• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.24 no.12
• /
• pp.1612-1617
• /
• 2020

Recently, research to reduce the accident rate by actively adopting artificial intelligence technology in the field of disaster safety technology is spreading. In particular, it is important to quickly search the Rescue Requester in order to effectively perform rescue activities at the disaster site. However, it is difficult to search for Rescue Requester due to the nature of the disaster environment. In this paper, We intend to develop an artificial intelligence system that can be operated in a smart helmet for firefighters to search for a rescue requester. To this end, the optimal SoC was selected and developed as an embedded system, and by testing a general-purpose artificial intelligence S/W, the embedded system for future smart helmet research was verified to be suitable as an artificial intelligence S/W operating platform.

• Proceedings of the Korean Society of Disaster Information Conference
• /
• 2023.11a
• /
• pp.278-281
• /
• 2023

연구목적: 본 연구는 요양병원 등 재난취약시설에 재난이 발생할 경우 잔류한 요구조자를 정확하게 파악하여 소방 등 대응기관에 제공하는 APC(Auto People Counting)의 인식률 개선에 목적이 있다. 현재 재난 발생 시 건물 내 요구조자의 현황 파악을 위해 대응기관이 재난 현장에 도착하여 건물관계자에게 직접 물어보고 있다. 이는 요구조자에 대한 부정확한 정보일 가능성이 있어 대응기관의 업무범위가 확대되고 이로인해 구조자의 안전에도 위험이 될 수 있다. APC는 건물내 출입하는 인원을 자동으로 집계하여 실시간 잔류인원 정보를 제공함으로써 재난 시 요구조자 현황을 정확히 파악할 수 있다. 본 연구에서는 APC가 보다 정확하게 출입 인원을 집계할 수 있도록 최적의 인공지능 알고리즘을 선정하는데 목적이 있다. 연구방법: 본 연구에서는 실제 재난취약시설에 설치되어 운영 중인 APC를 대상으로 카메라를 통해 출입 인원의 이미지를 인식하는 알고리즘을 개선하기 위해 CNN모델을 활용하여 베이스라인 모델링을 하였다. 다양한 알고리즘의 성능을 분석하여 상위 7개의 후보군을 선정하고 전이학습 모델을 활용하여 성능이 가장 우수한 최적의 알고리즘을 선정하는 방법으로 연구를 수행하였다. 연구결과: 실험결과 시간과 성능이 가장 좋은 Densenet201, Resnet152v2 모델의 정밀도와 재현율을 확인한 결과 모든 라벨에 대해서 정확도 100%를 나타내는 것을 확인할 수 있었다. 이 중 Densenet201 모델이 더 높은 성능을 보여주었다. 결론: 다양한 인공지능 알고리즘 중 APC에 적용할 수 있는 최적의 알고리즘을 선정하였고 이는 APC의 인식률을 개선하여 재난시 요구조자의 정보를 정확하게 파악하여 신속하고 안전한 구조작업이 가능할 것이다. 이는 요구조자의 안전한 구조뿐만 아니라 구조작업을 수행하는 구조자의 안전을 확보하는 데 기여할 것으로 기대된다. 향후 연무 등 다양한 재난상황에서 재난취약시설 내 출입인원을 정확하게 파악할 수 있도록 알고리즘 분석 및 학습에 대한 추가 연구가 요구된다.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2021.10a
• /
• pp.275-276
• /
• 2021

In the event of a fire in a complex, the identification of isolated people's location information is delayed, resulting in many casualties. In order to prevent such an accident, research on estimating the location of the requesters by detecting the wireless signal of the mobile phone at fire sites is in progress. The main concept is to use a wireless signal scanner to detect the wireless signal of a mobile phones at fire sites, and then position the mobile phone based on this. However, it is difficult to secure visibility at the fire site due to the smoke, and there is a difficulty in rescuing requesters in need compared with general disaster sites. Therefore, it will be one of the important issues to be solved to determine the minimum number of rescuers to be deployed according to the number and condition of the requesters. In this study, we propose a method to calculate the number of rescuers put to fire sites by using the radio signal generated from mobile phones and the information generated from the inertial sensor of the mobile phones.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2022.05a
• /
• pp.688-689
• /
• 2022

This paper proposes the development of an AI drone equipped with motion detection and thermal imaging camera to quickly rescue people from drowning accidents. Currently, when a drowning accident occurs, a large number of manpower must be put in to find the person who needs it, such as conducting a search operation. The time required for this process is too long, and especially the night search is more difficult for a person to do directly. To solve this situation, we are going to use AI drones.

• Journal of Internet Computing and Services
• /
• v.23 no.4
• /
• pp.57-64
• /
• 2022

If the inside of a building collapses due to a disaster such as fire, collapse, or natural disaster, the physical security inside the building is likely to become ineffective. Here, physical security is needed to minimize the human casualties and physical damages in the collapsed building. Therefore, this paper proposes an algorithm to minimize the damage in a disaster situation by fusing existing research that detects obstacles and collapsed areas in the building and a deep learning-based object detection algorithm that minimizes human casualties. The existing research uses a single camera to determine whether the corridor environment in which the robot is currently located has collapsed and detects obstacles that interfere with the search and rescue operation. Here, objects inside the collapsed building have irregular shapes due to the debris or collapse of the building, and they are classified and detected as obstacles. We also propose a method to detect rescue requesters-the most important resource in the disaster situation-and minimize human casualties. To this end, we collected open-source disaster images and image data of disaster situations and calculated the accuracy of detecting rescue requesters in disaster situations through various deep learning-based object detection algorithms. In this study, as a result of analyzing the algorithms that detect rescue requesters in disaster situations, we have found that the YOLOv4 algorithm has an accuracy of 0.94, proving that it is most suitable for use in actual disaster situations. This paper will be helpful for performing efficient search and rescue in disaster situations and achieving a high level of physical security, even in collapsed buildings.

