• Journal of the Korean Society of Safety
• /
• v.36 no.1
• /
• pp.56-63
• /
• 2021

The narrative texts of industrial accident reports help to identify accident risk factors. They relate the accident triggers to the sequence of events and the outcomes of an accident. Particularly, a set of related keywords in the context of the narrative can represent how the accident proceeded. Previous studies on text analytics for structuring accident reports have been limited to extracting individual keywords without context. We proposed a context-based analysis using a Natural Language Processing (NLP) algorithm to remedy this shortcoming. This study aims to apply Word2Vec of the NLP algorithm to extract adjacent keywords, known as word embedding, conducted by the neural network algorithm based on supervised learning. During processing, Word2Vec is conducted by adjacent keywords in narrative texts as inputs to achieve its supervised learning; keyword weights emerge as the vectors representing the degree of neighboring among keywords. Similar keyword weights mean that the keywords are closely arranged within sentences in the narrative text. Consequently, a set of keywords that have similar weights presents similar accidents. We extracted ten accident processes containing related keywords and used them to understand the risk factors determining how an accident proceeds. This information helps identify how a checklist for an accident report should be structured.

• Korean Journal of Biological Psychiatry
• /
• v.30 no.1
• /
• pp.24-30
• /
• 2023

Objectives Alzheimer's disease (AD) is the most common form of dementia in older adults, damaging the brain and resulting in impaired memory, thinking, and behavior. The identification of differentially expressed genes and related pathways among affected brain regions can provide more information on the mechanisms of AD. The aim of our study was to identify differentially expressed genes associated with AD and combined biomarkers among them to improve AD risk prediction accuracy. Methods Machine learning methods were used to compare the performance of the identified combined biomarkers. In this study, three publicly available gene expression datasets from the hippocampal brain region were used. Results We detected 31 significant common genes from two different microarray datasets using the limma package. Some of them belonged to 11 biological pathways. Combined biomarkers were identified in two microarray datasets and were evaluated in a different dataset. The performance of the predictive models using the combined biomarkers was superior to those of models using a single gene. When two genes were combined, the most predictive gene set in the evaluation dataset was ATR and PRKCB when linear discriminant analysis was applied. Conclusions Combined biomarkers showed good performance in predicting the risk of AD. The constructed predictive nomogram using combined biomarkers could easily be used by clinicians to identify high-risk individuals so that more efficient trials could be designed to reduce the incidence of AD.

• Journal of muscle and joint health
• /
• v.31 no.1
• /
• pp.53-63
• /
• 2024

Purpose: This study aimed to determine the prevalence of dizziness in adults and to identify factors associated with dizziness. Methods: This cross-sectional study used secondary data from the Eighth Korea National Health and Nutrition Examination Survey. Participants included 10,265 older adults aged≥40 years. Data were analyzed using descriptive statistics, the chi-squared test, and multinomial logistic regression with the SPSS/WIN 27.0 program. Results: The prevalence of dizziness was 26.2%, with 20.9% reporting episodic dizziness and 5.3% reporting chronic dizziness. Compared to that noted in the control group participants without dizziness, the risk of episodic or chronic dizziness was higher in women and in participants with older age, low education level, low income level, high perceived stress level, depression, tinnitus, and occupational noise exposure. Moreover, the risk of chronic dizziness was higher among those with a body mass index of <25 kg/m², stroke, cardiovascular disease, or severe hearing loss. Conclusion: The study underscores the need to comprehensively identify risk factors associated with dizziness and to develop interventions to prevent and manage the occurrence and chronicity of dizziness in the general population.

• Journal of the Korean Society of Safety
• /
• v.26 no.3
• /
• pp.8-14
• /
• 2011

The live-line works are very dangerous because of direct contacts with the distribution line or neighboring contacts. So the purpose of this study is to identify the risk factor by accident occurrence form and accident case analysis, and to suggest the quantified risk index by risk occurrence frequency and risk strength analysis. And the risk index assessment is researched by accident cases analysis on work type. Accident cases of transmission distribution line are researched based on data of the Ministry of Employment and Labor in the last ten-year period (2000~2009). In results of this paper, high risk isn't always a priority of safety measures. Risk occurrence frequency and risk strength have to be considered according to detail work types, work methods and conditions of field work. And safety management measures must be planned according to risk occurrence frequency and risk strength.

