Fire Disaster Research Articles

A study of engine room smoke detection based on proactive machine vision model for intelligent ship

Fire disaster causes damage to ships, pollute the environment, and threatens people's lives, so making early detection and reasonable decision is essential for avoiding catastrophic accidents. Smoke, as the main feature of fire, plays a significant role in early fire identification. However, challenged by the complex engine room (E/R) environment and shooting issues, the recognition performances of current smoke detection methods based on machine vision are unsatisfactory at the early fire stage. To address the issues, this paper proposes a proactive machine vision model based on the fusion of the transfer learning method and proactive perception technology for smoke detection. Firstly, a smoke images database is established based on similar environments (indoor and ship fire scenes) for the transfer learning module training, where more smoke features are extracted and learned from complex scenes. Afterward, real-time images are input into the trained model for local significance analysis which is applied as a triggering criterion for active smoke perception. When the significance indicator reaches the trigger condition, the proactive perception technology adopts reinforcement learning and proactive vision for further identifying detailed information about scenarios. By this processing, the internal and external parameters of the camera are adjusted to narrow and focus the targets of interest in the current scene. Finally, the ship E/R workshop and distribution box fire cases are selected to validate the proposed method. The experiment results indicate that the proposed model outperforms the existing techniques in accuracy as it has the potential to detect earlier smoke features.

Mitigating the Effects of Fire Outbreaks in Secondary Schools: Strategies for Safeguarding Children at Risk in Tanzania

This paper investigated alternative strategies for safeguarding Tanzania children from school fire disasters. The study was guided by change management theory. Data were collected from four secondary schools from two regions of Tanzania Mainland. A qualitative approach was employed and data were collected through face-to-face interviews, Focused Group Discussions and physical observations. The study involved 101 participants – 61 students, 35 teachers, 3 Heads of Schools and 2 members of the School Board. The study revealed that improved school infrastructures, provision of education to people, building harmony with the community, improved school security, installation of firefighting facilities in schools and identification of sources of fire were the appropriate strategies to manage fire. Combined efforts of the school, community, government and education supporters are of paramount importance for mitigating regular fire outbreaks in secondary schools.

Implementasi Standar Pelayanan Minimal (SPM) Penanggulangan Bencana Kebakaran Pada Dinas Pemadam Kebakaran Dan Penanggulangan Bencana Kota Makassar

This research aims to find out how the Minimum Service Standards (SPM) for Fire Disaster Management are implemented in the Makassar City Fire Department. This type of research uses a qualitative descriptive method, namely research that aims to provide an overview of the Implementation of Minimum Service Standards (SPM) for Fire Disaster Management in the Fire Service. Makassar City Fire where the author used the interview method. Data sources consist of primary data obtained through interviews, while secondary data is obtained from documents, notes, modules, official Wikipedia which can be supported by complete primary data. The results of research conducted at the Makassar City Fire Department Office, in the Implementation of Minimum Service Standards (Spm) for Fire Disaster Management, there are criteria, namely: How to Implement Minimum Service Standards (Spm) for Fire Disaster Management at the Makassar City Fire Department and Factors Inhibiting the Implementation of Service Standards Minimum (SPM). Based on the results of this research, it shows that the implementation of the Minimum Service Standards (Spm) for Fire Disaster Management at the Makassar City Fire Department has been carried out quite well and is in accordance with the achievements of the Minimum Service Standards at the Makassar City Fire Department, although there are still several inhibiting factors, but the attitude of responsibility of each member/employee of the Makasssar city fire department continues to be carried out.

Human Factors on Fire Hazards: A Correlation Study in a Vocational Education Environment

A fire disaster is one of the disasters that can harm many parties. The danger of fire can result in several threats to safety and property and can often even result in loss of life. There are various things that can start fires, namely human, equipment, and natural factors. The purpose of this study is to ascertain how human variables and fire dangers are related in vocational education environments. Negligence is a fundamental characteristic that cannot be prevented, but this can be minimized by knowing the causes of fires and steps that can be taken to reduce the potential danger of fires caused by human factors. This study includes a cross-sectional study design, a quantitative technique, and a correlational descriptive method. Data was collected by distributing questionnaires, as well as making observations as data to strengthen the results of questionnaire data analysis. The variables used in this research are Fire Fighting Knowledge (X1), Fire Incident Experience (X2), and Fire Fighting Behavior (Y). The study's findings indicate that knowledge and fire prevention behavior are significantly correlated, as are experience and fire prevention behavior, and that knowledge and experience are significantly correlated with fire prevention behavior.

