Search Results (3,125)

Emerging complex multi-step attacks such as Advanced Persistent Threats (APTs) pose significant risks to national economic development, security, and social stability. Effectively detecting these sophisticated threats is a critical challenge. While deep learning methods show promise in identifying unknown malicious behaviors, they often struggle with fragmented modal information, limited feature representation, and generalization. To address these limitations, we propose GATransformer, a new dual-modal detection method that integrates topological structure analysis with temporal sequence modeling. Its core lies in a cross-attention semantic fusion mechanism, which deeply integrates heterogeneous features and effectively mitigates the constraints of unimodal representations. GATransformer reconstructs network behavior representation via a parallel processing framework in which graph attention captures intricate spatial dependencies, and self-attention focuses on modeling long-range temporal correlations. Experimental results on the CIDDS-001 and CIDDS-002 datasets demonstrate the superior performance of our method compared to baseline methods with detection accuracies of 99.74% (nodes) and 88.28% (edges) on CIDDS-001 and 99.99% and 99.98% on CIDDS-002, respectively. Full article

Predicting the concentrations of air pollutants, particularly PM_2.5, with accuracy and dependability is crucial for protecting human health and preserving a healthy natural environment. This research proposes a deep learning-based, robust prediction system to predict regional PM_2.5 concentrations for the next one to twenty-four hours. To start, the input features of the prediction system are initially screened using a correlation analysis of various air pollutants and meteorological factors. Next, the BiTCN-ISInformer prediction model with a two-branch parallel architecture is constructed. On the one hand, the model improves the probabilistic sparse attention mechanism in the traditional Informer network by optimizing the sampling method from a single sparse sampling to a synergistic mechanism combining sparse sampling and importance sampling, which improves the prediction accuracy and reduces the computational complexity of the model; on the other hand, through the introduction of the bi-directional time-convolutional network (BiTCN) and the design of parallel architecture, the model is able to comprehensively model the short-term fluctuations and long-term trends of the temporal data and effectively increase the inference speed of the model. According to experimental research, the proposed model performs better in terms of prediction accuracy and performance than the most advanced baseline model. In the single-step and multi-step prediction experiments of Shanghai’s PM_2.5 concentration, the proposed model has a root mean square error (RMSE) ranging from 2.010 to 10.029 and a mean absolute error (MAE) ranging from 1.436 to 6.865. As a result, the prediction system proposed in this research shows promise for use in air pollution early warning and prevention. Full article

Failures of rotating machinery, such as bearings and gears, are a critical concern in industrial systems, leading to significant operational downtime and economic losses. A primary research challenge is achieving accurate fault diagnosis under complex industrial noise, where weak fault signatures are often masked by interference signals. This problem is particularly acute in demanding applications like offshore wind turbines, where harsh operating conditions and high maintenance costs necessitate highly robust and reliable diagnostic methods. To address this challenge, this paper proposes a novel Multi-Scale Domain Convolutional Attention Network (MSDCAN). The method integrates enhanced adaptive multi-domain feature extraction with a hybrid attention mechanism, combining information from the time, frequency, wavelet, and cyclic spectral domains with domain-specific attention weighting. A core innovation is the hybrid attention fusion mechanism, which enables cross-modal interaction between deep convolutional features and domain-specific features, enhanced by channel attention modules. The model’s effectiveness is validated on two public benchmark datasets for key rotating components. On the Case Western Reserve University (CWRU) bearing dataset, the MSDCAN achieves accuracies of 97.3% under clean conditions, 96.6% at 15 dB signal-to-noise ratio (SNR), 94.4% at 10 dB SNR, and a robust 85.5% under severe 5 dB SNR. To further validate its generalization, on the Xi’an Jiaotong University (XJTU) gear dataset, the model attains accuracies of 94.8% under clean conditions, 95.0% at 15 dB SNR, 83.6% at 10 dB SNR, and 63.8% at 5 dB SNR. These comprehensive results quantitatively validate the model’s superior diagnostic accuracy and exceptional noise robustness for rotating machinery, establishing a strong foundation for its application in reliable condition monitoring for complex systems, including wind turbines. Full article

