Search Results (757)

Movie genre classification is a significant challenge in narrative analysis, as traditional methods often fail to capture complex structural relationships within movie stories. This study introduces the Intra-Cluster Weighted Movie Network (ICWMN), a novel framework designed to improve classification by using intra-movie relationships through Graph Neural Networks (GNNs). We constructed a large-scale dataset of 1631 movie character networks using an automated pipeline comprising web scraping, regular expressions, and fine-tuned BERT models for entity recognition. To address the computational limitations of fully connected models, we partition ICWMN into clusters and establish edges only between the k-most similar nodes using the K-Nearest Neighbor algorithm and various distance measures, such as the Laplacian and NetLSD. XGBoost is applied to optimize high-dimensional node feature vectors. Experimental results demonstrate outstanding performance, with the Graph Attention Network (GAT) emerging as the top-performing architecture, resulting in classification accuracies that peak at $95.00\%$ on our 1631-movie dataset and an exceptional $97.30\%$ on the 773-movie Moviegalaxies dataset. These findings confirm that prioritizing spectral properties and cluster-based network topologies significantly improve the precision and stability of genre classification compared to state-of-the-art methods. Full article

Industrial control systems (ICS) are increasingly targeted by cyberattacks that manipulate physical processes while evading data-driven detectors trained on raw time-series data. This paper extracts 34–41 control-theoretic features, including tracking error, valve mismatch, sensor liveness, and their temporal derivatives, from Proportional–Integral–Derivative (PID) control loops and evaluates them using an Isolation Forest combined with a maximum z-score. On HAI 21.03, Stage 1 achieves a PA-F1 score of 0.8945, detecting 48 out of 50 attacks. On HAI 23.05, Stage 1 attains a PA-F1 score of 0.9210, surpassing seven deep-learning baselines by at least 23 PA-F1 points; the closest baseline, a learned Graph Neural Network (GNN), achieves 0.6890. Re-implementations of ConvBiLSTM-AE (PA-F1 = 0.6689) and TranAD (PA-F1 = 0.6838) on the same evaluation split confirm this performance gap. A controlled USAD experiment, with PA-F1 = 0.7343 for physics features versus 0.6687 for raw Supervisory Control and Data Acquisition (SCADA), demonstrates that the extracted features provide the detection signal independently of the model architecture. Adding a bidirectional Gated Recurrent Unit (GRU) refinement stage improves PA-F1 by 8.1 percentage points on HAI 21.03, but the same stage reduces it by 6.8 percentage points on HAI 23.05, where attacks manifest as brief perturbations; four alternative Stage 2 designs reproduce this degradation. We therefore characterize temporal refinement as beneficial only for sustained-deviation attacks and identify Stage 1 as the primary deployable detector. This study is the first to apply physics-informed features, report both PA-F1 and eTaPR on HAI 23.05, and perform per-window error diagnosis on this dataset. Results show that 10 of 15 detected windows are covered by fewer than 10% of their timesteps, revealing a structural tension between PA-F1 and eTaPR. Full article

Molecular property prediction is a fundamental task in drug discovery and materials design. While graph neural networks (GNNs) and SMILES-based Transformers have made significant strides, the former are often limited by local message-passing bottlenecks such as over-squashing, while the latter frequently lack explicit topological constraints and suffer from severe vocabulary imbalance. In this work, we revisit the granularity of molecular modeling and propose a representation learning framework built upon bond-level sequences. Our framework models molecules as sequences of directed bond tokens and introduces a structure-aware hybrid attention mechanism. By imposing hard topological constraints on a subset of attention heads to reinforce local connectivity while preserving global receptive fields in the remaining heads, the design is intended to separate short-range chemical bonding from long-range contextual dependencies. For pre-training, we implemented a multi-scale consistency learning paradigm, which utilizes an atom-centric group masking strategy to induce a hierarchical loss of local structural information and employs contrastive and triplet losses to ensure identity consistency across varying scales of structural degradation. Furthermore, by incorporating macro-scale physicochemical descriptors (e.g., LogP, TPSA) as global anchors, we examined how the inclusion of global attribute bias can provide weak physicochemical priors during pre-training, while its effect during downstream fine-tuning remains task-dependent. Experimental results demonstrate that our lightweight model, with approximately 3.5 million parameters, exhibits a dataset-dependent performance profile across MoleculeNet benchmarks and shows promising behavior on selected topology-sensitive tasks, particularly MUV. Ablation studies further analyze the contribution of bond-level connectivity, the stage-dependent dynamics of global attribute bias, structured masking, and pre-training configurations. Ultimately, this work provides an alternative representation design for molecular modeling, offering a parameter-efficient option for future molecular learning systems alongside traditional SMILES-based and graph-based formulations. Full article

