Search

Forest fires cause damage to life, biodiversity, and properties, affecting natural ecosystems, healthy and only. During the practical application of fire prevention, numerous detection techniques have been thoroughly researched to prevent devastating fires. The techniques improve early fire detection and accelerate emergency response, reducing damage and optimizing system containment operations. Wildfire detection requires a robust infrastructure for equipment, maintenance, and ongoing monitoring. Effective cooperation between components and integration of technologies is key to a consistent and comprehensive response to fires. This article proposes a fire monitoring system using drones, cameras, and edge computing technologies. We use Stochastic Petri Nets (SPN) to model the structure and evaluate the system's performance. The model is parameterizable, allowing adjustments to the components' resource capabilities and service time. Twenty-four parameters can be defined, making it possible to evaluate a wide variety of different scenarios. The results obtained in different scenarios in this work have the potential for auxiliary administrators of monitoring systems to estimate more than six analyses and plan more optimized architectures as needed. [ABSTRACT FROM AUTHOR]

Copyright of Fire Ecology is the property of Springer Nature and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

Fire detection and extinguishing systems are critical for safeguarding lives and minimizing property damage. These systems are especially vital in combating forest fires. In recent years, several forest fires have set records for their size, duration, and level of destruction. Traditional fire detection methods, such as smoke and heat sensors, have limitations, prompting the development of innovative approaches using advanced technologies. Utilizing image processing, computer vision, and deep learning algorithms, we can now detect fires with exceptional accuracy and respond promptly to mitigate their impact. In this article, we conduct a comprehensive review of articles from 2013 to 2023, exploring how these technologies are applied in fire detection and extinguishing. We delve into modern techniques enabling real-time analysis of the visual data captured by cameras or satellites, facilitating the detection of smoke, flames, and other fire-related cues. Furthermore, we explore the utilization of deep learning and machine learning in training intelligent algorithms to recognize fire patterns and features. Through a comprehensive examination of current research and development, this review aims to provide insights into the potential and future directions of fire detection and extinguishing using image processing, computer vision, and deep learning. [ABSTRACT FROM AUTHOR]

The paper introduces a new FireAndSmoke open dataset comprising over 22,000 images and 93,000 distinct instances compiled from 1200 YouTube videos and public Internet resources. The scenes include separate and combined fire and smoke scenarios and a curated set of difficult cases representing real-life circumstances when specific image patches may be erroneously detected as fire/smoke presence. The dataset has been constructed using both static pictures and video sequences, covering day/night, indoor/outdoor, urban/industrial/forest, low/high resolution, and single/multiple instance cases. A rigorous selection, preprocessing, and labeling procedure has been applied, adhering to the findability, accessibility, interoperability, and reusability specifications described in the literature. The performances of the YOLO-type family of object detectors have been compared in terms of class-wise Precision, Recall, Mean Average Precision (mAP), and speed. Experimental results indicate the recently introduced YOLO10 model as the top performer, with 89% accuracy and a mAP@50 larger than 91%. [ABSTRACT FROM AUTHOR]

Fire is a serious threat to people's lives and property. Be aimed at the low detection accuracy of the current fire detection system, a fire detection system based on one-chip computer is proposed in this work. To achieve fire detection and warning, the system collects these signals such as smoke and temperature from the surrounding environment, and processes them with a one-chip computer. The simulation experiments of the system are conducted with Proteus, and the experimental results indicate that the system can detect accurately. [ABSTRACT FROM AUTHOR]

Accurate fire ignition spatial location methods can serve the automatic fire suppression based on video. Although current fire detection systems based on monocular surveillance videos can quickly detect fires, it is impossible to obtain the 3D position due to the polysemy of 2D images. To further promote the universal application of automatic fire suppression, we propose a 3D indoor fire ignition location method based on monocular vision. This is the first study on spatial orientation of fire based on monocular vision. First, the indoor scene is quickly reconstructed as the basis of the scene. Second, based on our previous research on fire detection, the refined position of the fire in 2D images and its topological relationship with the space object are analyzed. The hierarchical constraints from 2 to 3D are established for the spatial orientation of the indoor fire ignition point. The experimental results show that the average absolute error is only 4.82 cm and that the average relative error is 1.71%. In addition, our method can be embedded into the existing fire prevention and control system at a low cost, further promoting the development of intelligent fire prevention and control. [ABSTRACT FROM AUTHOR]

Forest fire is a severe natural disaster, which leads to the destruction of forest ecology. At present, fire detection technology represented by convolutional neural network is widely used in forest resource protection, which can realize rapid analysis. However, in forest flame and smoke detection tasks, due to continuous expansion of the target range, a better detection effect cannot be achieved. This paper proposes an improved YOLOX method for multi-scale forest fire detection. This method proposes a novel feature pyramid model to reduce the information loss of high-level forest fire feature maps and enhance the representation ability of feature pyramids. Moreover, the method applies a small object data augmentation strategy to enrich the forest fire dataset, making it more suitable for the actual forest fire scene. According to the experimental results, the mAP of the model proposed in this paper reaches 79.64%, which is about 4.89% higher than the baseline network YOLOX. The method improves the accuracy of forest fire detection, reduces false alarms, and is suitable for real scenarios of forest fires. [ABSTRACT FROM AUTHOR]