Anomaly detection of catenary support components (CSCs) is an important component in railway condition monitoring systems. However, because the abnormal features of CSCs loosening are not obvious, and the current CNN models and visual Transformer models have problems such as limited remote modeling capabilities and secondary computational complexity, it is difficult for existing deep learning anomaly detection methods to effectively exert their performance. The state space model (SSM) represented by Mamba is not only good at long-range modeling, but also maintains linear computational complexity. In this paper, using the state space model (SSM), we proposed a new visual state space reconstruction network (VSM-UNet) for the detection of CSC loosening anomalies. First, based on the structure of UNet, a visual state space block (VSS block) is introduced to capture extensive contextual information and multi-scale features, and an asymmetric encoder–decoder structure is constructed through patch merging operations and patch expanding operations. Secondly, the CBAM attention mechanism is introduced between the encoder–decoder structure to enhance the model’s ability to focus on key abnormal features. Finally, a stable abnormality score calculation module is designed using MLP to evaluate the degree of abnormality of components. The experiment shows that the VSM-UNet model, learning strategy and anomaly score calculation method proposed in this article are effective and reasonable, and have certain advantages. Specifically, the proposed method framework can achieve an AUROC of 0.986 and an FPS of 26.56 in the anomaly detection task of looseness on positioning clamp nuts, U-shaped hoop nuts, and cotton pins. Therefore, the method proposed in this article can be effectively applied to the detection of CSCs abnormalities. Full article

Background/Objectives: The YSK olfactory function (YOF) test is a culturally adapted psychophysical tool that assesses threshold, discrimination, and identification. This study evaluated whether functional near-infrared spectroscopy (fNIRS) synchronized with routine YOF testing, combined with machine learning, can predict YOF subdomain performance in healthy adults, providing an objective neural correlate to complement behavioral testing. Methods: In this prospective diagnostic-accuracy (feasibility/validation) study in healthy adults with algorithm development, 100 healthy adults completed the YOF test while undergoing prefrontal/orbitofrontal fNIRS during odor blocks. Feature sets from ΔHbO/ΔHbR included time-domain descriptors, complexity (Lempel–Ziv), and information-theoretic measures (mutual information); the identification task used a hybrid attention–CNN. Separate models were developed for threshold (binary classification), discrimination (binary classification), and identification (binary classification). Performance was summarized with accuracy, area under the curve (AUC), F1-score, and (where applicable) sensitivity/specificity, using participant-level cross-validation. Results: The threshold classifier achieved accuracy 0.86, AUC 0.86, and F1 0.86, indicating strong discrimination of correct vs. incorrect threshold responses. The discrimination model yielded accuracy 0.75, AUC 0.76, and F1 0.75. The identification model (attention–convolutional neural network [CNN]) achieved accuracy 0.88, sensitivity 0.86, specificity 0.91, and F1 0.88. Feature-attribution (e.g., SHapley Additive exPlanations [SHAP]) provided interpretable links between fNIRS features and task performance for threshold and discrimination. Conclusions: Olfactory-evoked fNIRS signals can accurately predict YOF subdomain performance in healthy adults, supporting the feasibility of non-invasive, portable, near–real-time olfactory monitoring. These findings are preliminary and not generalizable to clinical populations; external validation in diverse cohorts is warranted. The approach clarifies the scientific essence of the method by (i) aligning psychophysical outcomes with objective hemodynamic signatures and (ii) introducing a feature-rich modeling pipeline (ΔHbO/ΔHbR + Lempel–Ziv complexity/mutual information; attention–CNN) that advances prior work. Full article