The proliferation of digital financial news offers unprecedented opportunities for automated analysis of market-moving events. This paper presents a framework for event-based sentiment analysis of financial news that leverages Large Language Models (LLMs). The approach brings together three complementary ideas: Retrieval-Augmented Generation (RAG) for contextual enhancement, Graph Neural Networks (GNNs) for modeling relationships between events, and a multi-agent ensemble for orchestrated reasoning. The methodology targets well-known difficulties in financial text processing, including domain-specific terminology, implicit event detection, and temporal reasoning, and it combines transformer-based event extraction with sentiment classification enhanced by external knowledge retrieval. We evaluate six model configurations on an aggregated corpus of 14,851 financial news samples. On the event-detection task, every configuration reaches a weighted F1-score of 100%; we show that this is a ceiling effect produced by a binary event/no-event formulation over a highly imbalanced dataset rather than evidence of a difficult problem being solved, and we discuss what it implies for how such systems should be evaluated. On three-way sentiment classification, the strongest configuration—the multi-agent ensemble—reaches 87.4% accuracy, narrowly ahead of a RoBERTa (Robustly Optimized BERT Pretraining Approach) baseline at 87.2%; however, because the gaps reported between models are small and we did not run significance testing, we report them as indicative rather than definitive. The GNN component is described as part of the proposed design, but it has not yet been validated experimentally, and we state this limitation explicitly. The framework produces interpretable, structured outputs suited to downstream use in algorithmic trading, risk assessment, and investment decision support, and the paper contributes a reusable financial NLP pipeline together with a candid account of where the current evidence is, and is not, convincing. Full article

Accurate prediction of student success is important for improving retention and supporting academic decision-making. This study investigates the use of Graph Neural Networks (GNNs) for modelling academic progression across 13 university faculties, focusing on how structured trajectory representations can capture temporal and relational dependencies in student records. Conventional machine learning approaches frequently rely on aggregated tabular indicators, which may obscure the temporal ordering and relational structure of academic trajectories. We propose a graph-based representation, termed the Academic Trajectory Graph (ATG), which encodes semester-to-semester course transitions and temporal relationships between enrollments. To evaluate its effectiveness, graph-based approaches (DGCNN, GCN, and node2vec-based embeddings) are compared with conventional machine learning models trained on aggregated tabular indicators. Experimental results show that aggregated academic indicators provide strong predictive performance, confirming the importance of cumulative progression signals. Among the graph-based approaches, DGCNN achieved the most consistent performance across faculties, reaching AUC values up to 0.988, accuracy up to 0.945, and F1-scores above 0.94 in several faculties. Although traditional tabular models generally achieved the strongest overall predictive performance, the ATG preserves temporal and relational information that is not captured by flat feature vectors, enabling trajectory-level analysis of academic pathways. The results indicate that graph-based trajectory modelling may provide additional structural insights in faculties exhibiting heterogeneous academic progression patterns, while offering competitive predictive performance. These findings highlight both the potential and the limitations of graph-based approaches for modelling structured educational data, suggesting that their effectiveness depends on the structural diversity of the underlying academic domain. Full article

