• 한국재난정보학회 논문집
• /
• 제19권4호
• /
• pp.968-975
• /
• 2023

연구목적: 화재 탐지시 불꽃/연기의 오탐지율이 높은 것을 확인하고 오탐지율을 낮추기 위해 화재 상황을 인식하여 분류하는 방법과 데이터셋을 제안하고자 한다. 연구방법: 동영상을 학습데이터로 활용하여 화재 상황의 특징을 추출하여 분류모델에 적용하고, 평가는 한국정보화진흥원(NIA)에서 진행하는 화재 데이터셋을 이용하여 Yolov8, Slowfast의 모델 성능을 비교 및 분석하였다. 연구결과: YOLO는 배경의 영향에 따라 탐지 성능이 민감하게 변화하며, 화재의 규모가 너무 크거나 작을 때에도 화재를 제대로 감지하지 못했다. SlowFast는 동영상의 시간 축을 같이 학습하기 때문에 비정형 객체에 대해 주변이 흐리거나 밝아 형상을 명확하게 유추할 수 없는 상황에서도 우수하게 화재를 탐지하는 것을 확인했다. 결론: 화재 탐지율은 이미지 데이터 방식보다는 동영상 기반의 인공지능 인식(Detection) 모델을 활용했을 때 더 적절했음을 확인했다.

• 반도체디스플레이기술학회지
• /
• 제22권2호
• /
• pp.77-80
• /
• 2023

Since fires in uncontrolled environments pose serious risks to society and individuals, many researchers have been investigating technologies for early detection of fires that occur in everyday life. Recently, with the development of deep learning vision technology, research on fire detection models using neural network backbones such as Transformer and Convolution Natural Network has been actively conducted. Vision-based fire detection systems can solve many problems with physical sensor-based fire detection systems. This paper proposes a fire detection method using the latest YOLOv8, which improves the existing fire detection method. The proposed method develops a system that detects sparks and smoke from input images by training the Yolov8 model using a universal fire detection dataset. We also demonstrate the superiority of the proposed method through experiments by comparing it with existing methods.

• 한국재난정보학회:학술대회논문집
• /
• 한국재난정보학회 2023년 정기학술대회 논문집
• /
• pp.202-203
• /
• 2023

최근 화재 탐지 분야는 불꽃 연기의 특징과 인공지능 인식(Detection) 모델을 활용하여 탐지율을 높이려는 연구가 많이 진행되어 왔다. 기존 화재 탐지 정확도를 높이기 위한 모델 연구 이외에도 불꽃·연기의 특징을 다양한 방법으로 데이터 가공한 학습 데이터셋을 활용하는 연구들이 진행되고 있다. 본 논문에서는 화재 탐지시 불꽃/연기의 오탐지율이 높은 것을 확인하고 오탐지율을 낮추기 위해 화재 상황을 인식하여 분류하는 방법과 데이터셋을 제안한다. 제안한 모델은 동영상을 학습데이터로 활용하여 화재 상황의 특징을 추출하여 분류모델에 적용하였다. 평가는 한국정보화진흥원(NIA)에서 진행하는 화재 데이터셋을 이용하여 Yolov8, Slowfast의 모델 성능을 비교 및 분석하였다.

• International Journal of Advanced Culture Technology
• /
• 제10권4호
• /
• pp.536-546
• /
• 2022

A society will lose a lot of something in this field when the forest fire broke out. If a forest fire can be detected in advance, damage caused by the spread of forest fires can be prevented early. So, we studied how to detect forest fires using CCTV currently installed. In this paper, we present a deep learning-based model through efficient image data construction for monitoring forest fire smoke, which is unstructured data, based on the deep learning model YOLOv5. Through this study, we conducted a study to accurately detect forest fire smoke, one of the amorphous objects of various forms, in YOLOv5. In this paper, we introduce a method of self-learning by producing insufficient data on its own to increase accuracy for unstructured object recognition. The method presented in this paper constructs a dataset with a fixed labelling position for images containing objects that can be extracted from the original image, through the original image and a model that learned from it. In addition, by training the deep learning model, the performance(mAP) was improved, and the errors occurred by detecting objects other than the learning object were reduced, compared to the model in which only the original image was learned.

• Steel and Composite Structures
• /
• 제51권1호
• /
• pp.25-41
• /
• 2024

The measurement of pile bearing capacity is crucial for the design of pile foundations, where in-situ tests could be costly and time needed. The primary objective of this research was to investigate the potential use of fuzzy-based techniques to anticipate the maximum weight that concrete driven piles might bear. Despite the existence of several suggested designs, there is a scarcity of specialized studies on the exploration of adaptive neuro-fuzzy inference systems (ANFIS) for the estimation of pile bearing capacity. This paper presents the introduction and validation of a novel technique that integrates the fire hawk optimizer (FHO) and equilibrium optimizer (EO) with the ANFIS, referred to as ANFIS_FHO and ANFIS_EO, respectively. A comprehensive compilation of 472 static load test results for driven piles was located within the database. The recommended framework was built, validated, and tested using the training set (70%), validation set (15%), and testing set (15%) of the dataset, accordingly. Moreover, the sensitivity analysis is performed in order to determine the impact of each input on the output. The results show that ANFIS_FHO and ANFIS_EO both have amazing potential for precisely calculating pile bearing capacity. The R² values obtained for ANFIS_FHO were 0.9817, 0.9753, and 0.9823 for the training, validating, and testing phases. The findings of the examination of uncertainty showed that the ANFIS_FHO system had less uncertainty than the ANFIS_EO model. The research found that the ANFIS_FHO model provides a more satisfactory estimation of the bearing capacity of concrete driven piles when considering various performance evaluations and comparing it with existing literature.