• International Journal of Advanced Culture Technology
• /
• v.11 no.1
• /
• pp.320-324
• /
• 2023

As urbanization accelerates and facilities that use energy increase, human life and property damage due to fire is increasing. Therefore, a fire monitoring system capable of quickly detecting a fire is required to reduce economic loss and human damage caused by a fire. In this study, we aim to develop an improved artificial intelligence model that can increase the accuracy of low fire alarms by mixing DeepSORT, which has strengths in object tracking, with the YOLOv5s model. In order to develop a fire detection model that is faster and more accurate than the existing artificial intelligence model, DeepSORT, a technology that complements and extends SORT as one of the most widely used frameworks for object tracking and YOLOv5s model, was selected and a mixed model was used and compared with the YOLOv5s model. As the final research result of this paper, the accuracy of YOLOv5s model was 96.3% and the number of frames per second was 30, and the YOLOv5s_DeepSORT mixed model was 0.9% higher in accuracy than YOLOv5s with an accuracy of 97.2% and number of frames per second: 30.

• International Journal of Advanced Culture Technology
• /
• v.9 no.4
• /
• pp.260-267
• /
• 2021

In this paper, we intend to use a new mixed model of YoloV5 and DeepSort. For fire detection, we want to increase the accuracy by automatically extracting the characteristics of the flame in the image from the training data and using it. In addition, the high false alarm rate, which is a problem of fire detection, is to be solved by using this new mixed model. To confirm the results of this paper, we tested indoors and outdoors, respectively. Looking at the indoor test results, the accuracy of YoloV5 was 75% at 253Frame and 77% at 527Frame, and the YoloV5+DeepSort model showed the same accuracy at 75% at 253 frames and 77% at 527 frames. However, it was confirmed that the smoke and fire detection errors that appeared in YoloV5 disappeared. In addition, as a result of outdoor testing, the YoloV5 model had an accuracy of 75% in detecting fire, but an error in detecting a human face as smoke appeared. However, as a result of applying the YoloV5+DeepSort model, it appeared the same as YoloV5 with an accuracy of 75%, but it was confirmed that the false positive phenomenon disappeared.

• Fire Science and Engineering
• /
• v.22 no.1
• /
• pp.76-83
• /
• 2008

In the subway fire case, it is important that judge accuracy subway fire type and on the initial response minimize accident damage. But when the subway fire accident occurring, if it have know impossible that accuracy subway fire type to judge at once though witnessing driver or emergency response staff. This study suggests type of five senses that using information of five sense take to the subway fire accident information which analyses five senses as occurring subway fire accident. Also it is proposed that emergency response system though fire scenario by using Activity-Action Diagram(AAD).

• Fire Science and Engineering
• /
• v.10 no.1
• /
• pp.25-43
• /
• 1996

This paper has been studied about promotion system for fire assessment. Mainly system carried out for BCJ (Building Center of Japan) and JFSC (Japan Fire Safety Center) fire risk assessment system. Much of the work of fire science and fire protection engineering is now explicitly designed to fill gaps or improve accuracy or flexibility In some comprehensive fire hazard or fire risk models.

• Journal of KIBIM
• /
• v.13 no.2
• /
• pp.37-46
• /
• 2023

The main objective of this study is to propose a method to enhance building safety using the Industry Foundation Classes (IFC) schema in Building Information Modeling (BIM). To achieve this goal, a fire object relationship diagram is created by using the Model View Definition (MVD) and Property Set (Pset) methodology, as well as the Work Breakdown Structure (WBS) based object relationship analysis. The proposed method illustrates how to represent objects and tasks related to fire prevention and human safety during a building fire, including variables that are relevant to these aspects. Furthermore, the proposed method offers the advantage of considering both the IFC object hierarchy and the project work hierarchy when creating new objects, thereby expanding the attribute information for fire safety and maintenance. However, upon confirmation via an IFC viewer after development, a problem with the accuracy of mapping between attributes and objects arises due to the issue of proxy representation of related object information and newly added object information in standard IFC. Therefore, in future research, a mapping method for fire safety objects will be developed to ensure accurate representation, and the scope of utilization of the fire safety object diagram will be expanded. Furthermore, efforts will be made to enhance the accuracy of object and task representation. This research is expected to contribute significantly to the technological development of building safety and fire facility design in the future.