• Journal of the Society of Disaster Information
• /
• v.15 no.2
• /
• pp.282-291
• /
• 2019

Purpose: In recent, mobile technology, as an axis of the fourth industry paradigm, is evolving into our daily life, economic activities and disaster safety management. However, since the location information service is insufficient, it is difficult to response the emergency situation adequately in the golden time. The purpose of this study is to propose a method to fine precisely the location of people who are in need of an emergency in the event of accidents and disasters. Method: This study investigates and compares existing literature and safety apps for national index number NFC application development. In addition, the system structure and the design method through the element technology through analysis of necessary function of the demander were carried out. Results: The results of this study were developed as a design and system that can be implemented in both direction and function to inform the location for emergency situation or disaster reporting in mobile. Conclution: It is possible to provide the disaster safety location service which can be utilized by the citizens in case of crisis by unifying the address system and integrating the location information using NFC.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2021.05a
• /
• pp.235-236
• /
• 2021

As a result of analyzing the fire accident of the Jecheon complex that occurred at the end of 2017, there have been many casualties due to delays in checking the location information of isolated people. In order to prevent such an accident, various research has been conducted to estimate the location of requesters by means of detecting wireless communication information of mobile phones existing at disaster sites. The main concept is to detect an RF signal of a mobile phone at fire sites and, based on this, precisely estimate the location of the mobile phone on the LOS/NLOS. However, it is difficult to get visibility at fire sites due to smoke and the fire. Therefore, apart from estimating the location of requesters, a research is also needed to determine the direction of entry within fire sites. In this paper, we propose a method to determine a direction of entry to provide effective rescue activities using wireless communication information of mobile phones.

• Journal of the Society of Disaster Information
• /
• v.19 no.4
• /
• pp.897-907
• /
• 2023

Purpose: In this study, We aim to estimate a untrained person's three postures using a 2D CNN model which is trained with minimal FFT data collected by a 24GHz FMCW radar. Method: In an indoor space, we collected FFT data for three distinct postures (standing, sitting, and lying) from three different individuals. To apply this data to a 2D CNN model, we first converted the collected data into 2D images. These images were then trained using the 2D CNN model to recognize the distinct features of each posture. Following the training, we evaluated the model's accuracy in differentiating the posture features across various individuals. Result: According to the experimental results, the average accuracy of the proposed scheme for the three postures was shown to be a 89.99% and it outperforms the conventional 1D CNN and the SVM schemes. Conclusion: In this study, we aim to estimate any person's three postures using a 2D CNN model and a 24GHz FMCW radar for disastrous situations in indoor. it is shown that the different posture of any persons can be accurately estimated even though his or her data is not used for training the AI model.

• Proceedings of the Safety Management and Science Conference
• /
• 2012.11a
• /
• pp.369-376
• /
• 2012

본 연구는 소방대원의 화재진압 업무를 인간공학적 평가도구(RULA, REBA)를 이용하여 분석하고 타업종(병원, 자동차업종)과의 비교를 수행하였다. 첫째, 소방대원들의 업무 중 화재진압 업무의 인간공학적 작업자세 분석 및 평가하여 극단적인 작업자세에 대해서 살펴보았다. 요구조자 1인 운반법은 RULA, REBA의 평가결과에서 모두 정밀조사가 필요하고 즉시 개선 조치가 요구되는 4단계로 평가되었다. 둘째, 화재진압 업무와 타업종과(병원, 자동차업종)의 분석 결과를 비교 분석을 실시하였다. RULA로 평가한 결과 3, 4단계가 차지하는 비율이 72%로 자동차 업종(74%)에서의 평가결과 보다 낮게 나타났지만 병원업종(37%)보다는 높게 나타났다. REBA로 평가한 결과 3, 4단계가 차지하는 비율이 36%로 병원(9%)과 자동차 업종(24%)에서의 평가결과보다 높게 평가된 것으로 나타났다.

• Proceedings of the KAIS Fall Conference
• /
• 2011.05b
• /
• pp.1044-1047
• /
• 2011

본 연구는 소방대원의 현장 작업자세 평가와 분석을 통하여 소방대원의 근골격계 부담작업 유해요인을 분석하고자 한다. B시에 소재하고 있는 소방서의 남자 소방대원을 대상으로 소방 현장에서 많이하는 자세 중 요구조자 이송작업자세, 방수작업자세, 유압구조장비 작업자세, 만능도끼작업 자세를 인간공학적 평가 기법인 Rapid Entire Body Assessment(REBA), Rapid Upper Limb Assessment(RULA)와 NIOSH Lifting Equation(NLE)를 이용하여 평가하고 분석하였다. 자세 분석결과, RULA 분석에서 모든 작업이 최고 점수인 7점으로 평가되었고 REBA는 5점에서 10점까지로 RULA분석에 비하여 낮은 점수를 나타내었다. 따라서, 소방대원들의 작업환경과 자세에 문제가 많다는 것을 알 수 있었다.