Multiscale network based on feature fusion for fire disaster detection in complex scenes

With the advent of high-resolution surveillance equipment, fire detection aimed at obtaining more detailed information has drawn considerable attention. The methods are based on convolutional neural networks (CNNs), which have been widely applied to automatically extract fire detection image features. However, the existing CNN-based fire detection methods are only designed for fixed-scale images. Thus, these methods are still difficult to use for fire detection due to the scale variation in the fire object and are infeasible for satisfying the requirement of various hardware of different scale images. In this paper, a fire disaster detection method that can deal with varied-scale images is proposed. First, the dense connection is used to enhance the information flow between different layers. Then, the groups channel attention is utilized to recalibrate the features. Finally, multiscale spatial feature pooling is employed to fuse different scale features. Specifically, the module allows us to predict different scale images. Experimental results demonstrate that the proposed method achieves 91.4 accuracy using fixed scale training, and 92.4 accuracy using multiscale training.

Nature and Extent of Deviant Behaviour among Secondary Students in Public Schools within Bungoma County, Kenya

The prevalence of fire disasters has become a global phenomenon, especially in public and private premises, particularly secondary schools and other learning institutions. Social decadence has been touted as one of the reasons for rebelliousness among secondary school students, which has in many cases led to the torching of schools. Whereas schools are expected to promote and enhance discipline and moral behaviors, in most instances, schools within Bungoma have experienced forms of deviant behavior that have resulted in fire disasters. Therefore, this study sought to examine the nature and extent of deviant behavior among public secondary schools in Bungoma County, Kenya. The study utilized Bronfenbrenner’s ecological systems theory. The study adopted a descriptive research design, and a sample of 384 was used. Proportionate and simple random sampling was used. The study found that there was high cases of deviant behaviors among students, led by theft of property (95.6%), followed by drug and substance use (64.8%). The study further found that peer pressure (83.3%) and drug and substance abuse (53.6%) were the main factors leading students to burn schools. The findings of the study revealed that 363 (95.6%) of respondents agreed that there are many theft cases among students and their fellow colleagues. The study concludes that most students abuse bhang, followed by chang'aa, and lastly, busaa. In regards to the effects of riots, the study concludes that riots mostly take the form of destruction of properties, followed by theft cases. In regards to types of theft cases, the study concludes that students have experienced theft of text books due to poverty and parenthood. Also, students steal these items mostly to sell them and get money. The school administration should enhance security measures through the installation of CCTVs and improved fencing to reduce the chances of sneaking out and drugs getting in. Students should be forced to pay for the damages caused during their riots. The governments should ensure schools have adequate and trained counselors in order to help in taming deviant behaviors such as drug and substance abuse, bullying, and theft. The school administration should have open communication with the students in order to avert riots and school fires.

Vulnerability Analysis of Fire Disaster Evacuation at old Thanjavur town, India using Space Syntax Method

Vulnerability Analysis of Fire Disaster Evacuation at old Thanjavur town, India using Space Syntax Method

A modified YOLOv5 architecture for efficient fire detection in smart cities

Fire disasters are considered to be among the most harmful hazards, causing fatalities, ecological and economic chaos, property damage, and they can even impact climate change. Early fire detection is necessary to overcome these losses and disruption. Fire detection using vision sensors is a promising research area that has gained significant attention from computer vision experts. Traditionally, low-level colour features were used for fire detection but they have now been superseded by effective deep learning models that achieve higher accuracy. However, these models also suffer from a higher false alarm rate, due to the fact that they treat fire detection as a classification task where the entire image is classified into a single class and the region of the proposal stage is ignored. Furthermore, the time complexity and model size limit these models from real-world implementation. To overcome these challenges, we propose a modified YOLOv5s model that integrates a Stem module in the backbone, replaces larger kernels with smaller ones in the SPP (Neck) and adds the P6 module into the head. This model achieves promising results with lower complexity and smaller model size, and is able to detect both small and large fire regions in images. Moreover, we contribute a medium-scale fire dataset that consists of three classes (i.e. vehicle fire, building fire, and indoor electric fire), with manual annotation according to the object detection model. This dataset will be made publicly available for research purposes. Finally, for fair evaluation, we re-implement 12 different state-of-the-art object detection models, including the proposed model, and trained them over a self-created dataset. We found that in comparison the proposed model had better detection performance and applicable in real-world scenario. Our codes and dataset will be publicly available at https://github.com/Hikmat-Yar/Modified-YOLOv5-Code.

