• Annual Conference of KIPS
• /
• 2023.11a
• /
• pp.709-711
• /
• 2023

안전관리를 위한 인공지능 기술은 꾸준히 연구되고 있는 분야다. 특히, 컴퓨터 비전 기술을 활용한 CCTV 영상 분석은 군중의 동선과 밀도를 파악하는데 유용하며, 대규모 실내 공간에서 체계적인 안전관리를 가능하게 한다. 그러나 기존의 CCTV 카메라를 사용한 군중 수 추정은 가려짐(occlusion)과 같은 한계가 있다. 본 논문은 무선 랜 신호 데이터 분석 기법을 활용하여 수집한 데이터를 활용하여 실내 환경에서 군중 수를 추정하고자 한다. 본 논문에서는 인원 수 분류 예측을 위해 셰이플릿 확장 변환(Random Dilated Shapelet Transform) 기법을 제안한다. 단일 데이터 세트 내 분류 결과와, TX, RX 배치 방식에 따른 분류 성능의 차이는 모델의 성능 부족보다 데이터의 특성을 고려한 새로운 접근 방법의 필요성을 알려준다.

• Annual Conference of KIPS
• /
• 2024.05a
• /
• pp.371-373
• /
• 2024

디지털 헬스케어 기술이 고도화되면서 디지털 치료제와 원격 의료 서비스가 의료 산업과 일상생활에 널리 활용되고 있다. 그러나 빅데이터 기반의 AI 서비스가 보편화될 수 있도록 데이터 수집, 가공, 활용 과정에서 개인정보가 남용되거나 유출되는 보안 위협도 증가하고 있다. 본 논문에서는 AI 챗봇을 활용한 정신건강 서비스를 위한 보안 위협 대응책을 마련하고 개인정보보호 가이드라인을 수립하여 사용자들에게 안전한 서비스를 제공하고 개인정보보호를 강화하는 AI 챗봇 서비스를 위한 데이터 보안 가이드라인을 제안한다.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2013.05a
• /
• pp.538-539
• /
• 2013

수평 자세제어에 관한 연구는 플랜트 외부에서 발생하는 미지의 진동이나 불특정 외란이 인가되었을 때 이러한 외란을 적절히 제거하여 플랜트의 안전성을 확보할 수 있는 중요한 기술이다. 특히 수평 자세제어에 대한 문제는 선박이나 항공기 등 진동이나 미지의 외란이 발생하는 비선형시스템에 대하여 플랜트의 안전성을 확보하기 위하여 다양한 제어 알고리즘을 적용하여 진동 및 외란을 제거하고 있다. 본 논문에서 활용하고자하는 수평 자세제어용 액추에이터는 전자기적 에너지를 직선운동을 하는 기계적 운동 에너지로 변환하는 장치로서 산업현장에서 많이 활용하고 있는 액추에이터이다. 이러한 리니어 액추에이터(linear actuator) 3개로 구성된 3축을 활용하여 리니어 액추에이터 상부에 놓여진 플랜트의 수평을 제어하고자 한다. 또한 플랜트의 수평 상태를 계측하기 위한 센서로는 플랜트에 인가되는 외란을 계측하기 위한 가속도 센서 및 정확한 플랜트의 자세를 계측하기 위한 자이로 센서를 활용하여 플랜트의 수평 상태를 계측하도록 하며, 3개의 리니어 액추에이터를 제어하기 위한 마이크로프로세서를 기반으로 PID 제어기를 설계하여 리니어 액추에이터를 활용한 수평제어 성능을 제시하고 한다.

