Search Results (232)

The rapid advancement of artificial intelligence is transforming agriculture by enabling data-driven plant disease monitoring and decision support. Soil-borne mosaic wheat virus (SBWMV) is a soil-transmitted virus disease that poses a serious threat to wheat production across multiple ecological zones. Due to the regional variability in environmental conditions and symptom expressions, accurately evaluating the severity of wheat soil-borne mosaic (WSBM) infections remains a persistent challenge. To address this, the problem is formulated as large-scale group decision-making process (LSGDM), where each planting plot is treated as an independent virtual decision maker, providing its own severity assessments. This modeling approach reflects the spatial heterogeneity of the disease and enables a structured mechanism to reconcile divergent evaluations. First, for each site, field observation of infection symptoms are recorded and represented using intuitionistic fuzzy numbers (IFNs) to capture uncertainty in detection. Second, a Bayesian graph convolutional networks model (Bayesian-GCN) is used to construct a spatial trust propagation mechanism, inferring missing trust values and preserving regional dependencies. Third, an enhanced spectral clustering method is employed to group plots with similar symptoms and assessment behaviors. Fourth, a feedback mechanism is introduced to iteratively adjust plot-level evaluations based on a set of defined agricultural decision indicators sets using a multi-granulation rough set (ADISs-MGRS). Once consensus is reached, final rankings of candidate plots are generated from indicators, providing an interpretable and evidence-based foundation for targeted prevention strategies. By using the WSBM dataset collected in 2017–2018 from Walla Walla Valley, Oregon/Washington State border, the United States of America, and performing data augmentation for validation, along with comparative experiments and sensitivity analysis, this study demonstrates that the AI-driven LSGDM model integrating enhanced spectral clustering and ADISs-MGRS feedback mechanisms outperforms traditional models in terms of consensus efficiency and decision robustness. This provides valuable support for multi-party decision making in complex agricultural contexts. Full article

Besides metabolic and cardiovascular parameters, fluctuations in endocrine and inflammatory biomarkers might be regarded as reliable indicators of allostatic load. Among them, glucocorticoids have been shown to correlate with social stress in animals, regardless of whether they are dominant or subordinate, thus highlighting the crucial role of physiological energetic costs, together with social challenges, in the onset and severity of allostasis. Therefore, in the present work, we evaluated and monitored monthly the concentration of cortisol in bristles (pg/mg) over six months in young (n = 8), sub-adult (n = 5) and adult female wild boars (n = 5), which were kept in a controlled State Forest in Southern Italy. Our data revealed higher concentrations of cortisol in young animals when compared to sub-adult (p < 0.01) and adult (p < 0.05) groups. Moreover, such an increase faded away over time, and cortisol concentrations were found to be overlapping those of sub-adult and adult groups, which did not display any significant variation throughout monitoring. Collectively, our findings suggest that the wild boars adapted to the controlled environment, thus preserving both a physiological state and animal welfare. Full article

Flash floods are natural disasters that have significant impacts on human life and economic damage. The detection of flash floods using remote-sensing techniques provides essential data for subsequent flood-risk assessment through the preparation of flood inventory samples. In this research, a new deep-learning approach for bi-temporal flash-flood detection in Synthetic Aperture Radar (SAR) is proposed. It combines a U-Net convolutional network with a Transformer model using a compact Convolutional Tokenizer (CCT) to improve the efficiency of long-range dependency learning. The hybrid model, namely CCT-U-ViT, naturally combines the spatial feature extraction of U-Net and the global context capability of Transformer. The model significantly reduces the number of basic blocks as it uses the CCT tokenizer instead of conventional Vision Transformer tokenization, which makes it the right fit for small flood detection datasets. This model improves flood boundary delineation by involving local spatial patterns and global contextual relations. However, the method is based on Sentinel-1 SAR images and focuses on Erbil, Iraq, which experienced an extreme flash flood in December 2021. The experimental comparison results show that the proposed CCT-U-ViT outperforms multiple baseline models, such as conventional CNNs, U-Net, and Vision Transformer, obtaining an impressive overall accuracy of 91.24%. Furthermore, the model obtains better precision and recall with an F1-score of 91.21% and mIoU of 83.83%. Qualitative results demonstrate that CCT-U-ViT can effectively preserve the flood boundaries with higher precision and less salt-and-pepper noise compared with the state-of-the-art approaches. This study underscores the significance of hybrid deep-learning models in enhancing the precision of flood detection with SAR data, providing valuable insights for the advancement of real-time flood monitoring and risk management systems. Full article

