A/C operation ON/OFF for the downsized cooling module. The results indicated that the cooling performance was about 94% level compared to that of the conventional cooling module. Therefore, we checked that the cooling module had good performance, and expected that the cooling module could meet the same cooling performance as conventional cooling module through optimization of components efficiency.

• Journal of the Society of Disaster Information
• /
• v.14 no.1
• /
• pp.28-35
• /
• 2018

The following research has focused and implemented on designing a system that classifies the severity of mass casualty situations across both normal and disaster levels. The system's algorithm has implemented requirements such as accuracy as well as user convenience. The developed e-Triage System has applied various severity classification algorithms implemented from IoT concepts. In order to overcome flaws of currently used severity classification systems, the e-Triage System used electronic elements including the NFC module. By using the mobile application's severity classification algorithm the system demonstrated quick and accurate assessment of patient. Four different LED lamps visualized the severity classification results and RTS scores were portrayed through FND(Flexible Numeric Display) after a two wave classification.

• Journal of Korean Biological Nursing Science
• /
• v.22 no.2
• /
• pp.90-101
• /
• 2020

Purpose: The purpose of this study was to build and verify a structural model that could predict the severity of irritable bowel syndrome in university students. Methods: Participants were 205 students enrolled in college with irritable bowel syndrome using the irritable bowel syndrome module of the ROME IV Adult Questionnaire. The data were collected using online questionnaires in AprilMay 2019. The data were analyzed using the SPSS WIN 25.0 and AMOS 20.0 programs. Results: 1) The symptom severity that participants experienced were mild (14.6%), moderate (45.4%), and severe (40%). 2) Fit indices of the model were x²= 79.66 (df = 52, p= .009), CFI= .94, TLI= .96, RMSEA= .05, RMR= 1.59, GFI= .94, and TLI= .96.3). The severity of irritable bowel syndrome was influenced directly by anxiety and sleep, and indirectly by family history, perfectionism, social support, coping, and stress. The severity of irritable bowel syndrome was indirectly affected by the following: family history through anxiety; perfectionism through stress, anxiety, and sleep; social support through coping, stress, anxiety, and sleep; coping through stress and anxiety; and stress through anxiety and sleep. Conclusion: Based on the results of this study, a nursing intervention is needed to reduce the anxiety and stress and improve the quality of sleep to improve the health of the college students and manage the symptoms of patients with irritable bowel syndrome.

• Transactions of the Korean Society of Automotive Engineers
• /
• v.20 no.6
• /
• pp.67-72
• /
• 2012

Novel Front End Module(FEM) with improved pedestrian protection is very important to reduce the severity of pedestrian injury. The FEM needs to have enough space from hood to absorb the energy from any pedestrian collision. In this study, the cooling performance of the FEM to cool the engine was investigated under 25% height reduction. The results indicated that the cooling performance analysis was about 86% level compared to that of the conventional FEM. Also, good qualitative agreement between CFD predictions and experimental measurements was found. This FEM needs the cooling performance enhancement for changed air flow path at the frontal part of vehicle. Therefore, we showed an improved performance using air guide setup and shape modification under the high load condition.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.17 no.10
• /
• pp.2627-2642
• /
• 2023

Parkinson's disease (PD) is a typical, chronic neurodegenerative disease involving the concentration of dopamine, which can disrupt motor activity and cause different degrees of gait disturbance relevant to PD severity in patients. As current clinical PD diagnosis is a complex, time-consuming, and challenging task that relays on physicians' subjective evaluation of visual observations, gait disturbance has been extensively explored to make automatic detection of PD diagnosis and severity rating and provides auxiliary information for physicians' decisions using gait data from various acquisition devices. Among them, wearable sensors have the advantage of flexibility since they do not limit the wearers' activity sphere in this application scenario. In this paper, an attention-based temporal network (ATN) is designed for the time series structure of gait data (vertical ground reaction force signals) from foot sensor systems, to learn the discriminative differences related to PD severity levels hidden in sequential data. The structure of the proposed method is illuminated by Transformer Network for its success in excavating temporal information, containing three modules: a preprocessing module to map intra-moment features, a feature extractor computing complicated gait characteristic of the whole signal sequence in the temporal dimension, and a classifier for the final decision-making about PD severity assessment. The experiment is conducted on the public dataset PDgait of VGRF signals to verify the proposed model's validity and show promising classification performance compared with several existing methods.

• Journal of Korean Society of Transportation
• /
• v.20 no.7
• /
• pp.107-116
• /
• 2002

Crash Cushion is a kind of safety facilities on roadside which acts the role of absorbing impact energy when vehicles are driven out of normal route such as Gore area of freeway off ramp. Criteria for severity index considering accident occurrence possibility are needed to have strong effect on installing the facilities. However, present criteria for establishing crash cushion design do not include such processes. Therefore, the paper presents two kinds of study to develop criteria for severity index. First of all, development of accident forecasting model on freeway off ramp is presented. The module is a relationship between accidents and road environment by negative binomial distribution (NB) which is called to reflect very well quality of accidents at Gore of crash cushion installed freeway Secondly, freeway exiting behavior model is developed because the human factor is the most important one. However, many literatures have shown between road environment and accidents which are more quantitative than human factor. The study supposed advanced process steps on actual freeway and analysed correlation between variables and accidents. The criteria for severity index is presented to determine whether to install or not by benefit cost analysis for each module. The standard for severity index will help to determine whether to install the crash cushion or not and to estimate severity for freeway and off ramp.

• Clinical and Experimental Reproductive Medicine
• /
• v.46 no.3
• /
• pp.125-131
• /
• 2019

Objective: To investigate serum 25-hydroxyl vitamin D (25(OH)D) and vitamin D-binding protein (VDBP) concentrations in women with endometriosis according to the severity of disease. Methods: Women with mild endometriosis (n = 9) and advanced endometriosis (n = 7), as well as healthy controls (n = 16), were enrolled in this observational study. Serum total 25(OH)D concentrations were analyzed using the Elecsys vitamin D total kit with the Cobas e602 module. Concentrations of bioavailable and free 25(OH)D were calculated. Concentrations of VDBP were measured using the Human Vitamin D BP Quantikine ELISA kit. Variables were tested for normality and homoscedasticity using the Shapiro-Wilk test and Leven F test, respectively. Correlation analysis was used to identify the variables related to total 25(OH)D and VDBP levels. To assess the effects of total 25(OH)D and VDBP levels in the three groups, multivariate generalized additive modeling (GAM) was performed. Results: Gravidity and parity were significantly different across the three groups. Erythrocyte sedimentation rate (ESR) and CA-125 levels increased as a function of endometriosis severity, respectively (p= 0.051, p= 0.004). The correlation analysis showed that total 25(OH)D levels were positively correlated with gravidity (r = 0.59, p< 0.001) and parity (r = 0.51, p< 0.003). Multivariate GAM showed no significant relationship of total 25(OH)D levels with EMT severity after adjusting for gravidity and ESR. However, the coefficient of total 25(OH)D levels with gravidity was significant (1.87; 95% confidence interval, 0.12-3.63; p= 0.040). Conclusion: These results indicate that vitamin D and VDBP levels were not associated with the severity of endometriosis.