• Proceedings of the Korea Water Resources Association Conference
• /
• 2018.05a
• /
• pp.238-238
• /
• 2018

2011년 동일본 대지진으로 발생된 지진해일로 인해 막대한 경제적 손실과 인명피해가 발생하였고, 2차적 사회적 피해가 지속되고 있다. 또한 국내에서도 최근 경주와 포항지역에서 지진이 발생하여 피해가 발생함에 따라 재난의 불확실성에 대한 대비의 중요성이 강조되고 있고, 과거 안전하다고 했던 재난에 대한 위험성에 대해 국민들의 관심이 증대되었다. 피해사례가 2차례 있는 지진해일의 경우도 동일본 대지진 이후로 전 세계적으로 해일에 대한 위험성이 재평가되고 있다. 지진해일은 해저에서 발생하는 지진에 의한 것으로 발생지점 및 강도 등을 예측하기가 쉽지 않으므로, 지진발생에 대한 가상 시나리오를 이용한 연구가 진행되고 있다. 가상 시나리오를 활용하여 현재까지 많은 침수예상도가 제작되었으나, 다양한 시나리오 대해서 검토되지 않았다. 따라서 본 연구에서는 과학적 보간법을 이용하여 수치모형을 수행하지 않고 기수행된 연구 DB를 활용하여 지진해일 피해를 예측하는 기술을 개발하였다. 연구 DB는 국립재난안전연구원에서 수행된 지진해일 자료를 활용하였고, 전국단위를 기반으로 지진규모 7.0~9.0 내에 지진해일을 유발하는 지진에 대해 지진해일의 피해를 예측할 수 있는 기술을 개발하였다. 기술을 검증하기 위해 5개의 진원지에 대하여 과거 발생 지진규모부터 극한의 지진규모를 가정한 수치모의 결과와 본 연구의 결과를 비교하였다. 본 연구는 격자 1km인 광역모형의 모의결과를 활용하였으므로 실제로 해안지역의 침수양상의 정확도가 높지 않지만 향후 고정밀 공간해상도에 대하여 모의를 수행한다면 지진해일로 발생하는 범람 및 침수를 보다 정밀하게 예측할 수 있을 것이라 기대된다.

• Journal of the Korean Society of Marine Environment & Safety
• /
• v.26 no.7
• /
• pp.798-809
• /
• 2020

Evidence-based policymaking and assessments for scientific administration have increased the importance of statistics (data) utilization. Statistics can explain specific phenomena by providing numerical values and are a public resource for national decision making. Due to these inherent attributes, statistics are utilized as baseline and base data for government policy determinations and the analysis of various phenomena. However, compared to the importance, the role of statistics is limited, and statistics are often used as simple abstracts, produced mainly for suppliers, not for consumers' perspectives to create value. This study explores the statistical data and other attributes that can be utilized for policies or research to address the problems mentioned above. The baseline statistical data used in this study is from the Maritime Distress Accident Statistical Yearbook published by the South Korean Coast Guard, and other additional attributes are from text analyses of vessel casualty situation reports from the South Korean Maritime Police. Collecting 56 attributes drawn from the text analysis and executing an EDA resulted in 88 attribute unions: 18 attribute unions had a satisfactory significance probability (p-value < .05) and a strong correlation coefficient above 0.7, and 70 attribute unions had a middle correlation. (over 0.4 and under 0.7). Additionally, to utilize the extra attributes discovered from the EDA politically, a keyword analysis for each detailed strategy of the disaster Preparation basic plan was executed, the utilization availability of the attributes was obtained using a matching process of keywords, and the EDA deducted attributes were examined.

• Korean Journal of Remote Sensing
• /
• v.38 no.6_3
• /
• pp.1749-1760
• /
• 2022

In modern society, human and social damages caused by natural disasters and frequent disaster accidents have been increased year by year. Prompt access to dangerous disaster sites that are inaccessible or inaccessible using state-of-the-art Earth observation equipment such as satellites, drones, and survey robots, and timely collection and analysis of meaningful disaster information. It can play an important role in protecting people's property and life throughout the entire disaster management cycle, such as responding to disaster sites and establishing mid-to long-term recovery plans. This special issue introduces the National Disaster Management Research Institute (NDMI)'s disaster management technology that utilizes various Earth observation platforms, such as mobile survey vehicles equipped with close-range disaster site survey sensors, drones, and survey robots, as well as satellite technology, which is a tool of remote earth observation. Major research achievements include detection of damage from water disasters using Google Earth Engine, mid- and long-term time series observation, detection of reservoir water bodies using Sentinel-1 Synthetic Aperture Radar (SAR) images and artificial intelligence, analysis of resident movement patterns in case of forest fire disasters, and data analysis of disaster safety research. Efficient integrated management and utilization plan research results are summarized. In addition, research results on scientific investigation activities on the causes of disasters using drones and survey robots during the investigation of inaccessible and dangerous disaster sites were described.

