Explore the vast range of titles available.

Fires are classified into five types: A, B, C, D, and F/K, according to the components involved in combustion. Recognizing fire classes is critical, since each kind demands a unique suppression approach. Proper fire classification helps to decrease the risk to both life and property. The fuel type is used to determine the fire class, so that the appropriate extinguishing agent can be selected. This study takes advantage of recent advances in deep learning, employing YOLOv11 variants (YOLO11n, YOLO11s, YOLO11m, YOLO11l, and YOLO11x) to classify fires according to their class, assisting in the selection of the correct fire extinguishers for effective fire control. Moreover, a hybrid model that combines YOLO11n and MobileNetV2 is developed for multi-class classification. The dataset used in this study is a combination of five existing public datasets with additional manually annotated images, to create a new dataset covering the five fire classes, which was then validated by a firefighting specialist. The hybrid model exhibits good performance across all classes, achieving particularly high precision, recall, and F1 scores. Its superior performance is especially reflected in the macro average, where it surpasses both YOLO11n and YOLO11m, making it an effective model for datasets with imbalanced classes, such as fire classes. The YOLO11 variants achieved high performance across all classes. YOLO11s exhibited high precision and recall for Class A and Class F, achieving an F1 score of 0.98 for Class A. YOLO11m also performed well, demonstrating strong results in Class A and No Fire with an F1 score of 0.98%. YOLO11n achieved 97% accuracy and excelled in No Fire, while also delivering good recall for Class A. YOLO11l showed excellent recall in challenging classes like Class F, attaining an F1 score of 0.97. YOLO11x, although slightly lower in overall accuracy of 96%, still maintained strong performance in Class A and No Fire, with F1 scores of 0.97 and 0.98, respectively. A similar study employing MobileNetV2 is compared to the hybrid model, and the results show that the hybrid model achieves higher accuracy. Overall, the results demonstrate the high accuracy of the hybrid model, highlighting the potential of the hybrid models and YOLO11n, YOLO11m, YOLO11s, and YOLO11l models for better classification of fire classes. We also discussed the potential of deep learning models, along with their limitations and challenges, particularly with limited datasets in the context of the classification of fire classes.

Wireless sensor networks (WSNs) are essential for a wide range of applications, including environmental monitoring and smart city developments, thanks to their ability to collect and transmit diverse physical and environmental data. The nature of WSNs, coupled with the variability and noise sensitivity of cost-effective sensors, presents significant challenges in achieving accurate data analysis and anomaly detection. To address these issues, this paper presents a new framework, called Online Adaptive Kalman Filtering (OAKF), specifically designed for real-time anomaly detection within WSNs. This framework stands out by dynamically adjusting the filtering parameters and anomaly detection threshold in response to live data, ensuring accurate and reliable anomaly identification amidst sensor noise and environmental changes. By highlighting computational efficiency and scalability, the OAKF framework is optimized for use in resource-constrained sensor nodes. Validation on different WSN dataset sizes confirmed its effectiveness, showing 95.4% accuracy in reducing false positives and negatives as well as achieving a processing time of 0.008 s per sample.

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 and analysis have been a central focus of numerous studies due to their importance in potentially reducing fire’s harmful impact. Fire detection and classification using artificial intelligence (AI) methods have drawn significant attention in the literature. These methods often tackle certain aspects of fire, such as classifying fire versus non-fire images or detecting smoke or flames. However, these studies lack emphasis on integrating the capabilities of large language models for fire classification. This study explores the potential of large language models, especially ChatGPT-4, in fire classification tasks. In particular, we utilize ChatGPT-4 for the first time to develop a classification approach for fire incidents. We evaluate this approach using two benchmark datasets: the Forest Fire dataset and the DFAN dataset. The results indicate that ChatGPT has significant potential for timely fire classification, making it a promising tool to complement existing fire detection technologies. Furthermore, it has the capability to provide users with more thorough information about the type of burning objects and risk level. By integrating ChatGPT, detection systems can benefit from the rapid analysis capabilities of ChatGPT to enhance response times and improve accuracy. Additionally, its ability to provide context-rich information can support better decision-making during fire episodes, making the system more effective overall. The study also examines the limitations of using ChatGPT for classification tasks.