The threat of forest fires to human life and property causes significant damage to human society. Early signs, such as small fires and smoke, are often difficult to detect. As a consequence, early detection of smoke and fires is crucial. Traditional forest fire detection models have shortcomings, including low detection accuracy and efficiency. The YOLOv8 model exhibits robust capabilities in detecting forest fires and smoke. However, it struggles to balance accuracy, model complexity, and detection speed. This paper proposes LD-YOLO, a lightweight dynamic model based on the YOLOv8, to detect forest fires and smoke. Firstly, GhostConv is introduced to generate more smoke feature maps in forest fires through low-cost linear transformations, while maintaining high accuracy and reducing model parameters. Secondly, we propose C2f-Ghost-DynamicConv as an effective tool for increasing feature extraction and representing smoke from forest fires. This method aims to optimize the use of computing resources. Thirdly, we introduce DySample to address the loss of fine-grained detail in initial forest fire images. A point-based sampling method is utilized to enhance the resolution of small-target fire images without imposing an additional computational burden. Fourthly, the Spatial Context Awareness Module (SCAM) is introduced to address insufficient feature representation and background interference. Also, a lightweight self-attention detection head (SADH) is designed to capture global forest fire and smoke features. Lastly, Shape-IoU, which emphasizes the importance of boundaries' shape and scale, is used to improve smoke detection in forest fires. The experimental results show that LD-YOLO realizes an mAP0.5 of 86.3% on a custom forest fire dataset, which is 4.2% better than the original model, with 36.79% fewer parameters, 48.24% lower FLOPs, and 15.99% higher FPS. Therefore, LD-YOLO indicates forest fires and smoke with high accuracy, fast detection speed, and a low model complexity. This is crucial to the timely detection of forest fires. [ABSTRACT FROM AUTHOR]

When a fire occurs underground, pre-existing emergency escape routes may become ineffective. Such scenarios necessitate the real-time planning of escape routes that consider evolving conditions and prioritize safety. This paper proposes a multi-objective real-time search method for emergency escape routes using dynamic programming to address these challenges. Firstly, this paper discusses how the evacuation of an underground mine fire caused by external factors depends on the fire monitoring system, personnel positioning system, and emergency evacuation system, as well as the modeling and solution methods of evacuation route planning. Then, based on fire smoke, CO, and temperature sensor data from the mine ventilation network structure and monitoring system, the possible smoke spread in the event of an underground fire was calculated. The objectives are to optimize both the shortest equivalent length of the path and the shortest time to walk through the smoke flow while ensuring that temporary escape time does not exceed the rated protection time of the self-rescuer. A mathematical model for emergency escape route planning is established under these conditions. A labeling algorithm based on dynamic programming is employed to find the Pareto optimal solution set of emergency evacuation routes that meet emergency requirements. Finally, two path evaluation indicators, namely "escape target priority" and "personnel temporary escape time", are introduced to re-rank the solutions in the Pareto optimal set, thereby obtaining disaster evacuation routes with different priorities. Example verification shows that the algorithm can quickly solve the disaster evacuation routes that meet the actual disaster evacuation needs in complex networks. Example verification shows that the algorithm can quickly solve the emergency escape routes in complex networks that meet actual emergency escape needs. [ABSTRACT FROM AUTHOR]

In this study, a novel method combining contour analysis with deep CNN is applied for fire detection. The method was made for fire detection using two main algorithms: one which detects the color properties of the fires, and another which analyzes the shape through contour detection. To overcome the disadvantages of previous methods, we generate a new labeled dataset, which consists of small fire instances and complex scenarios. We elaborated the dataset by selecting regions of interest (ROI) for enhanced fictional small fires and complex environment traits extracted through color characteristics and contour analysis, to better train our model regarding those more intricate features. Results of the experiment showed that our improved CNN model outperformed other networks. The accuracy, precision, recall and F1 score were 99.4%, 99.3%, 99.4% and 99.5%, respectively. The performance of our new approach is enhanced in all metrics compared to the previous CNN model with an accuracy of 99.4%. In addition, our approach beats many other state-of-the-art methods as well: Dilated CNNs (98.1% accuracy), Faster R-CNN (97.8% accuracy) and ResNet (94.3%). This result suggests that the approach can be beneficial for a variety of safety and security applications ranging from home, business to industrial and outdoor settings. [ABSTRACT FROM AUTHOR]

Factories play a crucial role in economic and social development. However, fire disasters in factories greatly threaten both human lives and properties. Previous studies about fire detection using deep learning mostly focused on wildfire detection and ignored the fires that happened in factories. In addition, lots of studies focus on fire detection, while smoke, the important derivative of a fire disaster, is not detected by such algorithms. To better help smart factories monitor fire disasters, this paper proposes an improved fire and smoke detection method based on YOLOv8n. To ensure the quality of the algorithm and training process, a self-made dataset including more than 5000 images and their corresponding labels is created. Then, nine advanced algorithms are selected and tested on the dataset. YOLOv8n exhibits the best detection results in terms of accuracy and detection speed. ConNeXtV2 is then inserted into the backbone to enhance inter-channel feature competition. RepBlock and SimConv are selected to replace the original Conv and improve computational ability and memory bandwidth. For the loss function, CIoU is replaced by MPDIoU to ensure an efficient and accurate bounding box. Ablation tests show that our improved algorithm achieves better performance in all four metrics reflecting accuracy: precision, recall, F1, and mAP@50. Compared with the original model, whose four metrics are approximately 90%, the modified algorithm achieves above 95%. mAP@50 in particular reaches 95.6%, exhibiting an improvement of approximately 4.5%. Although complexity improves, the requirements of real-time fire and smoke monitoring are satisfied. [ABSTRACT FROM AUTHOR]

With rising global temperatures, wildfires frequently occur worldwide during the summer season. The timely detection of these fires, based on unmanned aerial vehicle (UAV) images, can significantly reduce the damage they cause. Existing Convolutional Neural Network (CNN)-based fire detection methods usually use multiple convolutional layers to enhance the receptive fields, but this compromises real-time performance. This paper proposes a novel real-time semantic segmentation network called FireFormer, combining the strengths of CNNs and Transformers to detect fires. An agile ResNet18 as the encoding component tailored to fulfill the efficient fire segmentation is adopted here, and a Forest Fire Transformer Block (FFTB) rooted in the Transformer architecture is proposed as the decoding mechanism. Additionally, to accurately detect and segment small fire spots, we have developed a novel Feature Refinement Network (FRN) to enhance fire segmentation accuracy. The experimental results demonstrate that our proposed FireFormer achieves state-of-the-art performance on the publicly available forest fire dataset FLAME—specifically, with an impressive 73.13% IoU and 84.48% F1 Score. [ABSTRACT FROM AUTHOR]

