Search Results (2,712)

In this study, we investigate how computationally simplified activation functions affect predictive performance, inference latency, and energy usage in long short-term memory-based temperature prediction for wind turbine generator bearings. We tested three different types of long short-term memory (LSTM) cells, along with bidirectional LSTM (biLSTM) networks, to determine their effectiveness in modeling dynamic changes in gearbox bearing temperatures. We compared several activation-function variants, focusing on variants that are either computationally simple or known to give good performance in deep recurrent networks. The results show that the best-performing architectures achieved root mean squared errors (RMSEs) between $0.0798$ and $0.0822$, corresponding to coefficients of determination in the range of $R^2=0.84$–$0.85$. When applied across five turbines, the best-performing architectures (peephole and bidirectional) achieved root mean squared errors of $0.0898$, $0.0882$, and $0.042$, respectively. The best activation function-enhanced variant (the peephole) improved accuracy by approximately $3\%$ while maintaining low model complexity. These findings provide a practical and efficient solution for embedded predictive maintenance systems, providing high accuracy without incurring the computational cost of deeper or bidirectional architectures. Full article

The memristor has long been known as a nonvolatile memory technology alternative and has recently been explored for neuromorphic computing, owing to its capability to mimic the synaptic plasticity of the human brain. The architecture of a memristor synapse device allows ultra-high-density integration by internetworking with crossbar arrays, which benefits large-scale training and learning using advanced machine-learning algorithms. In this review, we present a statistical analysis of neuromorphic computing device publications from 2018 to 2025, focusing on various memristive systems. Furthermore, we provide a device-level perspective on biomimetic properties in hardware neural networks such as short-term plasticity (STP), long-term plasticity (LTP), spike timing-dependent plasticity (STDP), and spike rate-dependent plasticity (SRDP). Herein, we highlight the utilization of optoelectronic synapses based on 2D materials driven by a sequence of optical stimuli to mimic the plasticity of the human brain, further broadening the scope of memristor controllability by optical stimulation. We also highlight practical applications ranging from MNIST dataset recognition to hardware-based pattern recognition and explore future directions for memristor synapses in healthcare, including artificial cognitive retinal implants, vital organ interfaces, artificial vision systems, and physiological signal anomaly detection. Full article

This paper addresses the core conflict between long-range communication and ultra-low power requirements in sensing nodes for Wireless Sensor Networks (WSNs) by proposing a wake-up receiver (WuRx) design featuring nanowatt-level power consumption and high sensitivity. Conventional architectures are plagued by low energy efficiency, poor demodulation reliability, and insufficient clock synchronization accuracy, which hinders their practical application in real-world scenarios like WSNs. The proposed design employs an event-triggered mechanism, where a continuously operating, low-power WuRx monitors the channel and activates the main system only after validating a legitimate command, thereby significantly reducing standby power. At the system design level, a key innovation is direct conjugate matching between the antenna and a multi-stage rectifier, replacing the traditional 50 Ohm interface, which substantially improves energy transmission efficiency. Furthermore, a mean-detection demodulation circuit is introduced to dynamically generate an adaptive reference level, effectively overcoming the challenge of discriminating shallow modulation caused by signal saturation in the near-field region. At the baseband processing level, a configurable fault-tolerant correlator logic and a data-edge-triggered clock synchronization circuit are designed, combined with oversampling techniques to suppress clock drift and enhance the reliability of long data packet reception. Fabricated in a TSMC 0.18 µm CMOS process, the receiver features an ultra-low power consumption of 305 nW at 0.5 V and a high sensitivity of −47 dBm, enabling a communication range of up to 400 m in the 920–925 MHz band. Through synergistic innovation at both the circuit and system levels, this research provides a high-efficiency, high-reliability wake-up solution for long-range WSN nodes, effectively promoting the large-scale application of WSN technology in practical deployments. Full article