The inspection of power equipment is vital for maintaining the safe and reliable operation of power systems. Among various inspection tasks, the detection of defects in insulators and wind turbine blades holds particular importance. However, existing detection methods often suffer from limited accuracy, largely due to substantial scale variations among defect targets and the loss of features associated with small objects. To address these challenges, this paper proposes Inspection of Power Equipment-YOLO (IPE-YOLO), an enhanced defect detection algorithm based on the YOLOv8n framework. First, a Cross Stage Partial Multi-Scale Edge Information Enhancement (CSP_MSEIE) module is introduced to improve multi-scale feature extraction, enhancing the detection of targets with significant scale diversity while reducing computational complexity. Second, we reconstruct the neck network with a Context-Guided Spatial Feature Reconstruction for Feature Pyramid Networks (CGRFPN), which promotes cross-scale feature fusion and enriches the fine-grained details of small objects, thereby alleviating feature loss in deeper network layers. Finally, a Lightweight Shared Convolutional Detection Head (LSCD) is employed, leveraging shared convolutional layers to decrease model parameters and computational costs without sacrificing detection precision. Experimental results demonstrate that, compared to the baseline YOLOv8n model, IPE-YOLO improves defect detection accuracy for insulators and wind turbine blades by 2.6% and 2.9%, respectively, while reducing the number of parameters by 12.3% and computational costs by 24.7%. These results indicate that IPE-YOLO achieves a superior balance between accuracy and efficiency, making it well-suited for practical engineering deployments in power equipment inspection. Full article

The globalization of hardware design flows has increased the risk of Hardware Trojan (HT) insertion during the design phase. Graph-based learning methods have shown promise for HT detection at the Register Transfer Level (RTL). However, most existing approaches rely on representing RTL designs through a single graph structure. This single-view modeling paradigm inherently constrains the model’s ability to perceive complex behavioral patterns, consequently limiting detection performance. To address these limitations, we propose GNN-MFF, an innovative multi-view feature fusion model based on Graph Neural Networks (GNNs). Our approach centers on joint multi-view modeling of RTL designs to achieve a more comprehensive representation. Specifically, we construct complementary graph-structural views: the Abstract Syntax Tree (AST) capturing structure information, and the Data Flow Graph (DFG) modeling logical dependency relationships. For each graph structure, customized GNN architectures are designed to effectively extract its features. Furthermore, we develop a feature fusion framework that leverages a multi-head attention mechanism to deeply explore and integrate heterogeneous features from distinct views, thereby enhancing the model’s capacity to structurally perceive anomalous logic patterns. Evaluated on an extended Trust-Hub-based HT benchmark dataset, our model achieves an average F1-score of 97.08% in automated detection of unseen HTs, surpassing current state-of-the-art methods. Full article

Semantic segmentation is a crucial task in computer vision with broad applications in autonomous driving, intelligent surveillance, drone vision, and other fields. The current high-precision segmentation models generally suffer from large parameter sizes, high computational complexity, and substantial memory consumption, which limits their efficient deployment in embedded systems and resource-constrained environments. In addition, traditional methods exhibit significant limitations in handling multi-scale targets and object boundaries, particularly during deep feature extraction, where the loss of shallow spatial information often results in blurred boundaries and reduced segmentation accuracy. To address these challenges, we propose EfficientSegNet, a lightweight and efficient semantic segmentation network. This network features an innovative architecture that integrates the Cascade-Attention Dense Field (CADF) module and the Dynamic Weighting Feature Fusion (DWF) module, effectively reducing computational resource requirements while balancing global semantic information and local detail recovery. Experimental results demonstrate that EfficientSegNet achieves an excellent balance between segmentation accuracy and computational efficiency on multiple public datasets, providing robust support for real-time segmentation tasks and applications on resource-constrained devices. Full article