The particle number size distribution (PNSD) plays a crucial role in aerosol science and related industries. The recent surge in dense PNSD monitoring networks and measurement in harsh environments necessitates low-cost Electrical Mobility Sizers/Spectrometers (EMS). A miniature charger using the radioactive source of americium-241 charger was specifically developed for the low-cost EMS, with ion sources easily obtainable at low costs from smoke alarms. The ion concentration was over 5 × 1012 m−3. The measured charging efficiency of the charger aligns with the commonly used approximation formulae, while charge distributions deviate slightly from it. To solve this deviation issue, a reported inversion method is adopted which is based on the bipolar PNSD measurement. The practical use of the charger was theoretically explored, providing insights into the particle number concentration limits at commonly employed flow rates. This charger displays the potential for providing a cost-effective method of conditioning aerosol charging in large-scale or environmentally challenging PNSD measurements. Copyright © 2024 American Association for Aerosol Research [ABSTRACT FROM AUTHOR]

As urbanization accelerates, the prevalence of fire incidents leads to significant hazards. Enhancing the accuracy of remote fire detection systems while reducing computation complexity and power consumption in edge hardware are crucial. Therefore, this paper investigates an innovative lightweight Convolutional Spiking Neural Network (CSNN) method for fire detection based on acoustics. In this model, Poisson encoder and convolution encoder strategies are considered and compared. Additionally, the study investigates the impact of observation time steps, surrogate gradient functions, and the threshold and decay rate of membrane potential on network performance. A comparison is made between the classification metrics of the traditional Convolutional Neural Network (CNN) approaches and the proposed lightweight CSNN method. To assess the generalization performance of the proposed lightweight method, publicly available datasets are merged with our experimental data for training, which results in a high accuracy of 99.02%, a precision of 99.37%, a recall of 98.75%, and an F 1 score of 99.06% on the test datasets. [ABSTRACT FROM AUTHOR]

Aiming at the problems of data integration and information sharing in the calibration workshop of smoke alarm, combining OPC Unified Architecture (OPC UA) and digital twin technology, the OPC UA based digital twin smoke alarm calibration workshop information network framework is proposed. Using OPC UA information modeling technology, a digital workshop information model for smoke alarm calibration was constructed, and the static attribute set, process attribute set, and functional component set of the workshop were defined in detail. Taking the smoke box as an example, the information model construction was instantiated, and data collection and transmission were carried out with the digital twin model of the smoke box, achieving the implementation mapping between the twin model and physical entities. The results show that based on the proposed OPC UA information model, the interconnection and intercommunication of data at all levels of the digital twin smoke alarm calibration workshop can be achieved, and the workshop can be visualized, digitized, and flexible. [ABSTRACT FROM AUTHOR]

The time for smoke gas to reach a smoke detector would depend on its structural characteristics. However, previous studies have neglected to explore this issue. In this paper, three structural variables of a cylindrical smoke detector with a cover are chosen, and the response surface method is used to carry out the experimental design. Furthermore, the incidence point velocity and center point velocity are calculated using the computational fluid dynamics simulation, and the alarm time is obtained using a homemade device. The three parameters that influence the outcomes are then examined to obtain empirical formulas and the best solutions. Comparatively, we observe that the smoke ingress effect is most significantly influenced by the top cover height. After optimization, the incidence point velocity is increased by 115.94 %, the center point velocity is increased by 119.64 %, the alarm time is reduced by 68.57 %, and the gas flowability performance is noticeably improved. [ABSTRACT FROM AUTHOR]

Fire is a significant security threat that can lead to casualties, property damage, and environmental damage. Despite the availability of object-detection algorithms, challenges persist in detecting fires, smoke, and humans. These challenges include poor performance in detecting small fires and smoke, as well as a high computational cost, which limits deployments. In this paper, we propose an end-to-end object detector for fire, smoke, and human detection based on Deformable DETR (DEtection TRansformer) called FSH-DETR. To effectively process multi-scale fire and smoke features, we propose a novel Mixed Encoder, which integrates SSFI (Separate Single-scale Feature Interaction Module) and CCFM (CNN-based Cross-scale Feature Fusion Module) for multi-scale fire, smoke, and human feature fusion. Furthermore, we enhance the convergence speed of FSH-DETR by incorporating a bounding box loss function called PIoUv2 (Powerful Intersection of Union), which improves the precision of fire, smoke, and human detection. Extensive experiments on the public dataset demonstrate that the proposed method surpasses state-of-the-art methods in terms of the m A P (mean Average Precision), with m A P and m A P 50 reaching 66.7% and 84.2%, respectively. [ABSTRACT FROM AUTHOR]

Fire is a significant cause of fatalities and property loss. In tall spaces, early smoke dispersion is hindered by thermal barriers, and initial flames with limited smoke production may be obscured by ground-level structures. Consequently, smoke, temperature, and other fire sensor signals are weakened, leading to delays in fire detection by sensor networks. This paper proposes a multi-height and heterogeneous fusion discriminant model with a multilayered LSTM structure for the robust detection of weak fire signals in such challenging situations. The model employs three LSTM structures with cross inputs in the first layer and an input-weighted LSTM structure in the second layer to capture the temporal and cross-correlation features of smoke concentration, temperature, and plume velocity sensor data. The third LSTM layer further aggregates these features to extract the spatial correlation patterns among different heights. The experimental results demonstrate that the proposed algorithm can effectively expedite alarm response during sparse smoke conditions and mitigate false alarms caused by weak signals. [ABSTRACT FROM AUTHOR]

Copyright of Fire Ecology is the property of Springer Nature and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

