Search Results (3,039)

The rapid detection and confirmation of Suspicious Regions of Forest Fire (SRoFF) are critical for timely alerts and firefighting operations. In the early stages of forest fires, small flames and heavy occlusion lead to low accuracy, false detections, omissions, and slow inference in existing target-detection algorithms. We constructed the Suspicious Regions of Forest Fire Dataset (SRFFD), comprising publicly available datasets, relevant images collected from online searches, and images generated through various image enhancement techniques. The SRFFD contains a total of 64,584 images. In terms of effectiveness, the individual augmentation techniques rank as follows (in descending order): HSV (Hue Saturation and Value) random enhancement, copy-paste augmentation, and affine transformation. A detection model named SRoFF-Yolover is proposed for identifying suspicious regions of forest fire, based on the YOLOv8. An embedding layer that effectively integrates seasonal and temporal information into the image enhances the prediction accuracy of the SRoFF-Yolover. The SRoFF-Yolover enhances YOLOv8 by (1) adopting dilated convolutions in the Backbone to enlarge feature map receptive fields; (2) incorporating the Convolutional Block Attention Module (CBAM) prior to the Neck’s C2fLayer for small-target attention; and (3) reconfiguring the Backbone-Neck linkage via P2, P4, and SPPF. Compared with the baseline model (YOLOv8s), the SRoFF-Yolover achieves an 18.1% improvement in mAP@0.5, a 4.6% increase in Frames Per Second (FPS), a 2.6% reduction in Giga Floating-Point Operations (GFLOPs), and a 3.2% decrease in the total number of model parameters (#Params). The SRoFF-Yolover can effectively detect suspicious regions of forest fire, particularly during winter nights. Experiments demonstrated that the detection accuracy of the SRoFF-Yolover for suspicious regions of forest fire is higher at night than during daytime in the same season. Full article

Semi-enclosed bays are greatly affected by human activities and have undergone drastic changes in their ecological environment, which requires our continuous attention. Laizhou Bay (LZB) is a typical semi-closed bay that is greatly influenced by human activities, and it is highly representative on a global scale. Investigating the multi-scale variation in nutrient concentrations in semi-enclosed bays can provide scientific support for environmental management and policy adjustments. To address the limitations of in situ data and the high cost of field surveys, this study utilizes machine learning methods to construct MODIS remote sensing models for quantitatively analyzing the concentrations of dissolved inorganic nitrogen (DIN) and dissolved inorganic phosphorus (DIP) in the surface water of LZB, as well as the spatiotemporal factors influencing them. Among various methods tested, the Support Vector Machine Regression (SVR) algorithm demonstrated the best performance in retrieving nutrient concentrations in LZB. The R² values of the DIN and DIP retrieval results based on the SVR algorithm are 0.91 and 0.92, respectively, while the RMSE values are 5.43 and 0.08 μmol/L, respectively. The retrieval results indicate that nearshore nutrient concentrations are significantly higher than those in offshore areas. Temporally, from 2003 to 2024, the DIN concentration in l has decreased at a rate of 0.4 μmol/L/yr, while the DIP concentration has remained relatively stable. Given sufficient observation data, the proposed machine learning and remote sensing approach can be effectively applied to other bays, offering the advantages of long time series, high spatial resolution, and a low cost. Full article