Recent advances in plant electrophysiology and machine learning suggest that bioelectric signals in plants may encode environmentally relevant information beyond physiological processes. In this study, we present a novel framework to analyse waveforms from real-time bioelectrical potentials recorded in vascular plants. Using a multi-channel electrophysiological monitoring system, we acquired continuous data from Vitis vinifera samples in a vineyard plantation under natural conditions. Plants were in different health conditions: healthy; under the infection of Flavescence dorée; plants in recovery from the same disease; and dead stumps. These signals were used as input features for an ensemble of complex machine learning models, including recurrent neural networks, trained to infer short-term meteorological parameters such as temperature and humidity. The models demonstrated predictive capabilities, with accuracy comparable to sensor-based benchmarks between one and two degree Celsius for temperature, particularly in forecasting rapid weather transitions. Feature importance analysis revealed plant-specific electrophysiological patterns that correlated with ambient conditions, suggesting the existence of biological pre-processing mechanisms sensitive to microclimatic fluctuations. This bioinspired approach opens new directions for developing plant-integrated environmental intelligence systems, offering passive and biologically rooted strategies for ultra-local forecasting—especially valuable in remote, sensor-sparse, or climate-sensitive regions. Our findings contribute to the emerging field of plant-based sensing and biomimetic environmental monitoring, expanding the role of flora to biosensors, useful in Earth system observation tasks. Full article

Nonlinear complex systems exhibit emergent behavior, sensitivity to initial conditions, and rich dynamics arising from interactions among their components. A classical example of such a system is the Troesch problem—a nonlinear boundary value problem with wide applications in physics and engineering. In this work, we investigate and compare two distinct approaches to solving this problem: the Differential Transform Method (DTM), representing an analytical–symbolic technique, and Physics-Informed Neural Networks (PINNs), a neural computation framework inspired by physical system dynamics. The DTM yields a continuous form of the approximate solution, enabling detailed analysis of the system’s dynamics and error control, whereas PINNs, once trained, offer flexible estimation at any point in the domain, embedding the physical model into an adaptive learning process. We evaluate both methods in terms of accuracy, stability, and computational efficiency, with particular focus on their ability to capture key features of nonlinear complex systems. The results demonstrate the potential of combining symbolic and neural approaches in studying emergent dynamics in nonlinear systems. Full article

Unmanned aerial vehicle (UAV) image object detection has become an increasingly important research area in computer vision. However, the variable target shapes and complex environments make it difficult for the model to fully exploit its features. In order to solve this problem, we propose a UAV image object detection method based on a backbone feature reuse detection network, named BFRDNet. First, we design a backbone feature reuse pyramid network (BFRPN), which takes the model characteristics as the starting point and more fully utilizes the multi-scale features of backbone network to improve the model’s performance in complex environments. Second, we propose a feature extraction module based on multiple kernels convolution (MKConv), to deeply mine features under different receptive fields, helping the model accurately recognize targets of different sizes and shapes. Finally, we design a detection head preprocessing module (PDetect) to enhance the feature representation fed to the detection head and effectively suppress the interference of background information. In this study, we validate the performance of BFRDNet primarily on the VisDrone dataset. The experimental results demonstrate that BFRDNet achieves a significant improvement in detection performance, with the mAP increasing by 7.5%. To additionally evaluate the model’s generalization capacity, we extend the experiments to the UAVDT and COCO datasets. Full article

Network anomaly detection is widely used in network analysis and security prevention, in which reconstruction-based approaches have achieved remarkable results. However, attributed networks exhibit highly nonlinear relationships and time dependence over time, which make the anomalies more complex and ambiguous, resulting in anomaly detection still facing challenges. To this end, this study proposes an adversarial reconstruction framework with spectral-augmented and graph joint embedding for anomaly detection (GAN-SAGE), which integrates an autoencoder (AE) based on the frequency feature enhanced graph transformer (GT) into the generator for generating adversarial networks (GAN), improving network representation through adversarial training. The first stage of the encoding process captures the frequency domain information of the input timing data through spectral-augmented, and the second stage enhances the modeling capability of spatial structure and graph interaction dependency through multi-attribute coupling and GTs. We conducted extensive experiments on AIOps, SWaT and WADI datasets, demonstrating the effectiveness of GAN-SAGE compared to the state-of-the-art method. The detection performance of GAN-SAGE, respectively, improved by an average of 9.64%, 18.73% and 19.79% in terms of F1-score across the three datasets. Full article