Efficient Fire Segmentation for Internet-of-Things-Assisted Intelligent Transportation Systems

Rapid developments in deep learning (DL) and the Internet-of-Things (IoT) have enabled vision-based systems to efficiently detect fires at their early stage and avoid massive disasters. Implementing such IoT-driven fire detection systems can significantly reduce the corresponding ecological, social, and economic destruction; they can also provide smart monitoring for intelligent transportation systems (ITSs). However, deploying these systems requires lightweight and cost-effective convolutional neural networks (CNNs) for real-time processing on artificial intelligence (AI)-assisted edge devices. Therefore, in this paper, we propose an efficient and lightweight CNN architecture for early fire detection and segmentation, focusing on IoT-enabled ITS environments. We effectively utilize depth-wise separable convolution, point-wise group convolution, and a channel shuffling strategy with an optimal number of convolution kernels per layer, significantly reducing the model size and computation costs. Extensive experiments on our newly developed and other benchmark fire segmentation datasets reveal the effectiveness and robustness of our approach against state-of-the-art fire segmentation methods. Further, the proposed method maintains a balanced trade-off between the model efficiency and accuracy, making our system more suitable for IoT-driven fire disaster management in ITSs.

Penggunaan Buku Cerita Digital untuk Mengenalkan Mitigasi Bencana Kebakaran Bagi Anak Usia Dini

The research is about to develop digital storytelling media in introducing fire disaster mitigation for children aged 5 to 6. This research uses the ADDIE development model (Analyze, Design, Development, Implementation, and Evaluation). This research method was using questionnaire instruments for expert review and evaluation instruments one to one for children aged 5 – 6 years. The results of the validity test of the product by the material expert obtained a hard score of 100%. The product validity testing results by the media expert received a final score of 77.5%. The validity tests of practitioners or teachers at the PAUD Institute obtaining a value of 97.5%. Product effectiveness test results in children aged 5 – 6 years gave a final value of 80.1%. Research results showed that the digital storytelling books qualified. The digital storytelling media has been successful in introducing fire disaster mitigation to children aged 5-6 years. This book can provide an introduction to the dangers of playing with flammable objects, objects that can extinguish fires, and actions taken in the event of a fire. This book can be practically used as a learning medium by children with the support and guidance of teachers and parents.

Peningkatan Pengetahuan Tanggap Bencana Kebakaran Melalui VBE

Knowledge of fire disaster response is very necessary to avoid the risk of fire hazards that can occur such as loss of property, injury and even loss of life. The results of the preliminary assessment found that most of the education staff and cleaning service had not received information related to fire disaster response including independent evacuation, around 37 participants (59.5%) were less responsive to fire. Therefore, the community service team conducted fire disaster response counseling through Video Based Education (VBE) to increase the knowledge of educational staff and cleaning service at the Siti Walidah building, University of Muhammadiyah Yogyakarta (UMY). This method of implementing community service activities is carried out by providing education through video media which contains fire prevention in the building and self-evacuation. The results of the implementation of community service activities showed an increase in knowledge about fire disasters among education staff and cleaning service from a less level of knowledge 54%, moderate 46% and high 6% to a high level of knowledge 44%, moderate 39% and less 17%. Through the implementation of community service activities with education using VBE, it can improve knowledge of fire disaster response for education staff and cleaning service at the Siti Walidah UMY building.Keywords:, Disaster Response, Education, Fire, Knowledge Video Based Education

Utilising Deep Convolutional Neural Networks for Classifying Fire Disasters Through Surveillance: An Indoor and Outdoor Perspective to Predict Man-Made or Natural Disaster

Utilising Deep Convolutional Neural Networks for Classifying Fire Disasters Through Surveillance: An Indoor and Outdoor Perspective to Predict Man-Made or Natural Disaster