Fluorine magnetic resonance imaging (19F-MRI) is particularly promising for biomedical applications owing to the absence of fluorine in most biological systems. However, its use has been limited by the lack of safe and water-soluble imaging agents with high fluorine contents and suitable relaxation properties. We report innovative 19F-MRI agents based on supramolecular dendrimers self-assembled by an amphiphilic dendrimer composed of a hydrophobic alkyl chain and a hydrophilic dendron. Specifically, this amphiphilic dendrimer bears multiple negatively charged terminals with high fluorine content, which effectively prevented intra- and intermolecular aggregation of fluorinated entities via electrostatic repulsion. This permitted high fluorine nuclei mobility alongside good water solubility with favorable relaxation properties for use in 19F-MRI. Importantly, the self-assembling 19F-MRI agent was able to encapsulate the near-infrared fluorescence (NIRF) agent DiR and the anticancer drug paclitaxel for multimodal 19F-MRI and NIRF imaging of and theranostics for pancreatic cancer, a deadly disease for which there remains no adequate early detection method or efficacious treatment. The 19F-MRI and multimodal 19F-MRI and NIRF imaging studies on human pancreatic cancer xenografts in mice confirmed the capability of both imaging modalities to specifically image the tumors and demonstrated the efficacy of the theranostic agent in cancer treatment, largely outperforming the clinical anticancer drug paclitaxel. Consequently, these dendrimer nanosystems constitute promising 19F-MRI agents for effective cancer management. This study offers a broad avenue to the construction of 19F-MRI agents and theranostics, exploiting self-assembling supramolecular dendrimer chemistry. [ABSTRACT FROM AUTHOR]

Timely identification of a fire's origin in its initial stages is essential for minimizing human as well as material losses. Hence, formulating a methodology and algorithm for autonomously planning the flight path of an unmanned aerial vehicle (UAV) during fire monitoring to identify ignition sources early is a pressing objective. The proposed ignition detection method comprises three flight plans (FPs); Flight Plan A (FPA) involves surveying the monitored area with tacks, and assessing harmful substance concentrations in each pixel. Upon identifying a pixel surpassing the threshold concentration, Flight Plan B (FPB) directs the UAV control for targeted navigation, employing local planning based on calculating local differential operators within a nine-element mask. FPB enables the UAV to directly reach and pinpoint the fire source coordinates. Flight Plan C (FPC) outlines the UAV's return journey to the departure point from any pixel within the monitoring zone. A multi-criteria algorithm for UAV flight path control has been devised, facilitating the determination of local target pixels and subsequent Local Flight Plan (LFP) construction. The guiding principle for constructing an LFP is the 'at least three pixels on the tack' rule, yielding a nine-element matrix with known harmful substance concentrations in the target pixel. It enables the identification of pixels within the LFP where obtaining this matrix is unattainable. Mathematical modelling of the UAV flight control algorithm, as per the proposed methodology, was executed using MATLAB® R2019b, demonstrating control stability and accelerated attainment of ignition source pixel coordinates. The achieved speed surpassed the set goal by 1.5 to 2 times, contingent on the ignition source's location concerning the monitored territory's flyby direction. [ABSTRACT FROM AUTHOR]

The development and performance of two mass spectrometry (MS) workflows for the intraoperative diagnosis of isocitrate dehydrogenase (IDH) mutations in glioma is implemented by independent teams at Mayo Clinic, Jacksonville, and Huashan Hospital, Shanghai. The infiltrative nature of gliomas makes rapid diagnosis necessary to guide the extent of surgical resection of central nervous system (CNS) tumors. The combination of tissue biopsy and MS analysis used here satisfies this requirement. The key feature of both described methods is the use of tandem MS to measure the oncometabolite 2-hydroxyglutarate (2HG) relative to endogenous glutamate (Glu) to characterize the presence of mutant tumor. The experiments i) provide IDH mutation status for individual patients and ii) demonstrate a strong correlation of 2HG signals with tumor infiltration. The measured ratio of 2HG to Glu correlates with IDH-mutant (IDH-mut) glioma (P < 0.0001) in the tumor core data of both teams. Despite using different ionization methods and different mass spectrometers, comparable performance in determining IDH mutations from core tumor biopsies was achieved with sensitivities, specificities, and accuracies all at 100%. None of the 31 patients at Mayo Clinic or the 74 patients at Huashan Hospital were misclassified when analyzing tumor core biopsies. Robustness of the methodology was evaluated by postoperative re-examination of samples. Both teams noted the presence of high concentrations of 2HG at surgical margins, supporting future use of intraoperative MS to monitor for clean surgical margins. The power of MS diagnostics is shown in resolving contradictory clinical features, e.g., in distinguishing gliosis from IDH-mut glioma. [ABSTRACT FROM AUTHOR]

Fire poses a significant threat to daily life, causing both economic and social harm. To mitigate these damages, early detection of fire and smoke is crucial, and this paper introduces a model employing vision-based techniques. The proposed model utilizes image processing and convolutional neural networks to detect fire and smoke, providing insights into their intensity and any changes in a video. The model comprises two units for fire and smoke detection, each employing image preprocessing techniques, including rule-based color detection and motion detection, along with CNN. The calculated percentages of fire and smoke in the processed images offer detailed information about the severity of the hazards in a specific area. The model detects whether the intensity of fire and smoke is increasing, decreasing or constant. [ABSTRACT FROM AUTHOR]

In many smoke detection fields, such as fire detection in confined space of aircraft cargo hold, the false alarm rate is still high. In the closed and dark environment of the confined space cabin, the traditional video smoke detection method is difficult to find the fire early because of the limitation of lighting conditions. The advantage of fire detection based on infrared video image is that it does not need lighting conditions and has better performance in dark environment. There is a rapid temperature rise process in the confined space at the beginning of the fire, which is more easily captured by infrared cameras. However, there is little research on infrared frame detection methods in confined space. Therefore, based on the limited space environment of aviation industry, this paper studies the smoke detection problem under the infrared framework, and proposes a high-precision fire and smoke image detection algorithm based on infrared double convolution neural network. By modeling the texture features of neural network and infrared smoke frames, and using video frames as an auxiliary means to increase the number of available training images, the problem of insufficient infrared video data sets is solved. The experimental results show that the detection effect of this method is better than other comparison algorithms in limited space, and the detection false alarm rate is effectively reduced. [ABSTRACT FROM AUTHOR]