• Journal of IKEEE
• /
• v.26 no.3
• /
• pp.468-474
• /
• 2022

In this paper, we propose a method to implement a real-time fire alarm system using deep learning. The deep learning image dataset for fire alarms acquired 1,500 sheets through the Internet. If various images acquired in a daily environment are learned as they are, there is a disadvantage that the learning accuracy is not high. In this paper, we propose a fire image data expansion method to improve learning accuracy. The data augmentation method learned a total of 2,100 sheets by adding 600 pieces of learning data using brightness control, blurring, and flame photo synthesis. The expanded data using the flame image synthesis method had a great influence on the accuracy improvement. A real-time fire detection system is a system that detects fires by applying deep learning to image data and transmits notifications to users. An app was developed to detect fires by analyzing images in real time using a model custom-learned from the YOLO V4 TINY model suitable for the Edge AI system and to inform users of the results. Approximately 10% accuracy improvement can be obtained compared to conventional methods when using the proposed data.

• Journal of Advanced Navigation Technology
• /
• v.27 no.5
• /
• pp.685-689
• /
• 2023

The proposed system in the study aims to detect forest fires in real-time stream data received from the drone-camera. Recently, the number of wildfires has been increasing, and also the large scaled wildfires are frequent more and more. In order to prevent forest fire damage, many experiments using the drone camera and vision analysis are actively conducted, however there were many challenges, such as network speed, pre-processing, and model performance, to detect forest fires from real-time streaming data of the flying drone. Therefore, this study applied image data processing works to capture five good image frames for vision analysis from whole streaming data and then developed the object detection model based on YOLO_v2. As the result, the classification model performance of forest fire images reached upto 93% of accuracy, and the field test for the model verification detected the forest fire with about 70% accuracy.

• Fire Protection Technology
• /
• s.16
• /
• pp.20-23
• /
• 1994

This article investigates the different numerical methods, which are widely used for purpose of simulating a fire compartment the particular numerical methods such as finite difference, finite element, control Volume, and finite analysis are discribed in order to understand basic concepts and their applications. The fire simulations using fferent methods for the different physical geometrics have been reported in many recent literatures The convergence rate, the accuracy, and the stability are no simply dependent upon the specific method, The study of popular nu-merical methods by being compared among those is therefore significant to understand the nu-merical simulation of fire compartment.

• Fire Science and Engineering
• /
• v.28 no.3
• /
• pp.20-28
• /
• 2014

Effect of radiation models on the suppression limits in counterflow $CH_4$/air diffusion flame was numerically investigated with fundamental experiments for the numerical validation. $N_2$ and $CO_2$ were considered as extinguishing agents. The differences in extinguishing concentration between OTM and SNB radiation models which have different accuracy levels were examined. As a result, there is no considerable difference in extinguishing concentration for the $N_2$ dilution as the radiation models with different accuracy levels were used. As the $CO_2$ having strong radiative effect was diluted in the low strain flames, however, the radiation model with high predictive accuracy such as SNB should be used. In particular, the $CO_2$ dilution in fuel stream leads to the significant difference in extinguishing concentration between OTM and SNB models. Therefore, it is necessary that the radiation model should be reasonably chosen with the consideration of numerical accuracy and computational time for the prediction of extinguishing concentration.

• Journal of the Korea Institute of Military Science and Technology
• /
• v.16 no.6
• /
• pp.745-751
• /
• 2013

In naval gun firing, firing accuracy comes from the combination of each component's accuracy in CFCS (Command and Fire Control System) like tracking sensors and gun. Generally, battery alignment is done to correct the error between gun and tracking sensor by using boresight telescope on harbor and sea. But normally, the battery alignment can compensate only the static alignment error and ignore dynamic alignment error which is caused by own ship movement. There was no research on this dynamic alignment error until now. We propose a new way to analyze dynamic arrangement error by using image of boresight telescope. In case of the dynamic alignment error was due to time delay of own ship attitude information, we propose the way to compensate it.