• 한국재난정보학회 논문집
• /
• 제19권2호
• /
• pp.432-438
• /
• 2023

연구목적: 생활안전 예방서비스 앱에서 신고되는 이미지를 AI를 사용하여 실시간으로 위험 카테고리를 자동으로 분류하여 사용자에게 편리한 위험신고를 가능하게 하는 것을 목적으로 한다. 연구방법: 인터넷으로 상호연결되는 생활안전 예방서비스 플랫폼, 생활안전 예방서비스 앱, AI 모델 서빙 서버와 sftp 서버로 구성되는 시스템을 통하여 신고된 생활안전 이미지를 실시간으로 자동분류하며, 이때 사용되는 AI모델 생성을 위한 AI 학습 알고리즘도 개발하였다. 연구결과: 이미지를 실시간으로 AI 처리하여 자동으로 분류할 수 있게 되어, 신고자가 생활안전 관련 사항을 보다 편리하게 신고할 수 있게 되었다. 결론: 본 논문에서 제시하는 AI 이미지 자동분류 시스템은 90% 이상의 분류 정확도로 신고 이미지를 실시간으로 자동분류하여 신고자가 간편하게 생활안전 관련 이미지를 신고할 수 있게 되었으며 향후 생활안전 예방서비스 앱의 사용자의 증가에 따라 더욱 빠르고 정확한 AI 모델 개발 및 시스템 처리용량 향상이 필요하다.

• 한국의학물리학회지:의학물리
• /
• 제27권3호
• /
• pp.131-138
• /
• 2016

We analyzed the terminology and classification related to the risk management of radiation treatment overseas to establish the terminology and classification system for Korea. This study investigated the terminology and classification for radiotherapy risk management through overseas research materials from related organizations and associations, including the IAEA, WHO, British group, EC, and AAPM. Overseas risk management commonly uses the terms "near miss", "incident", and "adverse event", classified according to the degree of severity. However, several organizations have ambiguous terminologies. They use the term "near miss" for events such as a near event, close call, and good catch; the term "incident" for an event; and the term "adverse event" for the likes of an accident and an event. In addition, different organizations use different classifications: a "near miss" is generally classified as "incident" in most cases but not classified as such in BIR et al. Confusion might also be caused by the disunity of the terminology and classification, and by the ambiguity of definitions. Patient safety management of medical institutions in Korea uses the terms "near miss", "adverse event", and "sentinel event", which it classifies into eight levels according to the severity of risk to the patient. Therefore, the terminology and classification for radiotherapy risk management based on the patient safety management of medical institutions in Korea will help in improving the safety and quality of radiotherapy.

• 한국산업보건학회지
• /
• 제19권4호
• /
• pp.347-362
• /
• 2009

The United Nation agreed to adopt the Globally Harmonized System of Classification and Labelling of Chemicals (GHS) until 2008 to solve the significant differences enough to result in different labels or MSDS for the same chemical in different jurisdictions. Though the GHS is an ideal solution in the respect of pursuing only one format of a MSDS throughout the world, it may cause confusion at the beginning due to lack of information. So the Korean Ministry of Labor (MOL) revised the Industrial Safety and Health Act (ISHA) and related public notice on the classification & labelling of chemicals according to the GHS in 2006. The transition period for the implementation of the GHS for substances was set until Jun 30, 2010, and for mixtures until Jun 30, 2013. To promote the implementation of the GHS in Korea, we developed an application program for constructing MSDS database and a management program for providing MSDS contents on the web in accordance with the GHS. We analyzed the sixteen sections of MSDS by the GHS guideline, and the result showed the necessity to construct logically connected DB for chemical identifier, hazard classification, label, standard phrases and regulatory information. Each section of a MSDS was divided into sub-databases to update the database efficiently. According to Relational Database Management System (RDBMS), the sub-databases were automatically assembled and subsequently a full MSDS is produced. At present, MSDS database for 6,314 substances has been built and provided through internet as the MSDS Editing program. During the service period from January 1 to March 31, 13,666 users have searched MSDSs for 33,401 substances. During program review, some comments about the classification results and other MSDS element sources were reported but no technical bug reported. We expect that the MSDS DB management system in accordance with GHS will accelerate the implementation of the GHS in Korea.

• 해양환경안전학회:학술대회논문집
• /
• 해양환경안전학회 2017년도 추계학술발표회
• /
• pp.204-204
• /
• 2017

• 해양환경안전학회:학술대회논문집
• /
• 해양환경안전학회 2000년도 International Symposium:on the Maritime Management Systems for Safer and Cleaner Seas in the New Millennium
• /
• pp.102-160
• /
• 2000

• 한국산업보건학회지
• /
• 제23권3호
• /
• pp.287-298
• /
• 2013

Objectives: Workers who use chemicals are exposed to safety accidents and occupational diseases. Employers are required to provide workers with Material Safety Data Sheets (MSDSs) in order to prevent accidents and diseases related to chemicals. Thus, it is very important to offer reliable MSDSs. In this paper, we assessed the reliability of MSDSs for chemicals including formaldehyde. Methods: To evaluate MSDS reliability, we collected 14 MSDSs and bulk samples from the chemical industry. MSDS reliability was evaluated by the completeness of details. In order to evaluate the adequacy of the formaldehyde contents in a mixture, bulk samples were collected and analyzed by HPLC. The result of Globally Harmonized System (GHS) classification was confirmed by identifying physical chemical properties, toxicology information and ecological information. Results: The result of the evaluation of 14 MSDSs showed 76.29% average reliability on each item, especially 53.9% average appropriate rate on hazard risk classification. No chemicals failed to match between the content (%) in MSDSs and the result of analysis. Conclusions: To elevate MSDSs reliability, the certified education of MSDS drafters and reorganization of the MSDS circulation system is required.

