Search Results (12,185)

Synthetic Aperture Radar (SAR) onboard satellites provides high-resolution Earth imaging independent of weather conditions. SAR data are acquired by an aircraft or satellite and sent to a ground station to be processed. However, for novel applications requiring real-time analysis and decisions, onboard processing is necessary to escape the limited downlink bandwidth and latency. One such application is real-time target recognition, which has emerged as a decisive operation in areas such as defense and surveillance. In recent years, deep learning models have improved the accuracy of target recognition algorithms. However, these are based on optical image processing and are computation and memory expensive, which requires not only processing the SAR pulse data but also optimized models and architectures for efficient deployment in onboard computers. This paper presents a fast and accurate target recognition system directly on raw SAR data using a neural network model. This network receives and processes SAR echo data for fast processing, alleviating the computationally expensive DSP image generation algorithms such as Backprojection and RangeDoppler. Thus, this allows the use of simpler and faster models, while maintaining accuracy. The system was designed, optimized, and tested on low-cost embedded devices with low size, weight ,and energy requirements (Khadas VIM3 and Raspberry Pi 5). Results demonstrate that the proposed solution achieves a target classification accuracy for the MSTAR dataset close to 100% in less than 1.5 ms and 5.5 W of power. Full article

Digital Twin (DT) technology has emerged as a valuable tool for researchers and engineers, enabling them to optimize performance and enhance system efficiency. This paper presents a comprehensive Systematic Literature Review (SLR) following the PRISMA framework to explore current applications of DT technology in the power generation sector while highlighting key advancements. A new framework is developed to categorize DTs in terms of time-scale horizons and applications, focusing on power plant types (emissive vs. non-emissive), operational behaviors (including condition monitoring, predictive maintenance, fault detection, power generation prediction, and optimization), and specific components (e.g., power transformers). The time-scale is subdivided into a six-level structure to precisely indicate the speed and time range at which it is used. More importantly, each category in the application is further subcategorized into a three-level framework: component-level (i.e., fundamental physical properties and operational characteristics), system-level (i.e., interaction of subsystems and optimization), and service-level (i.e., value-adding service outputs). This classification can be utilized by various parties, such as stakeholders, engineers, scientists, and policymakers, to gain both a general and detailed understanding of potential research and operational gaps. Addressing these gaps could improve asset longevity and reduce energy consumption and emissions. Full article

This paper investigates Electrocardiogram (ECG) rhythm classification using a progressive deep learning framework that combines time–frequency representations with complementary hand-crafted features. In the first stage, ECG signals from the PhysioNet Challenge 2017 dataset are transformed into scalograms and input to diverse architectures, including Simple Convolutional Neural Network (SimpleCNN), Residual Network with 18 Layers (ResNet-18), Convolutional Neural Network-Transformer (CNNTransformer), and Vision Transformer (ViT). ViT achieved the highest accuracy (0.8590) and F1-score (0.8524), demonstrating the feasibility of pure image-based ECG analysis, although scalograms alone showed variability across folds. In the second stage, scalograms were fused with scattering and statistical features, enhancing robustness and interpretability. FusionViT without dimensionality reduction achieved the best performance (accuracy = 0.8623, F1-score = 0.8528), while Fusion ResNet-18 offered a favorable trade-off between accuracy (0.8321) and inference efficiency (0.016 s per sample). The application of Principal Component Analysis (PCA) reduced the dimensionality of the feature from 509 to 27, reducing the computational cost while maintaining competitive performance (FusionViT precision = 0.8590). The results highlight a trade-off between efficiency and fine-grained temporal resolution. Training-time augmentations mitigated class imbalance, enabling lightweight inference (0.006–0.043 s per sample). For real-world use, the framework can run on wearable ECG devices or mobile health apps. Scalogram transformation and feature extraction occur on-device or at the edge, with efficient models like ResNet-18 enabling near real-time monitoring. Abnormal rhythm alerts can be sent instantly to users or clinicians. By combining visual and statistical signal features, optionally reduced with PCA, the framework achieves high accuracy, robustness, and efficiency for practical deployment. Full article