Since the compressor system in underground gas storage (UGS) facilities operates under highly dynamic and complex injection conditions, traditional rule-based operation and mechanism-based modeling approaches prove inadequate for meeting the stringent requirements of high-accuracy prediction under such variable conditions. To address this, a data-driven two-phase prediction framework for compressor energy consumption is proposed. In the first phase, a convolutional neural network with efficient channel attention (CNN-ECA) is developed to accurately forecast key operating condition parameters. Based on these outputs, the second phase employs a compressor performance prediction model to estimate unit energy consumption with improved precision. In addition, a hybrid prediction strategy integrating a Transformer architecture is introduced to capture long-range temporal dependencies, thereby enhancing both single-step and multi-step forecasting performance. The proposed method is evaluated using operational data from eight compressors at the Xiangguosi underground gas storage. Experimental results show that the framework achieves high prediction accuracy, with a MAPE of 4.0779% (single-step) and 4.2449% (multi-step), outperforming advanced benchmark models. Full article

Drivable area (DA) detection in unstructured off-road environments remains challenging for unmanned ground vehicles (UGVs) due to limited field-of-view, persistent occlusions, and the inherent limitations of individual sensors. While existing fusion approaches combine aerial and ground perspectives, they often struggle with misaligned spatiotemporal viewpoints, dynamic environmental changes, and ineffective feature integration, particularly at intersections or under long-range occlusion. To address these issues, this paper proposes a cooperative air–ground perception framework based on multi-source data fusion. Our three-stage system first introduces DynCoANet, a semantic segmentation network incorporating directional strip convolution and connectivity attention to extract topologically consistent road structures from UAV imagery. Second, an enhanced particle filter with semantic road constraints and diversity-preserving resampling achieves robust cross-view localization between UAV maps and UGV LiDAR. Finally, a distance-adaptive fusion transformer (DAFT) dynamically fuses UAV semantic features with LiDAR BEV representations via confidence-guided cross-attention, balancing geometric precision and semantic richness according to spatial distance. Extensive evaluations demonstrate the effectiveness of our approach: on the DeepGlobe road extraction dataset, DynCoANet attains an IoU of 61.14%; cross-view localization on KITTI sequences reduces average position error by approximately 10%; and DA detection on OpenSatMap outperforms Grid-DATrNet by 8.42% in accuracy for large-scale regions (400 m × 400 m). Real-world experiments with a coordinated UAV-UGV platform confirm the framework’s robustness in occlusion-heavy and geometrically complex scenarios. This work provides a unified solution for reliable DA perception through tightly coupled cross-modal alignment and adaptive fusion. Full article

Accurate and energy-efficient localization of autonomous underwater vehicles (AUVs) remains a fundamental challenge due to the complex, bandwidth-limited, and highly dynamic nature of underwater acoustic environments. This paper proposes a fully adaptive deep reinforcement learning (DRL)-driven localization framework for AUVs operating in Underwater Acoustic Sensor Networks (UAWSNs). The localization problem is formulated as a Markov Decision Process (MDP) in which an intelligent agent jointly optimizes beacon selection and transmit power allocation to minimize long-term localization error and energy consumption. A hierarchical learning architecture is developed by integrating four actor–critic algorithms, which are (i) Twin Delayed Deep Deterministic Policy Gradient (TD3), (ii) Soft Actor–Critic (SAC), (iii) Multi-Agent Deep Deterministic Policy Gradient (MADDPG), and (iv) Distributed DDPG (D2DPG), enabling robust learning under non-stationary channels, cooperative multi-AUV scenarios, and large-scale deployments. A round-trip time (RTT)-based geometric localization model incorporating a depth-dependent sound speed gradient is employed to accurately capture realistic underwater acoustic propagation effects. A multi-objective reward function jointly balances localization accuracy, energy efficiency, and ranging reliability through a risk-aware metric. Furthermore, the Cramér–Rao Lower Bound (CRLB) is derived to characterize the theoretical performance limits, and a comprehensive complexity analysis is performed to demonstrate the scalability of the proposed framework. Extensive Monte Carlo simulations show that the proposed DRL-based methods achieve significantly lower localization error, lower energy consumption, faster convergence, and higher overall system utility than classical TD3. These results confirm the effectiveness and robustness of DRL for next-generation adaptive underwater localization systems. Full article

