Search Results (50)

Accurate heavy-duty vehicle load estimation is crucial for transportation and environmental regulation, yet current methods lack precision in data accuracy and practicality for field implementation. We propose a Self-Supervised Reconstruction Heterogeneous Graph Convolutional Network (SSR-HGCN) for load estimation using On-Board Diagnostics (OBD) data. The method integrates physics-constrained heterogeneous graph construction based on vehicle speed, acceleration, and engine parameters, leveraging graph neural networks’ information propagation mechanisms and self-supervised learning’s adaptability to low-quality data. The method comprises three modules: (1) a physics-constrained heterogeneous graph structure that, guided by the symmetry (invariance) of physical laws, introduces a structural asymmetry by treating kinematic and dynamic features as distinct node types to enhance model interpretability; (2) a self-supervised reconstruction module that learns robust representations from noisy OBD streams without extensive labeling, improving adaptability to data quality variations; and (3) a multi-layer feature extraction architecture combining graph convolutional networks (GCNs) and graph attention networks (GATs) for hierarchical feature aggregation. On a test set of 800 heavy-duty vehicle trips, SSR-HGCN demonstrated superior performance over key baseline models. Compared with the classical time-series model LSTM, it achieved average improvements of 20.76% in RMSE and 41.23% in MAPE. It also outperformed the standard graph model GraphSAGE, reducing RMSE by 21.98% and MAPE by 7.15%, ultimately achieving < 15% error for over 90% of test samples. This method provides an effective technical solution for heavy-duty vehicle load monitoring, with immediate applications in fleet supervision, overloading detection, and regulatory enforcement for environmental compliance. Full article

Cow behavior recognition constitutes a fundamental element of effective cow health monitoring and intelligent farming systems. Within large-scale cow farming environments, several critical challenges persist, including the difficulty in accurately capturing behavioral feature information, substantial variations in multi-scale features, and high inter-class similarity among different cow behaviors. To address these limitations, this study introduces an enhanced target detection algorithm for cow behavior recognition, termed RFR-YOLO, which is developed upon the YOLOv11n framework. A well-structured dataset encompassing nine distinct cow behaviors—namely, lying, standing, walking, eating, drinking, licking, grooming, estrus, and limping—is constructed, comprising a total of 13,224 labeled samples. The proposed algorithm incorporates three major technical improvements: First, an Inverted Dilated Convolution module (Region Semantic Inverted Convolution, RsiConv) is designed and seamlessly integrated with the C3K2 module to form the C3K2_Rsi module, which effectively reduces computational overhead while enhancing feature representation. Second, a Four-branch Multi-scale Dilated Attention mechanism (Four Multi-Scale Dilated Attention, FMSDA) is incorporated into the network architecture, enabling the scale-specific features to align with the corresponding receptive fields, thereby improving the model’s capacity to capture multi-scale characteristics. Third, a Reparameterized Generalized Residual Feature Pyramid Network (Reparameterized Generalized Residual-FPN, RepGRFPN) is introduced as the Neck component, allowing for the features to propagate through differentiated pathways and enabling flexible control over multi-scale feature expression, thereby facilitating efficient feature fusion and mitigating the impact of behavioral similarity. The experimental results demonstrate that RFR-YOLO achieves precision, recall, mAP50, and mAP50:95 values of 95.9%, 91.2%, 94.9%, and 85.2%, respectively, representing performance gains of 5.5%, 5%, 5.6%, and 3.5% over the baseline model. Despite a marginal increase in computational complexity of 1.4G, the algorithm retains a high detection speed of 147.6 frames per second. The proposed RFR-YOLO algorithm significantly improves the accuracy and robustness of target detection in group cow farming scenarios. Full article