This paper presents a hybrid fast charging strategy for static wireless power transfer (WPT) systems that synergistically combines pulsed current and multi-stage current (MCM) modes to enable rapid yet battery-health-conscious electric vehicle (EV) charging, thereby promoting sustainable transportation. The proposed approach employs a memetic algorithm (MA) to dynamically optimize the charging parameters, achieving an optimal balance between speed and battery longevity while maintaining 90.78% system efficiency at the SAE J2954-standard 85 kHz operating frequency. A neural-network-based state of charge (SOC) estimator provides accurate real-time monitoring, complemented by MA-tuned PI control for enhanced resonance stability and adaptive pulsed current–MCM profiles for the optimal energy transfer. Simulations and experimental validation demonstrate faster charging compared to that using the conventional constant current–constant voltage (CC-CV) methods while effectively preserving the battery’s state of health (SOH)—a critical advantage that reduces the environmental impact of frequent battery replacements and minimizes the carbon footprint associated with raw material extraction and battery manufacturing. By addressing both the technical challenges of high-power WPT systems and the ecological imperative of battery preservation, this research bridges the gap between fast charging requirements and sustainable EV adoption, offering a practical solution that aligns with global decarbonization goals through optimized resource utilization and an extended battery service life. Full article

In recent years, remote sensing imagery has become indispensable for applications such as environmental monitoring, land use classification, and urban planning. However, the physical constraints of satellite imaging systems frequently limit the spatial resolution of these images, impeding the extraction of fine-grained information critical to downstream tasks. Super-resolution (SR) techniques thus emerge as a pivotal solution to enhance the spatial fidelity of remote sensing images via computational approaches. While deep learning-based SR methods have advanced reconstruction accuracy, their high computational complexity and large parameter counts restrict practical deployment in real-world remote sensing scenarios—particularly on edge or low-power devices. To address this gap, we propose LSANet, a lightweight SR network customized for remote sensing imagery. The core of LSANet is the large separable kernel attention mechanism, which efficiently expands the receptive field while retaining low computational overhead. By integrating this mechanism into an enhanced residual feature distillation module, the network captures long-range dependencies more effectively than traditional shallow residual blocks. Additionally, a residual feature enhancement module, leveraging contrast-aware channel attention and hierarchical skip connections, strengthens the extraction and integration of multi-level discriminative features. This design preserves fine textures and ensures smooth information propagation across the network. Extensive experiments on public datasets such as UC Merced Land Use and NWPU-RESISC45 demonstrate LSANet’s competitive or superior performance compared to state-of-the-art methods. On the UC Merced Land Use dataset, LSANet achieves a PSNR of 34.33, outperforming the best-baseline HSENet with its PSNR of 34.23 by 0.1. For SSIM, LSANet reaches 0.9328, closely matching HSENet’s 0.9332 while demonstrating excellent metric-balancing performance. On the NWPU-RESISC45 dataset, LSANet attains a PSNR of 35.02, marking a significant improvement over prior methods, and an SSIM of 0.9305, maintaining strong competitiveness. These results, combined with the notable reduction in parameters and floating-point operations, highlight the superiority of LSANet in remote sensing image super-resolution tasks. Full article

Infrasound signal classification remains a critical challenge in geophysical monitoring systems, where classification performance is fundamentally constrained by feature extraction efficacy. Existing two-dimensional feature extraction methods suffer from inadequate representation of spatiotemporal signal dynamics, leading to performance degradation in long-distance detection scenarios. To overcome these limitations, we present a novel classification framework that effectively captures spatiotemporal infrasound characteristics through Gramian Angular Field (GAF) transformation. The proposed method introduces an innovative encoding scheme that transforms one-dimensional infrasonic waveforms into two-dimensional GAF images while preserving crucial temporal dependencies. Building upon this representation, we develop an advanced hybrid deep learning architecture that integrates ConvLSTM networks to simultaneously extract and correlate spatial and spectral features. Extensive experimental validation on both chemical explosion and seismic infrasound datasets shows our approach achieves 92.4% classification accuracy, demonstrating consistent superiority over four state-of-the-art benchmark methods. These findings demonstrate the effectiveness of the proposed method. Full article

