• 한국정보통신학회:학술대회논문집
• /
• 한국정보통신학회 2021년도 추계학술대회
• /
• pp.329-331
• /
• 2021

최근 헬스케어 분야에서 딥러닝을 활용한 다양한 사례가 증가하면서 웨어러블 기기를 통한 심전도 검사, 체성분 분석 등의 기능을 제공하여 합리적인 의사 결정을 제공하여 개인에게 맞는 프로세스를 제공할 수 있다. 딥러닝을 활용하기 위해서는 정제된 데이터 확보가 무엇보다 중요하며 이러한 데이터는 사람의 개입이나 비지도학습 등을 통해 이뤄지고 있다. 본 논문에서는 측정하기 쉬운 가슴둘레, 허리둘레와 같은 치수 데이터를 이용해 성별과 나이에 따른 군집별 비지도학습을 진행하고 이를 CNN으로 분류하는 모델을 제안한다. 데이터는 국가기술표준원에서 제공하고 있는 제7차 인체치수데이터를 활용하였다. 이를 통해 개인 맞춤형 체형관리 서비스나 비만 분석 등 다양한 응용 사례에 적용할 수 있을 것으로 사료된다.

• 대한세포병리학회지
• /
• 제9권2호
• /
• pp.139-146
• /
• 1998

The AutoPap 300 QC System is an automated device for the analysis and classification of conventional cervical cytology slides for quality control purpose. These studies evaluated the sensitivity of the AutoPap 300 QC System, and estimated morphologic features other than epithelial abnormality to identify a high quality control(QC) score with the AutoPap 300 QC System. The sensitivity of the AutoPap 300 QC System at 10% review rate for 210 cases of cervicovaginal cytology with low grade squamous intraepithelial lesion(LSIL) and higher grade lesion was assessed, and compared with a 10% random rescreening. The morphologic features, such as presence of endocervical component, dirty background, atrophy, abnormal ceil size, and celluiarity of single atypical cells were estimated in 45 cases of no review and 30 cases of QC review cases. The AutoPap 300 QC System identified 119(56.7%) out of 210 cases with LSIL and higher grade lesion at 10% review rate. It was more sensitive to squamous cell lesions$(50{\sim}62%)$ than to glandular lesions(10%). The dirty background and the scanty cellularity of single atypical cells were significantly related to low QC score. Conclusively, AutoPap 300 QC System is superior to human random rescreen for the identification of false negative smears. The upgrading of this device is required to enhance the defection of glandular lesion and certain Inadequate conditions of the slides.

• Safety and Health at Work
• /
• 제10권1호
• /
• pp.122-124
• /
• 2019

Simian malaria is a zoonotic disease caused by Plasmodium knowlesi infection. The common natural reservoir of the parasite is the macaque monkey and the vector is the Anopheles mosquito. Human cases of P. knowlesi infection has been reported in all South East Asian countries in the last decade, and it is currently the most common type of malaria seen in Malaysia and Brunei. Between 2007-2017, 73 cases of P. knowlesi infection were notified and confirmed to the Ministry of Health in Brunei. Of these, 15 cases (21%) were documented as work-related, and 28 other cases (38%) were classified as probably related to work (due to incomplete history). The occupations of those with probable and confirmed work related infections were border patrol officers, Armed Forces and security personnel, Department of Forestry officers, boatmen and researchers. The remaining cases classified as most likely not related to work were possibly acquired via peri-domestic transmission. The risk of this zoonotic infection extends to tourists and overseas visitors who have to travel to the jungle in the course of their work. It can be minimised with the recommended use of prophylaxis for those going on duty into the jungles, application of mosquito/insect repellants, and use of repellant impregnated uniforms and bed nets in jungle camp sites.