With the rapid expansion of multi-platform remote sensing applications, cloud contamination significantly impedes cross-platform data utilization. Current cloud detection methods face critical technical challenges in cross-platform settings, including neglect of atmospheric radiative transfer mechanisms, inadequate multi-scale structural decoupling, high intra-class variability coupled with inter-class similarity, cloud boundary ambiguity, cross-modal feature inconsistency, and noise propagation in pseudo-labels within semi-supervised frameworks. To address these issues, we introduce a Physics-Guided Multi-Representation Network (PGMRN) that adopts a student–teacher architecture and fuses tri-modal representations—Pseudo-NDVI, structural, and textural features—via atmospheric priors and intrinsic image decomposition. Specifically, PGMRN first incorporates an InfoNCE contrastive loss to enhance intra-class compactness and inter-class discrimination while preserving physical consistency; subsequently, a boundary-aware regional adaptive weighted cross-entropy loss integrates PA-CAM confidence with distance transforms to refine edge accuracy; furthermore, an Uncertainty-Aware Quadruple Consistency Propagation (UAQCP) enforces alignment across structural, textural, RGB, and physical modalities; and finally, a dynamic confidence-screening mechanism that couples PA-CAM with information entropy and percentile-based thresholding robustly refines pseudo-labels. Extensive experiments on four benchmark datasets demonstrate that PGMRN achieves state-of-the-art performance, with Mean IoU values of 70.8% on TCDD, 79.0% on HRC_WHU, and 83.8% on SWIMSEG, outperforming existing methods. Full article

Domain Generation Algorithms (DGAs) remain a persistent technique used by modern malware to establish stealthy command-and-control (C&C) channels, thereby evading traditional blacklist-based defenses. Detecting such evolving threats is especially challenging in decentralized environments where raw traffic data cannot be aggregated due to privacy or policy constraints. To address this, we present FedSAGE, a security-aware federated intrusion detection framework that combines Variational Autoencoder (VAE)-based latent representation learning with unsupervised clustering and resource-efficient client selection. Each client encodes its local domain traffic into a semantic latent space using a shared, pre-trained VAE trained solely on benign domains. These embeddings are clustered via affinity propagation to group clients with similar data distributions and identify outliers indicative of novel threats without requiring any labeled DGA samples. Within each cluster, FedSAGE selects only the fastest clients for training, balancing computational constraints with threat visibility. Experimental results from the multi-zones DGA dataset show that FedSAGE improves detection accuracy by up to 11.6% and reduces energy consumption by up to 93.8% compared to standard FedAvg under non-IID conditions. Notably, the latent clustering perfectly recovers ground-truth DGA family zones, enabling effective anomaly detection in a fully unsupervised manner while remaining privacy-preserving. These foundations demonstrate that FedSAGE is a practical and lightweight approach for decentralized detection of evasive malware, offering a viable solution for secure and adaptive defense in resource-constrained edge environments. Full article

The complex and variable operating conditions of sucker-rod pumping wells pose a significant challenge for the timely and accurate identification of oil well operating conditions. Effective deep learning based on measured multi-source data obtained from the sucker-rod pumping well production site offers a promising solution to the challenge. However, existing deep learning-based operating condition recognition methods are constrained by several factors: the limitations of traditional operating condition recognition methods based on single-source and multi-source data, the need for large amounts of labeled data for training, and the high robustness requirement for recognizing complex and variable data. Therefore, we propose a semi-supervised class-incremental sucker-rod pumping well operating condition recognition method based on measured multi-source data distillation. Firstly, we select measured ground dynamometer cards and measured electrical power cards as information sources, and construct the graph neural network teacher models for data sources, and dynamically fuse the prediction probability of each teacher model through the Squeeze-and-Excitation attention mechanism. Then, we introduce a multi-source data distillation loss. It uses Kullback-Leibler (KL) divergence to measure the difference between the output logic of the teacher and student models. This helps reduce the forgetting of old operating condition category knowledge during class-incremental learning. Finally, we employ a multi-source semi-supervised graph classification method based on enhanced label propagation, which improves the label propagation method through a logistic regression classifier. This method can deeply explore the potential relationship between labeled and unlabeled samples, so as to further enhance the classification performance. Extensive experimental results show that the proposed method achieves superior recognition performance and enhanced engineering practicality in real-world class-incremental oil extraction production scenarios with complex and variable operating conditions. Full article

