• Nuclear Engineering and Technology
• /
• v.55 no.2
• /
• pp.603-622
• /
• 2023

Human error (HE) is an important concern in safety-critical systems such as nuclear power plants (NPPs). HE has played a role in many accidents and outage incidents in NPPs. Despite the increased automation in NPPs, HE remains unavoidable. Hence, the need for HE detection is as important as HE prevention efforts. In NPPs, HE is rather rare. Hence, anomaly detection, a widely used machine learning technique for detecting rare anomalous instances, can be repurposed to detect potential HE. In this study, we develop an unsupervised anomaly detection technique based on generative adversarial networks (GANs) to detect anomalies in manually collected surveillance data in NPPs. More specifically, our GAN is trained to detect mismatches between automatically recorded sensor data and manually collected surveillance data, and hence, identify anomalous instances that can be attributed to HE. We test our GAN on both a real-world dataset and an external dataset obtained from a testbed, and we benchmark our results against state-of-the-art unsupervised anomaly detection algorithms, including one-class support vector machine and isolation forest. Our results show that the proposed GAN provides improved anomaly detection performance. Our study is promising for the future development of artificial intelligence based HE detection systems.

• Journal of the Korea Institute of Information Security & Cryptology
• /
• v.33 no.3
• /
• pp.561-575
• /
• 2023

The information security industry has seen a wide variety of growth over the past few decades. In particular, various solutions have been proposed in terms of technology, management, and institutional aspects. Nevertheless, it should be notedthat security accidents continue to occur every year. This proves that there are limitations to various business changes in the digital era as existing security is being promoted with technology-oriented and prevention-oriented policies. Thus, people-centric security (PCS) has recently become a hot topic in order to escape the limitations of traditional securityapproaches. Through the concept of information security violations, PCS strategic principles, and expert interviews, this studyaims to present a fundamental security incident response plan by classifying human-caused vulnerabilities into 5 categories and classifying them into 21 detailed components.

• Journal of Hydrogen and New Energy
• /
• v.34 no.3
• /
• pp.297-306
• /
• 2023

The frequency of fatal accidents that can occur at hydrogen refueling station was compared with the risk criterion for the general public suggested by the health and safety executive. If hydrogen refueling station meets the accident prevention facility standards presented in KGS Code FP216/217, it was confirmed that the risk of hydrogen refueling station was not at an unacceptable (intolerable) risk level. However, the risk of hydrogen refueling station due to small leak was analyzed as low as reasonably practicable. Therefore, methods for improving the safety instrumented function of hydrogen refueling station were reviewed. It was confirmed that the risk of hydrogen refueling station can be affected by the number of installed safety instrumentation system components, redundant architecture, mission time, proof test interval, etc. And methods for maintaining the risk of hydrogen refueling station at an acceptable risk level have been proposed.

• International conference on construction engineering and project management
• /
• 2015.10a
• /
• pp.192-194
• /
• 2015

The growing size and complex process in construction project recently leads to increase risk and the losses as well. Even though researchers have identified the major risk indicators, there is lack of comprehensive and quantitative research for identifying the relationship between the risk indicators and economic losses associated with construction projects. To address this shortage of research, this study defines risk indicators and create a framework to assess the influence of economic losses from the indicators. An insurance company's claim payout record was accepted as the dependent variable to reflect the real economic losses. Based on the claims, we categorized the causes and results of accidents. To establish framework, built environment vulnerability indicators and geographical vulnerability indicators were employed as the risk indicators. A Pearson correlation analysis was adopted to validate the relationship with loss ratio and risk indicators. Consequently, this framework and its results may offer significant references for under writers of insurance companies and loss prevention activities.