Human Activity Recognition (HAR) is crucial for understanding human behaviour through sensor data, with applications in healthcare, smart environments, and surveillance. While traditional HAR often relies on ambient sensors, wearable devices or vision-based systems, these approaches can face limitations in dynamic settings and raise privacy concerns. Device-free HAR systems, utilising Wi-Fi Channel State Information (CSI) to human movements, have emerged as a promising privacy-preserving alternative for next-generation health activity monitoring and smart environments, particularly for multi-user scenarios. However, current research faces challenges such as the need for substantial annotated training data, class imbalance, and poor generalisability in complex, multi-user environments where labelled data is often scarce. This paper addresses these gaps by proposing a hybrid deep learning approach which integrates signal preprocessing, targeted data augmentation, and a customised integration of CNN and Transformer models, designed to address the challenges of multi-user recognition and data scarcity. A random transformation technique to augment real CSI data, followed by hybrid feature extraction involving statistical, spectral, and entropy-based measures to derive suitable representations from temporal sensory input, is employed. Experimental results show that the proposed model outperforms several baselines in single-user and multi-user contexts. Our findings demonstrate that combining real and augmented data significantly improves model generalisation in scenarios with limited labelled data. Full article

Reliable fault diagnosis in aero-engine bearing systems is essential for maintaining process stability and safety. However, acquiring fault samples in aerospace applications is costly and difficult, resulting in severely limited data for model training. Traditional methods often perform poorly under such constraints, lacking the ability to extract discriminative features or effectively correlate observed signal changes with underlying process faults. To address this challenge, this study presents a process-oriented framework—WSET-CNN-OOA-LSSVM—designed for effective fault recognition in small-sample scenarios. The framework begins with Wavelet Synchroextracting Transform (WSET), enhancing time–frequency resolution and capturing energy-concentrated fault signatures that reflect degradation along the process timeline. A tailored CNN with asymmetric pooling and progressive dropout preserves temporal dynamics while preventing overfitting. To compensate for limited labels, confidence-based pseudo-labeling is employed, guided by Mahalanobis distance and adaptive thresholds to ensure reliability. Classification is finalized using an Osprey Optimization Algorithm (OOA)-enhanced Least Squares SVM, which adapts decision boundaries to reflect subtle process state transitions. Validated on both test bench and real aero-engine data, the framework achieves 93.4% accuracy with only five fault samples per class and 100% in full-scale scenarios, outperforming eight existing methods. Therefore, the experimental results confirm that the proposed framework can effectively overcome the data scarcity challenge in aerospace bearing fault diagnosis, demonstrating its practical viability for few-shot learning applications in industrial condition monitoring. Full article

Very high resolution (VHR) remote sensing change detection (CD) is crucial for monitoring Earth’s dynamics but faces challenges in capturing fine-grained changes and distinguishing them from pseudo-changes due to varying acquisition conditions. Existing deep learning methods often suffer from information loss via downsampling, obscuring details, and lack filter adaptability to spatial heterogeneity. To address these issues, we introduce Information-Preserving Adaptive Convolutional Network (IPACN). IPACN features a novel Information-Preserving Backbone (IPB), leveraging principles adapted from reversible networks to minimize feature degradation during hierarchical bi-temporal feature extraction, enhancing the preservation of fine spatial details, essential for accurate change delineation. Crucially, IPACN incorporates a Frequency-Adaptive Difference Enhancement Module (FADEM) that applies adaptive filtering, informed by frequency analysis concepts, directly to the bi-temporal difference features. The FADEM dynamically refines change signals based on local spectral characteristics, improving discrimination. This synergistic approach, combining high-fidelity feature preservation (IPB) with adaptive difference refinement (FADEM), yields robust change representations. Comprehensive experiments on benchmark datasets demonstrate that IPACN achieves state-of-the-art performance, showing significant improvements in F1 score and IoU, enhanced boundary delineation, and improved robustness against pseudo-changes, offering an effective solution for very high resolution remote sensing CD. Full article