Fraud detection in large-scale graphs presents significant challenges, especially in heterophilic graphs where linked nodes often belong to dissimilar classes or exhibit contrasting attributes. These asymmetric interactions, combined with class imbalance and limited labeled data, make it difficult to fully leverage node labels in semi-supervised learning frameworks. This study aims to address these challenges by proposing a novel framework, Spectrum-Constrained and Skip-Enhanced Graph Fraud Detection (SCSE-GFD), designed specifically for fraud detection in heterophilic graphs. The primary objective is to enhance fraud detection performance while maintaining computational efficiency. SCSE-GFD integrates several key components to improve performance. It employs adaptive polynomial convolution to capture multi-frequency signals and utilizes relation-specific spectral filtering to accommodate both homophilic and heterophilic structures. Additionally, a relation-aware mechanism is incorporated to differentiate between edge types, which enhances feature propagation across diverse graph connections. To address the issue of over-smoothing, skip connections are used to preserve both low- and high-level node representations. Furthermore, supervised edge classification is used to improve the structural understanding of the graph. Extensive experiments on real-world datasets, including Amazon and YelpChi, demonstrate SCSE-GFD’s effectiveness. The framework achieved state-of-the-art AUC scores of 96.21% on Amazon and 90.58% on YelpChi, significantly outperforming existing models. These results validate SCSE-GFD’s ability to improve fraud detection accuracy while maintaining efficiency. Full article

Background/Objectives: Regadenoson, a selective adenosine A_2A receptor agonist, is primarily prescribed for myocardial perfusion imaging (MPI). As its clinical use becomes more widespread in practice, assessing its safety in real-world settings is essential. Methods: In this research, disproportionality analysis was applied to evaluate the safety of Regadenoson by examining all adverse event (AE) reports since 2004 in the FDA Adverse Event Reporting System (FAERS), in which Regadenoson was identified as the primary suspected drug. The reporting odds ratio (ROR), proportional reporting ratio (PRR), multi-item gamma Poisson shrinker (MGPS), and Bayesian confidence propagation neural network (BCPNN) were used to analyze AEs associated with Regadenoson. The Weibull distribution was utilized to model the temporal risk of AEs. Results: The results confirmed some known adverse reactions, such as nausea, shortness of breath (dyspnea), palpitations/vomiting, headache, dizziness, chest pain, and flushing (facial redness or warmth), which were also listed on the drug’s label. New potential adverse reactions not mentioned in the label were identified, including micturition urgency, mental status changes, conversion disorder, eye movement disorder, and genital paraesthesia. This study highlighted the significance of monitoring AEs, particularly right after the start of Regadenoson administration. Conclusions: This study provides preliminary safety data on Regadenoson’s real-world use, corroborating known adverse effects while uncovering new potential risks. These findings offer valuable safety insights for clinicians when prescribing Regadenoson for the use of MPI. Full article

Hierarchical text classification (HTC) is a challenging task that requires classifiers to solve a series of multi-label subtasks considering hierarchical dependencies among labels. Recent studies have introduced prompt tuning to create closer connections between the language model (LM) and the complex label hierarchy. However, we find that the model’s attention to the prompt gradually decreases as the prompt moves from the input to the output layer, revealing the limitations of previous prompt tuning methods for HTC. Given the success of prefix tuning-based studies in natural language understanding tasks, we introduce Structural entroPy guIded pRefIx Tuning (SPIRIT). Specifically, we extract the essential structure of the label hierarchy via structural entropy minimization and decode the abstractive structural information as the prefix to prompt all intermediate layers in the LM. Additionally, a depth-wise reparameterization strategy is developed to enhance optimization and propagate the prefix throughout the LM layers. Extensive evaluation on four popular datasets demonstrates that SPIRIT achieves a state-of-the-art performance. Full article

