• Journal of Information Processing Systems
• /
• v.14 no.3
• /
• pp.751-770
• /
• 2018

Web applications are indispensable in the software industry and continuously evolve either meeting a newer criteria and/or including new functionalities. However, despite assuring quality via testing, what hinders a straightforward development is the presence of defects. Several factors contribute to defects and are often minimized at high expense in terms of man-hours. Thus, detection of fault proneness in early phases of software development is important. Therefore, a fault prediction model for identifying fault-prone classes in a web application is highly desired. In this work, we compare 14 machine learning techniques to analyse the relationship between object oriented metrics and fault prediction in web applications. The study is carried out using various releases of Apache Click and Apache Rave datasets. En-route to the predictive analysis, the input basis set for each release is first optimized using filter based correlation feature selection (CFS) method. It is found that the LCOM3, WMC, NPM and DAM metrics are the most significant predictors. The statistical analysis of these metrics also finds good conformity with the CFS evaluation and affirms the role of these metrics in the defect prediction of web applications. The overall predictive ability of different fault prediction models is first ranked using Friedman technique and then statistically compared using Nemenyi post-hoc analysis. The results not only upholds the predictive capability of machine learning models for faulty classes using web applications, but also finds that ensemble algorithms are most appropriate for defect prediction in Apache datasets. Further, we also derive a consensus between the metrics selected by the CFS technique and the statistical analysis of the datasets.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.18 no.4
• /
• pp.826-842
• /
• 2024

As 5G and AI continue to develop, there has been a significant surge in the healthcare industry. The COVID-19 pandemic has posed immense challenges to the global health system. This study proposes an FL-supported edge computing model based on federated learning (FL) for predicting clinical outcomes of COVID-19 patients during hospitalization. The model aims to address the challenges posed by the pandemic, such as the need for sophisticated predictive models, privacy concerns, and the non-IID nature of COVID-19 data. The model utilizes the FATE framework, known for its privacy-preserving technologies, to enhance predictive precision while ensuring data privacy and effectively managing data heterogeneity. The model's ability to generalize across diverse datasets and its adaptability in real-world clinical settings are highlighted by the use of SHAP values, which streamline the training process by identifying influential features, thus reducing computational overhead without compromising predictive precision. The study demonstrates that the proposed model achieves comparable precision to specific machine learning models when dataset sizes are identical and surpasses traditional models when larger training data volumes are employed. The model's performance is further improved when trained on datasets from diverse nodes, leading to superior generalization and overall performance, especially in scenarios with insufficient node features. The integration of FL with edge computing contributes significantly to the reliable prediction of COVID-19 patient outcomes with greater privacy. The research contributes to healthcare technology by providing a practical solution for early intervention and personalized treatment plans, leading to improved patient outcomes and efficient resource allocation during public health crises.

• The Journal of Korean society of community based occupational therapy
• /
• v.7 no.3
• /
• pp.35-42
• /
• 2017

Objective : The purposes of this study are to examine the correlations among work ability and sleep quality in bus driver and to find the factors affecting work ability. Methods : The participants were 120 inpatients with bus driver. The Work Ability Index(WAI) was used for measuring work ability and the Pittsburgh Sleep Quality Index (PSQI) was utilized to measure sleep quality. The relationships among the variables were examined with Pearson correlation coefficients. And the stepwise multiple regression analysis were performed to identify the predictive variables that explain changes of work ability. Results : As a result of analyzing correlation of variables affecting work ability, there was negative correlation in contact sleep quality(p<.001) and working hours(p<.001). Finally, Work ability was identified as a factor that explains 48.2% of change in sleep quality(p<.001) and working hours(p<.01). Conclusion : It was found that intimacy of bus driver was a major variable to affect work ability. The sleep quality and working hours should be considered as a way to improve the bus driver work ability.