• Journal of Digital Convergence
• /
• v.11 no.12
• /
• pp.467-477
• /
• 2013

The cloud computing has propagated rapidly and thus there is growing interest on the introduction of cloud services in the public institution. Accordingly, domestic public institution are adoption of cloud computing impose and devise a plan. In addition, more specifically, is building a cloud computing system in the public institution. However, solutions to various security threats(e.g., availability invasion of storage, access by unauthorized attacker, data downloaded from uncertain identifier, decrease the reliability of cloud data centers and so on) is required. For the introduction and revitalize of cloud services in the public institution. Therefore, in this paper, we propose a public key based secure data management scheme for the cloud data centers in public institution. Thus, the use of cloud computing in the public institutions, the only authorized users have access to the data center. And setting for importance and level of difficulty of public data management enables by systematic, secure, and efficient. Thus, cloud services for public institution to improve the overall security and convenience.

• Journal of the Korea Institute of Building Construction
• /
• v.20 no.1
• /
• pp.73-81
• /
• 2020

The main purpose of the study is to reduce the accident death rate in the construction industry. To achieve this goal, the safety planning tasks were analyzed and assessed in terms of the importance and preventive effects of the tasks. Through the extensive literature reviews, the safety planning tasks were identified and reviewed by safety managers. based on the safety planning tasks developed in the previous stage, a survey was conducted in order to receive responses by experts with knowledge on the effects and importance of preventive measures for safety. Then, the Importance Performance Analysis(IPA) method was employed to identify the safety manager's tasks that have an effect on performance indicators. Advice and guidance on making the employment rules, etc. (#18) and details about participation and consultation at the Occupational Safety and Health Committee (#16) were found to require revision and improvement of details and guidelines. The effective safety tasks identified are expected to have a critical role in reducing the accident death rate in the construction industry.

• 한국정보교육학회:학술대회논문집
• /
• 2021.08a
• /
• pp.303-308
• /
• 2021

In this study, we intended to present a class design plan that combines safety education and software education, which are very important in the school field, but are considered necessary for change. In order to realize safety education centered on indirect experience, the 12th class plan was devised as a "Smart Safety Commuter Road Production Project" using a physical computing tool called Bitbrick. Based on the 12th city's class plan, qualitative research was conducted with interviews with a total of five teachers, showing both the effectiveness and problems of applying them to the class. The effectiveness is that unlike conventional delivery-type safety education, indirect experience-oriented safety education centered on real-life situations is possible, and it can be expected that procedural thinking skills can be developed along with stimulating interest. However, the problem has been shown that the process of implementing the direct situation can be challenging and that even activities can be more efficient than group activities.

• KSCE Journal of Civil and Environmental Engineering Research
• /
• v.26 no.3D
• /
• pp.511-517
• /
• 2006

In this paper, we studied the techniques to analyze the flying safety area focused on the air base rules for military that has been the criteria of the altitude restrictions around the airfield for both civilian and military purposes in Korea. We wanted to present the effective method to analyze the restricted area and to help solving problems that could result recently from the altitude restrictions around the airfield at the beginning of the development projects. To do this we proposed the methods to effectively generate the model of the flying safety area in accordance with the air base rules using 3D GIS techniques and to automatically identify the obstructions caused by the natural and man-made features in those areas. To apply the proposed methods actually to the airfield chosen for the study area, we presented the approaches to generate geospatial informations based on the commercial digital maps and satellite imagery and by generating the flying safety area model, identifying the obstructions, and visualizing the integrated model for the flying safety area analysis we showed the practical usability of the proposed techniques.