For information security, entity and relation extraction can be applied in sensitive information protection, data leakage detection, and other aspects. The current approaches to entity relation extraction not only ignore the relevance and dependency between name entity recognition and relation extraction but also may result in the cumulative propagation of errors. To solve this problem, it is proposed that an end-to-end joint entity and relation extraction model based on the Attention mechanism and Graph Convolutional Network (GCN) to simultaneously extract named entities and their relationships. The model includes three parts: the detection of entity span, the construction of an entity relation weighted graph, and the inference of entity relation type. Firstly, the detection of entity spans is viewed as a sequence labeling problem, and a multi-feature fusion approach for word embedding representation is designed to calculate all entity spans in a sentence to form an entity span matrix. Secondly, the entity span matrix is employed in the Multi-Head Attention mechanism for constructing the weighted adjacency matrix of the entity relation graph. Finally, for the inference of entity relation type, considering the interaction between entities and relations, the entity span matrix and relation connection matrix are simultaneously fed into the GCN for integrated extraction of entities and relations. Our model is evaluated on the public NYT dataset, attaining a precision of 66.4%, a recall of 63.1%, and an F1 score of 64.7% for joint entity and relation extraction, significantly outperforming other approaches. Experiments demonstrate that the proposed model is helpful for inferring entities and relations, considering the interaction between entities and relations through the Attention mechanism and GCN. Full article

Cyber–physical systems (CPSs) serve as the pivotal core of Internet of Things (IoT) infrastructures, such as smart grids and intelligent transportation, deploying interconnected sensing devices to monitor operating status. With increasing decentralization, the surge in sensor devices expands the potential vulnerability to cyber attacks. It is imperative to conduct anomaly detection research on the multivariate time series data that these sensors produce to bolster the security of distributed CPSs. However, the high dimensionality, absence of anomaly labels in real-world datasets, and intricate non-linear relationships among sensors present considerable challenges in formulating effective anomaly detection algorithms. Recent deep-learning methods have achieved progress in the field of anomaly detection. Yet, many methods either rely on statistical models that struggle to capture non-linear relationships or use conventional deep learning models like CNN and LSTM, which do not explicitly learn inter-variable correlations. In this study, we propose a novel unsupervised anomaly detection method that integrates Sparse Autoencoder with Graph Transformer network (SGTrans). SGTrans leverages Sparse Autoencoder for the dimensionality reduction and reconstruction of high-dimensional time series, thus extracting meaningful hidden representations. Then, the multivariate time series are mapped into a graph structure. We introduce a multi-head attention mechanism from Transformer into graph structure learning, constructing a Graph Transformer network forecasting module. This module performs attentive information propagation between long-distance sensor nodes and explicitly models the complex temporal dependencies among them to enhance the prediction of future behaviors. Extensive experiments and evaluations on three publicly available real-world datasets demonstrate the effectiveness of our approach. Full article

The graph neural network (GNN) has shown outstanding performance in processing unstructured data. However, the downstream task performance of GNN strongly depends on the accuracy of data graph structural features and, as a type of deep learning (DL) model, the size of the training dataset is equally crucial to its performance. This paper is based on graph neural networks to predict and complete the target radio environment map (REM) through multiple complete REMs and sparse spectrum monitoring data in the target domain. Due to the complexity of radio wave propagation in space, it is difficult to accurately and explicitly construct the spatial graph structure of the spectral data. In response to the two above issues, we propose a multi-source domain adaptive of GNN for regression (GNN-MDAR) model, which includes two key modules: (1) graph structure alignment modules are used to capture and learn graph structure information shared by cross-domain radio propagation and extract reliable graph structure information for downstream reference signal receiving power (RSRP) prediction task; and (2) a spatial distribution matching module is used to reduce the feature distribution mismatch across spatial grids and improve the model’s ability to remain domain invariant. Based on the measured REMs dataset, the comparative results of simulation experiments show that the GNN-MDAR outperforms the other four benchmark methods in accuracy when there is less RSRP label data in the target domain. Full article

