Evaluating YOLOv5s and YOLOv8s for Kitchen Fire Detection: A Comparative Analysis

Kitchen fires pose a significant challenge and threat to people and the environment. Prompt response and accurate classification of fire occurrences are crucial to ensure safety and reduce potential property damage. This study addresses the need for effective fire detection technologies by evaluating the performance of the You Only Look Once version 5 medium (YOLOv5m) model using both hue, saturation, and value (HSV) and visible light (red, green, and blue [RGB]) color spaces. To reduce false positives, the experiment was expanded by including background images in the training dataset. Two kitchen fire datasets, one in RGB and one in HSV, were used to train and evaluate the model. Based on the results, HSV color space offers higher recall and precision for fire-on-pan detection, achieving 0.882 and 0.931, outperforming RGB. The best overall mean performance was in the first experiment, RGB without background images, resulting in the highest mean average precision (mAP)@0.5:0.95 score of 0.651. This performance was limited by lower recall and precision compared to HSV in specific fire scenarios. A key limitation of this study is its focus on kitchen environments, for which the findings may not be directly generalizable to other fire scenarios with different environmental conditions or fire characteristics. Furthermore, the study is limited to the YOLOv5m architecture, where other detection models may yield different results. In terms of kitchen fire detection, this study provides a comprehensive comparison of the RGB and HSV color spaces, offering insights into their benefits and drawbacks. This research shows that the HSV color space is useful in certain fire detection scenarios, and that combining the two color spaces yields an improved detection model for real-time applications.

Fire and smoke pose severe threats, causing damage to property and the environment and endangering lives. Traditional fire detection methods struggle with accuracy and speed, hindering real-time detection. Thus, this study introduces an improved fire and smoke detection approach utilizing the you only look once (YOLO)v8-based deep learning model. This work aims to enhance accuracy and speed, which are crucial for early fire detection. The methodology involves preprocessing a large dataset containing 5,700 images depicting fire and smoke scenarios. YOLOv8 has been trained and validated, outperforming some baseline models- YOLOv7, YOLOv5, ResNet-32, and MobileNet-v2 in the precision, recall, and mean average precision (mAP) metrics. The proposed method achieves 68.3% precision, 54.6% recall, 60.7% F1 score, and 57.3% mAP. Integrating YOLOv8 in fire and smoke detection systems can significantly improve response times, enhance the ability to mitigate fire outbreaks, and potentially save lives and property. This research advances fire detection systems and establishes a precedent for applying deep learning techniques to critical safety applications, pushing the boundaries of innovation in public safety.

Forest fires are severe ecological disasters worldwide that cause extensive ecological destruction and economic losses while threatening biodiversity and human safety. With the escalation of climate change, the frequency and intensity of forest fires are increasing annually, underscoring the urgent need for effective monitoring and early warning systems. This study investigates the application effectiveness of deep learning-based object detection technology in forest fire smoke recognition by using the YOLOv11x algorithm to develop an efficient fire detection model. The objective is to enhance early fire detection capabilities and mitigate potential damage. To improve the model’s applicability and generalizability, two publicly available fire image datasets, WD (Wildfire Dataset) and FFS (Forest Fire Smoke), encompassing various complex scenarios and external conditions, were employed. After 501 training epochs, the model’s detection performance was comprehensively evaluated via multiple metrics, including precision, recall, and mean average precision (mAP50 and mAP50-95). The results demonstrate that YOLOv11x excels in bounding box loss (box loss), classification loss (cls loss), and distribution focal loss (dfl loss), indicating effective optimization of object detection performance across multiple dimensions. Specifically, the model achieved a precision of 0.949, a recall of 0.850, an mAP50 of 0.901, and an mAP50-95 of 0.786, highlighting its high detection accuracy and stability. Analysis of the precision‒recall (PR) curve revealed an average mAP@0.5 of 0.901, further confirming the effectiveness of YOLOv11x in fire smoke detection. Notably, the mAP@0.5 for the smoke category reached 0.962, whereas for the flame category, it was 0.841, indicating superior performance in smoke detection compared with flame detection. This disparity primarily arises from the distinct visual characteristics of flames and smoke; flames possess more vivid colors and defined shapes, facilitating easier recognition by the model, whereas smoke exhibits more ambiguous and variable textures and shapes, increasing detection difficulty. In the test set, 86.89% of the samples had confidence scores exceeding 0.85, further validating the model’s reliability. In summary, the YOLOv11x algorithm demonstrates excellent performance and broad application potential in forest fire smoke recognition, providing robust technical support for early fire warning systems and offering valuable insights for the design of intelligent monitoring systems in related fields.

