• 한국정보통신학회논문지
• /
• 제26권9호
• /
• pp.1259-1265
• /
• 2022

최근 인공지능, 빅데이터, 사물인터넷 기술이 안전사고 예방을 위한 화재 감지, 가스나 유해 물질 감지 등 다양한 솔루션에서 활용되고 있다. 2021년 고용노동부에서 발간한 산업 재해 발생 현황에 따르면, 2020년과 비교해 재해율, 재해자 수, 사망자 수가 증가하였으며 최근에는 중대재해 처벌 등에 관한 법률과 같은 안전조치를 강화하는 등 제도적, 사회적 관심이 높아지고 있다. 본 논문에서는 한국지능정보사회진흥원(NIA)에서 제공한 데이터셋 구축 가이드라인을 참고하여 현장에서 직접 수집해 데이터셋을 직접 구축하고 YOLOv4로 학습하여 객체 탐지를 통해 충돌위험 객체 탐지 시스템을 제안하고자 한다. 위험 상황 규칙 위반에 대한 정확도는 실내 88%, 실외 92%의 탐지 성능을 보였다. 이러한 시스템을 통해 산업 현장에서 발생하는 안전사고를 사전에 분석해 지능형 플랫폼 연구에 활용이 가능할 것으로 사료된다.

• 한국토양비료학회지
• /
• 제50권5호
• /
• pp.434-451
• /
• 2017

For this study, groundwater samples for 3 years from 2011 through 2013 were collected at 106 groundwater monitoring site in Korea. These groundwater samples were analyzed for 13 pesticides such as cabofuran, pentachlorobenzene, hexachlorobenzene, simazine, atrazine, lindane (gamma-HCH), alachlor, heptachlor, chlordane (total), endosulfan (1, 2), dieldrin, endrin, 4,4-DDT. The objectives of this study were to determine the detection frequency and their concentrations of 13 pesticides and evaluate the health risk level considering ingestion, inhalation, and skin contact using concentrations of 13 pesticides in groundwater samples. An analysis was used for the simultaneous determination for 13 pesticides using GC-MS. GC-MS was performed on HP-5ms, using helium ($1ml\;min^{-1}$) as carrier gas. The average recoveries of the pesticides were from 92.8% to 120.8%. The limits of detection (LODs) were between $0.004{\mu}g\;L^{-1}$ and $0.118{\mu}g\;L^{-1}$ and the limits of quantification (LOQs) were between $0.012{\mu}g\;L^{-1}$ and $0.354{\mu}g\;L^{-1}$. 106 groundwater wells were selected. 54 wells were from well to monitor background groundwater quality and 52 wells were from well to monitor groundwater quality in industrial or contamination source area. Eight pesticides including pentachlorobenzene, lindane (Gamma-HCH), heptachlor, chlordane (total), Endosulfan (1, 2), dieldrin, endrin, and 4,4-DDT were not detected in groundwater samples. The detection frequency for hexachlorobenzene, alachlor, carbofuran and simazine was 23.4%, 11.4%, 7.3%, and 1.0%, respectively. Atrazine was detected once in 2011. The average concentrations were $0.00423{\mu}g\;L^{-1}$ for carbofuran, $0.000243{\mu}g\;L^{-1}$ for alachlor, $0.00015{\mu}g\;L^{-1}$ for simazine, and $0.00001{\mu}g\;L^{-1}$ for hexachlorobenzene. The detection frequency of hexachlorobenzene was high, but the average concentration was low. In the contaminated groundwater, the detection frequency for hexachlorobenzene, alachlor, carbofuran, simazine and atrazine was 26.1%, 21.3%, 7.1%, 1.9% and 0.3%, respectively. In the uncontaminated groundwater, detection frequency for hexachlorobenzene, carbofuran and alachlor were 20.2%, 7.5%, and 1.9% respectively. Simazine and atrazine were not detected at uncontaminated groundwater wells. According to the purpose of groundwater use, atrazine was detected for agricultural groundwater use. Hexachlorobenzene showed high detection frequency at agricultural groundwater use area where the animal feeding area and golf course area were located. Alachlor showed more than 50% detection frequency at cropping area, pollution concern river area, and golf course area. Atrazine was detected in agricultural water use area. By land use, the maximum detection frequency of alachlor was found near an orchard. For human risk assessment, the cancer risk for the 5 pesticides was between $10^{-7}$ and $10^{-10}$, while the non-cancer risk (HQ value) was between $10^{-4}$ and $10^{-6}$. For conclusion, these monitoring study needs to continue because of the possibility of groundwater contamination based on various purpose of groundwater use.

• Tuberculosis and Respiratory Diseases
• /
• 제72권2호
• /
• pp.140-148
• /
• 2012

Background: Detection and treatment of tuberculosis (TB) infection with contact investigation is a key component of TB control program. I evaluated the prevalence and risk factors for TB infection among contacts of recently diagnosed pulmonary TB patients in a tertiary hospital in Korea. Methods: 206 contacts of 90 adult pulmonary TB patients underwent tuberculin skin tests (TST) and chest radiography. The TST results were considered positive with an induration of 10 mm or more, suggesting TB infection. A standardized questionnaire was used to assess risk factors associated with TB infection. Results: TST was positive in 97 of 206 contacts of TB patients (47.1%) and positive rate of TST increased with age. The risk of TB infection was significantly associated with close contact with TB patients (sleeping in the same room) (odd ratio [OR], 4.94; 95% confidence interval [CI], 1.43~17.00). Conclusion: TB infection rate was higher in the elderly, and the risk of TB infection was significantly increased with close contact of TB patients.