Lubricating oil degradation directly impacts friction coefficient, wear rate, and lubrication regime transitions, making precise health quantification essential for predictive tribological maintenance. However, conventional evaluation methods fail to capture subtle tribological changes preceding lubrication failure, often oversimplifying complex multi-parameter relationships critical to friction and wear performance. To address this challenge, this study proposes Seasonal–Trend decomposition using Loess, a Factor Attention Network, a Temporal Convolutional Network, and an Informer with Long Short-Term Memory Variational Autoencoder (SFTI-LVAE) framework for continuous tribological health assessment of diesel engine lubricants. The approach integrates Seasonal–Trend decomposition using Loess (STL) for trend–seasonal separation, a Factor Attention Network (FAN) for multidimensional feature fusion, and a Temporal Convolutional Network (TCN)-enhanced Informer for capturing long-term tribological dependencies. By combining Long Short-Term Memory (LSTM) temporal modeling with Variational Autoencoder (VAE) reconstruction, the method quantifies lubricant health through reconstruction error, establishing a direct correlation between data deviation and tribological performance degradation. Additionally, permutation importance-based feature evaluation and parameter contribution quantification techniques enable deep mechanistic analysis and fault source tracing of lubricant health degradation. Experimental validation using multi-sensor monitoring data demonstrates that SFTI-LVAE achieves a 96.67% fault detection accuracy with zero false alarms, providing early warning 6.47 h before lubrication failure. Unlike traditional anomaly detection methods that only classify conditions as abnormal or normal, the proposed continuous health index reveals gradual tribological degradation processes, capturing subtle viscosity–temperature relationships and wear particle evolution indicating early lubrication regime transitions. The health index correlates strongly with tribological performance indicators, enabling a transition from reactive maintenance to predictive tribological management, providing an innovative solution for equipment health evaluation in the digital tribology era. Full article

Driven by the increasing global population and rapid urbanization, aircraft noise pollution has emerged as a significant environmental challenge, impeding the sustainable development of the aviation industry. Traditional noise prediction methods are limited by incomplete datasets, insufficient spatiotemporal consistency, and poor adaptability to complex meteorological conditions, making it difficult to achieve precise noise management. To address these limitations, this study proposes a novel noise prediction framework based on a hybrid Convolutional Neural Network–Bidirectional Long Short-Term Memory–Attention (CNN–BiLSTM–Attention) model. By integrating multi-source data, including meteorological parameters (e.g., temperature, humidity, wind speed) and aircraft trajectory data (e.g., altitude, longitude, latitude), the framework achieves high-precision prediction of aircraft noise. The Haversine formula and inverse distance weighting (IDW) interpolation are employed to effectively supplement missing data, while spatiotemporal alignment techniques ensure data consistency. The CNN–BiLSTM–Attention model leverages the spatial feature extraction capabilities of CNNs, the bidirectional temporal sequence processing capabilities of BiLSTMs, and the context-enhancing properties of the attention mechanism to capture the spatiotemporal characteristics of noise. The experimental results indicate that the model’s predicted mean value of 68.66 closely approximates the actual value of 68.16, with a minimal difference of 0.5 and a mean absolute error of 0.89%. Notably, the error remained below 2% in 91.4% of the prediction rounds. Furthermore, ablation studies revealed that the complete CNN–BiLSTM–AM model significantly outperformed single-structure models. The incorporation of the attention mechanism was found to markedly enhance both the accuracy and generalization capability of the model. These findings highlight the model’s robust performance and reliability in predicting aviation noise. This study provides a scientific basis for effective aviation noise management and offers an innovative solution for addressing noise prediction problems under data-scarce conditions. Full article

Nomex honeycomb composites (NHCs) are highly sensitive to the abnormal wear state of disc tools during cutting, leading to poor product quality. This paper proposes a real-time anomaly detection method combining a novel CNN–GRU–Attention (CGA) deep learning model with an Exponentially Weighted Moving Average (EWMA) control chart to monitor sensor data from the disc tool. The CGA model integrates an improved CNN layer to extract multidimensional local features, a GRU layer to capture long-term temporal dependencies, and a multi-head attention mechanism to highlight key information and reduce error accumulation. Trained solely on normal operation data to address the scarcity of abnormal samples, the model predicts cutting force time series with an RMSE of 0.5012, MAE of 0.3942, and R² of 0.9128, outperforming mainstream time series data prediction models. The EWMA control chart applied to the prediction residuals detects abnormal tool wear trends promptly and accurately. Experiments on real NHC cutting datasets demonstrate that the proposed method effectively identifies abnormal machining conditions, enabling timely tool replacement and significantly enhancing product quality assurance. Full article