Forest fires cause extensive environmental damage, making early detection crucial for protecting both nature and communities. Advanced computer vision techniques can be used to detect smoke and fire. However, accurate detection of smoke and fire in forests is challenging due to different factors such as different smoke shapes, changing light, and similarity of smoke with other smoke-like elements such as clouds. This study explores recent YOLO (You Only Look Once) deep-learning object detection models YOLOv9, YOLOv10, and YOLOv11 for detecting smoke and fire in forest environments. The evaluation focuses on key performance metrics, including precision, recall, F1-score, and mean average precision (mAP), and utilizes two benchmark datasets featuring diverse instances of fire and smoke across different environments. The findings highlight the effectiveness of the small version models of YOLO (YOLOv9t, YOLOv10n, and YOLOv11n) in fire and smoke detection tasks. Among these, YOLOv11n demonstrated the highest performance, achieving a precision of 0.845, a recall of 0.801, a mAP@50 of 0.859, and a mAP@50-95 of 0.558. YOLOv11 versions (YOLOv11n and YOLOv11x) were evaluated and compared against several studies that employed the same datasets. The results show that YOLOv11x delivers promising performance compared to other YOLO variants and models.

Fire detection is a critical task in environmental monitoring and disaster prevention, with traditional methods often limited in their ability to detect fire and smoke in real time over large areas. The rapid identification of fire and smoke in both indoor and outdoor environments is essential for minimizing damage and ensuring timely intervention. In this paper, we propose a novel approach to fire and smoke detection by integrating a vision transformer (ViT) with the YOLOv5s object detection model. Our modified model leverages the attention-based feature extraction capabilities of ViTs to improve detection accuracy, particularly in complex environments where fires may be occluded or distributed across large regions. By replacing the CSPDarknet53 backbone of YOLOv5s with ViT, the model is able to capture both local and global dependencies in images, resulting in more accurate detection of fire and smoke under challenging conditions. We evaluate the performance of the proposed model using a comprehensive Fire and Smoke Detection Dataset, which includes diverse real-world scenarios. The results demonstrate that our model outperforms baseline YOLOv5 variants in terms of precision, recall, and mean average precision (mAP), achieving a mAP@0.5 of 0.664 and a recall of 0.657. The modified YOLOv5s with ViT shows significant improvements in detecting fire and smoke, particularly in scenes with complex backgrounds and varying object scales. Our findings suggest that the integration of ViT as the backbone of YOLOv5s offers a promising approach for real-time fire detection in both urban and natural environments.