Given the increasing prevalence of wildland fires in the Western US, there is a critical need to develop tools to understand and accurately predict burn severity. We develop a novel machine learning model to predict post-fire burn severity using pre-fire remotely sensed data. Hydrological, ecological, and topographical variables collected from four regions of California — the site of the Kincade fire (2019), the CZU Lightning Complex fire (2020), the Windy fire (2021), and the KNP Fire (2021) — are used as predictors of the differenced normalized burn ratio. We hypothesize that a Super Learner (SL) algorithm that accounts for spatial autocorrelation using Vecchia's Gaussian approximation will accurately model burn severity. We use a cross-validation study to show that the spatial SL model can predict burn severity with reasonable classification accuracy, including high burn severity events. After fitting and verifying the performance of the SL model, we use interpretable machine learning tools to determine the main drivers of severe burn damage, including greenness, elevation, and fire weather variables. These findings provide actionable insights that enable communities to strategize interventions, such as early fire detection systems, pre-fire season vegetation clearing activities, and resource allocation during emergency responses. When implemented, this model has the potential to minimize the loss of human life, property, resources, and ecosystems in California. [ABSTRACT FROM AUTHOR]

The implementation of early and accurate detection of aircraft cargo compartment fire is of great significance to ensure flight safety. The current airborne fire detection technology mostly relies on single-parameter smoke detection using infrared light. This often results in a high false alarm rate in complex air transportation environments. The traditional deep learning model struggles to effectively address the issue of long-term dependency in multivariate fire information. This paper proposes a multi-technology collaborative fire detection method based on an improved transformers model. Dual-wavelength optical sensors, flue gas analyzers, and other equipment are used to carry out multi-technology collaborative detection methods and characterize various feature dimensions of fire to improve detection accuracy. The improved Transformer model which integrates the self-attention mechanism and position encoding mechanism is applied to the problem of long-time series modeling of fire information from a global perspective, which effectively solves the problem of gradient disappearance and gradient explosion in traditional RNN (recurrent neural network) and CNN (convolutional neural network). Two different multi-head self-attention mechanisms are used to classify and model multivariate fire information, respectively, which solves the problem of confusing time series modeling and classification modeling in dealing with multivariate classification tasks by a single attention mechanism. Finally, the output results of the two models are fused through the gate mechanism. The research results show that, compared with the traditional single-feature detection technology, the multi-technology collaborative fire detection method can better capture fire information. Compared with the traditional deep learning model, the multivariate fire prediction model constructed by the improved Transformer can better detect fires, and the accuracy rate is 0.995. [ABSTRACT FROM AUTHOR]

Copyright of Fire Safety Science is the property of Fire Safety Science Editorial Office and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

The forest is a natural habitat for a variety of fauna and flora, and helps to maintain the ecosystem equilibrium. However, wildfire incidents and deforestation lead to forest degradation. Moreover, most of the existing methods, to preserve the forest resources, are ineffective due to their large establishment cost, more power consumption, and poor coverage. This paper brings out a sustainable solution by developing a forest protection system (FPS) that uses internet of things (IoT) technology together with long range (LoRa) communication. The work focuses on the development of an IoT framework for the detection of any intrusion into the forest as well as the detection of fire incidents in the vicinity of the equipment. Powering the equipment through solar energy makes the system cost-effective. The system is examined in terms of acquisition of data from sensor nodes pertaining to forest protection, relaying the same to the cloud using LoRa wide area network (LoRaWAN) technology and analyzing using cloud based visualization tools. The developed system has been deployed at Eturnagaram Wildlife Sanctuary, Mulugu district, Telangana, India for validation in the forest environment. The obtained results have shown that the system has an accuracy of 97.14% for intrusion detection and 100% for fire detection. [ABSTRACT FROM AUTHOR]

The central question of our study is which determinants drive smoke alarm ownership and intention to purchase one, and whether we can increase smoke alarm ownership by addressing these determinants in a communication‐based intervention. We first made an inventory of possible determinants for smoke alarm prevention by consulting prominent prevention behavior theories protection motivation theory and Health Belief Model and other relevant literature. We expanded this list of determinants based on interviews (n = 15) and used survey data representative for the Netherlands to decide to focus on smoke alarm ownership (rather than installation or maintenance). We then tested the determinants of smoke alarm ownership and buying intention in a survey (n = 622). Based on these results, we ran an A/B test (n = 310) of two messages to stimulate smoke alarm ownership: one emphasized the determinants we found to be strong predictors in the survey (know‐how, social norm, annoyance) and one emphasized typical determinants that are often addressed in campaigns but were poor predictors in the survey (vulnerability, severity, benefits). Results showed that the message based on the strong determinants resulted in a significant increase in smoke alarm ownership (9.1%) compared to the control group (0.9%; p = 0.027), while the message using the typical determinants did not lead to significant effects. Taken together, our results give a promising direction for interventions to increase smoke alarm ownership, and above all, show that a comprehensive problem analysis for a specific target behavior is a necessary step to induce behavioral change. [ABSTRACT FROM AUTHOR]

The introduction of hydrogen into the gas grid requires stricter safety measures due to its enhanced flammability compared to natural gas. Detecting small hydrogen leaks is crucial for meeting health and safety requirements, given hydrogen's potential for easy ignition and the hazards associated with its combustion. This paper presents an overview of the quantification of small hydrogen leaks, regarding conversions between common units of measurement, namely concentration and leak rate. In addition, the need for traceable assessments of hydrogen leakage was also considered, which included proposal of the design, calibration, and metrological evaluation of portable hydrogen reference leaks in the range of 10−6 to 10−4 Std cm3/s, the latter being considered as the lowest side of the range of interest for quantifying hydrogen leaks. Two methods of manufacturing leak artefacts, namely conductance and permeation, are explored, and the produced leaks were used to test two hydrogen leak detectors with different working principles. A calibration technique based on a constant pressure gas flowmeter is described together with the uncertainty budget. The study provides insights into the challenges of calibrating detectors for hydrogen leaks, highlighting the importance of traceability in ensuring safety and environmental protection in the context of hydrogen infrastructure. It was demonstrated that reference leaks are highly suitable to test hydrogen leak detectors in the mentioned flow range due to their simplicity, high reliability, low depletion rate and high portability. • Traceability of small hydrogen leaks is challenging. • Reference leaks allow quantitative testing of hydrogen leak detectors. • Designs for the construction of hydrogen reference leaks are disclosed. • Hydrogen reference leaks can be calibrated by a constant pressure gas flowmeter. • Linearity and reproducibility of hydrogen leak detector was assessed. [ABSTRACT FROM AUTHOR]

