Search Results (277)

Interagency collaboration is fundamental to search and rescue (SAR) operations, bringing together police, volunteers, fire services, paramedics, and other responders to locate missing persons and save lives. Although collaboration is recognized as beneficial to operational effectiveness, little is known about how collaborative work shapes responders’ occupational experiences. Drawing on qualitative data from 406 police and SAR volunteer personnel, this study explores how interagency collaboration both supports and challenges those involved in missing persons SAR responses. Findings identified collaboration as a critical operational resource that expanded personnel capacity, strengthened decision-making, improved access to specialized expertise, facilitated knowledge sharing, and enhanced SAR effectiveness. Yet also, participants described collaboration as a source of occupational strain. Role ambiguity, delayed activation, communication difficulties, competing organizational priorities, authority and legitimacy tensions, and inconsistent recognition of expertise created frustration, stress, and additional coordination demands for both police and volunteers. Findings suggest that collaboration should be understood as both an operational necessity and an important component of the occupational environment in which SAR personnel work/volunteer. These findings have important implications for strengthening interagency collaboration and supporting responder well-being. Full article

Reliable fire detection is essential for ensuring the safe operation of power distribution substations. This study proposes a fire recognition framework for substation surveillance environments. First, an illumination adaptation module is introduced to enhance feature representation under varying illumination conditions. Second, an adaptive spatial feature extraction framework is developed to jointly capture local smoke patterns and large-scale diffusion structures. Third, an illumination-aware classification loss is proposed to explicitly incorporate illumination information into the optimization process, thereby improving recognition performance under challenging illumination conditions. Experimental results demonstrate that the proposed framework achieves superior recognition performance compared with representative vision models while maintaining competitive inference efficiency, highlighting its practical applicability to substation surveillance. Full article

Automated power-worksite monitoring requires accurate event recognition and auditable explanations. This paper presents PowerXGraph++, a regulation-constrained spatiotemporal evidence-graph framework for missing PPE, boundary crossing, unsafe proximity, falls, and fire/smoke. Typed evidence tokens are encoded by a transformer; full-context prediction is separated from explanation selection, and explanations are tested for sufficiency, necessity, sparsity, and regulation consistency. Distillation, event-boundary counterfactuals, background-invariance training, and non-inferiority checkpoint selection preserve predictive performance. On annotation-derived construction-PPE graphs, three-seed Macro-F1, violation recall, and rationale F1 were 0.989, 0.965, and 0.901. Under the same frozen predictor, the supervised, grammar-aware selector attained rationale F1 of 0.983 and regulation consistency of 1.000, although the post hoc baselines lacked equivalent supervision. A single YOLO reproduction run using seed 17 on 197 matched person graphs yielded Macro-F1 of 0.844, missing-PPE recall of 0.591, and rationale F1 of 0.660. Expert evaluation produced Fleiss’ kappa of 0.740 and method-to-majority rationale F1 of 0.870. Held-out-camera reasoning and a two-camera fence-crossing pilot provide additional evidence under supplied-evidence conditions; the results do not establish automatic generation of every semantic predicate or unrestricted raw video performance. Full article

Fire regimes are changing globally, yet dominant fire governance remains centred on emergency response and suppression, often neglecting fire’s ecological functions and cultural significance. Although community-based burning practices persist across many fire-dependent landscapes, particularly in Africa, they rarely receive institutional recognition or appropriate governance. Integrated Fire Management and Community-Based Fire Management frameworks have called for bottom-up approaches that integrate biological, environmental, and social dimensions while prioritising local governance and customary fire practices. However, practical mechanisms for eliciting socio-cultural values, operationalising participation, and addressing power asymmetries in fire decision-making remain limited. This article documents the application of Legislative Theatre as a participatory approach to co-develop an Integrated Fire Management plan in eastern Angola. Through 37 stories based on lived experiences and collective, performance-based exercises exploring fire-related problems across seven villages, communities articulated diverse fire uses, values, and shared norms for improving local fire governance. Our findings show that theatre-based methods enabled the expression of embodied, emotional, and experiential knowledge often overlooked by conventional engagement approaches, while supporting knowledge co-production and participant agency. We argue that Legislative Theatre and storytelling provide practical tools for strengthening the socio-cultural dimensions of Integrated Fire Management, provided they are carefully facilitated, culturally adapted, and supported through long-term engagement. Full article