PurposeThe purpose of this work is to develop and evaluate artificial intelligence (AI) models, specifically neural networks, random forest and XGBoost, for fault detection and localization in dynamic systems. By comparing the performance of these models in terms of accuracy, precision, recall and other key metrics, this study aims to identify the most effective approach for predictive maintenance in various engineering applications. The results provide insights into the strengths and limitations of each model, offering practical guidance for implementing AI-driven solutions to enhance operational reliability and efficiency in industries reliant on complex, dynamic machinery.Design/methodology/approachThis study employs a comparative analysis of three machine learning algorithms – neural networks, random forest and XGBoost for fault detection in dynamic systems. The methodology includes data preprocessing, feature extraction and hyperparameter optimization using grid search and randomized search techniques. The models are trained and validated using cross-validation, with performance evaluated on accuracy, precision, recall, F1 Score and ROC AUC. Statistical tests, including ANOVA and paired T-tests, are applied to assess the significance of the differences between models. The approach ensures a rigorous evaluation of each model’s strengths and limitations for practical applications in predictive maintenance.FindingsThe findings reveal that XGBoost consistently outperforms neural networks and random forest in key performance metrics such as accuracy, precision and ROC AUC, demonstrating its effectiveness in fault detection for dynamic systems. The statistical analysis using ANOVA and paired T-tests confirms the significance of XGBoost’s superior performance. While random forest shows robust interpretability and neural networks perform well in certain scenarios, XGBoost’s ability to handle imbalanced data and deliver high accuracy makes it the most suitable model for predictive maintenance applications. These results provide a clear direction for selecting machine learning models in fault detection tasks.Research limitations/implicationsThe research is limited by the use of a specific dataset and may not generalize to all dynamic systems or industrial environments. While XGBoost demonstrated superior performance, further validation is needed with diverse datasets and real-world conditions. Additionally, the study focuses on a few key metrics and does not explore other potential factors such as computational efficiency and scalability in large-scale systems. Future work should incorporate additional datasets, including real-time data and explore hybrid approaches or model ensembles to improve performance further and ensure broader applicability across various engineering applications.Practical implicationsThis study provides practical insights for implementing AI-based fault detection in dynamic systems, particularly in predictive maintenance. By identifying XGBoost as the most effective model, industries can leverage this algorithm to improve operational reliability and reduce downtime. The findings offer a clear methodology for data preprocessing, model training and performance evaluation, which can be directly applied in sectors like manufacturing, energy and automotive. The research also highlights the importance of selecting the right model based on system requirements, offering practical guidance for engineers seeking to integrate AI solutions into their maintenance and monitoring processes.Originality/valueThis study offers a unique contribution by providing a comprehensive comparison of three widely-used machine learning models – neural networks, random forest and XGBoost – specifically applied to fault detection in dynamic systems. Through the use of statistical tests to validate the significance of performance differences, it offers a rigorous and objective assessment of each model’s capabilities. The findings deliver practical value to industries seeking to implement AI-driven predictive maintenance. By highlighting XGBoost’s superior performance and offering clear guidelines for model selection and implementation, this work addresses a critical gap in the literature related to AI applications in fault detection.

Background: Detection and classification of microcalcifications in breast tissues is crucial for early breast cancer diagnosis and long-term treatment. Objective: This paper aims to propose a robust model capable of detection and classification of breast cancer calcifications in digital mammogram images using Deep Convolutional Neural Networks (DCNN). Materials and methods: An expert breast radiologist annotated the 3,265 clinical mammogram images to create a comprehensive ground truth dataset comprising 2,500 annotations for malignant and benign calcifications. This dataset was utilized to train our model, a two-stage detection system incorporating a Region-based Convolutional Neural Network (RCNN) with AlexNet and support vector machines to enhance the system’s robustness. The proposed model was compared to the one-stage detection, utilizing YOLOv4 combined with the Cross-Stage Partial Darknet53 (CSPDarknet53) architecture. A separate dataset of 504 mammogram images was explicitly set aside for model testing. The efficacy of the proposed model was evaluated based on key performance metrics, including precision, recall, F1 score, and mean average precision (mAP). Results: The results showed that the proposed RCNN-2 model could automatically identify and categorize calcifications as malignant or benign, outperforming the YOLOv4 models. The RCNN-2’s overall effectiveness, as evaluated by precision, recall, F1 score, and mean average precision (mAP), achieved scores of 0.82, 0.85, 0.83, and 0.74, respectively. Conclusion: The proposed RCNN-2 model demonstrates very effective detection and classification of calcification in mammogram images, especially in high-dense breast images. The performance of the proposed model was compared to that of YOLOv4, and it can be concluded that the proposed RCNN model yields outstanding performance. The model can be a helpful tool for radiologists.

There are more interests in better understanding kitchen fires with multiple burning sources in this paper because of the demand in the construction industry. Computational Fluid Dynamics (CFD) was applied to study kitchen fires with multiple burning sources using experimental data reported earlier. A room of length 3.6 m, width 2.4 m and height 2.4 m was constructed with a door of width 2.0 m and height 1.9 m to provide natural ventilation. Chinese frying pans of diameter 0.36 m filled with 1000 mL quality soybean oil were used as the burning sources. Three typical fire scenarios with two, four and six burning sources were selected for the numerical study. Numerical experiments were then carried out for justifying the measured transient temperature using the CFD tool Fire Dynamics Simulator (FDS). Grid sensitivity, two boundary conditions and the heat release rate emitted by each burning source were investigated. The results in this paper indicated that for simulations on fire scenarios with high heat release rate and high fire temperature under natural ventilation, thermal radiation heat transfer into the wall surface should be included. The distances between the burning sources and the ventilation vent would affect the burning duration.

