Search Results (1,767)

Infrared thermal field (ITF) prediction for meter boxes is crucial for the early warning of power system faults, yet this method faces three major challenges: data sparsity, complex geometry, and resource constraints in edge computing. Existing physics-informed neural network-graph neural network (PINN-GNN) approaches suffer from redundant physics residual calculations (over 70% of flat regions contain little information) and poor model generalization (requiring retraining for new box types), making them inefficient for deployment on edge devices. This paper proposes the PhysGraphIR framework, which employs an Adaptive Residual Sampling (ARS) mechanism to dynamically identify hotspot region nodes through a physics-aware gating network, calculating physics residuals only at critical nodes to reduce computational overhead by over 80%. In this study, a `hotspot region’ is explicitly defined as a localized area exhibiting significant temperature elevation relative to the background—typically concentrated around electrical connection terminals or wire entrances—which is critical for identifying potential thermal faults under sparse data conditions. Additionally, it utilizes a Physics Knowledge Distillation Graph Neural Network (Physics-KD GNN) to decouple physics learning from geometric learning, transferring universal heat conduction knowledge to specific meter box geometries through a teacher–student architecture. Experimental results demonstrate that on both synthetic and real-world meter box datasets, PhysGraphIR achieves a hotspot region mean absolute error (MAE) of 11.8 °C under 60% infrared data missing conditions, representing a 22% improvement over traditional PINN-GNN. The training speed is accelerated by 3.1 times, requiring only five infrared samples to adapt to new box types. The experiments prove that this method significantly enhances prediction accuracy and computational efficiency under sparse infrared data while maintaining physical consistency, providing a feasible solution for edge intelligence in power systems. Full article

Constructing a temperature and humidity prediction model for greenhouse-grown tomatoes is of great significance for achieving resource-efficient and sustainable greenhouse environmental control and promoting healthy tomato growth. However, traditional models often struggle to simultaneously capture long-term temporal trends, short-term local dynamic variations, and the coupling relationships among multiple variables. To address these issues, this study develops an iT-LSTM-CA multi-step prediction model, in which the inverted Transformer (iTransformer, iT) is employed to capture global dependencies across variables and long temporal scales, the Long Short-Term Memory (LSTM) network is utilized to extract short-term local variation patterns, and a cross-attention (CA) mechanism is introduced to dynamically fuse the two types of features. Experimental results show that, compared with models such as Gated Recurrent Unit (GRU), Temporal Convolutional Network (TCN), Recurrent Neural Network (RNN), LSTM, and Bidirectional Long Short-Term Memory (Bi-LSTM), the iT-LSTM-CA achieves the best performance in multi-step forecasting tasks at 3 h, 6 h, 12 h, and 24 h horizons. For temperature prediction, the R² ranges from 0.96 to 0.98, with MAE between 0.42 °C and 0.79 °C and RMSE between 0.58 °C and 1.06 °C; for humidity prediction, the R² ranges from 0.95 to 0.97, with MAE between 1.21% and 2.49% and RMSE between 1.78% and 3.42%. These results indicate that the iT-LSTM-CA model can effectively capture greenhouse environmental variations and provide a scientific basis for environmental control and management in tomato greenhouses. Full article

Intelligent Transportation Systems (ITS) have progressively incorporated machine learning to optimize traffic efficiency, enhance safety, and improve real-time decision-making. However, the traditional centralized machine learning (ML) paradigm faces critical limitations regarding data privacy, scalability, and single-point vulnerabilities. This study explores FL as a decentralized alternative that preserves privacy by training local models without transferring raw data. Based on a systematic literature review encompassing 39 ITS-related studies, this work classifies applications according to their architectural detail—distinguishing systems from models—and identifies three families of federated learning (FL) frameworks: privacy-focused, integrable, and advanced infrastructure. Three representative frameworks—Federated Learning-based Gated Recurrent Unit (FedGRU), Digital Twin + Hierarchical Federated Learning (DT + HFL), and Transfer Learning with Convolutional Neural Networks (TFL-CNN)—were comparatively analyzed against a client–server baseline to assess their suitability for ITS adaptation. Our qualitative, architecture-level comparison suggests that DT + HFL and TFL-CNN, characterized by hierarchical aggregation and edge-level coordination, are conceptually better aligned with scalability and stability requirements in vehicular and traffic deployments than pure client–server baselines. FedGRU, while conceptually relevant as a meta-framework for coordinating multiple organizational models, is primarily intended as a complementary reference rather than as a standalone architecture for large-scale ITS deployment. Through application-level evaluations—including traffic prediction, accident detection, transport-mode identification, and driver profiling—this study demonstrates that FL can be effectively integrated into ITS with moderate architectural adjustments. This work does not introduce new experimental results; instead, it provides a qualitative, architecture-level comparison and adaptation guideline to support the migration of ITS applications toward federated learning. Overall, the results establish a solid methodological foundation for migrating centralized ITS architectures toward federated, privacy-preserving intelligence, in alignment with the evolution of edge and 6G infrastructures. Full article