• 한국안전학회지
• /
• 제27권4호
• /
• pp.90-95
• /
• 2012

To prevent similar accidents with the basis of industrial accidents already occurred in industrial plants, it would be possible only after true causes are grasped. Unfortunately, however, most accident investigation carried out with the basis of legal regulation failed to grasp them so that similar accidents have been repeated without cease. This research aimed to find out differences between results from conventional accident investigation and those from human error analysis, and to draw out effective and practical counter-plans against industrial accidents occurred repeatedly in an autoglass manufacturing company. As for analysis, about 110 accident cases that occurred for last 7 years were collected, and by adopting the Comprehensive Human Error Analysis Technique developed by the previous researchers, not direct causes but basic fundamental causes that might induce workers to human errors were sought. In consequence, the result showed that facility factors or environmental factors such as improper layout, mistakes in engineering design, and malfunction of interlock system were authentic major accident causes as opposed to managerial factors such as personal carelessness or failure to wearing personal protective equipments, and/or improper work methods.

• 대한인간공학회지
• /
• 제34권2호
• /
• pp.103-113
• /
• 2015

Objective: This study proposes a systematic process to present the analysis methods and solutions of organizational root causes to human errors on the railroad. Background: In fact, organizational root cause such as organizational culture is an important factor in the safety concerns on human errors in the nuclear power plant, railroad and aircraft. Method: The proposed process is as follows: 1) define analysis boundary 2) select human error taxonomy 3) perform accident analysis 4) draw root causes with FGI 5) review root causes analysis with survey 6) chart analysis of root causes, and 7) propose alternatives and solutions. Results: As a result, root causes of the organizations like railroad and nuclear power plant came from the educational problems, violations, payoff system, safety culture and so forth. Conclusion: The proposed process does predict potential railroad accident through retrospect error analysis by building new human error taxonomies and problem solution. Application: This study would contribute to examination of the relationship between human error-based accidents and organizational root causes.

• 대한인간공학회지
• /
• 제29권2호
• /
• pp.241-248
• /
• 2010

In accident analysis, it is essential to understand the causal pathways of the accident. Although numerous accident models have been developed to help analysts understand how and why an accident occurs, most of them do not include all elements related to the accident in various fields. Thus analysis of human error accidents in railway operations using these existing models may be possible, but inevitably incomplete. For a more thorough analysis of the accidents in railway operations, a more exhaustive model of accident causation is needed. This paper briefly reviews four recent accident causation models, and proposes a new model that overcomes the limitations of the existing models for the analysis of human error accidents in railway operations. In addition, the usefulness and comprehensiveness of the proposed model is briefly tested by explaining 12 railway accident cases with the model. The proposed accident causation model is expected to improve understanding of how and why an accident/incident occurs, and help prevent analysts from missing any important aspect of human error accidents in railway operations

• 한국가금학회지
• /
• 제31권2호
• /
• pp.109-118
• /
• 2004

Avian influenza(AI) is an epizootic disease of variable severity caused by type A influenza viruses of the orthomyxovirus group. Chickens were the most frequently affected avian species with AI viruses. There were many outbreaks of fowl plague, now known as highly pathogenic AI(HP AI), throughout the world since Perroncito described the fowl plague in 1978 in Italy. In recent years HPAI viruses of different serotypes such as H5, H7 and H9 has been isolated from humans on several occasions either related with outbreak of HPAI in birds or not. In 1997, one of the most noteworthy events in AI history was the human mortality with H5N1 HPAI virus infection in Hong Kong. Six persons of total 18 persons with clinical signs of influenza were died. Recently the human cases with mortality related with HP AI outbreaks in poultry industry has been increased such as outbreaks of HP AI throughout Asia countries including Korea, Japan, China, Vietnam, Thailand and others in 2003. Although these outbreaks revealed the capable of spreading from birds to human, the capability for transmission between people was not clear. Therefore, this report will review the possibility of HP AI infection in human associated with HPAI outbreak in poultry industry.