Fire and smoke detection is crucial for the safe mining of coal energy, but previous fire-smoke detection models did not strike a perfect balance between complexity and accuracy, which makes it difficult to deploy efficient fire-smoke detection in coal mines with limited computational resources. Therefore, we improve the current advanced object detection model YOLOv8s based on two core ideas: (1) we reduce the model computational complexity and ensure real-time detection by applying faster convolutions to the backbone and neck parts; (2) to strengthen the model's detection accuracy, we integrate attention mechanisms into both the backbone and head components. In addition, we improve the model's generalization capacity by augmenting the data. Our method has 23.0% and 26.4% fewer parameters and FLOPs (Floating-Point Operations) than YOLOv8s, which means that we have effectively reduced the computational complexity. Our model also achieves a mAP (mean Average Precision) of 91.0%, which is 2.5% higher than the baseline model. These results show that our method can improve the detection accuracy while reducing complexity, making it more suitable for real-time fire-smoke detection in resource-constrained environments.

Fire incidents pose a significant threat to human life and property security. Accurate fire detection plays a crucial role in promptly responding to fire outbreaks and ensuring the smooth execution of subsequent firefighting efforts. Fixed-size convolutions struggle to capture the irregular variations in smoke and flames that occur during fire incidents. In this paper, we introduce FireViT, an adaptive lightweight backbone network that combines a convolutional neural network (CNN) and transformer for fire detection. The FireViT we propose is an improved backbone network based on MobileViT. We name the lightweight module that combines deformable convolution with a transformer as th DeformViT block and compare multiple builds of this module. We introduce deformable convolution in order to better adapt to the irregularly varying smoke and flame in fire scenarios. In addition, we introduce an improved adaptive GELU activation function, AdaptGELU, to further enhance the performance of the network model. FireViT is compared with mainstream lightweight backbone networks in fire detection experiments on our self-made labeled fire natural light dataset and fire infrared dataset, and the experimental results show the advantages of FireViT as a backbone network for fire detection. On the fire natural light dataset, FireViT outperforms the PP-LCNet lightweight network backbone for fire target detection, with a 1.85% increase in mean Average Precision (mAP) and a 0.9 M reduction in the number of parameters. Additionally, compared to the lightweight network backbone MobileViT-XS, which similarly combines a CNN and transformer, FireViT achieves a 1.2% higher mAP while reducing the Giga-Floating Point Operations (GFLOPs) by 1.3. FireViT additionally demonstrates strong detection performance on the fire infrared dataset.

During flight, aircraft cargo compartments are in a confined state. If a fire occurs, it will seriously affect flight safety. Therefore, fire detection systems must issue alarms within seconds of a fire breaking out, necessitating high real-time performance for aviation fire detection systems. In addressing the issue of fire target detection, the YOLO series models demonstrate superior performance in striking a balance between computational efficiency and recognition accuracy when compared with alternative models. Consequently, this paper opts to optimize the YOLO model. An enhanced version of the FDY-YOLO object detection algorithm is introduced in this paper for the purpose of instantaneous fire detection. Firstly, the FaB-C3 module, modified based on the FasterNet backbone network, replaces the C3 component in the YOLOv5 framework, significantly decreasing the computational burden of the algorithm. Secondly, the DySample module is used to replace the upsampling module and optimize the model’s ability to extract the features of small-scale flames or smoke in the early stages of a fire. We introduce RFID technology to manage the cameras that are capturing images. Finally, the model’s loss function is changed to the MPDIoU loss function, improving the model’s localization accuracy. Based on our self-constructed dataset, compared with the YOLOv5 model, FDY-YOLO achieves a 0.8% increase in mean average precision (mAP) while reducing the computational load by 40%.

In recent years, advancements in smart home technologies have underscored the need for the development of early fire and smoke detection systems to enhance safety and security. Traditional fire detection methods relying on thermal or smoke sensors exhibit limitations in terms of response time and environmental adaptability. To address these issues, this paper introduces the multi-scale information transformer–DETR (MITI-DETR) model, which incorporates multi-scale feature extraction and transformer-based attention mechanisms, tailored specifically for fire detection in smart homes. MITI-DETR achieves a precision of 99.00%, a recall of 99.50%, and a mean average precision (mAP) of 99.00% on a custom dataset designed to reflect diverse lighting and spatial conditions in smart homes. Extensive experiments demonstrate that MITI-DETR outperforms state-of-the-art models in terms of these metrics, especially under challenging environmental conditions. This work provides a robust solution for early fire detection in smart homes, combining high accuracy with real-time deployment feasibility.