The ubiquity of smartphones has transformed them into primary repositories of sensitive data; however, traditional one-time authentication mechanisms create a critical trust gap by failing to verify identity post-unlock. Our aim is to mitigate these vulnerabilities and align with the Zero Trust Architecture (ZTA) framework and philosophy of “never trust, always verify,” as formally defined by the National Institute of Standards and Technology (NIST) in Special Publication 800-207. This study introduces a robust continuous authentication (CA) framework leveraging multimodal behavioral biometrics. A dedicated application was developed to synchronously capture touch, sliding, and inertial sensor telemetry. For feature modeling, a heterogeneous deep learning pipeline was employed to capture modality-specific characteristics, utilizing Convolutional Neural Networks (CNNs) for sensor data, Long Short-Term Memory (LSTM) networks for curvilinear sliding, and Gated Recurrent Units (GRUs) for discrete touch. To resolve performance degradation caused by class imbalance in Zero Trust environments, a Grid Search Optimization (GSO) strategy was applied to optimize a weighted voting ensemble, identifying the global optimum for decision thresholds and modality weights. Empirical validation on a dataset of 35,519 samples from 15 subjects demonstrates that the optimized ensemble achieves a peak accuracy of 99.23%. Sensor kinematics emerged as the primary biometric signature, followed by touch and sliding features. This framework enables high-precision, non-intrusive continuous verification, bridging the critical security gap in contemporary mobile architectures. Full article

The integration of emojis into Early Childhood Education (ECE) presents a promising avenue for enhancing student engagement, emotional expression, and comprehension. While prior studies suggest the benefit of visual aids in learning, systematic frameworks for pedagogically aligned emoji recommendation remain underdeveloped. This paper presents EduEmoji-ECE, a pedagogically annotated dataset of early-childhood learning text segments. Specifically, the proposed model incorporates Bidirectional Encoder Representations from Transformers (BERTs) for contextual embedding extraction, Gated Recurrent Units (GRUs) for sequential pattern recognition, Deep Neural Networks (DNNs) for classification and emoji recommendation, and DECOC for improving emoji class prediction robustness. This hybrid BERT-GRU-DNN-DECOC architecture effectively captures textual semantics, emotional tone, and pedagogical intent, ensuring the alignment of emoji class recommendation with learning objectives. The experimental results show that the system is effective, with an accuracy of 95.3%, a precision of 93%, a recall of 91.8%, and an F1-score of 92.3%, outperforming baseline models in terms of contextual understanding and overall accuracy. This work helps fill a gap in AI-based education by combining learning with visual support for young children. The results suggest an association between emoji-enhanced materials and improved engagement/comprehension indicators in our exploratory classroom setting; however, causal attribution to the AI placement mechanism is not supported by the current study design. Full article