The stock market plays a crucial role in the financial system, with its price movements reflecting macroeconomic trends. Due to the influence of multifaceted factors such as policy shifts and corporate performance, stock prices exhibit nonlinearity, high noise, and non-stationarity, making them difficult to model accurately using a single approach. To enhance forecasting accuracy, this study proposes a hybrid forecasting framework that integrates wavelet denoising, multi-head attention-based BiLSTM, ARIMA, and XGBoost. Wavelet transform is first employed to enhance data quality. The multi-head attention BiLSTM captures nonlinear temporal dependencies, ARIMA models linear trends in residuals, and XGBoost improves the recognition of complex patterns. The final prediction is obtained by combining the outputs of all models through an inverse-error weighted ensemble strategy. Using the CSI 300 Index as an empirical case, we construct a multidimensional feature set including both market and technical indicators. Experimental results show that the proposed model clearly outperforms individual models in terms of RMSE, MAE, MAPE, and R². Ablation studies confirm the importance of each module in performance enhancement. The model also performs well on individual stock data (e.g., Fuyao Glass), demonstrating promising generalization ability. This research provides an effective solution for improving stock price forecasting accuracy and offers valuable insights for investment decision-making and market regulation. Full article

This paper introduces EmotionTFN (Emotion-Multi-Scale Temporal Fusion Network), a novel hierarchical temporal fusion architecture that addresses key challenges in IoT emotion recognition by processing diverse sensor data while maintaining accuracy across multiple temporal scales. The architecture integrates physiological signals (EEG, PPG, and GSR), visual, and audio data using hierarchical temporal attention across short-term (0.5–2 s), medium-term (2–10 s), and long-term (10–60 s) windows. Edge computing optimizations, including model compression, quantization, and adaptive sampling, enable deployment on resource-constrained devices. Extensive experiments on MELD, DEAP, and G-REx datasets demonstrate 94.2% accuracy on discrete emotion classification and 0.087 mean absolute error on dimensional prediction, outperforming the best baseline (87.4%). The system maintains sub-200 ms latency on IoT hardware while achieving a 40% improvement in energy efficiency. Real-world deployment validation over four weeks achieved 97.2% uptime and user satisfaction scores of 4.1/5.0 while ensuring privacy through local processing. Full article

Traumatic Brain Injury (TBI) is a major global health concern and a leading cause of death and disability, especially in young adults. It triggers complex secondary injury cascades, e.g., calcium dysregulation, mitochondrial dysfunction and protease activation, that extend well beyond the initial mechanical insult to drive ongoing neurodegeneration. The calcium-dependent protease calpain has emerged as a central mediator of TBI cellular pathology. Calpain cleaves a broad range of cytoskeletal and regulatory proteins across neuronal compartments, disrupting axonal integrity, synaptic function and calcium homeostasis. Despite decades of research, calpain remains an elusive therapeutic target. In this review, we examine the spatial and temporal patterns of calpain activation in the traumatically injured brain, categorize key calpain substrates by structure and location, and assess their mechanistic roles in TBI pathology. We also review recent advances in next-generation calpain-2 selective inhibitors with enhanced specificity and preclinical efficacy and discuss the emerging use of calpain-cleaved protein fragments such as SBDP145 and SNTF as candidate biomarkers for TBI diagnosis and progression. Drawing on molecular, preclinical, and clinical data, we argue that calpain warrants renewed attention as both a therapeutic target and mechanistic biomarker in TBI. It may be time for Cinderella to leave the basement. Full article

Time series clustering finds wide application but is often limited by data quality and the inherent limitations of existing methods. Compared to high-dimensional structured data like images, the low-dimensional features of time series contain less information, and endogenous noise can easily obscure important patterns. When dealing with massive time series data, existing clustering methods often focus on mining associations between sequences. However, ideal clustering results are difficult to achieve by relying solely on pairwise association analysis in the presence of noise and information scarcity. To address these issues, we propose a framework called Patch Graph Mamba (PG-Mamba). For the first time, the spatio-temporal patterns of a single sequence are explored by dividing the time series into multiple patches and constructing a spatio-temporal graph (STG). In this graph, these patches serve as nodes, connected by both spatial and temporal edges. By leveraging Mamba-driven long-range dependency learning and a decoupled spatio-temporal graph attention mechanism, our framework simultaneously captures temporal dynamics and spatial relationships and, thus, enabling the effective extraction of key information from time series. Furthermore, a spatio-temporal adjacency matrix reconstruction loss is introduced to mitigate feature space perturbations induced by the clustering loss. Experimental results demonstrate that PG-Mamba outperforms state-of-the-art methods, offering new insights into time series clustering tasks. Across the 33 datasets of the UCR time series archive, PG-Mamba achieved the highest average rank of 3.606 and secured the most first-place rankings (13). Full article