The forecasting of crude oil production is essential to economic plans and decision-making in the oil and gas industry. Several techniques have been applied to forecast crude oil production. Artificial Intelligence (AI)-based techniques are promising that have been applied successfully to several sectors and are capable of being applied to different stages of oil exploration and production. However, there is still more work to be done in the oil sector. This paper proposes an optimized gradient boosting (GB) model by genetic algorithm (GA) called GA-GB for forecasting crude oil production. The proposed optimized model was applied to forecast crude oil in several countries, including the top producers and others with less production. The GA-GB model of crude oil forecasting was successfully developed, trained, and tested to provide excellent forecasting of crude oil production. The proposed GA-GB model has been applied to forecast crude oil production and has also been applied to oil price and oil demand, and the experiment of the proposed optimized model shows good results. In the experiment, three different actual datasets are used: crude oil production (OProd), crude oil price (OPrice), and oil demand (OD) acquired from various sources. The GA-GB model outperforms five regression models, including the Bagging regressor, KNN regressor, MLP regressor, RF regressor, and Lasso regressor.

The Internet of Things (IoT) is a widely used technology in automated network systems across the world. The impact of the IoT on different industries has occurred in recent years. Many IoT nodes collect, store, and process personal data, which is an ideal target for attackers. Several researchers have worked on this problem and have presented many intrusion detection systems (IDSs). The existing system has difficulties in improving performance and identifying subcategories of cyberattacks. This paper proposes a deep-convolutional-neural-network (DCNN)-based IDS. A DCNN consists of two convolutional layers and three fully connected dense layers. The proposed model aims to improve performance and reduce computational power. Experiments were conducted utilizing the IoTID20 dataset. The performance analysis of the proposed model was carried out with several metrics, such as accuracy, precision, recall, and F1-score. A number of optimization techniques were applied to the proposed model in which Adam, AdaMax, and Nadam performance was optimum. In addition, the proposed model was compared with various advanced deep learning (DL) and traditional machine learning (ML) techniques. All experimental analysis indicates that the accuracy of the proposed approach is high and more robust than existing DL-based algorithms.

Climate change poses a significant challenge to wind energy production. It involves long-term, noticeable changes in key climatic factors such as wind power, temperature, wind speed, and wind patterns. Addressing climate change is essential to safeguarding our environment, societies, and economies. In this context, accurately forecasting temperature and wind power becomes crucial for ensuring the stable operation of wind energy systems and for effective power system planning and management. Numerous approaches to wind change forecasting have been proposed including both traditional forecasting models and deep learning models. Traditional forecasting models have limitations since they cannot describe the complex nonlinear relationship in climatic data, resulting in low forecasting accuracy. Deep learning techniques have promising non-linear processing capabilities in weather forecasting. To further advance the integration of deep learning in climate change forecasting, we have developed a hybrid model called CNN-ResNet50-LSTM, comprising a Convolutional Neural Network (CNN), a Deep Convolutional Network (ResNet50), and a Long Short-Term Memory (LSTM) model to predict two climate change factors: temperature and wind power. The experiment was conducted using three publicly available datasets: Wind Turbine Scada (Scada) Dataset, Saudi Arabia Weather history (SA) dataset, and Wind Power Generation Data for 4 locations (WPG) dataset. The forecasting accuracy is evaluated using several evaluation metrics, including the coefficient of determination ( ), Mean Squared Error (MSE), Mean Absolute Error (MAE), Median Absolute Error (MedAE) and Root Mean Squared Error (RMSE). The proposed CNN-ResNet50-LSTM model was also compared to five regression models: Dummy Regressor (DR), Kernel Ridge Regressor (KRR), Decision Tree Regressor (DTR), Extra Trees Regressor (ETR), and Stochastic Gradient Descent Regressor (SGDR). Findings revealed that CNN-ResNet50-LSTM model achieved the best performance, with scores of 98.84% for wind power forecasting in the Scada dataset, 99.01% for temperature forecasting in the SA dataset, 98.58% for temperature forecasting and 98.35% for wind power forecasting in the WPG dataset. The CNN-ResNet50-LSTM model demonstrated promising potential in forecasting both temperature and wind power. Additionally, we applied the CNN-ResNet50-LSTM model to predict climate changes up to 2030 using historical data, providing insights that highlight its potential for future forecasting and decision-making.