Unmanned Aerial Vehicles (UAVs) have become essential tools across critical domains, including infrastructure inspection, public safety monitoring, traffic surveillance, environmental sensing, and target tracking, owing to their ability to collect high-resolution spatial data rapidly. However, maintaining stable and accurate flight trajectories remains a significant challenge, particularly during autonomous missions in dynamic or uncertain environments. This study presents a novel flight path prediction framework based on Gated Recurrent Units (GRUs), designed for both single-step and multi-step-ahead forecasting of four-dimensional UAV coordinates, Easting (X), Northing (Y), Altitude (Z), and Time (T), using historical sensor flight data. Model performance was systematically validated against traditional Recurrent Neural Network architectures. On unseen test data, the GRU model demonstrated enhanced predictive accuracy in single-step prediction, achieving a MAE of 0.0036, Root Mean Square Error (RMSE) of 0.0054, and a (R²) of 0.9923. Crucially, in multi-step-ahead forecasting designed to simulate real-world challenges such as GPS outages, the GRU model maintained exceptional stability and low error, confirming its resilience to error accumulation. The findings establish that the GRU-based model is a highly accurate, computationally efficient, and reliable solution for UAV trajectory forecasting. This framework enhances autonomous navigation and directly supports the data integrity required for high-fidelity photogrammetric mapping, ensuring reliable site assessment in complex and dynamic environments. Full article

Memory resident malware, particularly fileless and heavily obfuscated types, continues to pose a major problem for endpoint defense tools, as these threats often slip past traditional signature-based detection techniques. Deep learning has shown promise in identifying such malicious activity, but its use in real Security Operations Centers (SOCs) is still limited because the internal reasoning of these neural network models is difficult to interpret or verify. In response to this challenge, we present HAGEN, a hierarchical attention architecture designed to combine strong classification performance with explanations that security analysts can understand and trust. HAGEN processes memory artifacts through a series of attention layers that highlight important behavioral cues at different scales, while a gated mechanism controls how information flows through the network. This structure enables the system to expose the basis of its decisions rather than simply output a label. To further support transparency, the final classification step is guided by representative prototypes, allowing predictions to be related back to concrete examples learned during training. When evaluated on the CIC-MalMem-2022 dataset, HAGEN achieved 99.99% accuracy in distinguishing benign programs from major malware classes such as spyware, ransomware, and trojans, all with modest computational requirements suitable for live environments. Beyond accuracy, HAGEN produces clear visual and numeric explanations—such as attention maps and prototype distances—that help investigators understand which memory patterns contributed to each decision, making it a practical tool for both detection and forensic analysis. Full article

Recent advances in deep learning have had a significant impact on biomedical applications, driving precise actions in automated diagnostic processes. However, integrating neural networks into medical devices requires meeting strict requirements regarding computing power, energy efficiency, reconfigurability, and latency, essential conditions for real-time inference. Field-Programmable Gate Array (FPGA) architectures provide a high level of flexibility, performance, and parallel execution, thus making them a suitable option for the real-world implementation of machine learning (ML) and deep learning (DL) models in systems dedicated to the analysis of physiological signals. This paper presents a review of intelligent algorithms for electrocardiogram (ECG) signal classification, including Support Vector Machines (SVMs), Artificial Neural Networks (ANNs), Recurrent Neural Networks (RNNs), Long Short-Term Memory Networks (LSTMs), and Convolutional Neural Networks (CNNs), which have been implemented on FPGA platforms. A comparative evaluation of the performances of these hardware-accelerated solutions is provided, focusing on their classification accuracy. At the same time, the FPGA families used are analyzed, along with the reported performances in terms of operating frequency, power consumption, and latency, as well as the optimization strategies applied in the design of deep learning hardware accelerators. The conclusions emphasize the popularity and efficiency of CNN architectures in the context of ECG signal classification. The study aims to offer a current overview and to support specialists in the field of FPGA design and biomedical engineering in the development of accelerators dedicated to physiological signals analysis. Full article

The existing multimodal image classification methods often suffer from several key limitations: difficulty in effectively balancing local detail and global topological relationships in hyperspectral image (HSI) feature extraction; insufficient multi-scale characterization of terrain features from light detection and ranging (LiDAR) elevation data; and neglect of deep inter-modal interactions in traditional fusion methods, often accompanied by high computational complexity. To address these issues, this paper proposes a comprehensive deep learning framework combining convolutional neural network (CNN), a graph convolutional network (GCN), and wavelet transform for the joint classification of HSI and LiDAR data, including several novel components: a Spectral Graph Mixer Block (SGMB), where a CNN branch captures fine-grained spectral–spatial features by multi-scale convolutions, while a parallel GCN branch models long-range contextual features through an enhanced gated graph network. This dual-path design enables simultaneous extraction of local detail and global topological features from HSI data; a Spatial Coordinate Block (SCB) to enhance spatial awareness and improve the perception of object contours and distribution patterns; a Multi-Scale Elevation Feature Extraction Block (MSFE) for capturing terrain representations across varying scales; and a Bidirectional Frequency Attention Encoder (BiFAE) to enable efficient and deep interaction between multimodal features. These modules are intricately designed to work in concert, forming a cohesive end-to-end framework, which not only achieves a more effective balance between local details and global contexts but also enables deep yet computationally efficient interaction across features, significantly strengthening the discriminability and robustness of the learned representation. To evaluate the proposed method, we conducted experiments on three multimodal remote sensing datasets: Houston2013, Augsburg, and Trento. Quantitative results demonstrate that our framework outperforms state-of-the-art methods, achieving OA values of 98.93%, 88.05%, and 99.59% on the respective datasets. Full article