• Nuclear Engineering and Technology
• /
• 제51권6호
• /
• pp.1561-1574
• /
• 2019

A standard form of six stylized human intrusion scenarios for a near-surface disposal facility (e.g. the planned Korean repository, Gyeongju Phase II) is proposed through re-categorization of totally thirty-one past cases reported in public literature. A reference assessment framework for inadvertent human intrusion is newly developed using GENII Version 2 conforming to the ICRP Publication 60 and thereafter. Calculated dose from the assessment framework is verified by comparing with hand calculation results for simplified model equations independently derived. Results from GENII Version 2 and 1.485 show inevitable differences, which is mainly attributed to the difference in the external dose assessment model. If intake dose coefficients in GENII Version 1.485 are modified, the difference can be reduced but still exist to an extent. Through deterministic and probabilistic sensitivity analysis, most affecting four parameters are derived and uncertainties of the parameters are quantified. It is expected that the reference assessment framework together with representative stylized scenarios can be used to do a human intrusion impact assessment for a specific repository using site-specific information. Especially, the past practice of human intrusion impact assessment using GENII Version 1.485 with or without modification may be replaced with the new assessment framework developed in this study.

• 대한세포병리학회지
• /
• 제9권2호
• /
• pp.129-137
• /
• 1998

Although the success of the Papanicolaou test as a screening tool of cervical cancer is evident, there still exists $2{\sim}5%$ of discrepancy rate by both human and machine. To improve the qualilty of cervico-vaginal cytology, the authors compared cervicovaginal smear with cervical biopsy diagnoses, and analysed the causes of discrepancies. Among 30,922 cervicovaginal smears from June 1996 to April 1997 at our hospital, there were 271 cases of cervicovaginal smear with subsequent cervical punch or LEEP cone biopsies within several months. The biopsies and smears from a total of 98 discordant cases were reviewed. The discrepancy was attributed to sampling errors in 43 cases(43.9%), and to cytologic diagnosis in 49 cases(50.0%). Among these, 43 cases were interpretative errors(categories A;19, B;16 and C;8) whereas six cases were screening errors(categories B:2 and C:4). Among cervical biopsy cases, errors were present in four. As for 10% random rescreening, cytotechnologists reviewed 3,196 of 30,922 smears during the same period, There were 43 cases of screening error(categories A;27, B;16). Cytologic/histologic correlation was superior to 10% random rescreening of negative cases. The most effective method for quality improvement in cervicovaginal cytology was to implement both quality control(rescreening) and qualify assurance(cytologic/histologic correlation) programs.

• 대한병리학회지
• /
• 제52권6호
• /
• pp.404-410
• /
• 2018

Background: Fine-needle aspiration cytology serves as a safe, economical tool in evaluating thyroid nodules. However, about 30% of the samples are categorized as indeterminate. Hence, many immunocytochemistry markers have been studied, but there has not been a single outstanding marker. We studied the efficacy of CD56 with human bone marrow endothelial cell marker-1 (HBME-1) in diagnosis in the Bethesda System for Reporting Thyroid Cytopathology (TBSRTC) category III. Methods: We reviewed ThinPrep liquid-based cytology (LBC) samples with Papanicolaou stain from July 1 to December 31, 2016 (2,195 cases) and selected TBSRTC category III cases (n=363). Twenty-six cases were histologically confirmed as benign (six cases, 23%) or malignant (20 cases, 77%); we stained 26 LBC slides with HBME-1 and CD56 through the cell transfer method. For evaluation of reactivity of immunocytochemistry, we chose atypical follicular cell clusters. Results: CD56 was not reactive in 18 of 20 cases (90%) of malignant nodules and showed cytoplasmic positivity in five of six cases (83%) of benign nodules. CD56 showed high sensitivity (90.0%) and relatively low specificity (83.3%) in detecting malignancy (p=.004). HBME-1 was reactive in 17 of 20 cases (85%) of malignant nodules and was not reactive in five of six cases (83%) of benign nodules. HBME-1 showed slightly lower sensitivity (85.0%) than CD56. The specificity in detecting malignancy by HBME-1 was similar to that of CD56 (83.3%, p=.008). CD56 and HBME-1 tests combined showed lower sensitivity (75.0% vs 90%) and higher specificity (93.8% vs 83.3%) in detecting malignancy compared to using CD56 alone. Conclusions: Using CD56 alone showed relatively low specificity despite high sensitivity for detecting malignancy. Combining CD56 with HBME-1 could increase the specificity. Thus, we suggest that CD56 could be a useful preoperative marker for differential diagnosis of TBSRTC category III samples.