• Journal of Korean Academy of Nursing
• /
• v.42 no.6
• /
• pp.853-860
• /
• 2012

Purpose: The purposes of this study were to develop a Minimal Insomnia Screening Scale for Korean adults (KMISS) and to evaluate psychometric properties and discriminant ability of the developed scale. Methods: Data from a cross-sectional survey of 959 Korean adults were analyzed to develop the summated insomnia scale, which was evaluated in terms of reliability, validity, and discriminant ability by receiver operating characteristics (ROC) curve analysis. Results: Item-total correlations ranged between .71-.79 and Cronbach's ${\alpha}$ was .87. Adequate validity was also evident. ROC-curve analysis showed area under ROC was .87 (95% CI: .84-.90) and identified the optimal cut-off score as ${\leq}20$ (sensitivity, .83; specificity, .75; positive/negative predictive values, .40/.95). Using this cut-off score, the prevalence of insomnia in the study sample was 26.3% and most frequent among women and the oldest group. Conclusion: Data supports the psychometric properties of KMISS as a possible insomnia screening instrument. KMISS also shows promise as a convenient ultra-short screening measure of insomnia for adults and epidemiological studies in community health care settings.

• Journal of Korean Academy of Nursing
• /
• v.42 no.6
• /
• pp.810-818
• /
• 2012

Purpose: This study was done to explore factors relating to number of falls among community-dwelling elders, based on gender. Methods: Participants were 403 older community dwellers (male=206, female=197) aged 60 or above. In this study, 8 variables were identified as predictive factors that can result in an elderly person falling and as such, supports previous studies. The 8 variables were categorized as, exogenous variables; perceived health status, somatization, depression, physical performance, and cognitive state, and endogenous variables; fear of falling, ADL & IADL and frequency of falls. Results: For men, ability to perform ADL & IADL (${\beta}_{32}$=1.84, p<.001) accounted for 16% of the variance in the number of falls. For women, fear of falling (${\beta}_{31}$=0.14, p<.05) and ability to perform ADL & IADL (${\beta}_{32}$=1.01, p<.001) significantly contributed to the number of falls, accounting for 15% of the variance in the number of falls. Conclusion: The findings from this study confirm the gender-based fall prediction model as comprehensive in relation to community-dwelling elders. The fall prediction model can effectively contribute to future studies in developing fall prediction and intervention programs.

• The Korean Journal of Rehabilitation Nursing
• /
• v.17 no.1
• /
• pp.10-17
• /
• 2014

Purpose: The Leeds Sleep Evaluation Questionnaire (LSEQ) translated into Korean was modified to easily apply and reduce respondents' confusion and was evaluated for psychometric properties and discriminant ability. Methods: A total of 960 Korean adults aged 45 years and older participated in this cross-sectional survey. To test reliability, validity and discriminant ability, Cronbach's alpha, correlation analysis, confirmatory factor analysis, simple regression analysis and receiver operating characteristics (ROC) curve analysis were used. Results: Item-total correlations ranged between 62~.85 and Cronbach's alpha was .95. Area under ROC was .86 (95% CI: .83~.90) and the optimal cutoff score was identified as ${\leq}$ 66 (sensitivity, .77; specificity, .84; positive/negative predictive values, .49/.95). Using this cutoff score, the prevalence of insomnia in the study sample was 25.8% and tended to be more common in female and older groups. Conclusion: The data supported the psychometric properties of Korean Modified Leeds Sleep Evaluation Questionnaire (KMLSEQ) as an acceptable sleep measurement. In addition, KMLSEQ is likely to be a useful screening tool for insomnia.

• Journal of Electrical Engineering and Technology
• /
• v.13 no.3
• /
• pp.1265-1274
• /
• 2018

This paper proposes a virtual flux (VF) and positive-sequence power based control strategy to improve the performance of grid-interfaced three-phase voltage source converters against unbalanced and distorted grid conditions. By using a second-order generalized integrator (SOGI) based VF observer, the proposed strategy achieves an AC voltage sensorless and grid frequency adaptive control. Aiming to realize a balanced sinusoidal line current operation, the fundamental positive-sequence component based instantaneous power is utilized as the control variable. Moreover, the fundamental negative-sequence VF feedforward and the harmonic attenuation ability of a sequence component generator are employed to further enhance the unbalance regulation ability and the harmonic tolerance of line currents, respectively. Finally, the proposed scheme is completed by combining the foregoing two elements with a predictive direct power control (PDPC). In order to verify the feasibility and validity of the proposed SOGI-VFPDPC, the scenarios of unbalanced voltage dip, higher harmonic distortion and grid frequency deviation are investigated in simulation and experimental studies. The corresponding results demonstrate that the proposed strategy ensures a balanced sinusoidal line current operation with excellent steady-state and transient behaviors under general grid conditions.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.18 no.1
• /
• pp.1-14
• /
• 2024