Traditional urban building energy modeling often overlooks the complexity of spatial configurations and mutual shading effects, thereby limiting its accuracy. This study proposes a novel, interpretable, data-driven framework based on heterogeneous graph neural networks (GNNs) to uncover and characterize the complex interrelationships between building morphology and urban topology. Using a parametric platform, this study generated a graph dataset of 285 residential blocks in Wuhan, structured as a dual-level graph: Building Zone Graphs (BZGs) and Building Layout Graphs (BLGs). Four GNN models were trained based on the dataset, and the evaluated results demonstrate that GraphTransformer outperforms GCN, GAT, and GraphSAGE in capturing long-range spatial relationships―particularly those arising from shading and solar access interactions. On a validation set, GraphTransformer achieved superior predictive accuracy, with R² scores exceeding 0.85 and 0.90 for cooling and heating energy predictions, respectively. After that, post hoc interpretability analysis by GNNExplainer identified three important morphology features influencing building energy consumption. Critically, the model found that shading relationships encoded as graph edges―especially those between southern and western façades―had statistically significant influence on building energy consumption. Finally, this work establishes an efficient, interpretable surrogate modeling framework for urban-scale energy analysis, delivering quantifiable, design-actionable insights to support sustainable urban development. Full article

Despite their demonstrated effectiveness in modeling sensor interaction networks for industrial fault diagnosis, graph neural networks (GNNs) still encounter two key limitations: black-box operation that lacks transparency in fault identification and propagation analysis, and unreliable attention mechanisms whose weights fail to faithfully reflect the genuine relevance of sensors or their interactions. To tackle these challenges, we put forward the Stochastic Mask Causal Graph Network, a novel framework that integrates a learnable stochastic masking mechanism guided by the information bottleneck principle. Unlike conventional attention-based or post-hoc approaches, our method automatically suppresses label-irrelevant graph components while preserving causally relevant structures, thereby providing faithful inherent interpretability without biased assumptions and effectively removing spurious correlations to enhance generalization. Comprehensive experiments on realistic complex industrial system datasets demonstrate that the proposed method achieves superior diagnostic accuracy and enhanced interpretability compared with existing advanced approaches. Full article

Despite their extended detection ranges and superior precision compared with onboard sensors, roadside perception systems suffer from severe occlusion artifacts in complex traffic, causing significant tracking failures and ID switches. To address this, we propose a novel Dynamic Occlusion–Predictive Neural Network tailored to challenging roadside environments. First, we introduce a Transformer-based Dynamic Occlusion State Predictor to explicitly model the temporal evolution of occlusion. Unlike traditional tracking methods, this module continuously forecasts future occlusion ratios for each target by analyzing historical occlusion patterns. Critically, these predictions are integrated into the tracking framework as dynamic weighting factors in the loss function, enabling the model to adaptively penalize tracking errors based on the predicted occlusion severity and significantly enhancing robustness against dynamic occlusion scenarios. Second, leveraging the predicted occlusion states, we propose a GNN-based Spatial Reasoning Module to address trajectory fragmentation. This module constructs a heterogeneous graph integrating road occupancy information and neighboring vehicle poses to infer the existence and motion patterns of targets within occluded regions. By analyzing scene-level physical constraints, it generates motion predictions for invisible targets and links these inferred states to fragmented trajectories, ensuring temporally continuous tracking even during prolonged visual occlusions. Experiments on the DAIR-V2X and our self-collected roadside dataset show that our framework outperforms state-of-the-art methods in precision and robustness, achieving a 5.1% MOTA gain over the best baseline. This advantage peaks under high occlusion, where preserving ID continuity and minimizing failures validates its efficacy for real-world roadside multi-target tracking. Full article