Traffic systems are quintessential complex systems, characterized by nonlinear interactions, multiscale dynamics, and emergent spatiotemporal patterns over complex networks. These properties make traffic prediction highly challenging, as it requires jointly modeling stable global topology and time-varying local dependencies. Existing graph neural networks often rely on predefined or static learnable graphs, overlooking hidden dynamic structures, while most RNN- or CNN-based approaches struggle with long-range temporal dependencies. This paper proposes a Spatiotemporal Causal–Trend Network (SCTN) tailored to complex transportation networks. First, we introduce a dual-path adaptive graph learning scheme: a static graph that captures global, topology-aligned dependencies of the complex network, and a dynamic graph that adapts to localized, time-varying interactions. Second, we design a Gated Temporal Attention Module (GTAM) with a causal–trend attention mechanism that integrates 1D and causal convolutions to reinforce temporal causality and local trend awareness while maintaining long-range attention. Extensive experiments on two real-world PeMS traffic flow datasets demonstrate that SCTN consistently achieves superior accuracy compared to strong baselines, reducing by 3.5–4.5% over the best-performing existing methods, highlighting its effectiveness for modeling the intrinsic complexity of urban traffic systems. Full article

In image super-resolution tasks, methods based on Generative Adversarial Networks (GANs), Transformer models, and diffusion models demonstrate robust global modeling capabilities and outstanding performance. However, their computational costs remain prohibitively high, limiting deployment on resource-constrained devices. Meanwhile, frequency-domain approaches based on convolutional neural networks (CNNs) capture complementary structural information but lack long-range dependencies, resulting in suboptimal perceptual image quality. To overcome these limitations, we propose a micro-Transformer-based architecture. This framework enriches high-frequency image information through wavelet transform-based frequency-domain features, integrates spatio-temporal and frequency-domain cross-feature fusion, and incorporates a discriminator constraint to achieve image super-resolution. Extensive experiments demonstrate that this approach achieves competitive PSNR/SSIM performance while maintaining reasonable computational complexity. Its visual quality and efficiency outperform most existing SR methods. Full article

Real-valued inter-residue distance maps provide essential spatial information for understanding protein folding mechanisms and guiding downstream applications such as function annotation, drug discovery, and structural modeling. However, existing prediction methods often struggle to capture long-range dependencies and to maintain topological consistency across different structural scales. To address these challenges, we propose a novel prediction framework that integrates a Mamba architecture, based on a selective state space model, to effectively model global interactions, and incorporates the Kolmogorov–Arnold Network (KAN) to enhance nonlinear structural representation. Extensive experiments on standard benchmark datasets, including CASP13, CASP14, and CASP15, demonstrate prediction accuracies of 86.53%, 85.44%, and 82.77%, respectively, outperforming state-of-the-art approaches. These results indicate that the proposed framework substantially improves the fidelity of real-valued distance prediction and offers a promising tool for downstream structural and functional studies. Full article