Early and reliable fire and smoke detection is essential for forest-fire warning and emergency response, especially in UAV-view and complex-background imagery, where small fire spots and diffuse smoke are easily affected by illumination variations and visually similar high-brightness or cloud- and fog-like backgrounds. To address these challenges, this paper formulates early fire and smoke recognition as a bounding-box detection task and proposes a Detail–Scale–Context Detection Network, named DSC-Det. DSC-Det is designed as a lightweight one-stage detection network and introduces three task-oriented components: a Detail–Context Downsampling Module (DCDM) for reducing information loss during early feature compression, a Dynamic Dual-Branch Fusion Module (DDFM) for adaptive multi-scale feature interaction under complex backgrounds, and a Shared-Regression Asymmetric Classification Head (SACH) for improving classification adaptation across feature layers while maintaining shared regression. Experiments on a constructed forest-fire-oriented fire and smoke dataset for UAV-view and complex-background monitoring scenes show that DSC-Det achieves 90.1% $\mathit{mAP}{@}_{0.5}$ and 66.9% $\mathit{mAP}{@}_{0.5:0.95}$, outperforming the lightweight reference detector by 2.3% and 4.4%, respectively. The results demonstrate that DSC-Det improves early forest-fire and smoke detection with controlled model complexity. Full article

Background/Objectives: This paper focusses on the use of artificial intelligence (AI) in automated firearm and ammunition identification. It concentrates on firing pin impressions on fired cartridge cases and secondary rifling land impressions on fired bullets, since these traces represent two different problems in forensic ballistic comparison. The main question was whether machine learning and deep learning methods can support the comparison process while the final assessment remains in the hands of the firearms examiner. Methods: This study combines a critical methodological analysis of AI-based firearm identification with applied experimental results. A convolutional neural network (CNN) was used for firing pin mark classification, the reliability of which was assessed using output neuron parameters A1, A1/A2, and A1−A2. For bullet marks, CNN-based semantic binarization was applied to secondary rifling land impressions, followed by random forest classification of the binarized image pairs. Data augmentation was used to address the limited number of original training objects in this study. Results: Considering the three highest CNN output signals increased the overall firing pin classification accuracy from 82.6% to 92.8%, while the accuracy for unknown-class marks increased from 60.8% to 79.1%. CNN-based binarization of bullet marks achieved accuracy = 0.88 ± 0.05, recall = 0.76 ± 0.06, precision = 0.83 ± 0.06, F1 = 0.79 ± 0.05, and MCC = 0.71 ± 0.06. The random forest classification of binarized bullet mark pairs achieved an accuracy of approximately 84–86%. Conclusions: The findings indicate that AI can improve speed, consistency, candidate selection, image preprocessing, and reliability assessment in forensic ballistics. However, AI outputs remain dependent on dataset quality, firearm and ammunition variability, unknown class recognition, and external validation. The most reliable model is a hybrid human–AI workflow in which the algorithm supports the firearms examiner but does not replace expert judgement. Full article

In recent years, unmanned aerial vehicles (UAVs) have gradually become an important tool for forest fire monitoring due to their flexibility and wide-area observation capability. However, existing detection algorithms still struggle to achieve a balance between computational complexity and detection performance in diverse background conditions, and data for such scenarios remain limited. Therefore, this paper proposes a lightweight forest fire smoke detection model based on YOLOv10n. Specifically, we introduce the RepViTBlock module to enhance smoke feature extraction and improve detection accuracy with low computational cost. Meanwhile, we design a Lightweight Efficient Convolutional Detection head (LECD), which improves smoke target recognition and localization while reducing the number of parameters and computational overhead of the detection head. We also adopt the Minimum Point Distance Intersection over Union (MPDIoU) as the bounding-box regression loss function to improve the localization accuracy of smoke bounding-box regression. In addition, we construct a UAV-perspective Forest Fire Smoke (UFFS) dataset, which contains typical forest fire smoke, nearby thin smoke, distant small-scale smoke, and smoke under diverse background conditions. Experiments were conducted on both the UFFS dataset and the Wildfire Smoke V1 dataset. The experimental results show that, compared with the baseline model, the proposed model reduces the number of parameters by 36.7% and GFLOPs by 42.3% on the UFFS dataset, while improving mAP50 by 1.3% and mAP50-95 by 3.7%. In addition, recall increases by 3.2% and precision increases by 3.6%, indicating an improved trade-off between detection accuracy and model complexity. Full article