Fire is a dangerous and unwanted calamity that can destroy properties and lives in forest and urban areas within a few minutes. The effects of which may not be reversible. Therefore, computer vision-based methods can be essential in early fire detection tasks. But existing approaches combining computer vision and deep learning based methods are unsuitable for memory-constrained surveillance devices(CCTV and IP Sensors) with low computational power. This necessitates generating an automated system that can detect and localize this anomaly suitable for such small devices. Hence, this article proposes a custom framework of novel FireDL for fire detection and localization. The proposed FireDL is a lightweight model with 2.2 million parameters only. When trained on the same datasets, FireDL is eight times lighter than VGG16 and six times lighter than the Densenet121. The FireDL model comprises two modules: one for feature extraction containing four blocks of convolutions and the second for classification containing one block of fully connected layers. The experiments were conducted on two named Set 1(DeepFire) and Set 2(self-created using Foggia, Ko et al., etc.). It attained an accuracy of 97.63% on Set 1 and 99.82% on Set 2. Extensive experiments performed on Set 1 and Set 2 confirm its reliability for a real-world scenario. [ABSTRACT FROM AUTHOR]

This study explores the analysis of hydrogen gas from a distance using a Raman lidar spectrometer. Hydrogen gas is a flammable gas with risk of explosion, making accurate and quick detection crucial. In this study, we evaluated the performance of a Raman lidar spectrometer for detecting hydrogen gas from a distance. Experiments were conducted at distances of 1, 3, 5, 10, 20, and 30 m. To assess the long-range measurement capability at various hydrogen concentrations, we analyzed the accuracy and sensitivity. The findings suggest that the sensor can perform quick and accurate detection even at low concentrations, maintaining high sensitivity at a distance. Thus, Raman lidar spectrometers are promising for real-time remote detection of hydrogen gas. This study provides guidance for the effective utilization of Raman lidar sensors for hydrogen gas detection and monitoring in diverse application areas such as industrial fire prevention, safety management, environmental monitoring, and energy production. • We propose a rapid and accurate method for detecting hydrogen gas at long distances using Raman LIDAR spectrometers. • Exploring the critical applications in safety management and fire prevention due to the explosive nature of hydrogen gas. • Evaluating Raman LIDAR spectrometer performance at distances ranging from 1 m to 30 m while maintaining high sensitivity. • Demonstrating the capability to swiftly and precisely detect even low concentrations of hydrogen gas and providing essential guidelines for long-range hydrogen gas analysis using Raman LIDAR spectrometers. • Raman LIDAR spectrometers in various fields, including industrial settings, environmental monitoring, and energy production. [ABSTRACT FROM AUTHOR]

Smoke detectors face the challenges of increasing accuracy, sensitivity, and high reliability in complex use environments to ensure the timeliness, accuracy, and reliability of very early fire detection. The improvement and innovation of the principle and algorithm for smoke particle concentration detection provide opportunities for improving the performance of the detector. This study represents a new refinement of the smoke concentration detection principle based on capacitive detection of cell structures, and detection signals are processed by a multiscale smoke particle concentration detection algorithm to calculate smoke concentration. Through experiments, it was found that the detector provides effective detection of smoke particle concentrations ranging from 0 to 10% obs/m; moreover, when the detection accuracy is greater than a certain number of parts per million (PPM), the sensitivity of the detector can reach the PPM level; furthermore, the detector can detect smoke particle concentrations higher than the PPM level accuracy even in an environment with a certain concentration of petroliferous and dust particles of different sizes. [ABSTRACT FROM AUTHOR]

To improve the power generation efficiency of offshore wind turbines and address the problem of high fire monitoring and warning costs, we propose a data-driven fire warning method based on transfer learning for wind turbines in this paper. This paper processes wind turbine operation data in a SCADA system. It uses an extreme gradient-boosting tree (XGBoost) algorithm to build an offshore wind turbine unit fire warning model with a multiparameter prediction function. This paper selects some parameters from the dataset as input variables for the model, with average cabin temperature, average outdoor temperature, average cabin humidity, and average atmospheric humidity as output variables. This paper analyzes the distribution information of input and output variables and their correlation, analyzes the predicted difference, and then provides an early warning for wind turbine fires. This paper uses this fire warning model to transfer learning to different models of offshore wind turbines in the same wind farm to achieve fire warning. The experimental results show that the prediction performance of the multiparameter is accurate, with an average MAPE of 0.016 and an average RMSE of 0.795. It is better than the average MAPE (0.051) and the average RMSE (2.020) of the prediction performance of a backpropagation (BP) neural network, as well as the average MAPE (0.030) and the average RMSE (1.301) of the prediction performance of random forest. The transfer learning model has good prediction performance, with an average MAPE of 0.022 and an average RMSE of 1.469. [ABSTRACT FROM AUTHOR]

This paper addresses the challenge of training deep learning models for fire smoke scene detection from multi-sensor, multi-spectral satellite imagery, where spectral bands vary and training data is scarce, especially for new sensors. We introduce a novel cross-sensor transfer learning approach enhanced by spectral pattern extraction, notably aided by a deep learning (DL) module called Input Amplification (IA). Our contribution includes the creation of two datasets, Landsat_smk2770 and Sentinel2_smk, with varying spectral bands. We employ a model named IA_VIB_SD which incorporates IA and is designed specifically for fire smoke scene detection. We investigated the transferability of the Landsat_smk2770-trained IA_VIB_SD model to the Sentinel2_smk dataset using various transfer learning techniques, and compared the performance of the transferred model with the benchmark IA_VIB_SD model exclusively trained on pure Sentinel2_smk data. Our proposed transfer learning approach resulted in a transferred model with an average accuracy 5% higher than the benchmark model. Notably, Our proposed transfer learning approach outperformed existing transfer learning methods by more than 1% in terms of the accuracy, even when trained on a mere 10% of the Sentinel2_smk dataset. This research advances fire smoke scene detection from multi-sensor, multi-spectral satellite imagery. [ABSTRACT FROM AUTHOR]

