• International conference on construction engineering and project management
• /
• 2022.06a
• /
• pp.304-311
• /
• 2022

Construction inspection is a crucial stage that ensures that all contractual requirements of a construction project are verified. The construction inspection capabilities among state highway agencies have been greatly affected due to budget reduction. As a result, efficient inspection practices such as risk-based inspection are required to optimize the use of limited resources without compromising inspection quality. Automated prioritization of textual requirements according to their criticality would be extremely helpful since contractual requirements are typically presented in an unstructured natural language in voluminous text documents. The current study introduces a novel model for predicting the risk level of requirements using machine learning (ML) algorithms. The ML algorithms tested in this study included naïve Bayes, support vector machines, logistic regression, and random forest. The training data includes sequences of requirement texts which were labeled with risk levels (such as very low, low, medium, high, very high) using the fuzzy logic systems. The fuzzy model treats the three risk factors (severity, probability, detectability) as fuzzy input variables, and implements the fuzzy inference rules to determine the labels of requirements. The performance of the model was examined on labeled dataset created by fuzzy inference rules and three different membership functions. The developed requirement risk prediction model yielded a precision, recall, and f-score of 78.18%, 77.75%, and 75.82%, respectively. The proposed model is expected to provide construction inspectors with a means for the automated prioritization of voluminous requirements by their importance, thus help to maximize the effectiveness of inspection activities under resource constraints.

• International Journal of Contents
• /
• v.16 no.1
• /
• pp.75-86
• /
• 2020

As the elderly population is becoming an aging society, the elderly are experiencing many problems. Social security costs for the elderly are increasing and the un-linked social phenomenon is emerging. Thus, the social infrastructure and welfare system established in the past economic growth period are in danger of not functioning properly. People socially isolated or with chronic diseases among the elderly are exposed to various accidents. Thus, an active healthcare management service is imperative. Additionally, in the event of a dangerous situation, the system must have ways to notify guardians (family or medical personnel) regarding appropriate action. Thus, in this paper, we propose the smartphone-based healthcare and emergency response service platform. The proposed service platform aggregates movement of relevant data in real-time using a smartphone. Based on aggregated data, it will always recognize the user's movements and current state using the human motion recognition mechanism. Thus, the proposed service platform provides real-time status monitoring, activity reports, a health calendar, location-based hospital information, emergency situation detection, and cloud messaging server-based efficient notification to several subscribers such as family, guardians, and medical personnel. Through this service, users or guardians can augment the level of care for the elderly through the reports. Also, if an emergency situation is detected, the system immediately informs guardians so as to minimize the risk through immediate response.

• Journal of the Korean Society of Fisheries and Ocean Technology
• /
• v.55 no.1
• /
• pp.82-93
• /
• 2019

The International Labor Organization (ILO) selected fishing as the most dangerous group of jobs in the world, and it is well known in Korea as a 4D industry. Offshore large purse seine accounts for the largest portion of the fishing industry in the coastal region with high death rate and the accident rate. The repeated disaster rate survey by the Korea Maritime Institute (KMI) shows offshore large purse seiner is the highest at 22.3 percent and coastal gill nets and offshore stow net are following at 12.4 percent and 11.9 percent in order. Therefore, risk factors occurring in offshore large purse seiners were analyzed based on data from the National Federation of Fisheries Cooperatives (NFFC) for three years from 2015 to 2017 and 4M (Man, Machine, Media, Management) 3E (Engineering, Education, Enforcement) techniques were used to provide a safe fishing environment. The number of accidents on offshore large purse seiners each year was more than 150, and the number of accidents on every fishing boats was as high as 17 percent in 2015. If the accident rate and the risk level were divided by insurance, the accident resulting from contact with machinery was the highest, and the risk of a contact with gear was low but frequently occurring. This was caused by collisions and contact with gear in situations where death and disappearance risk are not high, and accident types in situations where death and loss risk are considered to be contact with machinery, falls or other accidents. Through these analysis techniques, the frequency and risk of each type of accident on a offshore large purse seiners can be demonstrated, and it is expected to raise awareness of a safer fishing environment and contribute to the reduction of accidents.