• International Journal of Internet, Broadcasting and Communication
• /
• v.16 no.2
• /
• pp.255-266
• /
• 2024

The purpose is to evaluate evacuation safety by simulating the toxic effects of hydrogen fluoride leaks in areas surrounding national industrial complexes and to suggest alternatives for areas that do not satisfy evacuation safety. For human casualties caused by hydrogen fluoride leakage accidents, Available Safe Egress Time (ASET) is calculated by the toxic effects quantified with the Areal Locations of Hazardous Atmospheres (ALOHA), an off-site consequence assessment program. The Required Safe Egress Time (RSET) is calculated through Pathfinder, an evacuation simulation program. Evacuation safety is assessed by comparing ASET and RSET. The ALOHA program was used to evaluate the time to reach AEGL-2 concentration in 12 scenarios. The Pathfinder program was used to assess the total evacuation time of the high school among specific fire-fighting objects. Of the 12 accident scenarios, ASET was larger than RSET in the worst-case scenarios 1 and 9. For the remaining 10 accident scenarios, the ASET is smaller than the RSET, so we found that evacuation safety is not guaranteed, and countermeasures are required. Since evacuation safety is not satisfactory, we proposed to set up an evacuation area equipped with positive pressure equipment and air respirators inside specific fire-fighting objects such as the high school.

• The Korean Journal of Emergency Medical Services
• /
• v.28 no.2
• /
• pp.21-31
• /
• 2024

Purpose: This study aims to examine how college students perceive the usage environment of electric kickboards, recognize safety issues, and seek ways to improve them. Methods: A descriptive survey was conducted on 180 college students from November 1 to November 8, 2023, to analyze the environment and risks associated with using electric kickboards. Results: College students perceived electric kickboards as extremely dangerous. However, they did not receive safety education and 76.4% of the subjects did not wear safety helmets when driving electric kickboards. Women suggested lowering the speed of electric kickboards, including in certain sections, and emphasized that the more accidents they experienced, the more necessary it was to improve regulations. Conclusion: This study comprehensively illustrates the perception of risk and speed improvement among electric kickboard users, and emphasizes the need to prepare detailed guidelines for implementing and operating safety education.

• Journal of IKEEE
• /
• v.28 no.3
• /
• pp.397-404
• /
• 2024

This paper presents the design and implementation results of a Raspberry-Pi-based embedded system with an FPGA accelerator that can detect and classify objects using an FMCW radar sensor for preventing door collision accidents in vehicles. The proposed system performs a radar sensor signal processing and a deep learning processing that classifies objects into bicycles, automobiles, and pedestrians. Since the CNN algorithm requires substantial computation and memory, it is not suitable for embedded systems. To address this, we implemented a lightweight deep learning model, BNN, optimized for embedded systems on an FPGA, and verified the results achieving a classification accuracy of 90.33% and an execution time of 20ms.

• Journal of the Society of Disaster Information
• /
• v.17 no.4
• /
• pp.864-881
• /
• 2021

Purpose: This study aims is to provide a total care solution preventing disaster based on Big Data and AI technology and to service safety considered by individual situations and various risk characteristics. The purpose is to suggest a method that customized comprehensive index services to prevent and respond to safety accidents for calculating the living safety index that quantitatively represent individual safety levels in relation to daily life safety. Method: In this study, we use method of mixing AHP(Analysis Hierarchy Process) and Likert Scale that extracted from consensus formation model of the expert group. We organize evaluation items that can evaluate life safety prevention services into risk indicators, vulnerability indicators, and prevention indicators. And We made up AHP hierarchical structure according to the AHP decision methodology and proposed a method to calculate relative weights between evaluation criteria through pairwise comparison of each level item. In addition, in consideration of the expansion of life safety prevention services in the future, the Likert scale is used instead of the AHP pair comparison and the weights between individual services are calculated. Result: We obtain result that is weights for life safety prevention services and reflected them in the individual risk index calculated through the artificial intelligence prediction model of life safety prevention services, so the comprehensive index was calculated. Conclusion: In order to apply the implemented model, a test environment consisting of a life safety prevention service app and platform was built, and the efficacy of the function was evaluated based on the user scenario. Through this, the life safety index presented in this study was confirmed to support the golden time for diagnosis, response and prevention of safety risks by comprehensively indication the user's current safety level.