As the core technology of clean and efficient utilization of coal, coal gasification technology plays an important role in reducing environmental pollution, improving coal utilization, and achieving sustainable energy development. In order to ensure the safe, stable, and long-term operation of coal gasification plant, aiming to address the strong subjectivity of dynamic Bayesian network (DBN) prior data in dynamic risk assessment, this study takes the coal slurry preparation system—the main piece of equipment in the initial stage of the coal gasification process—as the research object and uses a long short-term memory (LSTM) model combined with a back propagation (BP) neural network model to optimize DBN prior data. To further validate the superiority of the model, a gated recurrent unit (GRU) model was introduced for comparative verification. The mean absolute error (MAE), root mean square error (RMSE), and coefficient of determination are used to evaluate the generalization ability of the LSTM model. The results show that the LSTM model’s predictions are more accurate and stable. Bidirectional inference is performed on the DBN of the optimized coal slurry preparation system to achieve dynamic reliability analysis. Thanks to the forward reasoning of DBN in the coal slurry preparation system, quantitative analysis of the system’s reliability effects is conducted to clearly demonstrate the trend of system reliability over time, providing data support for stable operation and subsequent upgrades. By conducting reverse reasoning, key events and weak links before and after system optimization can be identified, and targeted improvement measures can be proposed accordingly. Full article

Symmetry and asymmetry are foundational design principles in artificial intelligence, defining the balance between invariance and adaptability in multimodal learning systems. In audio-visual speaker verification, where speech and lip-motion features are jointly modeled to determine whether two utterances belong to the same individual, these principles govern both fairness and discriminative power. In this work, we analyze how symmetry and asymmetry emerge within a gated-fusion architecture that integrates Time-Delay Neural Networks and Bidirectional Long Short-Term Memory encoders for speech, ResNet-based visual lip encoders, and a shared Conformer-based temporal backbone. Structural symmetry is preserved through weight-sharing across paired utterances and symmetric cosine-based scoring, ensuring verification consistency regardless of input order. In contrast, asymmetry is intentionally introduced through modality-dependent temporal encoding, multi-head attention pooling, and a learnable gating mechanism that dynamically re-weights the contribution of audio and visual streams at each timestep. This controlled asymmetry allows the model to rely on visual cues when speech is noisy, and conversely on speech when lip visibility is degraded, yielding adaptive robustness under cross-modal degradation. Experimental results demonstrate that combining symmetric embedding space design with adaptive asymmetric fusion significantly improves generalization, reducing Equal Error Rate (EER) to 3.419% on VoxCeleb-2 test dataset without sacrificing interpretability. The findings show that symmetry ensures stable and fair decision-making, while learnable asymmetry enables modality awareness together forming a principled foundation for next-generation audio-visual speaker verification systems. Full article

Recent advances in automated learning techniques have enhanced the analysis of biomedical signals for detecting sleep stages and related health abnormalities. However, many existing models face challenges with imbalanced datasets and the dynamic nature of evolving sleep states. In this study, we present a robust algorithm for classifying sleep states using electroencephalogram (EEG) data collected from 33 healthy participants. We extracted dynamic, brain-inspired features, such as microstates and Lempel–Ziv complexity, which replicate intrinsic neural processing patterns and reflect temporal changes in brain activity during sleep. An optimal feature set was identified based on significant spectral ranges and classification performance. The classifier was developed using a convolutional neural network (CNN) combined with gated recurrent units (GRUs) within a reinforcement learning framework, which models adaptive decision-making processes similar to those in biological neural systems. Our proposed biomimetic framework illustrates that a multivariate feature set provides strong discriminative power for sleep state classification. Benchmark comparisons with established approaches revealed a classification accuracy of 98% using the optimized feature set, with the framework utilizing fewer EEG channels and reducing processing time, underscoring its potential for real-time deployment. These findings indicate that applying biomimetic principles in feature extraction and model design can improve automated sleep monitoring and facilitate the development of novel therapeutic and diagnostic tools for sleep-related disorders. Full article