• Korean Chemical Engineering Research
• /
• v.46 no.2
• /
• pp.376-382
• /
• 2008

There are many accidents such as fire and explosion in laboratories that have caused a great loss to lives and property in spite of the effort to the enhancement of laboratory safety level for years. Development of laboratory safety management system is a necessary to improve safety level because the accidents of similar types have periodically occurred in laboratories. The laboratory safety management system may reduce many accidents and a serious loss in laboratory. In this study, we summarized major items for a risk management and safety improvement based on the analysis results of various accidents in the laboratories. And then the laboratory safety management system was developed containing a laboratory safety management manual, a laboratory management system, a education management system, a MSDS (material safety data sheet) management system and a laboratory safety audit system. It may have a potential application for the laboratory safety management in the chemical laboratories.

• Journal of the Society of Disaster Information
• /
• v.19 no.3
• /
• pp.490-497
• /
• 2023

Purpose: Since the 1990s, Korea has been making various efforts to prevent serious industrial accidents, such as implementing a hazardous risk prevention plan and implementing a process safety management system, but a series of recent major industrial accidents have shown its limitations. Therefore, this study aims to present measures to improve safety management of PSM target workplaces. Method: Investigate previous studies and cases on improving safety management at workplaces subject to PSM, seek ways to improve safety management at workplaces subject to PSM based on existing safety management, and evaluate safety management system one of the causes of accidents. Therefore, a safety education program is established to increase employees' safety awareness and understanding, and to improve the safety level. Result: Measures such as establishing an organizational culture to improve safety management of PSM target workplaces, responding to disasters, systematic safety management, replacing and strengthening old facilities, and strengthening management's firm commitment to safety were presented. Conclusion: Through this study, it is meaningful to present a systematic plan to secure safety to reduce precious lives and damage, and it is expected to be useful in considering the direction of PSM improvement for each workplace.

• Korean Journal of Soil Science and Fertilizer
• /
• v.41 no.3
• /
• pp.228-234
• /
• 2008

The purpose of this study was to predict environmental distribution of anthracene, benzene, benzo[a]pyrene, 1-methylphenanthrene and phenanthrene in a four phase biopile system - air, water, soil and non aqueous phase liquid (NAPL) phase using level I fugacity model. Soil samples used for this study were collected from three sites in the United Kingdom which were historically contaminated with petroleum hydrocarbons. The level I fugacities (f) for the five contaminants were markedly different, however, the fugacities of each contaminant in three soil samples did not show significant difference. NAPL and soil were the dominant phases for all five contaminants. Results of this study indicated that difference in percentage of organic carbon strongly influenced the partitioning behavior of the cntaminants. The presence of benzene calls for an urgent need for risk-based management of air and water phase. Whereas insignificant amount of chemicals leached in the water phase for other organic contaminants showing greatly reduced potential of groundwater contamination. Furthermore, this study helped us to confirm the association of risk critical contaminants with the residual saturation in treated soils. They also can be used to emphasize the importance of accounting for the partitioning behavior of both NAPL and soil phases in the process of the risk assessment of the sites contaminated with petroleum hydrocarbons.

• Journal of Preventive Medicine and Public Health
• /
• v.36 no.4
• /
• pp.383-389
• /
• 2003

Objective : Studies have suggested that beer is associated with a high risk of mortality and morbidity. The purpose of this study was to investigate how types of alcoholic beverage are related to high risk acute harm. Methods : Data from the 1997 Korea's Behavioral Risk Factor Surveillance System Survey, collected through telephone questionings, were analyzed based on multi-stage stratified random sampling(N=1,045). Among those who had drunk at least one type of alcoholic beverage in the last month, one episode where the drinker had consumed the highest level of ethanol was selected, and the alcohol consumption per drinking day categorized into four risk levels of short-term, 'acute' harm, according to the WHO guidelines. Employing ordered logistic regression analyses, as the explanatory variables, types of alcoholic beverage, with and without socioeconomic characteristics, were considered. Results : Spirits and soju were more than ten and three times, respectively, more likely than beer, while makkolli and wine were almost as likely as beer, to involve high risk drinking, irrespective of controlling for the socioeconomic characteristics. Conclusions : Unlike most Western countries, in Korea, beer, rather than spirits or soju, is generally less likely to be associated with high risk drinking for acute harm, The influence of beverage types on high risk drinking for acute harm appears to vary between countries.