Existing 3D point cloud enhancement methods typically rely on artificially designed geometric transformations or local blending strategies, which are prone to introducing illogical deformations, struggle to preserve global structure, and exhibit insufficient adaptability to diverse degradation patterns. To address these limitations, this paper proposes SFD-ADNet—an adaptive deformation framework based on a dual spatial–frequency domain. It achieves 3D point cloud augmentation by explicitly learning deformation parameters rather than applying predefined perturbations. By jointly modeling spatial structural dependencies and spectral features, SFD-ADNet generates augmented samples that are both structurally aware and task-relevant. In the spatial domain, a hierarchical sequence encoder coupled with a bidirectional Mamba-based deformation predictor captures long-range geometric dependencies and local structural variations, enabling adaptive position-aware deformation control. In the frequency domain, a multi-scale dual-channel mechanism based on adaptive Chebyshev polynomials separates low-frequency structural components from high-frequency details, allowing the model to suppress noise-sensitive distortions while preserving the global geometric skeleton. The two deformation predictions dynamically fuse to balance structural fidelity and sample diversity. Extensive experiments conducted on ModelNet40-C and ScanObjectNN-C involved synthetic CAD models and real-world scanned point clouds under diverse perturbation conditions. SFD-ADNet, as a universal augmentation module, reduces the mCE metrics of PointNet++ and different backbone networks by over 20%. Experiments demonstrate that SFD-ADNet achieves state-of-the-art robustness while preserving critical geometric structures. Furthermore, models enhanced by SFD-ADNet demonstrate consistently improved robustness against diverse point cloud attacks, validating the efficacy of adaptive space-frequency deformation in robust point cloud learning. Full article

Flat soda–lime–silicate glass is the dominant glass type used in contemporary buildings. This paper provides a comprehensive and integrated review of the scientific principles and technological processes that underpin its manufacture, processing, and structural performance. The discussion spans the glass transition and the nature of the glassy state; the network structure of soda–lime–silicate glass, with its inherent lack of long-range order; and its physical and mechanical properties, including fracture. The industrial production of flat soda–lime–silicate glass (melting, float-forming, and annealing) and its subsequent processing (thermal tempering, chemical strengthening, and coating) are described in detail, with emphasis on how they influence residual stresses, surface and edge quality, and structural reliability. Environmental considerations and ongoing advances in energy efficiency and decarbonisation are also examined. By linking the fundamentals of glass science to modern structural design standards, particularly the forthcoming Eurocode 10 for glass structures, the article seeks to equip structural engineers with an informed understanding of glass as a high-performance material for innovative and sustainable design. Full article

Recent reports have revealed that the number of lower limb amputees worldwide has increased as a result of war, accidents, and vascular diseases and that transfemoral amputation accounts for 39% of cases, highlighting the need to develop an improved functional prosthetic knee joint that improves the amputee’s ability to resume activities of daily living. To enable transfemoral prosthesis users to walk on level ground, accurate prediction of the intended knee joint angle is critical for transfemoral prosthesis control. Therefore, the purpose of this research was to develop a technique for estimating knee joint angle utilizing a long short-term memory (LSTM) network and kinematic data collected from inertial measurement units (IMUs). The proposed LSTM network was trained and tested to estimate the contralateral knee angle using data collected from twenty able-bodied subjects using a lab-developed sensory gadget, which included four IMUs. Accordingly, the present work represents a feasibility investigation conducted on able-bodied individuals rather than a clinical validation for amputee gait. This study contributes to the field of bionics by mimicking the natural biomechanical behavior of the human knee joint during gait cycle to improve the control of artificial prosthetic knees. The proposed LSTM model learns the contralateral knee’s motion patterns in able-bodied gait and demonstrates the potential for future application in prosthesis control, although direct generalization to amputee users is outside the scope of this preliminary study. The contralateral LSTM models exhibited a real-time RMSE range of 2.48–2.78° and a correlation coefficient range of 0.9937–0.9991. This study proves the effectiveness of LSTM networks in estimating contralateral knee joint angles and shows their real-time performance and robustness, supporting its feasibility while acknowledging that further testing with amputee participants is required. Full article

Accurate prediction of lithium battery remaining useful life (RUL) is crucial for battery management systems to monitor battery health status. However, RUL prediction remains challenging due to capacity non-stationarity caused by capacity regeneration phenomena. Therefore, this study proposes a novel RUL prediction framework that combines a two-stage decomposition strategy with a parallel Informer-LSTM architecture. First, STL decomposition is employed to decompose the capacity sequence into trend, seasonal, and residual components. The VMD method further refines the residual component from STL, extracting the underlying multiscale subsignals. Subsequently, a parallel dual-channel prediction network is constructed: the Informer branch captures global long-range dependencies to prevent trend drift, while the LSTM branch models local nonlinear dynamics to reconstruct fluctuations associated with capacity regeneration. Experiments on the NASA dataset demonstrate that this framework achieves an MAE below 0.0109, an RMSE below 0.0160, and an R² above 0.9950. Additional validation on the Oxford battery dataset confirms the model’s robust generalization capability under dynamic conditions, with an MAE of 0.0017. This further demonstrates that the proposed RUL prediction framework achieves significantly enhanced prediction accuracy and stability, offering a reliable solution for battery health status detection in battery management systems. Full article