Starches isolated as by-products from protein extraction of three cowpea and three moth bean cultivars were investigated for their structural and functional properties, including particle size, apparent amylose content (AAC), crystallinity, gelatinisation and retrogradation behaviour, pasting properties, and gel texture. Cowpea starches exhibited higher AAC, gelatinisation temperatures, retrogradation enthalpy, and gel strength, indicating greater thermal stability and stronger gel network formation. In contrast, moth bean starches showed lower ACC, higher relative crystallinity, and greater gelatinisation enthalpy, reflecting more compact native crystalline structures, due to a higher amylopectin content. The lower AAC of moth beans resulted in limited retrogradation and softer gels. To evaluate the multivariate relationships among the starch samples, cluster analysis was performed, which grouped the samples according to botanical origin. This classification underscored the distinct structural and functional attributes differentiating cowpea and moth bean starches. These findings provide insight into cultivar-dependent starch behaviour. Cowpea starches may be suited for applications requiring thermal stability and a firm texture, such as noodle formulations and microwave foods, while moth bean starches offer potential for products with smooth textures and low retrogradation, such as in instant or ready-to-eat food products. Full article

Theoretical foundations are presented for the application of information–entropy methods from statistical physics to the determination of stellar evolutionary stages. A balance equation involving normalized conditional information and entropy is proposed. The conditional information is defined as the difference between the entropy of the phase space and the conditional probability entropy. A correspondence is demonstrated between theoretical predictions and observational data from stellar emission spectra with respect to their evolutionary classification. The proposed methodology is further applied to the analysis of complex FS CMa-type objects, which exhibit dusty and gaseous structures with components at different evolutionary stages. In this context, the conditional information derived from asymmetric spectral lines is shown to be consistent with the theoretical criteria for the evolutionary status of single, binary, and unclassified stars. Full article

This study presents the application of Mycelial_Net, a biologically inspired deep learning architecture, to the analysis and classification of mineral images in thin section under optical microscopy. The model, inspired by the adaptive connectivity of fungal mycelium networks, was trained on a test mineral image database to extract structural features and to classify various minerals. The performance of Mycelial_Net was evaluated in terms of accuracy, robustness, and adaptability, and compared against conventional convolutional neural networks. The results demonstrate that Mycelial_Net, properly integrated with Residual Networks (ResNets), offers superior analysis capabilities, interpretability, and resilience to noise and artifacts in petrographic images. This approach holds promise for advancing automated mineral identification and geological analysis through adaptive AI systems. Full article

To address prevalent challenges in field-based wheat pest recognition—namely, viewpoint perturbations, sample scarcity, and heterogeneous data distributions—a pest identification framework named CropCLR-Wheat is proposed, which integrates self-supervised contrastive learning with an attention-enhanced mechanism. By incorporating a viewpoint-invariant feature encoder and a diffusion-based feature filtering module, the model significantly enhances pest damage localization and feature consistency, enabling high-accuracy recognition under limited-sample conditions. In 5-shot classification tasks, CropCLR-Wheat achieves a precision of 89.4%, a recall of 87.1%, and an accuracy of 88.2%; these metrics further improve to 92.3%, 90.5%, and 91.2%, respectively, under the 10-shot setting. In the semantic segmentation of wheat pest damage regions, the model attains a mean intersection over union (mIoU) of 82.7%, with precision and recall reaching 85.2% and 82.4%, respectively, markedly outperforming advanced models such as SegFormer and Mask R-CNN. In robustness evaluation under viewpoint disturbances, a prediction consistency rate of 88.7%, a confidence variation of only 7.8%, and a prediction consistency score (PCS) of 0.914 are recorded, indicating strong stability and adaptability. Deployment results further demonstrate the framework’s practical viability: on the Jetson Nano device, an inference latency of 84 ms, a frame rate of 11.9 FPS, and an accuracy of 88.2% are achieved. These results confirm the efficiency of the proposed approach in edge computing environments. By balancing generalization performance with deployability, the proposed method provides robust support for intelligent agricultural terminal systems and holds substantial potential for wide-scale application. Full article

Image classification is central to computer vision, supporting applications from autonomous driving to medical imaging, yet state-of-the-art convolutional neural networks remain constrained by heavy floating-point operations (FLOPs) and parameter counts on edge devices. To address this accuracy–efficiency trade-off, we propose a unified lightweight framework built on a pruning-aware coordinate attention block (PACB). PACB integrates coordinate attention (CA) with L1-regularized channel pruning, enriching feature representation while enabling structured compression. Applied to MobileNetV3 and RepVGG, the framework achieves substantial efficiency gains. On GTSRB, MobileNetV3 parameters drop from 16.239 M to 9.871 M (–6.37 M) and FLOPs from 11.297 M to 8.552 M (–24.3%), with accuracy improving from 97.09% to 97.37%. For RepVGG, parameters fall from 7.683 M to 7.093 M (–0.59 M) and FLOPs from 31.264 M to 27.918 M (–3.35 M), with only ~0.51% average accuracy loss across CIFAR-10, Fashion-MNIST, and GTSRB. Complexity analysis further confirms PACB does not increase asymptotic order, since the additional CA operations contribute only lightweight lower-order terms. These results demonstrate that coupling CA with structured pruning yields a scalable accuracy–efficiency trade-off under hardware-agnostic metrics, making PACB a promising, deployment-ready solution for mobile and edge applications. Full article