Evaluation of Multi-Spectral Band Efficacy for Mapping Wildland Fire Burn Severity from PlanetScope Imagery

Increased spatial resolution has been shown to be an important factor in enabling machine learning to map burn extent and severity with extremely high accuracy. Unfortunately, the acquisition of drone imagery is a labor-intensive endeavor, making the capture of drone imagery impractical for large catastrophic fires, which account for the majority of the area burned each year in the western US. To overcome this difficulty, satellites, such as PlanetScope, are now available which can produce imagery with remarkably high spatial resolution (approximately three meters). In addition to having higher spatial resolution, PlanetScope imagery contains up to eight bands in the visible and near-infrared spectra. This study examines the efficacy of each of the eight bands observed in PlanetScope imagery using a variety of feature selection methods, then uses these bands to map the burn extent and biomass consumption of three wildland fires. Several classifications are produced and compared based on the available bands, resulting in highly accurate maps with slight improvements as additional bands are utilized. The near-infrared band proved contribute most to increased mapping accuracy, while the green 1 and yellow bands contributed the least.

Remote Sensing applications for effective fire disaster management plans: A review

The current context of climate change and imminent global warming is leading to changes in temperature and rainfall patterns worldwide which affect soil moisture, vegetation and soil conditions, the incidence of dry and wet events, and consequently, the occurrence, intensity, and magnitude of fires. Fires harm people’s quality of life as they can disrupt economic activities and affect public health. Additionally, fires damage the environment, accelerating water and wind erosion processes, altering air quality, and contributing to ecosystem degradation. Pampas in Argentina was selected as an example to study fires at a regional scale using Remote Sensing techniques due to its status as one of the most fertile plains in the world and the country’s most densely populated area. The fires are carefully analyzed and described considering three stages: i) pre-fires, ii) fires, and iii) post-fires. Afterwards, fire disaster management plans are described to assess these events, reduce their impacts on society and biodiversity, and minimize the ecosystems’ recovery time. In this sense, this manuscript aims to review the relationships between climate change, global warming, and the occurrence of fires. Additionally, it proposes to analyze the potential of Remote Sensing in analyzing these events at a regional scale to provide the mechanisms and tools necessary for formulating fire disaster management plans.

Remote Sensing applications for effective fire disaster management plans: A review

The current context of climate change and imminent global warming is leading to changes in temperature and rainfall patterns worldwide which affect soil moisture, vegetation and soil conditions, the incidence of dry and wet events, and consequently, the occurrence, intensity, and magnitude of fires. Fires harm people’s quality of life as they can disrupt economic activities and affect public health. Additionally, fires damage the environment, accelerating water and wind erosion processes, altering air quality, and contributing to ecosystem degradation. Pampas in Argentina was selected as an example to study fires at a regional scale using Remote Sensing techniques due to its status as one of the most fertile plains in the world and the country’s most densely populated area. The fires are carefully analyzed and described considering three stages: i) pre-fires, ii) fires, and iii) post-fires. Afterwards, fire disaster management plans are described to assess these events, reduce their impacts on society and biodiversity, and minimize the ecosystems’ recovery time. In this sense, this manuscript aims to review the relationships between climate change, global warming, and the occurrence of fires. Additionally, it proposes to analyze the potential of Remote Sensing in analyzing these events at a regional scale to provide the mechanisms and tools necessary for formulating fire disaster management plans.

Fire Disaster Mitigation in Dense Settlements in Batu Merah Country

Fire is a disaster that cannot be predicted when and where it will occur. Many fire disasters occur in dense settlements, so dense settlements become vulnerable to the danger of fire disasters. Negeri Batu Merah is one of the densely populated settlements located near the central area of Ambon City. This dense residential condition has resulted in settlements in Batu Merah Country becoming areas that are potentially vulnerable to fire disasters. This research aims to determine the distribution of fire disaster vulnerability levels in dense settlements in Batu Merah State. Apart from that, this research also aims to provide recommendations for reducing the level of fire vulnerability in the study area. The analytical methods used in this research are spatial analysis, appreciation analysis and descriptive analysis. Based on the results of the vulnerability analysis in the study area, the level of fire vulnerability is divided into three, namely low, high and very high levels of vulnerability. Interventions to reduce the level of fire vulnerability can be carried out by mitigating efforts both structurally and non-structurally by adding fire extinguishing facilities, widening residential roads, and widening roads in the Batu Merah settlements.