Time-series forecasting is extensively used in the actual world. Recent research has shown that Transformers with a self-attention mechanism at their core exhibit better performance when dealing with such problems. However, most of the existing Transformer models used for time series prediction use the traditional encoder-decoder architecture, which is complex and leads to low model processing efficiency, thus limiting the ability to mine deep time dependencies by increasing model depth. Secondly, the secondary computational complexity of the self-attention mechanism also increases computational overhead and reduces processing efficiency. To address these issues, the paper designs an efficient multi-layer attention-based time-series forecasting model. This model has the following characteristics: (i) It abandons the traditional encoder-decoder based Transformer architecture and constructs a time series prediction model based on multi-layer attention mechanism, improving the model's ability to mine deep time dependencies. (ii) A cross attention module based on cross attention mechanism was designed to enhance information exchange between historical and predictive sequences. (iii) Applying a recently proposed sparse attention mechanism to our model reduces computational overhead and improves processing efficiency. Experiments on multiple datasets have shown that our model can significantly increase the performance of current advanced Transformer methods in time series forecasting, including LogTrans, Reformer, and Informer.

• Journal of The Korean Association For Science Education
• /
• v.20 no.1
• /
• pp.101-111
• /
• 2000

The present study was carried out to investigate the actual condition of the evaluation of science learning in the secondary school, and to develop the basic data for the improvement of the science learning assessment. Various questions for three evaluative domains were asked to 51 science teachers with the questionnaire during the in-service training course for certificate on summer in 1998. The cognition of the table of specification appeared high as 98% responses to the questionnaire, but the teachers' ability to distinguish behavioral elements was low as 47% responses. The evaluative rate of three domains for knowledge, skill and attitude appeared as 45%, 35% and 20% evaluation in both diagnostic and formative evaluation and 40%, 40% and 20% evaluation in summative evaluation. The evaluation of process skill appeared a tendency depending on laboratory reports as 61%, and was higher rather than in the formative evaluation or summative evaluation. In the evaluation of attitude domain, about a half of teachers answered that they evaluated the domain with laboratory reports as 43%, and some teachers evaluated the domain with teacher's observation as 33%. Also there were a few teachers who did not evaluate the attitude domain as 8%. The rate for the elements of the process skill appeared 86% responses in the interpretation of data, 31% in the observative ability, 18% in the predictive ability, 14% in the classified ability, 12% in the measuring and data-investigating ability, 4% in the discussion ability, and 2% in the investigating ability. We could find out that many teachers had given higher rate in the evaluation of process skill and attitude rather than before the present study, therefore there was more improvement in the evaluation for process skill and attitude domain after the 6th curriculum.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.19 no.3
• /
• pp.389-398
• /
• 2018

This study examined the influence of problem solving ability, communication skill and self-efficacy on clinical competence of nursing students. The research subjects were 184 grade 4 nursing students in D and G city. Data were collected from September 1 to September 10, 2016 and analyzed by independent t-test, one-way ANOVA, Pearson's correlation, and stepwise multiple regression using the IBM SPSS/WIN 20.0 program. The results showed that the problem solving ability was 3.60, communication skill was 3.79, and self-efficacy was 3.45. The clinical competence was positively correlated with problem solving ability, communication skill and self-efficacy. Problem solving ability (${\beta}=0.283$, p<0.001), self-efficacy (${\beta}=0.249$, p<0.001), motivation for nursing (${\beta}=0.182$, p=0.002), communication skills (${\beta}=0.176$, p=0.016), and interpersonal relationships (${\beta}=0.101$, p=0.082) explained 42.8% of the total variance in clinical competence of nursing students. The most significant predictors of clinical competence were problem solving ability, followed by self-efficacy and communication skills. Therefore, it is necessary to develop an empowerment program to improve problem solving ability, self-efficacy and communication skills of nursing students.