Considerable efforts have been devoted to accurately monitoring the depth of anesthesia to ensure patient safety during surgery. Traditional approaches typically rely on electroencephalogram (EEG)-based indices, such as the Bispectral Index (BIS), which require specialized equipment. In contrast, electrocardiogram (ECG) signals are widely available in clinical settings and can be conveniently acquired via wearable devices, while also exhibiting strong responsiveness to anesthetic agents. Inspired by biomimetic physiological regulation mechanisms, this study proposes a wearable-compatible ECG-based framework for depth-of-anesthesia detection that leverages autonomic nervous system characteristics and a knowledge graph-enhanced graph convolutional network (GCN). ECG recordings from 110 patients were preprocessed, and 20 anesthesia-related features were extracted, spanning morphological, statistical, spectral, heart rate variability (HRV), and entropy-based descriptors; feature selection methods identified 13 discriminative features. A patient-level knowledge graph was first constructed using the 88 training patients (1760 nodes), and test patient nodes were incorporated only after training was complete for inductive inference. Experimental results demonstrate that the proposed deep knowledge GCN achieves a test accuracy of 98.18% in distinguishing between awake and deep sleep anesthesia states, indicating that biomimetic, wearable-compatible ECG analysis combined with knowledge graph learning holds strong potential as a cost-effective alternative to traditional EEG-based anesthesia monitoring systems. Full article

Electroencephalography (EEG) offers a noninvasive, high-temporal-resolution modality for estimating mental workload. However, session-to-session variability limits the generalizability of workload classifiers, and few systematic cross-session evaluations are reported in the literature. This study systematically evaluates domain adaptation methods for cross-session mental workload classification using the publicly available COG-BCI dataset within an evaluation framework that may guide future studies on EEG-based classification models. We make four contributions: (i) integration of Optimal Transport (OT) with Graph Neural Networks (GNNs) to model spatial relationships and align feature distributions under strict session-wise separation; (ii) a data-centric evaluation pipeline incorporating Self-Organizing Map (SOM) visualizations for data exploration and a heuristic loss function for model selection; (iii) a strict cross-session protocol examining the effects of graph construction, feature selection, and data splits; and (iv) comparison of OT with CORrelation ALignment (CORAL) and GNN with EEGNet. Incorporating OT improved test accuracies across all experimental configurations. SOM visualizations confirmed enhanced feature alignment after OT. Our results highlight the potential of OT for mitigating session-to-session variability and underscore the importance of a data-centric approach and rigorous cross-session evaluation when developing classifiers for complex cognitive state estimation. Future work should explore semi-supervised OT strategies and scalable implementations for real-time applications. Full article

Background/Objectives: Machine learning has emerged as a transformative force in drug discovery, revolutionizing traditional research paradigms and profoundly improving the efficiency, cost-effectiveness, and speed of the drug development cycle for novel drugs. Colorectal cancer is one of the most prevalent malignant tumors and imposes a heavy burden on global public health due to its high morbidity, mortality, and poor prognosis. Cyclooxygenase-2 (COX-2) is a key therapeutic target of colorectal cancer and has been extensively applied in the development of novel anti-colorectal cancer drugs. Methods: In this study, we systematically compared the performance of Random Forest Classifier (RFC), deep learning (DL), and graph neural network (GNN) models, including GAT (Graph Attention Network), GCN (Graph Convolutional Network), and MPNN (Message Passing Neural Network), with diverse features in the classification task of COX-2 inhibitors, based on a custom COX-2 inhibitors dataset and a Traditional Chinese Medicine (TCM)-derived compound library. The optimal model was subsequently used to screen for potential COX-2 inhibitors. Additionally, the key substructures governing COX-2 inhibitory activity were also identified and analyzed. Finally, the prioritized candidate compounds underwent experimental validation. Results: Both RFC and DL models outperformed GNN models. Through further comparative analysis of models’ predictive performance, the RFC model was ultimately verified as the optimal model for activity screening of TCM-derived compounds. The molecular interactions and binding affinities between predicted candidate compounds and COX-2 were further investigated. Finally, the selected lead compound, dehydrocostus lactone, was experimentally confirmed to possess potent COX-2 inhibitory activity. Conclusions: This study highlights that the RFC model is highly effective in screening bioactive components from TCM under small-dataset conditions, providing a solid foundation for subsequent related research in this field. Full article

