• Proceedings of the Safety Management and Science Conference
• /
• 1999.11a
• /
• pp.9-21
• /
• 1999

안전공학이 추구하는 사회적인 목표는 산업에 종사하는 사람들의 생명과 건강을 지키고, 재해에 의한 생산설비나 원자재, 제품의 손실을 막는 것이다. 광범위한 산업안전 연구 중에서 재해 통계 분석에 관한 연구는 다양한 종류의 재해에 관한 기초적 정보를 제공함으로서, 이에 따른 문제점의 파악이나 안전대책의 설정 등 안전관리에 있어서 의사결정이나 연구 방향을 결정하는 중요한 역할을 하고 있다. 현재 사업장 등에서 안전관리를 실시하는데, 안전수준의 평가로서 세계적으로 널리 이용되고 있는 계산식은 단위시간당의 재해발생 건수로 나타내어지는 도수율, 또는 근로자 1천만명당 재해발생 인원수를 나타내는 연 천인율이 등이 있다. 영국 A.H,A Wynn등이 광산재해의 예로 실시한 시간의 재해발생율의 차이를 재해발생 간격의 분포에 사용하여 검증했었다. 이것을 기반으로 재해발생 간격을 추정하고 검증함으로 재해발생 확률을 도출하여 안전관리의 새로운 척도를 제시하고자 한다. 이미 일본에서 많은 연구가 이루어져 왔으며, 이를 기초로 노동재해 발생수를 통한 통상의 검증법과 축차검증법의 이용으로 재해의 성향을 분석하여 그 결과를 재해의 예측에 이용함으로 재해예방을 실현하고자 한다. 그래서, 실제 국내에 정유공장의 데이터를 이용하여, 이 분포 알고리즘을 검증하는데 본 논문의 목적이 있다.

• Journal of Korean Society of Transportation
• /
• v.28 no.6
• /
• pp.85-97
• /
• 2010

The present study aims at estimating the model of bus bunching duration along with its influential determinants in an attempt to understand the status of bus bunching being created by buses from various routes converging into one bus stop. To do so, the duration analysis, a well-known survival analysis, was adopted in order to capture the distribution of duration time as for 8 base lines, accordingly developing the model best fit for weibull distribution. Key attention to draw out the duration time model for bus bunching phenomena was laid, by analyzing 18 impact factors, on such criterion variables as number of berth, number of bus line in each berth and maximum capacity of on-and-off passengers in each line. Comparison in two typical types of bus lane was made between bus-only center lane(Dobong Mia-ro) and normal street-side lane(Tongil Euiju-ro). In this regard, the study, based on the model as above, suggested appropriate alternatives to improve the bus operation by effectively controlling bus bunching.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.14 no.9
• /
• pp.4572-4579
• /
• 2013

South Korea people and government pour growing interest on emergency evacuation shelters due to recent threatening of North Korea provocation. However, survey says the border area suffers lack of 278 shelters compared to population, needless to say the lack of class-2 shelter in case of provocation. Firstly, this study visualized the evacuation buffer area and summarized acceptable population for all class (1~4) shelters in Cheoan neighbor(dong). Specifically, for the class-2 shelter coverage in old downtown neighbor (Sungjung-dong, Jungang-dong, Munsung-dong), this study calculated evacuation excluded population and deficient shelter area through GIS buffer analysis. As a result, the old downtown needs $25,546m^2$ shelter area more that can accommodate 56%(30,657man) of the population.

• The Journal of the Korea Contents Association
• /
• v.17 no.6
• /
• pp.643-649
• /
• 2017

This research is to compare factors which influence to mobilize police force necessary for crowd gathering occasions, and the purpose of this research is to prepare scientific basis for mobilization of police force by understanding order of priority of obstructive factors to mobilize police force for progressing safe crowd gathering occasions. Crowd gathering occasion has a characteristic that minor cause can lead to huge damage because many people concentrically gather at a specific place. In order to control these risks, it is necessary to analyze criteria on order of priority which can arouse risk to mobilize police force. In this research, I classified the factors influencing safety of crowd gathering occasion as internal risk factor, external risk factor and traffic safety threatening and set up the level of private security manpower and participants mobilized to crowd gathering occasion as independent variable and set up mobilized police force from 2013 to 2014 as dependent variable and analyzed it hierarchical analysis. From the result of analysis, the biggest influence to mobilization of police force for crown gathering occasion was the number of participants, and next self order-keeping agents and reason of mobilizing police force. Based on the result of analysis that the biggest factor to mobilize police force to crowd gathering occasion is the number of participants, it can be resulted that the number of participants influence to the risk of crowd gathering occasion.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.11 no.2
• /
• pp.709-719
• /
• 2010

As the world has had a high recognition of security since 9/11 attacks in 2001, many countries and international organizations around the world are making strenuous efforts in establishing stronger security, centering on areas with high possibility of terrorist attacks. In particular, harbor facilities where a great deal of trade take place between countries, have high possibilities of becoming the objects of terrorist attacks and also of becoming places of trading objects and illegal items which might be leveraged for terror attacks. In this study, I have explained the current status of the harbor entrance system through existing documents, interviews and field trips to harbors and have also introduced improvement measures using RFID technology from the viewpoint of BP(Business Process). I expect that this study will be used as basic materials because I have studied the number of people entering harbors and working procedures for vehicle entrance, which have not been studied so far and also laid out various factors to be considered to introduce RFID technology.

