• Korean Journal of Adult Nursing
• /
• v.27 no.5
• /
• pp.559-571
• /
• 2015

Purpose: This study is to determine the predictive validity of the St. Thomas Risk Assessment Tool in Falling Elderly Inpatients (STRATIFY) for inpatients' fall risk. Methods: A literature search was performed to identify all studies published between 1946 and 2014 from periodicals indexed in Ovid Medline, Embase, CINAHL, KoreaMed, NDSL and other databases, using the following key words; 'fall', 'fall risk assessment', 'fall screening', 'mobility scale', and 'risk assessment tool'. The QUADAS-II was applied to assess the internal validity of the diagnostic studies. Fourteen studies were analyzed using meta-analysis with MetaDisc 1.4. Results: The predictive validity of STRATIFY was as follows; pooled sensitivity .75 (95% CI: 0.72~0.78), pooled specificity .69 (95% CI: 0.69~0.70) respectively. In addition, the pooled sensitivity in the study that targets only the over 65 years of age was .89 (95% CI: 0.85~0.93). Conclusion: The STRATIFY's predictive validity for fall risk is at a moderate level. Although there is a limit to interpret the results for heterogeneity between the literature, STRATIFY is an appropriate tool to apply to hospitalized patients of the elderly at a potential risk of accidental fall in a hospital.

• Quality Improvement in Health Care
• /
• v.22 no.2
• /
• pp.27-40
• /
• 2016

Purpose: Globally, falls are a major public health problem. The study aimed to evaluate the predictive validity of the Timed Up and Go test (TUGT) as a screening tool for fall risk. Methods: An electronic search was performed Medline, EMBASE, CINAHL, Cochran Library, KoreaMed and the National Digital Science Library and other databases, using the following keywords: 'fall', 'fall risk assessment', 'fall screening', 'mobility scale', and 'risk assessment tool'. The QUADAS-II was applied to assess the internal validity of the diagnostic studies. Thirteen studies were analyzed using meta-analysis with MetaDisc 1.4. Results: The selected 13 studies reporting predictive validity of TUGT of fall risks were meta-analyzed with a sample size of 1004 with high methodological quality. Overall predictive validity of TGUT was as follows. The pooled sensitivity 0.72 (95% confidence interval [CI]: 0.67-0.77), pooled specificity 0.58 (95% CI: 0.54-0.63) and sROC AUC was 0.75 respectively. Heterogeneity among studies was a moderate level in sensitivity. Conclusion: The TGUT's predictive validity for fall risk is at a moderate level. Although there is a limit to interpret the results for heterogeneity between the literature, TGUT is an appropriate tool to apply to all patients at a potential risk of accidental fall in a hospital or long-term care facility.

• PNF and Movement
• /
• v.16 no.3
• /
• pp.495-503
• /
• 2018

Purpose: This study analyzes the predictive power of upper extremity activity and the activities of daily living in patients with stroke using an easy-to-use evaluation tool. Methods: The Fugl-Meyer assessment (FMA) of the upper extremity and action research arm test (ARAT) are performed, and the Korean modified Barthel index (K-MBI) is measured. The predictive power of the upper extremity activity level and the daily activity level are analyzed using regression analysis. The statistical significance level is 0.05. Results: The coefficient of determination, R2, for predicting the ARAT using FMA was high at 0.88, but the regression equation for predicting the K-MBI using the FMA and ARAT did not show a statistically significant difference. Conclusion: The assessment of the upper extremity should be performed at the activity level, as well as the impairment level. The assessment for predicting the activities of daily living should be carried out for each level of the international classification of functioning (ICF), disability, and health, which can be linked to daily life, in addition to the assessment of the upper arm. Future research should conduct more diverse analyses using the ICF assessment tools at various levels.

• The Journal of Information Systems
• /
• v.33 no.2
• /
• pp.125-142
• /
• 2024

Purpose The purpose of this study is to identify and analyze the key factors influencing congestion in the in-out transportation at port container terminals, and to design of a predictive model for in-out congestion based on these analysis. This study focused on architecting a deep learning-based predictive model. Design/methodology/approach This study was conducted through the following methodology. First, hypotheses were established and data were analyzed to examine the impact of vessel schedules and external truck schedules on in-out transportation. Next, explored time series forecasting models to a design the architecture for deep learning-based predictive model. Findings According to the empirical analysis results, this study confirmed that vessel schedules significantly affect in-out transportation. Specifically, the volume of transportation increases as the vessel arrival/departure time and the cargo cutoff time approach. Additionally, significant congestion patterns in transportation volume depending on the day of the week and the time of day were observed.