Accurate detection and counting of rice ears serve as a critical indicator for yield estimation, but the complex conditions of paddy fields limit the efficiency and precision of traditional sampling methods. We propose REU-YOLO, a model specifically designed for UAV low-altitude remote sensing to collect images of rice ears, to address issues such as high-density and complex spatial distribution with occlusion in field scenes. Initially, we combine the Additive Block containing Convolutional Additive Self-attention (CAS) and Convolutional Gated Linear Unit (CGLU) to propose a novel module called Additive-CGLU-C2F (AC-C2f) as a replacement for the original C2f in YOLOv8. It can capture the contextual information between different regions of images and improve the feature extraction ability of the model, introduce the Dropblock strategy to reduce model overfitting, and replace the original SPPF module with the SPPFCSPC-G module to enhance feature representation and improve the capacity of the model to extract features across varying scales. We further propose a feature fusion network called Multi-branch Bidirectional Feature Pyramid Network (MBiFPN), which introduces a small object detection head and adjusts the head to focus more on small and medium-sized rice ear targets. By using adaptive average pooling and bidirectional weighted feature fusion, shallow and deep features are dynamically fused to enhance the robustness of the model. Finally, the Inner-PloU loss function is introduced to improve the adaptability of the model to rice ear morphology. In the self-developed dataset UAVR, REU-YOLO achieves a precision (P) of 90.76%, a recall (R) of 86.94%, an mAP_0.5 of 93.51%, and an mAP_0.5:0.95 of 78.45%, which are 4.22%, 3.76%, 4.85%, and 8.27% higher than the corresponding values obtained with YOLOv8 s, respectively. Furthermore, three public datasets, DRPD, MrMT, and GWHD, were used to perform a comprehensive evaluation of REU-YOLO. The results show that REU-YOLO indicates great generalization capabilities and more stable detection performance. Full article

The process of dissection is essential to the study of anatomy, with the variety of colours, shapes, patterns and textures revealing the distinctive features of each anatomical system, but it can also be misleading, because while the body’s constituent ‘parts’ have traditionally been classified according to their appearance, assumed functions and perceived importance, this basic information can be interpreted in different ways. Living organisms are intrinsically indeterminate, which implies that the conclusions arrived at through the study of anatomy are not necessarily congruent with the anatomical reality, and the abstract classifications of the connective tissues (CTs) are a case in point. This paper highlights a seventeenth-century interpretation of CT anatomy that was pushed aside as the musculoskeletal duality assumed functional dominance and relegated the fascial tissues to mere ancillary roles. In other words, an architectural framework of tensioned fibrous tissues that encompasses a complex body-wide heterarchy of space-filling compartments under compression and reasserts the structural significance of the soft CTs. The problems with orthodox classifications are then discussed alongside a mechano-structural role for the ‘loose’ fibrillar network: a closed-chain kinematic system that guides changes in the relative positions of adjacent compartments and refutes the notion of fascial ‘layers’. Full article

With the increasing demand for intelligent mobility assistance among the visually impaired, machine guide dogs based on computer vision have emerged as an effective alternative to traditional guide dogs, owing to their flexible deployment and scalability. To enhance their visual perception capabilities in complex urban environments, this paper proposes an improved YOLOv8-based detection algorithm, termed TFP-YOLO, designed to recognize traffic signs such as traffic lights and crosswalks, as well as small obstacle objects including pedestrians and bicycles, thereby improving the target detection performance of machine guide dogs in complex road scenarios. The proposed algorithm incorporates a Triplet Attention mechanism into the backbone network to strengthen the perception of key regions, and integrates a Triple Feature Encoding (TFE) module to achieve collaborative extraction of both local and global features. Additionally, a P2 detection head is introduced to improve the accuracy of small object detection, particularly for traffic lights. Furthermore, the WIoU loss function is adopted to enhance training stability and the model’s generalization capability. Experimental results demonstrate that the proposed algorithm achieves a detection accuracy of 93.9% and a precision of 90.2%, while reducing the number of parameters by 17.2%. These improvements significantly enhance the perception performance of machine guide dogs in identifying traffic information and obstacles, providing strong technical support for subsequent path planning and embedded deployment, and demonstrating considerable practical application value. Full article