The increasing deployment of lithium-ion batteries in electromobility, industrial logistics, and stationary energy storage systems has introduced new operational safety challenges associated with thermal runaway, fire development, and the release of hazardous substances. Although significant attention has been devoted to battery design and fire suppression technologies, less emphasis has been placed on the development of integrated monitoring systems capable of identifying abnormal thermal behaviour during routine storage and handling operations. This paper presents an operational framework for the early detection of thermal anomalies in lithium-ion battery storage facilities based on the integration of thermal imaging technology, multi-level alarm logic, automated notification processes, and predefined response procedures. The proposed framework was developed using a risk-based approach and implemented within an industrial environment where lithium-ion batteries and battery modules are routinely stored and handled. The methodology included hazard identification, determination of critical monitoring zones, configuration of thermal detection devices, establishment of alarm thresholds, and integration with existing fire protection infrastructure. Particular attention was devoted to ensuring rapid identification, localization, verification, and escalation of abnormal thermal conditions before the occurrence of visible fire manifestations. The implemented monitoring framework comprised a total of 21 thermal imaging cameras, including four fixed radiometric thermal imaging cameras and seventeen local thermal monitoring cameras, covering five risk-prioritized monitoring zones within an industrial lithium-ion battery storage facility. During operational deployment, the system recorded 21 Yellow Alerts, 6 Red Alerts, and 4 false alarms, with an average response time of 4.2 min. Experimental verification further demonstrated that, although directly exposed battery modules were measured at approximately 60 °C, enclosure within the battery pack significantly attenuated the externally detectable thermal signature, with surface temperatures decreasing to approximately 23–31 °C after prolonged enclosure. The results demonstrate that the proposed framework enables continuous operational monitoring, supports timely identification of abnormal thermal behaviour, and provides a structured basis for rapid decision-making and emergency response in industrial lithium-ion battery storage facilities. The integration of thermal monitoring with structured alarm management and response procedures creates a comprehensive safety chain that contributes to reducing the probability of delayed incident recognition. The presented approach provides practical guidance for industrial operators seeking to improve lithium-ion battery safety and may serve as a foundation for the future development of operational safety requirements for battery storage facilities. The principal contribution of this study is the documented implementation and operational evaluation of an integrated thermal monitoring and response system under routine automotive production conditions. Full article

Ceramic production generates large quantities of fired waste that is durable, non-biodegradable, and increasingly difficult to manage through conventional waste disposal practices. This study analyzes how ceramic waste is transformed into sustainable value in Jingdezhen, China, a city where ceramic production and cultural heritage have developed over more than a millennium. Using a qualitative multiple-case design, this study examines representative cases from three ceramic waste reutilization pathways: industrial reuse, environment-oriented reuse, and craft-based artistic reuse. The analysis shows that ceramic waste creates sustainable value through three interconnected processes: material transformation, economic activation, and cultural re-signification. Industrial cases primarily promote resource recovery and product innovation; public and environmental projects improve environmental awareness by integrating ceramic waste into urban spaces; and artistic practices reinterpret discarded ceramics as a medium for historical reflection, cultural expression, and public engagement. Based on these findings, the study proposes a material economic cultural analytical framework that explains how these value dimensions interact to transform ceramic waste from an environmental burden into a strategic resource. This study goes beyond documenting feasible ceramic waste recycling models by demonstrating that effective circular resource management in heritage-based industrial regions depends not only on technical recycling practices but also on cultural connotations and public recognition, which, together, generate value across environmental, economic, and cultural significance. These findings extend the scope of circular economy research by demonstrating a viable pathway for heritage-based industrial regions to leverage their own cultural heritage in transforming ceramic waste into environmental, economic, and cultural value. They also provide a practical model for other heritage-based regions seeking to align waste management with sustainable development. Full article