Detecting fake news is a challenging task and an important area of research for social media researchers. This task also involves clarifying accountability mechanisms that demonstrate the credibility of quotable sources, such as networks that document the spread of misinformation. Deep learning techniques, particularly neural networks that rely on popular graph representation techniques such as graph convolutional networks (GCNs), are increasingly being utilized to detect fake news, fake accounts, and rumors spreading through social media. In this paper, features were extracted using TF-IDF, Bag-of-Words, and bigrams. The evaluation was conducted using the standard Kaggle/ISOT and GossipCop datasets, which include news headlines and published models. Using the extracted features, the proposed GCN-based model/classifier achieved a high detection accuracy of 95% by combining TF-IDF and Bag-of-Words representations. The results demonstrate that the extracted features improve the efficiency of the detection model. Full article

As hardware Trojans (HTs) are becoming increasingly stealthy in global semiconductor supply chains, the need for both robust and explainable detection methods is pressing. The use of deep learning models (e.g., Siamese networks, Transformer models) in side-channel signals has shown promising detection accuracy. Yet, they are black-box, data-intensive, and do not expose the causal, structural, and temporal relationships that indicate the presence of HTs. In this paper, we present a causality-focused and explainable detection framework that goes beyond pattern matching. We develop a Self-Supervised Spatio-Temporal Graph Neural Network (SST-GNN) that embeds spatio-temporal side-channel information. Our approach builds a graph that models gate-level components as nodes with temporal power and electromagnetic (EM) features, and functional and physical connections as edges. To address label scarcity, a common problem in real-world applications, we leverage a self-supervised pretraining approach. In particular, a context-aware contrastive loss allows the model to differentiate valid augmentations of benign subgraphs and their side-channel signatures, thus capturing general representations of benign components without Trojan labels. This involves a Causality-Aware GNN (CA-GNN) layer, which embeds differentiable causal discovery into graph learning. This process decouples correlation from causation, identifying the pathways potentially affected by HT trigger and payload. To explain decision making, a gradient-based graph explainer localizes minimal decisive subcircuits and pivotal time windows, generating intuitive detection reports. We evaluated our method on the IEEE Hardware Trojan Side-Channel Dataset (with netlist data), achieving state-of-the-art results (F1 > 0.98). In particular, the model achieves over 60% improvement in Trojan localization precision and false-positive rate, compared to Transformer-based approaches, with high label efficiency and adversarial robustness. Full article

We propose QwenMoE-SC, a semantic communication framework that integrates a Mixture-of-Experts (MoE) Large Language Model with three complementary modules: (1) a Graph Neural Network (GNN)-based Unequal Error Protection (UEP) plug-in that assigns semantic importance scores via syntactic dependency graph message passing for adaptive bit allocation, without modifying the pre-trained LLM; (2) NEFTune noise injection during fine-tuning for channel robustness; and (3) a Communication-aware Direct Preference Optimization (C-DPO) strategy that favors semantically faithful yet token-efficient transmissions. Comprehensive ablation studies on AWGN and Rayleigh fading channels show that each component contributes distinct gains, and their combination consistently outperforms traditional separation-based methods and neural baselines in sentence similarity, BLEU score, and semantic-level BER, with the largest improvements at low-to-mid SNR regimes. QwenMoE-SC can also serve as a semantic interface layer within expert and decision-support systems, enabling robust, bandwidth-efficient communication between data sources, inference engines, and human users. Full article

Traffic accident prediction is a key challenge in road safety, and it is necessary to accurately identify high-risk sections from different data sources. Although graphical neural networks (GNNs) simulate the road network topology well, they ignore the visual and environmental clues from physical road conditions. This paper addresses this gap by proposing a Sequential Geometric Reasoning Network (SGR-Net), a deep learning framework for multimodal accident prediction. Unlike prior GNN-based approaches, SGR-Net introduces a Geometry–State Attentive Fusion (GSAF) module—its main novelty—which dynamically integrates visual features from satellite imagery with structural graph contexts. The framework also includes a stability-aware training objective and meta-learning for cross-region generalization. We evaluate on a large-scale dataset covering six U.S. states with over nine million accidents and one million satellite images. SGR-Net achieves strong results, with AUROC up to 96.8% and MAE as low as 0.08 in Delaware. Ablations confirm the GSAF module is essential: removing it reduces AUROC by 2.7% and increases MAE by over 40%. The framework establishes a new state-of-the-art for multimodal traffic accident prediction. Full article