Fire is one of the most harmful hazards that affect daily life. The existing fire detection methods have the problems of large computation, slow detection speed, and low detection accuracy to varying degrees, and do not achieve a better trade-off between model complexity, accuracy, and detection speed. In this paper, a multiscale fire image detection method combining Convolutional Neural Network(CNN) and Transformer is proposed. In the shallow layer of the model, the CNN-based multiscale feature extraction module is used to obtain rich fire image information. In the deep layers of the model, the powerful global learning ability of the Transformer is used to carry out overall perception and macroscopic understanding of images. The experimental results show that the best detection accuracy of the model can reach 94.62%, and the fastest detection speed can reach 158.12FPS, F1 score is stable at around 94%, which is fully capable of real-time and accurate detection of fire. Compared with the existing detection methods, this method has higher detection accuracy under similar model complexity and detection speed. With similar detection accuracy, our method has a faster detection speed. The proposed method achieves a better balance between model complexity, detection speed, and accuracy. [ABSTRACT FROM AUTHOR]

The early detection of wildfires is a crucial challenge in environmental monitoring, pivotal for effective disaster management and ecological conservation. Traditional detection methods often fail to detect fires accurately and in a timely manner, resulting in significant adverse consequences. This paper presents FireXplainNet, a Convolutional Neural Network (CNN) base model, designed specifically to address these limitations through enhanced efficiency and precision in wildfire detection. We optimized data input via specialized preprocessing techniques, significantly improving detection accuracy on both the Wildfire Image and FLAME datasets. A distinctive feature of our approach is the integration of Local Interpretable Model-agnostic Explanations (LIME), which facilitates a deeper understanding of and trust in the model's predictive capabilities. Additionally, we have delved into optimizing pretrained models through transfer learning, enriching our analysis and offering insights into the comparative effectiveness of FireXplainNet. The model achieved an accuracy of 87.32% on the FLAME dataset and 98.70% on the Wildfire Image dataset, with inference times of 0.221 and 0.168 milliseconds, respectively. These performance metrics are critical for the application of real-time fire detection systems, underscoring the potential of FireXplainNet in environmental monitoring and disaster management strategies. [ABSTRACT FROM AUTHOR]

Forest fire is natural disasters that are sudden, destructive and difficult to handle and rescue, with millions of hectares of forests burned every year all over the world, causing serious ecological damage, loss of life and property. Therefore, timely detection and treatment of early fire is of positive and important significance for forest fire early control. The fire detection method based on image processing is one of the most important means of preventing the occurrence of large-scale forest fires at present by extracting the flame and smoke features in the image and quickly determining the location of the fire. The current deep learning-based forest fire early detection methods have problems such as high false alarm rate due to small detection targets and complex environmental background, and large number of detection model parameters. In view of this, this paper proposes a lightweight early forest fire and smoke detection method based on GS-YOLOv5. Firstly, this paper proposes a novel Super-SPPF structure to replace the SPPF structure in YOLOv5, by which the output of the feature extraction network is used as input, and the input is divided into two branches to retain more semantic information, and the GhostConv operation is performed separately to reduce the number of model parameters. The Super-SPPF structure performs the serial MaxPooling operation on one of the branches, which improves the computation speed by choosing a smaller pooling kernel, and then fuses the outputs of the two branches to reduce the false alarm rate of the detection model. Secondly, C3Ghost is utilized instead of the C3 module in YOLOv5 to further reduce the number of detection model parameters. Finally, the coordinate attention (CA) module is introduced in backbone of YOLOv5 to obtain the relationship between channels and space, which enables the network to obtain the location information of interest more accurately and further improves the detection accuracy of early fires. In this paper, a self-constructed DL-Fire dataset is used to verify the performance of the GS-YOLOv5 detection model by collecting environmental interference samples and combining them with the D-Fire dataset. The experimental results show that the detection accuracy of GS-YOLOv5 is 95.9%, and the model size is 10.58 mb. Compared with YOLOv5, false alarm rate is reduced from 12% to 6% and computational complexity is reduced from 16.0 GFlops to 12.8 GFlops by GS-YOLOv5. [ABSTRACT FROM AUTHOR]

The article reviews issues associated with the operation of stationary and non-stationary electronic fire alarm systems (FASs). These systems are employed for the fire protection of selected buildings (stationary) or to monitor vast areas, e.g., forests, airports, logistics hubs, etc. (non-stationary). An FAS is operated under various environmental conditions, indoor and outdoor, favourable or unfavourable to the operation process. Therefore, an FAS has to exhibit a reliable structure in terms of power supply and operation. To this end, the paper discusses a representative FAS monitoring a facility and presents basic tactical and technical assumptions for a non-stationary system. The authors reviewed fire detection methods in terms of fire characteristic values (FCVs) impacting detector sensors. Another part of the article focuses on false alarm causes. Assumptions behind the use of unmanned aerial vehicles (UAVs) with visible-range cameras (e.g., Aviotec) and thermal imaging were presented for non-stationary FASs. The FAS operation process model was defined and a computer simulation related to its operation was conducted. Analysing the FAS operation process in the form of models and graphs, and the conducted computer simulation enabled conclusions to be drawn. They may be applied for the design, ongoing maintenance and operation of an FAS. As part of the paper, the authors conducted a reliability analysis of a selected FAS based on the original performance tests of an actual system in operation. They formulated basic technical and tactical requirements applicable to stationary and mobile FASs detecting the so-called vast fires. [ABSTRACT FROM AUTHOR]

Wildland fires cause economic and ecological damage with devastating consequences, including loss of life. To reduce these risks, numerous fire detection and recognition systems using deep learning techniques have been developed. However, the limited availability of annotated datasets has decelerated the development of reliable deep learning techniques for detecting and monitoring fires. For such, a novel dataset, namely, SWIFT, is presented in this paper for detecting and recognizing wildland smoke and fires. SWIFT includes a large number of synthetic images and videos of smoke and wildfire with their corresponding annotations, as well as environmental data, including temperature, humidity, wind direction, and speed. It represents various wildland fire scenarios collected from multiple viewpoints, covering forest interior views, views near active fires, ground views, and aerial views. In addition, three deep learning models, namely, BoucaNet, DC-Fire, and CT-Fire, are adopted to recognize forest fires and address their related challenges. These models are trained using the SWIFT dataset and tested using real fire images. BoucaNet performed well in recognizing wildland fires and overcoming challenging limitations, including the complexity of the background, the variation in smoke and wildfire features, and the detection of small wildland fire areas. This shows the potential of sim-to-real deep learning in wildland fires. [ABSTRACT FROM AUTHOR]