Accurate detection in the early stages of a fire is a crucial prerequisite for the efficient implementation of fire suppression and emergency rescue operations. Its accuracy and timeliness directly affect the control of disaster loss severity. Traditional fire detection methods mainly include three categories, which are manual inspection, sensor detection, and visual recognition. However, manual inspection is restricted by labor costs and time efficiency, making it difficult to achieve large-scale, high-frequency and real-time fire monitoring. Sensor detection is easily interfered by environmental factors such as temperature, humidity, and dust, leading to frequent false alarms and missed alarms. Visual recognition technology has shortcomings in aspects such as detailed feature perception, dynamic scene modeling, and reasoning robustness in complex environments, making it difficult to meet the requirements of high-precision detection. To address these issues, this study innovatively proposes a lightweight fire and smoke detection model based on semantic enhancement and frequency domain perception modeling, which is named the SemaFire you only look once (SemaFire-YOLO) model. The model constructs a large language and vision assistant (LLaVA) semantic guidance module, which uses a large language model to understand and guide the semantic features of images, thereby enhancing the saliency representation intensity of small and weak target regions. Then, a Haar wavelet-based downsampling module is adopted, which compresses spatial information while preserving high-frequency features such as flame edges and smoke textures, improving the accuracy of target recognition. Next, the convolution modulation mechanism is introduced to replace the traditional attention mechanism, enhancing the overall modeling efficiency and reducing computational overhead. Finally, a Dynamic Tanh normalization module is adopted to replace the batch normalization module in the traditional YOLO algorithm, strengthening the model’s representation stability and reasoning robustness under unstable input distributions. Experimental results show that the SemaFire-YOLO model achieves a mean average precision (mAP@0.5) of 64.30% on the fire image dataset, which is 0.8, 2.0, 0.6, and 3.8 percentage points higher than that of mainstream models such as YOLOv5n, YOLOv8n, YOLOv11n, and YOLOv12n, respectively. It exhibits better boundary detection capability and practical deployment potential. Through visual analysis, the results indicate that the improved SemaFire-YOLO model achieves more accurate detection and higher confidence in actual complex scenarios, further verifying the model’s robustness and accuracy in complex scenarios such as low contrast and dynamic fire conditions. Full article

Automated compliance checking for building fire protection design requires accurate extraction of domain-specific entities from technical code provisions. However, building fire protection codes contain highly specialized terminology, hierarchical clause structures, and complex regulatory semantics, which make manual information extraction time-consuming and error-prone. This study develops a domain-specific named entity recognition approach for Chinese building fire protection design codes. An expert-annotated dataset was constructed from five representative codes, containing 2748 annotated provisions and 13,877 entity mentions across nine entity categories. A RoBERTa-BiLSTM-CRF model was then developed to capture contextual semantic representations, bidirectional sequence dependencies, and label-transition constraints. Results suggest that the proposed model achieves 88.34%, 88.31%, and 88.32% for precision, recall, and F1-score, respectively. The extracted entities can be organized into structured and traceable records, providing a foundation for downstream building fire protection knowledge management and automated compliance checking. Full article

Early and reliable detection of forest fires is essential for reducing environmental damage and ensuring public safety. Deep learning-based object detection enables automated fire monitoring across heterogeneous sensing platforms, including satellite, Unmanned Aerial Vehicle (UAV), and ground-based imaging systems. However, differences in spatial resolution, viewing geometry, and computational constraints present challenges for developing unified detection models. This study presents a comparative benchmarking analysis of the lightweight YOLOv26-nano model for forest fire detection using the FASDD dataset, comprising satellite, UAV, and ground-based imagery. A unified experimental protocol with five-fold cross-validation is adopted to ensure robustness and cross-platform generalization. Performance is enhanced through data augmentation, contrast-limited adaptive histogram equalization, and stochastic gradient descent optimization. Experimental results demonstrate that YOLOv26-nano achieves reliable detection accuracy and demonstrates promising computational characteristics under simulated resource-constrained edge-computing conditions. The proposed benchmarking framework provides a standardized reference for multi-platform fire detection and highlights the suitability of nano-scale object detection models for scalable wildfire monitoring and early-warning systems. Full article