Resource-constrained devices, including low-power Internet of Things (IoT) nodes, microcontrollers, and edge computing platforms, have increasingly become the focal point for deploying on-device intelligence. By integrating artificial intelligence (AI) closer to data sources, these systems aim to achieve faster responses, reduce bandwidth usage, and preserve privacy. Nevertheless, implementing AI in limited hardware environments poses substantial challenges in terms of computation, energy efficiency, model complexity, and reliability. This paper provides a comprehensive review of state-of-the-art methodologies, examining how recent advances in model compression, TinyML frameworks, and federated learning paradigms are enabling AI in tightly constrained devices. We highlight both established and emergent techniques for optimizing resource usage while addressing security, privacy, and ethical concerns. We then illustrate opportunities in key application domains—such as healthcare, smart cities, agriculture, and environmental monitoring—where localized intelligence on resource-limited devices can have broad societal impact. By exploring architectural co-design strategies, algorithmic innovations, and pressing research gaps, this paper offers a roadmap for future investigations and industrial applications of AI in resource-constrained devices. Full article

Enhancing the detection capabilities of marine vessels is crucial for maritime security and intelligence acquisition. However, accurately identifying small ships in complex oceanic environments remains a significant challenge, as these targets are frequently obscured by ocean waves and other disturbances, compromising recognition accuracy and stability. To address this issue, we propose YOLO-ssboat, a novel small-target ship recognition algorithm based on the YOLOv8 framework. YOLO-ssboat integrates the C2f_DCNv3 module to extract fine-grained features of small vessels while mitigating background interference and preserving critical target details. Additionally, it employs a high-resolution feature layer and incorporates a Multi-Scale Weighted Pyramid Network (MSWPN) to enhance feature diversity. The algorithm further leverages an improved multi-attention detection head, Dyhead_v3, to refine the representation of small-target features. To tackle the challenge of wake waves from moving ships obscuring small targets, we introduce a gradient flow mechanism that improves detection efficiency under dynamic conditions. The Tail Wave Detection Method synergistically integrates gradient computation with target detection techniques. Furthermore, adversarial training enhances the network’s robustness and ensures greater stability. Experimental evaluations on the Ship_detection and Vessel datasets demonstrate that YOLO-ssboat outperforms state-of-the-art detection algorithms in both accuracy and stability. Notably, the gradient flow mechanism enriches target feature extraction for moving vessels, thereby improving detection accuracy in wake-disturbed scenarios, while adversarial training further fortifies model resilience. These advancements offer significant implications for the long-range monitoring and detection of maritime vessels, contributing to enhanced situational awareness in expansive oceanic environments. Full article

Accurate recognition of student emotions in smart classrooms is vital for understanding learning states. Visible light-based facial expression recognition is often affected by illumination changes, making thermal infrared imaging a promising alternative due to its robust temperature distribution symmetry. This paper proposes CTIFERK, a thermal infrared facial expression recognition model integrating Kolmogorov–Arnold Networks (KANs). By incorporating multiple KAN layers, CTIFERK enhances feature extraction and fitting capabilities. It also balances pooling layer information from the MobileViT backbone to preserve symmetrical facial features, improving recognition accuracy. Experiments on the Tufts Face Database, the IRIS Database, and the self-constructed GUET thermalface dataset show that CTIFERK achieves accuracies of 81.82%, 82.19%, and 65.22%, respectively, outperforming baseline models. These results validate CTIFERK’s effectiveness and superiority for thermal infrared expression recognition in smart classrooms, enabling reliable emotion monitoring. Full article

Railway safety inspections, a critical component of modern transportation systems, face significant challenges from adverse weather conditions, like fog and rain, which degrade image quality and compromise inspection accuracy. To address this limitation, we propose a novel deep learning-based image dehazing algorithm optimized for outdoor railway environments. Our method integrates adaptive high-pass filtering and bilateral grid processing during the feature extraction phase to enhance detail preservation while maintaining computational efficiency. The framework uniquely combines RGB color channels with atmospheric brightness channels to disentangle environmental interference from critical structural information, ensuring balanced restoration across all spectral components. A dual-attention mechanism (channel and spatial attention modules) is incorporated during feature fusion to dynamically prioritize haze-relevant regions and suppress weather-induced artifacts. Comprehensive evaluations demonstrate the algorithm’s superior performance: On the SOTS-Outdoor benchmark, it achieves state-of-the-art PSNR (35.27) and SSIM (0.9869) scores. When tested on a specialized railway inspection dataset containing 12,840 fog-affected track images, the method attains a PSNR of 30.41 and SSIM of 0.9511, with the SSIM being marginally lower (0.0017) than DeHamer while outperforming other comparative methods in perceptual clarity. Quantitative and qualitative analyses confirm that our approach effectively restores critical infrastructure details obscured by atmospheric particles, improving defect detection accuracy by 18.6 percent compared to non-processed images in simulated inspection scenarios. This work establishes a robust solution for weather-resilient railway monitoring systems, demonstrating practical value for automated transportation safety applications. Full article