• 한국안전학회지
• /
• 제32권5호
• /
• pp.88-95
• /
• 2017

As the safety fields are expanding to a variety of industrial fields, safety technology has been developed by convergence between industrial safety fields such as mechanics, ergonomics, electronics, chemistry, construction, and information science. As the technology convergence is facilitating recently advanced safety technology, it is important to explore the trends of safety technology for understanding which industrial technologies have been integrated thus far. For studying the trends of technology, the patent is considered one of the useful sources that has provided the ample information of new technology. The patent has been also used to identify the patterns of technology convergence through various quantitative methods. In this respect, this study aims to identify the convergence patterns and fields of safety technology using association rule mining(ARM)-based patent co-classification(co-class) analysis. The patent co-class data is especially useful for constructing convergence network between technological fields. Through linkages between technological fields, the core and hub classes of convergence network are explored to provide insight into the fields of safety technology. As the representative method for analyzing patent co-class network, the ARM is used to find the likelihood of co-occurrence of patent classes and the ARM network is presented to visualize the convergence network of safety technology. As a result, we find three major convergence fields of safety technology: working safety, medical safety, and vehicle safety.

• 한국산업보건학회지
• /
• 제24권3호
• /
• pp.345-352
• /
• 2014

Objectives: This study is aimed to describe the current situation about urinary biomarker N-methylformamide(NMF) for workers exposed to N,N-dimethylformamide(DMF) according to industrial classification. Materials: Special health examination records of the workers who had undergone urinary biological monitoring in 2013 were collected. The numbers and percentage of workers, whose urinary NMF values were above the limit of detection(LOD) and above the biological exposure index(BEI) were calculated. Health relatedness with DMF as judged by their doctors was also described. All description was classified according to the $9^{th}$ Korean Standard Industrial Classification(KSIC). Results: It appeared that most workers exposed to DMF belong to manufacturing section(80.7%). The geometric mean(GM) values of urinary NMF were 6.25 mg/L, 3.54, and 3.86 for the manufacturing section, professional, scientific and technical activities section, and for the construction section respectively. In detail, it seemed that division of textiles(except apparel) (GM 7.51 mg/L), division of leather, luggage and footwear(11.59 mg/L), and division of rubber and plastic products(6.89 mg/L) were highly exposed to DMF with a high percentage of workers with urinary NMF values above BEI. This was probably due to the effect of skin absorption that the division of leather, luggage and footwear showed the highest urine NMF GM. Conclusions: It seemed that workers in manufacture industries such as textile, leather, luggage, footwear, rubber and plastic products were highly exposed to DMF. So, efforts should be focused on those industries in order to effectively diminish worker's exposure. Further studies to compare DMF air-monitoring with bio-monitoring according to industrial classification should be considered.

• 한국안전학회지
• /
• 제32권5호
• /
• pp.179-185
• /
• 2017

Accident analysis is an essential process to make basic data for accident prevention. Most researches depend on survey data and accident statistics to analyze accidents, but these kinds of data are not sufficient for systematic and detailed analysis. We, in this paper, propose an accident classification model that extracts task type, original cause materials, accident type, and the number of deaths from accident reports. The classification model is a support vector machine (SVM) with word occurrence features, and these features are selected based on mutual information. Experiment shows that the proposed model can extract task type, original cause materials, accident type, and the number of deaths with almost 100% accuracy. We also develop an accident ontology to express the information extracted by the classification model. Finally, we illustrate how the proposed classification model and ontology effectively works for the accident analysis. The classification model and ontology are expected to effectively analyze various accidents.

• 대한예방한의학회지
• /
• 제19권2호
• /
• pp.123-133
• /
• 2015

The new formular for herbal medicine-safety classification in terms of evidence-based medicine was developed and applied to evaluate various herbal medicines in the previous study. This study is aimed to evaluate the frequently-used herbal medicines inducing toxic metabolites or reactive intermediates(RI), such as Ligusticum wallichii Franch, Angelica sinensis, Glycyrrhizae Radix, Rehmanniae Radix, based on 6 safety grades calculated from human equivalent dose(HED)-based MOS(margin of safety). HED-based MOS can be explained as the ratio of theoretical ALD(approximate lethal dose) of human as $LD_1$(lethal dose of 1%)/ clinical maximum dose as $ED_{99}$(Effective dose of 99%). The herbal medicine showing the ratio less than 1 belongs to Class 1, but the herbal medicine showing the ratio more than 500 belongs to Class 6 with the lowest toxicity. As a result, they were evaluated as class 2 for Angelica sinensis and Glycyrrhizae Radix, class 3 for Ligusticum wallichii Franch and Rehmanniae Radix. These resultant grades for 4 herbal medicines were lower than the grade expected under consideration that these herbal medicines are used very frequently in oriental clinics. These low grades would be due to their ingredients which is biotransformed to toxic metabolites.