Conventional fire monitoring systems frequently exhibit high false alarm rates, delayed response times, and a lack of closed-loop control capabilities, which severely constrain their deployment in complex real-world environments. To address these issues, this paper proposes an embedded fire detection, tracking, and extinguishing system based on multimodal information fusion and a lightweight neural model. The system follows a “Perception–Decision–Execution–Feedback” closed-loop paradigm and is implemented on a heterogeneous cooperative computing architecture comprising OpenMV4 H7 Plus and STM32F103C8T6 microcontrollers. The perception layer implements a decision-level RGB-infrared fusion mechanism that incorporates a pruned, INT8-quantized lightweight FOMO model, enabling real-time fire detection with an inference latency of 210 ms and a model size of merely 1.8 MB under resource-constrained embedded conditions. The decision layer employs a Bayesian inference-based multimodal fusion framework that effectively suppresses spurious fire interference. The vision-only false detection rate is 15.3%. After infrared fusion verification, the system-level false alarm rate is reduced to 2.0% on the interference test set. In the execution layer, a sixth-degree polynomial jet trajectory model was established and combined with an improved PID–PI dual-loop controller to enable dynamic optimization of spray angle and flow rate in real time. Experimental results demonstrate that the proposed system achieves an average fire recognition accuracy of 95.6% with a false alarm rate as low as 1.4%. Furthermore, it realizes an extinguishing accuracy better than ±5 cm within an effective operating range of 10–60 cm and completes the entire perception-to-extinguishing cycle within 8.5 s under illumination conditions ranging from 50 to 100,000 lux. These results demonstrate the excellent real-time capability, robustness, and energy efficiency of the proposed system, providing a practical and scalable solution for autonomous embedded fire-fighting applications in household, industrial, and warehouse environments. Full article

Aircraft cargo compartment fires constitute a significant type of aviation fire, posing a grave threat to aviation safety. To guard against and respond to such fires, existing aircraft cargo compartments are equipped with smoke detection fire detectors, which rely on perceiving changes in smoke transmittance to determine the onset of a fire. However, these detectors offer relatively low recognition accuracy and cannot provide a direct visual representation of the fire. In this work, we introduce a fire recognition method built on image sensors and a deep learning model. In light of the irregular shapes of flames and smoke, an improved interactive triplet attention mechanism (ITAM) is integrated into the You Only Look Once version 5 (YOLOv5) model, enhancing the model’s recognition accuracy. Furthermore, the original Neck structure is replaced with an Asymptotic Feature Pyramid Network (AFPN), improving the model’s ability to recognize small targets, which is particularly useful for detecting flames and smoke early in a fire. This paper further improves the model’s recognition accuracy by introducing the Focaler-IoU loss function, which balances the feature learning of hard and easy samples. Therefore, the network model in this paper is named IATF-YOLO. Ablation experiments demonstrate that our algorithm improves accuracy by 2%, while comparative experiments with several mainstream baseline models show that our algorithm achieves a 0.7% accuracy improvement, with a final peak accuracy of 93.6%. Full article

In 1926, a group of younger Black artists produced Fire!!, a short-lived but generative publication that sought to interrupt dominant scripts of racial uplift, citizenship, and cultural recognition. Refusing incrementalist visions tethered to Western and U.S. centered norms of belonging, the editors desired an otherwise form of cultural production, one generated outside prevailing regimes of representation. This essay reads Fire!! as a model of breach and mobilizes it to interrogate the contemporary (anti-)diversity, equity, inclusion, and access (DEIA) landscape. Drawing on interdisciplinary system literature, I first trace the narrative logics that organize DEIA discourse, attending to how retrenchment operates through recursive patterns that normalize anti-Black constraint across policy and practice. I then theorize “reading against the grain” as a method for apprehending what exceeds these loops. Through a close reading of Fire!!, I argue that Black cultural production formed outside dominant registers functions as a mechanism for interrupting coherence, exposing the epistemic architectures that structure society and the Human while gesturing toward other modes of existence. Full article