More than 80% of people who commit suicide disclose their intention to do so on social media. The main information we can use in social media is user-generated posts, since personal information is not always available. Identifying all possible emotions in a single textual post is crucial to detecting the user’s mental state; however, human emotions are very complex, and a single text instance likely expresses multiple emotions. This paper proposes a new multi-label emotion graph representation for social media post-based mental health classification. We first construct a word–document graph tensor to describe emotion-based contextual representation using emotion lexicons. Then, it is trained by multi-label emotions and conducts a graph propagation for harmonising heterogeneous emotional information, and is applied to a textual graph mental health classification. We perform extensive experiments on three publicly available social media mental health classification datasets, and the results show clear improvements. Full article

This paper discusses a key technique for passive localization and tracking of radiation sources, which obtains the motion trajectory of radiation sources carried by unmanned aerial vehicles (UAVs) by continuously or periodically localizing it without the active participation of the radiation sources. However, the existing methods have some limitations in complex signal environments and non-stationary wireless propagation that impact the accuracy of localization and tracking. To address these challenges, this paper extends the $\delta$-generalized labeled multi-Bernoulli (GLMB) filter to the scenario of passive localization and tracking based on the random finite-set (RFS) framework and provides the extended Kalman filter (EKF) and unscented Kalman filter (UKF) implementations of the $\delta$-GLMB filter, which fully take into account the nonlinear motion of the radiation source. By modeling the “obstacle scenario” and the influence of external factors (e.g., weather, terrain), our proposed GLMB filter can accurately track the target and capture its motion trajectory. Simulation results verify the effectiveness of the GLMB filter in target identification and state tracking. Full article

Few-shot learning aims to solve the difficulty in obtaining training samples, leading to high variance, high bias, and over-fitting. Recently, graph-based transductive few-shot learning approaches supplement the deficiency of label information via unlabeled data to make a joint prediction, which has become a new research hotspot. Therefore, in this paper, we propose a novel ensemble semi-supervised few-shot learning strategy via transductive network and Dempster–Shafer (D-S) evidence fusion, named ensemble transductive propagation networks (ETPN). First, we present homogeneity and heterogeneity ensemble transductive propagation networks to better use the unlabeled data, which introduce a preset weight coefficient and provide the process of iterative inferences during transductive propagation learning. Then, we combine the information entropy to improve the D-S evidence fusion method, which improves the stability of multi-model results fusion from the pre-processing of the evidence source. Third, we combine the L2 norm to improve an ensemble pruning approach to select individual learners with higher accuracy to participate in the integration of the few-shot model results. Moreover, interference sets are introduced to semi-supervised training to improve the anti-disturbance ability of the mode. Eventually, experiments indicate that the proposed approaches outperform the state-of-the-art few-shot model. The best accuracy of ETPN increases by 0.3% and 0.28% in the 5-way 5-shot, and by 3.43% and 7.6% in the 5-way 1-shot on miniImagNet and tieredImageNet, respectively. Full article

Multi-person pose tracking is a challenging task. It requires identifying the human poses in each frame and matching them across time. This task still faces two main challenges. Firstly, sudden camera zooming and drastic pose changes between adjacent frames may result in mismatched poses between them. Secondly, the time relationships modeled by most existing methods provide insufficient information in scenarios with long-term occlusion. In this paper, to address the first challenge, we propagate the bounding boxes of the current frame to the previous frame for pose estimation, and match the estimated results with the previous ones, which we call the Backward Temporal Pose-Matching (BTPM) module. To solve the second challenge, we design an Association Across Multiple Frames (AAMF) module that utilizes long-term temporal relationships to supplement tracking information lost in the previous frames as a Re-identification (Re-id) technique. Specifically, we select keyframes with a fixed step size in the videos and label other frames as general frames. In the keyframes, we use the BTPM module and the AAMF module to perform tracking. In the general frames, we propagate poses in the previous frame to the current frame for pose estimation and association, which we call the Forward Temporal Pose-Matching (FTPM) module. If the pose association fails, the current frame will be set as a keyframe, and tracking will be re-performed. In the PoseTrack 2018 benchmark tests, our method shows significant improvements over the baseline methods, with improvements of 2.1 and 1.1 in mean Average Precision (mAP) and Multi-Object Tracking Accuracy (MOTA), respectively. Full article