• The Journal of Information Systems
• /
• v.28 no.2
• /
• pp.129-152
• /
• 2019

Purpose The purpose of this study is to empirically identify the risky behavior of mobile device users using the Internet of Things on a situational perspective. Design/methodology/approach This study made a design of the research model based on model of the determinants of risk behavior. Data were collected through a survey including hypothetical scenario. SmartPLS 2.0 was used for the structural model analysis and t-test was conducted to compare the between normal and situational behavior. Findings The results were as follows. First, the central roles of risk propriety and risk perception were verified empirically. Second, we identified the role of locus of control as a new factor of impact on risky behavior. Third, mobile risk propensity has been shown to increase risk perception. Fouth, it has been shown that risk perception does not directly affect risky behavior and reduce the relationship between mobile risk propensity and risk behavior. According to the empirical analysis result, Determinants of risk behavior for mobile users were identified based on a theoretical framework. And it raised the need to pay attention to the impact of locus of control on risk behavior in the IS security field. It provided direction to the approach to risky behavior of mobile device users. In addition, this study confirmed that there was a possibility of taking risky behavior in the actual decision-making.

• Journal of the Korean Operations Research and Management Science Society
• /
• v.20 no.1
• /
• pp.85-99
• /
• 1995

Increasingly, risk analysis is becoming important ingredients in achieving the successful implementation and application in the area of the project management. The project management system is designed to manage or control the project resources on a given activity within time, cost and performance so called TPPM (Total Productive Project Management). In this research, a risk analysis model misproposed to identify potential problem areas, quantify the risks, and generated the chice of the action that can be taken to reduce the risk. In addition two analysis models are proposed : 1) risk factor model and 2) network simulation model using VERT (Venture Evaluation and Review Technique ). The objective of the remodels is to estimate the schedule, cost performance risks. These proposed quantitative models for project risk analysis are proving its value for the project managers who need to assess the risk of changes in cost, schedule, or performance. The proposed models will be used in the area of project selection, evaluation and the allocation of project resources.

• Journal of the Korean Society of Safety
• /
• v.35 no.2
• /
• pp.61-66
• /
• 2020

As asbestos-containing buildings are getting older, asbestos deconstruction works are increasing. As a result, accident risks such as falls, cuts, electric shocks, and suffocation are increasing. Existing studies are mostly about health management and institutional policy research and there is little research on work risk. So workplace risk assessments that are easily applicable in the field are required to be applied. Sealing is the first process of asbestos deconstruction and is the first step to ensure worker's safety. Job Safety Analysis(JSA) and Checklist were used to identify the risk factors and to calculate the level of the risk. By comparing the two risk assessment tools, it was figured out that the JSA is appropriate for the initial process and change of work procedure while Checklist is appropriate for repetitive work. Because the sealing process is sort and simple, it is unlikely to cause serious injury. But since the risk of falling and cuts are exist, safety education and supervision are necessary to maintain a safe working environment.

• Journal of the Korea Institute of Military Science and Technology
• /
• v.12 no.3
• /
• pp.309-316
• /
• 2009

The risk management is a method to identify and to handle risk factors. In this paper, we introduce a methodology that can be used to measure of system's performance risk by combining system's TPM(technical performance measures) in the R&D(research and development) program for defense acquisition. By applying the suggested procedure, we can monitor risk trends in R&D program by calculation of system's overall TPM and find out where management should target to reduce or remove the system's performance risk.

• Culinary science and hospitality research
• /
• v.14 no.4
• /
• pp.232-243
• /
• 2008

The purpose of this study is to investigate Korean wine consumers' perceived risk dimensions affecting wine purchasing behavior and identify the differences in the dimensions by wine involvement. Questionnaires were collected from the wine purchasers of wine retailer shops in Seoul. 230 data were analysed using SPSS package(v. 12.0). Findings were as follows: (1) There were 5 dimensions in the perceived risk of wine purchasing: functional, social, physical, psychological, financial. Social dimension was the most serious risk for wine consumers, then come psychological, functional, financial, and physical ones. (2) There were significant differences in the perceived risk dimensions by involvement level except the financial dimension. The perception level of wine purchasing risk was relatively low in the high involvement group while high in the middle and low involvement groups.

• Journal of the Korean Home Economics Association
• /
• v.41 no.11
• /
• pp.49-60
• /
• 2003

The purposes of this study were (1) to assess the perceived evaluation of family financial risk safeguards and (2) to identify demographic variables, financial security and financial communication which were an influence on the perceived evaluation of family financial risk safeguards. The data were collected from 598 housewives using an on-line survey. The major findings of this study were as follows: first, the perceived evaluation of financial risk safeguards was lower than the median(2.80). Especially, the perceived evaluation of financial risk safeguard for children's education had the highest score. Second, the variables which were an influence on the financial communication of husbands and wives were‘financial security’ and ‘years which they have been married’. Third, the perceived evaluation of financial risk safeguards was significantly different according to financial security and the financial communication of husbands and wives.