This work concerns how to effectively detect the fire in early stage using computer vision method. As known, the flame of early fire is small and cannot be effectively detected by traditional fire detectors. Inspired by color characteristics of flame, we proposed a Shallow Guide Deep Network (SGDNet) to address the problems in existing early fire detection models. We first investigate the feature of fire in YCbCr color space, then design an SGD module to fuse shallow features, so as to guide the fusion of deep features. Backbone, anchors, head and IoU of model are redesigned according to the features of early fire to not only fuse the deep features but also reduce the size and infer time. Finally, we implement a Early Stage Fire Detection System based on our SGDNet, using embedded device as computing platform, connecting 4 IP cameras for test. Multithread is widely utilized in system for detecting and the reading and conversion operations of video streams, which effectively improves the execution efficiency and reduces the delay of system. Experimental results on dataset show high performance of our model with the advantage of small size and parameter. Application in actual scenarios proves that the delay for detection is about 1.2 s, which fulfills the requirement of early fire warning. [ABSTRACT FROM AUTHOR]

Dementia is a clinical illness that becomes more common as people get older. It is defined by a decline in cognitive abilities across several domains and eventually impacts everyday functioning. Consequently, this leads to a decline in autonomy, impairment, dependence on assistance even criminal tendencies/insecure behaviors and ultimately, the disease frequently results in mortality. Particularly with regard to neurodegenerative disorders, various forms of dementia are correlated with criminal activity. According to research, criminal and socially inappropriate behavior is prevalent among dementia patients and is sometimes the initial symptom of the disease. Alzheimer's Disease (AD) is responsible for 60-80% of all occurrences of dementia, and its occurrence increases double every five years beyond the age of 65. Given the availability of health data and the decrease in data processing costs, it is now feasible to detect Alzheimer's disease at an early stage. The objective of this study is to classify individuals as either Alzheimer's sufferers or healthy individuals by employing various machine learning techniques. The "OASIS-2 dataset", which consists of "longitudinal MRI data" from both nondemented and demented older adults, was utilized for this study. Given its potential for early detection of Alzheimer's dementia, the study is anticipated to enhance clinical decision support systems pertaining to modifiable risk factors. [ABSTRACT FROM AUTHOR]

With the growth of open areas comes an ever-increasing risk of fire. However, there is a problem with the present approaches to fire detection, which rely on smoke sensors for wide regions. The advent of video surveillance systems has greatly improved our ability to detect smoke and flames coming from a distance and reduced this risk. Point sensors are slower at detecting fires than cameras when image processing is used. Moreover, using this video and image data presents processing challenges due to the enormous volume of data involved. Several approaches have recently been put forth to address this issue and distinguish between fire and smoke. Earlier methods included image processing algorithms for flame and smoke detection as well as motion-based estimation of smoke. Recently, a variety of techniques have been put forth using deep learning and convolutional neural networks (CNNs) to predict and automatically identify fire and smoke in videos and images. In this study, we review previous studies of fire/smoke detection systems based on machine vision and deep learning. The foundations of image processing techniques, CNN, and their applicability to video smoke and fire detection are explained. A discussion of current data sets and an overview of recent methods applied in this field The difficulties and potential solutions for advancing the application of CNN in this field are discussed. Then a comparison for researchers in the last years based on the dataset, year, technique, limitation, and accuracy they got The CNNs have been found to have a high potential for detecting open areas, and improved development can help create a system that would significantly reduce the loss of human life and property. Remarks for future work were concluded. [ABSTRACT FROM AUTHOR]

Early fire identification is critical to saving lives and property. One viable strategy for improving fire detection systems' efficacy and precision is the use of Internet of Things (IoT) technology. This article details research into the conception and development of an IoT, ESP32-based, Arduino MEGA-connected smart pre-alert detection system for fires. Because of its flexible nature, the Arduino microcontroller can easily exchange data with various sensors for real-time monitoring and analysis. This study surveys the existing literature to provide insight into many approaches to early fire detection (forecasting), such as sensor fusion methods and the use of the intelligence concept as a pre-predictor. The research highlights the need to set up sophisticated fire monitoring and alarm systems and to develop predictive models based on sensor data. This study illustrates how embedded systems via IoT technology and the ESP32 architecture may improve the efficiency and dependability of very early fire detection systems. This research adds to the expanding corpus of information that may be used to improve fire safety in contemporary settings. The proposal's sensors include an Arduino MEGA, an ESP32, a MAX6675 module, an MQ-Smoke, and an MQ-Natural Gas for collecting data, which are then processed using Cloud Firebase and a sleek mobile interface that can be reached overseas at any time. [ABSTRACT FROM AUTHOR]

Fire is a common but serious disaster, which poses a great threat to human life and property. Therefore, fire-smoke detection technology is of great significance in various fields. In order to improve the detection ability of tiny-fire, so as to realize the prediction and suppression of fire as soon as possible, we proposed an efficient and accurate tiny-fire detection method based on the optimized YOLOv7, and we named the improved model YOLOv7-FIRE. First, we introduced the BiFormer into YOLOv7 to make the network pay more attention to the fire-smoke area. Second, we introduced the NWD technique to enhance the perception of the algorithm for small targets, and provided richer semantic information by modeling the context information around the target. Finally, CARAFE was applied for content-aware feature reorganization, which preserved the details and texture information in the image and improved the quality of fire-smoke detection. Furthermore, in order to improve the robustness of the improved algorithm, we expanded the fire-smoke dataset. The experimental results showed that YOLOv7-FIRE as significantly better than the previous algorithm in detection accuracy and recall rate, the Precision increased from 75.83% to 82.31%, and the Recall increased from 66.43% to 74.02%. [ABSTRACT FROM AUTHOR]