Due to the wide availability and usage of connected devices in Internet of Things (IoT) networks, the number of attacks on these networks is continually increasing. A particularly serious and dangerous type of attack in the IoT environment is the botnet attack, where the attackers can control the IoT systems to generate enormous networks of “bot” devices for generating malicious activities. To detect this type of attack, several Intrusion Detection Systems (IDSs) have been proposed for IoT networks based on machine learning and deep learning methods. As the main characteristics of IoT systems include their limited battery power and processor capacity, maximizing the efficiency of intrusion detection systems for IoT networks is still a research challenge. It is important to provide efficient and effective methods that use lower computational time and have high detection rates. This paper proposes an aggregated mutual information-based feature selection approach with machine learning methods to enhance detection of IoT botnet attacks. In this study, the N-BaIoT benchmark dataset was used to detect botnet attack types using real traffic data gathered from nine commercial IoT devices. The dataset includes binary and multi-class classifications. The feature selection method incorporates Mutual Information (MI) technique, Principal Component Analysis (PCA) and ANOVA f-test at finely-granulated detection level to select the relevant features for improving the performance of IoT Botnet classifiers. In the classification step, several ensemble and individual classifiers were used, including Random Forest (RF), XGBoost (XGB), Gaussian Naïve Bayes (GNB), k-Nearest Neighbor (k-NN), Logistic Regression (LR) and Support Vector Machine (SVM). The experimental results showed the efficiency and effectiveness of the proposed approach, which outperformed other techniques using various evaluation metrics.

Unmanned Aerial Vehicles (UAVs) seem to be the most efficient way of achieving the intended aerial tasks, according to recent improvements. Various researchers from across the world have studied a variety of UAV formations and path planning methodologies. However, when unexpected obstacles arise during a collective flight, path planning might get complicated. The study needs to employ hybrid algorithms of bio-inspired computations to address path planning issues with more stability and speed. In this article, two hybrid models of Ant Colony Optimization were compared with respect to convergence time, i.e., the Max-Min Ant Colony Optimization approach in conjunction with the Differential Evolution and Cauchy mutation operators. Each algorithm was run on a UAV and traveled a predetermined path to evaluate its approach. In terms of the route taken and convergence time, the simulation results suggest that the MMACO-DE technique outperforms the MMACO-CM approach.

A system that can fly off and touches down to execute particular tasks is a flying robot. Nowadays, these flying robots are capable of flying without human control and make decisions according to the situation with the help of onboard sensors and controllers. Among flying robots, Unmanned Aerial Vehicles (UAVs) are highly attractive and applicable for military and civilian purposes. These applications require motion planning of UAVs along with collision avoidance protocols to get better robustness and a faster convergence rate to meet the target. Further, the optimization algorithm improves the performance of the system and minimizes the convergence error. In this survey, diverse scholarly articles were gathered to highlight the motion planning for UAVs that use bio-inspired algorithms. This study will assist researchers in understanding the latest work done in the motion planning of UAVs through various optimization techniques. Moreover, this review presents the contributions and limitations of every article to show the effectiveness of the proposed work.