• Journal of Environmental Science International
• /
• v.22 no.12
• /
• pp.1579-1587
• /
• 2013

This study was performed to evaluate the asbestos exposure levels and to calculate excess lifetime cancer risk (ELCR) for the risk assessment of the asbestos fibers released from asbestos-cement slate roofing (ASR) building. Total number of ASR buildings was into 21,267 in Busan, and 82.03 percent of the buildings was residential houses, and 43.61 percent of the buildings was constructed in 1970s. For this study, ten buildings were selected randomly among the ASR buildings. The range of airborne asbestos concentration in the selected ten ASR buildings was from 0.0016 to 0.0067 f/mL, and the concentration around no-admitted ASR buildings was higher than that around admitted buildings. The ELCR based on US EPA IRIS (integrated risk information system) model is within 3.5E-05 ~ 1.5E-04 levels, and the ELCR of no-admitted ASR buildings was higher than 1.0E-04 (one person per million) level that is considered a more aggressive approach to mitigate risk. These results indicate that the cancer risk from ASR buildings is higher than other buildings, and systematic public management is required for control of no-admitted ASR buildings within near future.

• Journal of Radiation Protection and Research
• /
• v.16 no.1
• /
• pp.53-72
• /
• 1991

An integrated model is developed in this paper for the performance assessment of high level radioactive waste repository. This integrated model consists of two simple mathematical models. One is a multiple-barrier failure model of the repository system based on constant failure rates which provides source terms to biosphere. The other is a biosphere model which has multiple pathways for radionuclides to reach to human. For the parametric uncertainty and sensitivity analysis for the risk assessment of high level radioactive waste repository, Latin hypercube sampling and rank correlation techniques are applied to this model. The former is cost-effective for large computer programs because it gives smaller error in estimating output distribution even with smaller number of runs compared to crude Monte Carlo technique. The latter is good for generating dependence structure among samples of input parameters. It is also used to find out the most sensitive, or important, parameter groups among given input parameters. The methodology of the mathematical modelling with statistical analysis will provide useful insights to the decision-making of radioactive waste repository selection and future researches related to uncertain and sensitive input parameters.

• Journal of Korean Society of Water and Wastewater
• /
• v.20 no.6
• /
• pp.799-811
• /
• 2006

As an alternative measure to replace reactive stance with proactive one, a risk based management scheme has been commonly applied to enhance public satisfaction on water service by providing a higher creditable solution to handle a rehabilitation problem of pipe having high potential risk of leaks. This study intended to examine the feasibility of a simulation model to predict a recurrence probability of pipe leaks. As a branch of the data mining technique, probabilistic neural network (PNN) algorithm was applied to infer the extent of leaking recurrence probability of water network. PNN model could classify the leaking level of each unit segment of the pipe network. Pipe material, diameter, C value, road width, pressure, installation age as input variable and 5 classes by pipe leaking probability as output variable were built in PNN model. The study results indicated that it is important to pay higher attention to the pipe segment with the leak record. By increase the hydraulic pipe pressure to meet the required water demand from each node, simulation results indicated that about 6.9% of total number of pipe would additionally be classified into higher class of recurrence risk than present as the reference year. Consequently, it was convinced that the application of PNN model incorporated with a data base management system of pipe network to manage municipal water distribution network could make a promise to enhance the management efficiency by providing the essential knowledge for decision making rehabilitation of network.