• Proceedings of the KIPE Conference
• /
• 2015.07a
• /
• pp.63-64
• /
• 2015

The control of IPMSM(Interior Permanent Magnet Synchronous Motor) for electric vehicle is important to track torque reference depended on accelerator. This paper executes IPMSM control applied the predictive current control which has good dynamic characteristic and, compare PI control with predictive current control to verify dynamic characteristic through simulation.

• International journal of advanced smart convergence
• /
• v.8 no.3
• /
• pp.193-200
• /
• 2019

Accruals-Quality(AQ) is an important proxy for evaluating the quality of accounting information disclosures. High-quality accounting information will provide high predictability and precision in the disclosure of earnings and will increase the response to stock prices. And high Accruals-Quality, such as mitigating heterogeneity in accounting information interpretation, provides information usefulness in capital markets. The purpose of this study is to suggest how AQ, which represents the quality of accounting information disclosure, is transformed into digitized data in real-time in combination with IT information technology and provided to financial analyst's information environment in real-time. And AQ is a framework for predictive analysis through big data log analysis system. This real-time information from AQ will help financial analysts to increase their activity and reduce information asymmetry. In addition, AQ, which is provided in real time through IT information technology, can be used as an important basis for decision-making by users of capital market information, and is expected to contribute in providing companies with incentives to voluntarily improve the quality of accounting information disclosure.

• Journal of Information Processing Systems
• /
• v.17 no.3
• /
• pp.630-644
• /
• 2021

Educational data analysis is attracting increasing attention with the rise of the big data industry. The amounts and types of learning data available are increasing steadily, and the information technology required to analyze these data continues to develop. The early identification of potential dropout students is very important; education is important in terms of social movement and social achievement. Here, we analyze educational data and generate predictive models for student dropout using logistic regression, a decision tree, a naïve Bayes method, and a multilayer perceptron. The multilayer perceptron model using independent variables selected via the variance analysis showed better performance than the other models. In addition, we experimentally found that not only grades but also extracurricular activities were important in terms of preventing student dropout.

• Design & Manufacturing
• /
• v.17 no.1
• /
• pp.27-32
• /
• 2023

In this paper, we intend to predict the mass of the spiral using CAE and machine learning. First, We generated 125 data for the experiment through a complete factor design of 3 factors and 5 levels. Next, the data were derived by performing a molding analysis through CAE, and the machine learning process was performed using a machine learning tool. To select the optimal model among the models learned using the learning data, accuracy was evaluated using RMSE. The evaluation results confirmed that the Support Vector Machine had a good predictive performance. To evaluate the predictive performance of the predictive model, We randomly generated 10 non-overlapping data within the existing injection molding condition level. We compared the CAE and support vector machine results by applying random data. As a result, good performance was confirmed with a MAPE value of 0.48%.

• Communications for Statistical Applications and Methods
• /
• v.30 no.5
• /
• pp.437-451
• /
• 2023

Generalized linear models and generalized linear mixed models (GLMMs) are fundamental tools for predictive analyses. In insurance, GLMMs are particularly important, because they provide not only a tool for prediction but also a theoretical justification for setting premiums. Although thousands of resources are available for introducing GLMMs as a classical and fundamental tool in statistical analysis, few resources seem to be available for the insurance industry. This study targets insurance professionals already familiar with basic actuarial mathematics and explains GLMMs and their linkage with classical actuarial pricing tools, such as the Buhlmann premium method. Focus of the study is mainly on the modeling aspect of GLMMs and their application to pricing, while avoiding technical issues related to statistical estimation, which can be automatically handled by most statistical software.

• Asia pacific journal of information systems
• /
• v.31 no.2
• /
• pp.185-196
• /
• 2021

The paper aims to analyze and predict sales of liquor in the state of Iowa by applying machine learning algorithms to models built for prediction. We have taken recourse of Azure ML and Spark ML for our predictive analysis, which is legacy machine learning (ML) systems and Big Data ML, respectively. We have worked on the Iowa liquor sales dataset comprising of records from 2012 to 2019 in 24 columns and approximately 1.8 million rows. We have concluded by comparing the models with different algorithms applied and their accuracy in predicting the sales using both Azure ML and Spark ML. We find that the Linear Regression model has the highest precision and Decision Forest Regression has the fastest computing time with the sample data set using the legacy Azure ML systems. Decision Tree Regression model in Spark ML has the highest accuracy with the quickest computing time for the entire data set using the Big Data Spark systems.