Accurate prediction of effluent quality indicators is essential for ensuring stable operation and regulatory compliance in wastewater treatment plants. However, the inherent spatial distribution and temporal fluctuations of wastewater processes present significant challenges for modeling. In this study, we propose a dynamic multi-scale spatio-temporal Transformer (DMST-Transformer) with a symmetric architecture to enhance prediction accuracy in complex wastewater systems. Unlike conventional asymmetric designs, the DMST-Transformer extracts spatial and temporal features in parallel using a spatial graph convolutional network and a multi-scale self-attention mechanism coupled with a dynamic self-tuning module. The model is evaluated on a full-process dataset collected from a municipal wastewater treatment plant, with biochemical oxygen demand selected as the target indicator. Experimental results on test data show that the DMST-Transformer achieves a coefficient of determination of 0.93, root mean square error of 1.40 mg/L, and mean absolute percentage error of 6.61%, outperforming classical models such as linear regression, partial least squares, and graph convolutional networks, as well as advanced deep learning baselines including Transformer and ST-Transformer. Ablation studies confirm the complementary effectiveness of the spatial and temporal modules, and computational time comparisons demonstrate the model’s suitability for real-time applications. These results validate the practical potential of the DMST-Transformer for robust effluent quality monitoring in wastewater treatment plants. Future research will focus on scaling the model to larger and more diverse datasets, extending it to predict additional water quality indicators, and deploying it in real-time environmental monitoring systems to support intelligent water resource management. Full article

In HPC systems, job scheduling plays a critical role in determining resource allocation and task execution order. With the continuous expansion of computing scale and increasing system complexity, modern HPC scheduling faces two major challenges: a massive decision space consisting of tens of thousands of computing nodes and a huge job queue, as well as complex temporal dependencies between jobs and dynamically changing resource states.Traditional heuristic algorithms and basic reinforcement learning methods often struggle to effectively address these challenges in dynamic HPC environments. This study proposes a novel scheduling framework that combines GTrXL with PPO, achieving significant performance improvements through multiple technical innovations. The framework leverages the sequence modeling capabilities of the Transformer architecture and selectively filters relevant historical scheduling information through a dual-gate mechanism, improving long sequence modeling efficiency compared to standard Transformers. The proposed SECT module further enhances resource awareness through dynamic feature recalibration, achieving improved system utilization compared to similar attention mechanisms. Experimental results on multiple datasets (ANL-Intrepid, Alibaba, SDSC-SP2) demonstrate that the proposed components achieve significant performance improvements over baseline PPO implementations. Comprehensive evaluations on synthetic workloads and real HPC trace data show improvements in resource utilization and waiting time, particularly under high-load conditions, while maintaining good robustness across various cluster configurations. Full article

With the continuous advancement of artificial intelligence (AI) technology, AI algorithms have demonstrated exceptional aircraft control capabilities in highly dynamic and complex scenarios such as aerial combat. However, the inherent lack of explainability in AI algorithms poses a significant challenge to gaining sufficient trust, presenting potential safety risks that could lead to aircraft loss of control. This limitation hinders the widespread adoption of AI in practical applications. To enhance human–AI trust, improve system stability and safety, and advance the deployment of AI algorithms in practical settings, this study proposes an approach to describe and explain AI decision-making behaviors using natural language. Natural language is a straightforward medium for expressing information, which avoids the need for additional decoding or interpretation, particularly in rapidly changing battlefield environments, enabling pilots to quickly comprehend the intentions of AI algorithms and thereby fostering trust in AI systems. This study constructs a dataset of AI decision behavior description and interpretation based on adversarial temporal data in an aerial combat scenario and introduces an encoder–decoder framework that integrates an attentional mechanism. Findings from the experiments suggest that this approach effectively delineates and elucidates the AI decision-making behaviors, thereby facilitating mutual trust between humans and AI. Full article