• Journal of Korean Academy of Nursing
• /
• v.7 no.2
• /
• pp.11-21
• /
• 1977

Many in nursing look back on Nursing Research history and proudly point to the fact that emphasis in nursing research has changed from studying the nurse to studying nursing practice. In recent years, much emphasis has been placed on seeking a method of evaluating the quality of nursing care. In spite of these attempts, however, an instrument for evaluating the quality of nursing care that is actually applicable in the clinical area has not been found. The Purposes of this study are as follows: 1) To develop the instrument to be used in evaluating the quality of nursing care provided in the Neuro - Surgery Constant Care Unit of Severance Hospital 2) To evaluate the quality of nursing care in the clinical area. 3) To provide the necessary information for improvement of quality of nursing care. The instrument for evaluating the quality of nursing care, developed by the investigator, was composed of 7 nursing goals and divided into 65 standards of nursing performance. The 7 nursing goal are as follows : 1) Maintenance of airway 2) Maintenance of fluid at electrolyte balance 3) Maintenance of elimination 4) Personal hygiene 5) Optimum activity 6) Prevention of accidents 7) Emotional care The study population defined was composed of all the case (51) who were admitted in the Neuro- Surgery Constant Care Unit of Severance Hospital from May 7-13, 1976. The observation method was used and the data was subjected to the %, X²-test, T-test, F-test and Correlation. The results of tile study were as follows : 1. Levels of nursing performance regarding nursing goals. Seven different nursing care indices were constructed in terms of nursing goals. The index scores were grouped arbitrarily into ,j categories such as "excellent", "good", "moderate", "incomplete", and "poor"based upon the investigator′s personal judgement. a. The nursing index of maintaining airway showed that 78% of the patients fell within the "excellent" and 22% of the patients, fell within the "good" category. b. The nursing index of maintaining fluid & electrolyte balance showed that 95% of the patients fell within the "excellent" and 5 % of the patients fell within the "good" category. c. The nursing index of maintaining elimination showed that 100% of the patients fell within the "excellent" category. d. The nursing index of personal hygiene revealed that 49% of the patients fell within the "excellent" and 51% of the patients fell within the "good" category. e. The nursing index of optimum activity showed that 63% of the patients fell within the "excellent" and 32% of the patients fell within tile "good" and 5% of patients fell within the "moderate" category. f. The nursing index of prevention of accidents showed that 100% of the patients foil within the "excellent" category. g. The nursing index of emotional cart revealed that 27% of the patients fell within the "excellent", 24 % of the patients fell within tile "good", 29 % of the patients fell within the "incomplete" category. From these findings it is disclosed that the quality of nursing care provided in the Neuro- Surgery Constant Care Unit of Severance Hospital was excellent. h. There were statistically significant differences between the nursing index of physical care and emotional care. (t=8.73, D. F. =100. p<0.01) It is revealed that more physical care then emotional care was carried out by nurses. 2. Levels of nursing performance regarding general characteristics of the patients. No significant differences were observed statistically with the nursing indices of nursing goals according to the sex (t=0.084, D. F. =12, p>0.05). Age (F=0.1251, D. F. : 3.18. p 〉0.05), absence or presence of operating experiences (t=0.6032, D. F. =12, p〉0.05, levels of consciousness (F=0.31, D. F. :3. 18, p >0.05) 3. Relationship between the levels of consciousness and the nursing index of each nursing goal. There was negative correlation between the levels of consciousness and the nursing index of maintaining airway (r=-0. 5449, p<0.01) and personal hygiene (r= -0.4075, p<0.01) There was positive correlation between the levels of consciousness and the nursing index of optimum activity (r=0.3936, p <0.01) and emotional care (r=0.7819, p〈0.01). There was slight correlation between the levels of consciousness and the nursing index of maintaining fluid & electrolyte balance (r=-0.3418, 0.010.05) and preventing accidents (r=0.1441, p>0.05.

• Child Health Nursing Research
• /
• v.19 no.4
• /
• pp.282-290
• /
• 2013

Purpose: The purpose of this study was to analyze life respect-related content in the 7th to 10th grade textbooks of middle and high schools. Methods: Sixty two textbooks adopted as middle and high school textbooks were analyzed for content on life respect. Results: There were 6 categories related to life respect content in the 7th to 9th grade textbooks ("prevention of accidents and the first-aid", "mental health", "sex and health", "prevention of drug abuse, smoking and drinking", "normal life and health", and "society and health"). Content on life respect in the 10th grade textbooks was categorized as "drug abuse, smoking, drinking, and health", "sex and health", "mental health", "life science and treating human life too lightly", "normal life and health", and "society and health". Conclusion: Content on life respect attached importance to more practical issue such as prevention of violence and suicide rather than fundamental understanding about self and life. These results suggest that the content on life respect should help adolescents find their own values and meaning of life within the concept of coexistence.