A method for multi-person mobile virtual reality fire evacuation drills based on pose estimation: Consistency of vision and perception

Fire disasters present significant risks, emphasizing the need for effective evacuation drills. Traditional drills in real environments have limitations such as safety risks and poor repeatability. Immersive Virtual Reality (iVR) provides a safer, more engaging alternative, but early iVR-based drills were restricted due to hardware limitations. The advent of mobile virtual reality has overcome some of these restrictions. However, challenges remain in multi-person evacuation scenarios, such as difficulties in relative positioning and the real time interaction of evacuees. This study addresses these issues using pose estimation for accurate positioning in virtual reality devices. Furthermore, we developed a framework for conducting evacuation drills in a real environment using mobile virtual reality, ensuring consistency in participants' visual and perceptual experiences. Subsequently, we designed two experiments to validate this methodology and framework. The experimental results demonstrated that the evacuation process, using pose estimation, effectively eliminates cumulative error, maintaining an approximate error of 0.04 m between the real and virtual environments. Participants also reported having a better experience and found it easier to interact with others during the mobile virtual reality evacuation.

Sistem Deteksi Kebakaran Menggunakan Esp32 Dan Arduino

,. Fire disasters are disasters that occur more often than other disasters such as floods, landslides, earthquakes or tsunamis. This disaster can happen at any time and no one knows for sure when this disaster will come. The impact of a fire disaster is not only material but can result in the loss of human life. Factors that cause fire disasters often occur due to human negligence and fires often occur in houses where the occupants are abandoned. The research carried out this time focuses on creating a fire detection system using ESP32 and Arduino. The system uses three sensors, namely a temperature sensor, a gas sensor and a fire sensor. Temperature sensors are useful for monitoring room temperature conditions, fire sensors are useful for detecting the presence of fire in a fire disaster and gas sensors are useful for detecting the presence of smoke that appears as a result of a fire disaster. This system uses Arduino Uno and ESP32 microcontrollers. The results of the fire detection system are expected to reduce the occurrence of fire accidents and also losses caused by fire accidents

Indeixicality in Political Discourse in Ghana: The Case of Former President John Mahama’s Speech at the National Memorial Service for Victims of June 03, 2015 Flood and Fire Disaster

This paper examines the indexicals in President John Dramani Mahama's speech, which was given on June 3, 2015, amid the flood and fire incident in Ghana, which resulted in the deaths of over 150 people. The speech's use of various indexicals—including their types, frequency, and effects—is covered. The study makes the case that, by using first-person pronouns like "I" and "my," the speaker successfully achieved self-projection and demonstrated empathy in his speech. The speech also used all indexicals, including person, spatial, temporal, discourse, and social, at different rates. Additionally, Deixis was used to make emotive appeals to the audience's emotions, an elusive emotional scale that compels one to support him. Without considering the value of their discourse, politicians frequently employ this tactic to gain the public's trust.

Eliminating scale effect: Development and attenuation of coal spontaneous combustion

Low temperature oxidation can occur in coal and coal piles, which can lead to severe fires in coal fields, storage rooms, and goaf areas. An important feature of these coal fire disasters is their large scale, providing a favorable environment for the inoculation of coal fires. A new method for studying coal oxidation reactions, which combines theoretical analysis with multi physical field numerical models, has been proposed to eliminate the influence of scale effects. Based on the theoretical analysis, the reliable numerical simulation conditions are obtained, and the results are compared with those of large coal spontaneous combustion experiment. The temperature, gas and reaction rate of coal oxidation have been analyzed and verified. The attenuation characteristics of coal oxidation reaction under sealed and nitrogen retarding measures have also been analyzed with emphasis. The research results indicate that the proposed new simulation method has been proven to be effective through multiple results validation. Sealing measures can weaken coal oxidation reactions, but heat elimination is slower. The measure of injecting nitrogen can quickly control local coal oxidation reactions and remove heat. The greater the flow rate of inert gas, the better the retarding effect on coal. The development process of coal oxidation will form “quasi spherical” and “crescent shaped”, which are prominent characteristics of slow oxidation and rapid propagation, respectively.