With the widespread implementation of bridge structural health monitoring (SHM) systems, monitored bridge networks have gradually formed. Understanding vehicle loads and considering spatio-temporal correlations within bridge networks is critical for structural condition assessment and maintenance decision making. This study aims to predict traffic flows by investigating traffic flow correlations within a bridge network using multi-bridge data, thereby supporting bridge network-level SHM. A transformer-based traffic flow prediction model considering spatio-temporal correlations of bridge networks (ST-TransNet) is proposed. It integrates external factors (processed via fully connected networks) and multi-period traffic flows of input bridges (captured by self-attention encoders) to generate traffic flow predictions through a self-attention decoder. Validated using weigh-in-motion data from an 8-bridge network, the proposed ST-TransNet reduces prediction root mean square error (RMSE) to 12.76 vehicles/10 min, outperforming a series of baselines—SVR, CNN, BiLSTM, CNN&BiLSTM, ST-ResNet, transformer, and STGCN—with significant relative reductions of 40.5%, 36.9%, 36.6%, 37.3%, 35.6%, 31.1%, and 22.8%, respectively. Ablation studies confirm the contribution of each component of the external factors and multi-period traffic flows, particularly the recent traffic flow data. The proposed ST-TransNet effectively captures underlying the spatio-temporal correlations of traffic flow within bridge networks, offering valuable insights for enhancing bridge assessment and maintenance. Full article

To address the challenges of photovoltaic (PV) power prediction in highly dynamic environments. We propose an improved Long Short-Term Memory (ILSTM) model. The model uses Principal Component Analysis (PCA) and Particle Swarm Optimization (PSO) for feature selection, ensuring key information is preserved while reducing dimensionality. The Depthwise Separable Convolution (DSC) module extracts spatial features, while the Channel-Spatial Attention Mechanism (CBAM) focuses on important time-dependent patterns. Finally, Bidirectional Long Short-Term Memory (BiLSTM) captures nonlinear dynamics and long-term dependencies, boosting prediction performance. The model is called DSC-CBAM-BiLSTM. It selects important features adaptively. It captures key spatial-temporal patterns and improves forecasting performance based on RMSE, MAE, and $R^2$. Extensive experiments using real-world PV datasets under varied meteorological scenarios show the proposed model significantly outperforms traditional approaches. Specifically, RMSE and MAE are reduced by over 70%, and the coefficient of determination ($R^2$) is improved by 8.5%. These results confirm the framework’s effectiveness for real-time, short-term PV forecasting and its applicability in energy dispatching and smart grid operations. Full article

Existing methods for diagnosing depression rely heavily on subjective evaluations, whereas electroencephalography (EEG) emerges as a promising approach for objective diagnosis due to its non-invasiveness, low cost, and high temporal resolution. However, current EEG analysis methods are constrained by volume conduction effect and class imbalance, both of which adversely affect classification performance. To address these issues, this paper proposes a multi-stage deep learning model for EEG-based depression classification, integrating a cortical feature extraction strategy (CFE), a feature attention module (FA), a graph convolutional network (GCN), and a focal adversarial domain adaptation module (FADA). Specifically, the CFE strategy reconstructs brain cortical signals using the standardized low-resolution brain electromagnetic tomography (sLORETA) algorithm and extracts both linear and nonlinear features that capture cortical activity variations. The FA module enhances feature representation through a multi-head self-attention mechanism, effectively capturing spatiotemporal relationships across distinct brain regions. Subsequently, the GCN further extracts spatiotemporal EEG features by modeling functional connectivity between brain regions. The FADA module employs Focal Loss and Gradient Reversal Layer (GRL) mechanisms to suppress domain-specific information, alleviate class imbalance, and enhance intra-class sample aggregation. Experimental validation on the publicly available PRED+CT dataset demonstrates that the proposed model achieves a classification accuracy of 85.33%, outperforming current state-of-the-art methods by 2.16%. These results suggest that the proposed model holds strong potential for improving the accuracy and reliability of EEG-based depression classification. Full article