• 한국안전학회지
• /
• 제27권5호
• /
• pp.164-170
• /
• 2012

In this study, a new technique for detecting near miss using 4M risk assessment method is suggested. Until now, the safety education with instances of near miss has just been progressed in most industrial settings, without any systematic guideline. By menas of appling 4M risk assessment method, the organized technique, which could effectively manage the fundamental prevention of industrial accident in advance, is developed. The organized technique of near miss-management suggested in this study will take an effective role in basically expanding the application of risk assessment method, as well as in contributing the activity of zero-accident as a safety guideline in hazardous workshops.

• Journal of Information Technology Applications and Management
• /
• 제23권4호
• /
• pp.25-39
• /
• 2016

Asset prices decline sharply and stock markets collapse when financial crisis happens. Recently we have encountered more frequent financial crises than ever. 1998 currency crisis and 2008 global financial crisis triggered academic researches on early warning systems that aim to detect the symptom of financial crisis in advance. This study proposes a risk recovery index for detection of good opportunities from financial market instability. We use SVM classifier algorithms to separate recovery period from unstable financial market data. Input variables are KOSPI index and V-KOSPI200 index. Our SVM algorithms show highly accurate forecasting results on testing data as well as training data. Risk recovery index is derived from our SVM-trained outputs. We develop a trading system that utilizes the suggested risk recovery index. The trading result records very high profit, that is, its annual return runs to 121%.

• 대한안전경영과학회지
• /
• 제9권2호
• /
• pp.97-111
• /
• 2007

In risk assessment, there are several methods such as Safety Review, Checklist, FMEA(Failure Mode and Effect Analysis), FTA(Fault Tree Analysis), ETA (Event Tree Analysis) etc, however, the level of accident is indentified by the probability of accident and severity resulting from accident which used widely in assessing accidents and disasters. In this paper, the risk assessment method to decide the level of risk will be introduced by using severity, frequency and detection according to accident theory.

• 식품과학과 산업
• /
• 제54권1호
• /
• pp.2-10
• /
• 2021

Microplastics with a size of less than 5 mm have emerged as an important environmental and food safety issue, as they have been detected not only in marine but also in terrestrial ecosystem and drinking water. Although many studies have been conducted on the exposure of microplastics and the effects on human health, the lack of standardized experimental methods for microplastics has been reviewed as a major problem. In order to overcome this, European countries such as the Netherlands and Germany are conducting a project to develop detection methods for microplastics as well as to establish the risk assessment methodologies for microplastics. Being the microplastics suggested to have a substantially potential risk on human health, reliable risk assessments should be conducted considering the various sources of microplastics, chemical pollutants and biological factors. In addition, international standards and regulations should be applied.

• 한국정보처리학회:학술대회논문집
• /
• 한국정보처리학회 2021년도 춘계학술발표대회
• /
• pp.323-325
• /
• 2021

In this article, we have improved the prediction of hypertension detection using the feature selection method for the Korean national health data named by the KNHANES database. The study identified a variety of risk factors associated with chronic hypertension. The paper is divided into two modules. The first of these is a data pre-processing step that uses a factor analysis (FA) based feature selection method from the dataset. The next module applies a predictive analysis step to detect and predict hypertension risk prediction. In this study, we compare the mean standard error (MSE), F1-score, and area under the ROC curve (AUC) for each classification model. The test results show that the proposed FIFA-OE-NB algorithm has an MSE, F1-score, and AUC outcomes 0.259, 0.460, and 64.70%, respectively. These results demonstrate that the proposed FIFA-OE method outperforms other models for hypertension risk predictions.

• 항공우주시스템공학회지
• /
• 제1권4호
• /
• pp.7-12
• /
• 2007

From the beginning of aviation history, in-flight smoke/fire events have been a serious issue. As aircraft are getting larger and are becoming more auto-piloted and aircraft systems are getting more complex, it is an increasing risk of in-flight smoke/fire accidents accompanied with fire events. Therefore, we review the statistics of fire/smoke accidents in order to enhance an understanding for risk of in-flight smoke events, and present the certification requirements for smoke per KAS Part 25. In addition, we provide acceptable methods of complying with related requirements, such as smoke detection test, smoke penetration test and smoke evacuation test.

• 대한치과의사협회지
• /
• 제49권3호
• /
• pp.153-158
• /
• 2011

Oral precancerous lesion is a morphologically altered tissue in which oral cancer is more likely to occur than is apparently normal counterpart. As dentists always do oral examination and dental treatment, with fundamental knowledge and attention of this lesion, it is relatively easy to find one. If followed by proper treatment and management, it is possible to minimize its oral cancer progression, or at least delay it. Even if it were to progress to oral cancer, very early detection is possible. However, no specific biomarkers are present at the moment that could reveal oral precnacerous lesion that is high risk of oral cancer progression. Since early detection of oral cancer followed by treatment could show good prognosis with just a simple ablative surgery. Dentists should also instruct people to avoid risk factor related oral cancer progression and take natural compound having anticancer effect. Hereby, As a primary care givers, dentists play an important role in prevention of oral cancer.