A majority of hyperspectral super-resolution methods aim to enhance the spatial resolution of hyperspectral imaging data (HSI) by integrating high-resolution multispectral imaging data (MSI), leveraging rich spectral information for various geospatial applications. Key challenges include spectral distortions from high-frequency spatial data, high computational complexity, and limited training data, particularly for new-generation sensors with unique noise patterns. In this contribution, we propose a novel parallel patch-wise sparse residual learning (P²SR) algorithm for resolution enhancement based on fusion of HSI and MSI. The proposed method uses multi-decomposition techniques (i.e., Independent component analysis, Non-negative matrix factorization, and 3D wavelet transforms) to extract spatial and spectral features to form a sparse dictionary. The spectral and spatial characteristics of the scene encoded in the dictionary enable reconstruction through a first-order optimization algorithm to ensure an efficient sparse representation. The final spatially enhanced HSI is reconstructed by combining the learned features from low-resolution HSI and applying an MSI-regulated guided filter to enhance spatial fidelity while minimizing artifacts. P²SR is deployable on a high-performance computing (HPC) system with parallel processing, ensuring scalability and computational efficiency for large HSI datasets. Extensive evaluations on three diverse study sites demonstrate that P²SR consistently outperforms traditional and state-of-the-art (SOA) methods in both quantitative metrics and qualitative spatial assessments. Specifically, P²SR achieved the best average PSNR (25.2100) and SAM (12.4542) scores, indicating superior spatio-spectral reconstruction contributing to sharper spatial features, reduced mixed pixels, and enhanced geological features. P²SR also achieved the best average ERGAS (8.9295) and Q2n (0.5156), which suggests better overall fidelity across all bands and perceptual accuracy with the least spectral distortions. Importantly, we show that P²SR preserves critical spectral signatures, such as Fe²⁺ absorption, and improves the detection of fine-scale environmental and geological structures. P²SR’s ability to maintain spectral fidelity while enhancing spatial detail makes it a powerful tool for high-precision remote sensing applications, including mineral mapping, land-use analysis, and environmental monitoring. Full article

Hepatocellular carcinoma (HCC) is a leading cause of cancer-related mortality worldwide, so its detection and monitoring are critical. However, contrast-enhanced magnetic resonance imaging (CE-MRI) is particularly vulnerable to complex, unstructured noise, which compromises image quality and diagnostic accuracy. This study proposes the use of NLE-ANSNet, a deep learning-based denoizing framework that integrates multilevel noise level estimators (NLEs) and adaptive noise scaling (ANS) within residual blocks. The model performs progressive, stagewise noise suppression at multiple feature depths, dynamically adjusting normalization based on localized noise estimates. This enables context-aware denoizing, preserving fine anatomical details. To simulate clinically realistic conditions, we developed a hybrid noise simulation framework that combines Gaussian, Poisson, and Rician noise at the pixel level. This framework aims to approximate a balanced noise distribution for evaluation purposes, with both mean and median noise levels reported to enhance evaluation robustness and prevent bias from extreme cases. NLE-ANSNet achieves a PSNR of 34.01 dB and an SSIM of 0.9393, surpassing those of state-of-the-art models. The method aims to support diagnostic reliability by preserving image structure and intensity fidelity in CE-MRI interpretation. In addition to quantitative analysis, a qualitative assessment was conducted to visually compare denoizing outputs across models, further demonstrating NLE-ANSNet’s superior ability to suppress noise while preserving diagnostically critical information. Unlike previous approaches, this study introduces a denoizing framework that combines multilevel noise estimation and adaptive noise scaling specifically tailored for CE-MRI in HCC under hybrid noise conditions—a clinically relevant and underexplored area. Overall, this study supports improved clinical decision making in HCC management. Full article