With the growing frequency of fire incidents, the demand for rapid and accurate fire detection technologies has become increasingly critical. In this study, we evaluate segmentation-based object detection models YOLO (You Only Look Once) v5-seg, YOLOv8-seg, and YOLOv11-seg for their ability to detect flames and smoke under identical experimental conditions. A total of 5,000 fire images were collected and split into training, validation, and test datasets. The same hardware environment and hyperparameter settings were used for model training to ensure a fair comparison. The experimental results reveal that YOLOv11-seg achieved the best overall performance, with a Precision of 0.710, Recall of 0.570, F1-score of 0.632, and mAP (mean Average Precision) 50 of 0.600. Notably, YOLOv11-seg achieved the highest Recall and mAP values for smoke detection, underscoring its effectiveness in identifying smoke—a critical factor for early fire detection. In terms of efficiency, YOLOv8-seg demonstrated the fastest inference speed, while YOLOv5-seg offered advantages in lightweight model size. However, YOLOv11-seg provided a balanced trade-off between computational cost and detection accuracy, making it the most suitable model for real-world fire response scenarios. Accordingly, this study proposes YOLOv11-seg as a robust baseline model for segmentation-based fire detection and provides a foundational reference for future research on deep learning-driven intelligent fire video analysis.

Smart fire detection is essential for people’s safety and property. The effective utilization of innovative technologies provides fast fire detection before intensification. Automatic fire systems commonly utilize passive sensors that are damaged by sunlight and environmental conditions. To address this problem, this study provides AI-based fire and smoke detection system that uses a You Only Look Once (YOLO) smart object detection algorithm integrated with a deep learning convolutional neural network architecture(CNN) and Android Studio to achieve the desired requirements. This prototype uses Common Objects in Context (COCO) datasheets for YOLO modelling. The incorporated camera continuously monitors the consumer for immediate notification. The system uses Android applications to monitor the parameters. The application architecture uses the Django framework to communicate the developed system with the Android application and the YOLO model. The Android application was designed using Android studio software to provide online information via cloud-based systems. Compared with conventional fire detection systems that consist of heat, flame, gas, and smoke sensors with high power consumption, installation, and preventive maintenance. The designed system considers AI fire detection algorithms using images and video forms. Further advancements in this state-of-the-art technology can improve the industrial application of early fire detection.

The cervical vertebral maturation (CVM) method is essential to determine the timing of orthodontic and orthopedic treatment. In this paper, a target detection model called DC-YOLOv5 is proposed to achieve fully automated detection and staging of CVM. A total of 1800 cephalometric radiographs were labeled and categorized based on the CVM stages. We introduced a model named DC-YOLOv5, optimized for the specific characteristics of CVM based on YOLOv5. This optimization includes replacing the original bounding box regression loss calculation method with Wise-IOU to address the issue of mutual interference between vertical and horizontal losses in Complete-IOU (CIOU), which made model convergence challenging. We incorporated the Res-dcn-head module structure to enhance the focus on small target features, improving the model's sensitivity to subtle sample differences. Additionally, we introduced the Convolutional Block Attention Module (CBAM) dual-channel attention mechanism to enhance focus and understanding of critical features, thereby enhancing the accuracy and efficiency of target detection. Loss functions, precision, recall, mean average precision (mAP), and F1 scores were used as the main algorithm evaluation metrics to assess the performance of these models. Furthermore, we attempted to analyze regions important for model predictions using gradient Class Activation Mapping (CAM) techniques. The final F1 scores of the DC-YOLOv5 model for CVM identification were 0.993, 0.994 for mAp0.5 and 0.943 for mAp0.5:0.95, with faster convergence, more accurate and more robust detection than the other four models. The DC-YOLOv5 algorithm shows high accuracy and robustness in CVM identification, which provides strong support for fast and accurate CVM identification and has a positive effect on the development of medical field and clinical diagnosis.