Gait recognition using wearable sensor data is crucial for healthcare, rehabilitation, and monitoring neurological and musculoskeletal disorders. This study proposes a deep learning framework for gait classification using inertial measurements from four body-mounted IMU sensors (head, lower back, and both feet). The data were collected from a publicly available, clinically annotated dataset comprising 1356 gait trials from 260 individuals with diverse pathologies. The framework, G-MASA-TCN (Gait Multi-Anchor, Space-Aware Temporal Convolutional Network), integrates multi-scale temporal fusion, graph-informed spatial modeling, and residual dilated convolutions to extract discriminative gait signatures. To ensure both high performance and interpretability, Integrated Gradients is incorporated as an explainable AI (XAI) method, providing sensor-level and temporal attributes that reveal the features driving model decisions. The framework is evaluated via repeated cross-validation experiments, reporting detailed metrics with cross-run statistical analysis (mean ± standard deviation) to assess robustness. Results show that G-MASA-TCN achieves 98% classification accuracy for neurological, orthopedic, and healthy cohorts, demonstrating superior stability and resilience compared to baseline architectures, including Gated Recurrent Unit (GRU), Transformer neural networks, and standard TCNs, and 98.4% accuracy in identifying individual subjects based on gait. Furthermore, the model offers clinically meaningful insights into which sensors and gait phases contribute most to its predictions. This work presents an accurate, interpretable, and reliable tool for gait pathology recognition, with potential for translation to real-world clinical settings. Full article

This work investigates the deployment of Deep Learning (DL) models for network intrusion detection on resource-constrained IoT devices, using the public CICIoT2023 dataset. In particular, we consider the following DL models: Long Short-Term Memory (LSTM), Gated Recurrent Unit (GRU), Recurrent Neural Network (RNN), Convolutional Neural Network (CNN), Temporal Convolutional Network (TCN), Multi-Layer Perceptron (MLP). Bayesian optimization is employed to fine-tune the models’ hyperparameters and ensure reliable performance evaluation across both binary (2-class) and multi-class (8-class, 34-class) intrusion detection. Then, the computational complexity of each DL model is analyzed—in terms of the number of Multiply–ACCumulate operations (MACCs), RAM usage, and inference time—through the STMicroelectronics Cube.AI Analyzer tool, with models being deployed on an STM32H7S78-DK board. To assess the practical deployability of the considered DL models, a trade-off score (balancing classification accuracy and computational efficiency) is introduced: according to this score, our experimental results indicate that MLP and TCN outperform the other models. Furthermore, Post-Training Quantization (PTQ) to 8-bit integer precision is applied, allowing the model size to be reduced by more than $90\%$ with negligible performance degradation. This demonstrates the effectiveness of quantization in optimizing DL models for real-world deployment on resource-constrained IoT devices. Full article

Short-term wind speed forecasting is challenged by the nonlinear, non-stationary, and highly volatile characteristics of wind speed series, which hinder the performance of traditional prediction models. To improve forecasting capability, this study proposes a hybrid modeling framework that integrates multi-strategy adaptive particle swarm optimization (MASPSO), a convolutional neural network (CNN), a gated recurrent unit (GRU), and an attention mechanism. Within this modeling architecture, the CNN extracts multi-scale spatial patterns, the GRU captures dynamic temporal dependencies, and the attention mechanism highlights salient feature components. MASPSO is further incorporated to perform global hyperparameter optimization, thereby improving both prediction accuracy and generalization. Evaluation on real wind farm data confirms that the proposed modeling framework delivers consistently superior forecasting accuracy across different wind speed conditions, with significantly reduced prediction errors and improved robustness in multi-step forecasting tasks. Full article