Background/Objectives: Parkinsonian gait is characterized by impaired motor adaptability, altered temporal organization, and reduced movement variability. While data augmentation is commonly used to mitigate class imbalance in gait-based machine learning models, conventional strategies often ignore physiological differences between healthy and pathological movements, potentially distorting meaningful motor dynamics. This study explores whether preserving healthy motor variability while selectively augmenting pathological gait signals can improve the robustness and physiological coherence of gait pattern classification models. Methods: Eight patients with Parkinsonian gait patterns and forty-eight healthy participants performed walking tasks on the Motigravity platform under hypogravity conditions. Full-body kinematic data were acquired using wearable inertial sensors. A selective augmentation strategy based on smooth time-warping was applied exclusively to pathological gait segments (×5, σ = 0.2), while healthy gait signals were left unaltered to preserve natural motor variability. Model performance was evaluated using a hybrid convolutional neural network–long short-term memory (CNN–LSTM) architecture across multiple augmentation configurations. Results: Selective augmentation of pathological gait signals achieved the highest classification performance (94.1% accuracy, AUC = 0.97), with balanced sensitivity (93.8%) and specificity (94.3%). Performance decreased when augmentation exceeded an optimal range of variability, suggesting that beneficial augmentation is constrained by physiologically plausible temporal dynamics. Conclusions: These findings demonstrate that physiology-informed, selective data augmentation can improve gait pattern classification under constrained data conditions. Rather than supporting disease-specific diagnosis, this proof-of-concept study highlights the importance of respecting intrinsic differences in motor variability when designing augmentation strategies for clinical gait analysis. Future studies incorporating disease-control cohorts and subject-independent validation are required to assess specificity and clinical generalizability. Full article

Background/Objectives: Diagnosing Rotator Cuff Tears (RCTs) via Magnetic Resonance Imaging (MRI) is clinically challenging due to complex 3D anatomy and significant interobserver variability. Traditional slice-centric Convolutional Neural Networks (CNNs) often fail to capture the necessary volumetric context for accurate grading. This study aims to develop and validate the Patient-Aware Vision Transformer (Pa-ViT), an explainable deep-learning framework designed for the automated, patient-level classification of RCTs (Normal, Partial-Thickness, and Full-Thickness). Methods: A large-scale retrospective dataset comprising 2447 T2-weighted coronal shoulder MRI examinations was utilized. The proposed Pa-ViT framework employs a Vision Transformer (ViT-Base) backbone within a Weakly-Supervised Multiple Instance Learning (MIL) paradigm to aggregate slice-level semantic features into a unified patient diagnosis. The model was trained using a weighted cross-entropy loss to address class imbalance and was benchmarked against widely used CNN architectures and traditional machine-learning classifiers. Results: The Pa-ViT model achieved a high overall accuracy of 91% and a macro-averaged F1-score of 0.91, significantly outperforming the standard VGG-16 baseline (87%). Notably, the model demonstrated superior discriminative power for the challenging Partial-Thickness Tear class (ROC AUC: 0.903). Furthermore, Attention Rollout visualizations confirmed the model’s reliance on genuine anatomical features, such as the supraspinatus footprint, rather than artifacts. Conclusions: By effectively modeling long-range dependencies, the Pa-ViT framework provides a robust alternative to traditional CNNs. It offers a clinically viable, explainable decision support tool that enhances diagnostic sensitivity, particularly for subtle partial-thickness tears. Full article