• Proceedings of the Korea Institute of Fire Science and Engineering Conference
• /
• 2013.04a
• /
• pp.71-72
• /
• 2013

이 연구는 하트세이버를 배지를 수여 받은 구급대원과 심정지 환자 중 심폐소생술로 자발순환이 회복된 후 환자를 대상으로 심정지 생존의 요인을 파악하고 분석한 결과 심정지에서 소생한 환자의 75%가 가정에서 발생되었으며, 출동에서 현장까지 도착 소요시간이 6.1분, 현장심폐소생술 소요시간 6.2분, 출동에서 병원 응급실 도착까지 소요시간 23.0분이 소요되었다. 또한 목격자에 의해 시행된 심폐소생술은 50.0%, 발견 당시 심장리듬은 심실세동이 87.5%, 무수축 12.5%였고, 심폐소생술과 동시에 자동제세동기를 사용한 환자는 87.5%, 심폐소생술만 시행한 환자 12.5%, 기관내삽관 시행이 12.5%였다. 자발순환이 회복된 환자에게 시행된 심폐소생술 소요시간은 10.9분 이었으며, 책임구급대원은 1급응급구조사가 75.0%, 출동 구급인원은 3명 출동이 87.5%였다.

• Proceedings of the Korean Society of Computer Information Conference
• /
• 2023.07a
• /
• pp.335-338
• /
• 2023

국방 무기체계의 운용유지를 위해서는 숙련자에 의한 신뢰성있는 정비 지원이 필요하다. 특히, 고도의 기술력을 바탕으로 연구/제작된 해군 무기체계를 유지하기 위해서는 이와같은 정비 지원이 무엇보다 중요하다. 해군에서는 효과적인 정비지원을 위해 수개의 정비지원부대를 조직하여 운용하고 있다. 원활한 정비지원부대의 운용을 위해 다년간 기술력을 축적한 정비인원의 중도 이탈을 예방하는 것이 요구되므로, 본 논문에서는 머신러닝을 적용하여 해군 정비지원부대의 퇴직자 예측 모델을 제안하였다. 정비인력의 만족도와 관계가 있을 것으로 예상되는 봉급, 특근율 등을 변수로 사용하였고, F1 Score를 통해 모델의 성능을 평가한 결과 0.7이상의 높은 성능을 보였다. 이 모델을 통해 조기 퇴직이 예상되는 그룹의 공통 개선소요를 파악하여 사전 조치가 가능할 것으로 판단하였다.

• Journal of the Korean Institute of Landscape Architecture
• /
• v.50 no.5
• /
• pp.90-102
• /
• 2022

In recent years, as interest in healing increases, outdoor spaces with the concept of healing have been created. For more professional and in-depth planning and design, the perception and characteristics of outdoor healing places through social media posts were analyzed using NER. Text mining was conducted using 88,155 blog posts, and frequency analysis and clique cohesion analysis were conducted. Six elements were derived through a literature review, and two elements were added to analyze the perception and the characteristics of healing places. As a result, visitors considered place elements, date and time, social elements, and activity elements more important than personnel, psychological elements, plants and color, and form and shape when visiting healing places. The analysis allowed the derivation of perceptions and characteristics of healing places through keywords. From the results of the Clique, keywords, such as places, date and time, and relationship, were clustered, so it was possible to know where, when, what time, and with whom people were visiting places for healing. Through the study, the perception and characteristics of healing places were derived by analyzing large-scale data written by visitors. It was confirmed that specific elements could be used in planning and marketing.

• Journal of the Society of Disaster Information
• /
• v.20 no.1
• /
• pp.199-205
• /
• 2024

Purpose: This study aims to improve the recognition rate of Auto People Counting (APC) in accurately identifying and providing information on remaining evacuees in disaster-vulnerable facilities such as nursing homes to firefighting and other response agencies in the event of a disaster. Methods: In this study, a baseline model was established using CNN (Convolutional Neural Network) models to improve the algorithm for recognizing images of incoming and outgoing individuals through cameras installed in actual disaster-vulnerable facilities operating APC systems. Various algorithms were analyzed, and the top seven candidates were selected. The research was conducted by utilizing transfer learning models to select the optimal algorithm with the best performance. Results: Experiment results confirmed the precision and recall of Densenet201 and Resnet152v2 models, which exhibited the best performance in terms of time and accuracy. It was observed that both models demonstrated 100% accuracy for all labels, with Densenet201 model showing superior performance. Conclusion: The optimal algorithm applicable to APC among various artificial intelligence algorithms was selected. Further research on algorithm analysis and learning is required to accurately identify the incoming and outgoing individuals in disaster-vulnerable facilities in various disaster situations such as emergencies in the future.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.17 no.6
• /
• pp.33-38
• /
• 2016

Understanding of current features of collapsed buildings, terrain, and other infrastructures is a critical issue for disaster site managers. On the other hand, a comprehensive site investigation of current location of survivors buried under the remains of a building is a difficult task for disaster managers due to the difficulties in acquiring the various information on the disaster sites. To overcome these circumstances, such as large disaster sites and limited capability of rescue workers, this study makes use of a drone (unmanned aerial vehicle) to effectively obtain current image data from large disaster areas. The framework of 3D model reconstruction of disaster sites using aerial imagery acquired by drones was also presented. The proposed methodology is expected to assist fire fighters and workers on disaster sites in making a rapid and accurate identification of the survivors under collapsed buildings.