This study evaluates the feasibility of using a lightweight, off-the-shelf sensing system for short-term stress detection during exergaming. Most existing studies in stress detection compare rest and task conditions, providing limited insight into continuous stress dynamics, and there is no agreement on optimal sensor configurations. To address these limitations, we investigated dynamic stress responses induced by a cognitive–motor task designed to simulate rehabilitation-like scenarios. Twenty-three participants completed the experiment, providing electrodermal activity (EDA), blood volume pulse (BVP), self-report, and in-game data. Features extracted from physiological signals were analyzed statistically, and shallow machine learning classifiers were applied to discriminate among stress levels. EDA-based features reliably differentiated stress conditions, while BVP features showed less consistent behavior. The classification achieved an overall accuracy of 0.70 across four stress levels, with most errors between adjacent levels. Correlations between EDA dynamics and perceived stress scores suggested individual variability possibly linked to chronic stress. These results demonstrate the feasibility of low-cost, unobtrusive stress monitoring in interactive environments, supporting future applications of dynamic stress detection in rehabilitation and personalized health technologies. Full article

This study presents a self-supervised learning framework for detecting frequency disturbances in power systems using high-resolution time series data. Employing data from the UK National Grid, we apply the Temporal Contrastive Self-Supervised Learning (TC-TSS) approach to learn task-agnostic embeddings from unlabelled 60-s rolling window segments of frequency measurements. The learned representations are then used to train four traditional classifiers, Logistic Regression (LR), Support Vector Machine (SVM), Multi-Layer Perceptron (MLP), and Random Forest (RF), for binary classification of frequency stability events. The proposed method is evaluated using over 15 million data points spanning six months of system operation data. Results show that classifiers trained on TC-TSS embeddings performed better than those using raw input features, particularly in detecting rare disturbance events. ROC-AUC scores for MLP and SVM models reach as high as 0.98, indicating excellent separability in the latent space. Visualisations using UMAP and t-SNE further demonstrate the clustering quality of TC-TSS features. This study highlights the effectiveness of contrastive representation learning in the energy domain, particularly under conditions of limited labelled data, and proves its suitability for integration into real-time smart grid applications. Full article

The increasing complexity of web-based attacks requires the development of more effective Web Application Firewall (WAF) systems. In this study, we extend previous work by evaluating and comparing the performance of seven machine learning models for multilabel classification of web traffic, using the ECML/PKDD 2007 dataset. This dataset contains eight classes: seven representing different types of attacks and one representing normal traffic. Building on prior experiments that analyzed Recurrent Neural Network (RNN), Gated Recurrent Unit (GRU), and Long Short-Term Memory (LSTM) models, we incorporate four additional models frequently cited in the related literature: Random Forest (RF), Support Vector Machine (SVM), Gradient Boosting (GB), and Feedforward Neural Networks (NN). Each model is trained and evaluated under consistent preprocessing and validation protocols. We analyze their performance using key metrics such as accuracy, precision, recall, F1-score, and training time. The results provide insights into the suitability of each method for WAF classification tasks, with implications for real-time intrusion detection systems and security automation. This study represents the first unified multilabel evaluation of classical and deep learning approaches on the ECML/PKDD 2007 dataset, offering guidance for practical WAF deployment. Full article

Circulation type classification (CTC) is an important method in atmospheric sciences, which reveals the relationship between atmospheric circulation and regional weather and climate. Accurate circulation classification helps to improve weather forecasting accuracy and supports climate change research. China has complex topography and significant spatiotemporal variability in its circulation patterns, making the study of circulation type classification in this region highly significant. This study aims to evaluate the applicability of several mainstream objective CTC methods in the China region. We applied methods including T-mode principal component analysis (PCT), Ward linkage, K-means, and Self-Organizing Maps (SOM) to classify the sea-level pressure daily mean fields from 1993 to 2023 in the study area, and compared the classification results in terms of internal metrics, continuity, seasonal variation, separability of related meteorological variables (e.g., temperature, precipitation), and stability to spatiotemporal resolution. The results show that each method has its advantages in different contexts, with the K-means method showing the best overall performance. Additionally, an optimized approach combining PCT and K-means is proposed. Full article

Periodontitis, a prevalent chronic infectious disease triggered by oral biofilm microbiota, results in progressive destruction of periodontal supporting tissues, and conventional treatments have limited therapeutic effects on it. Hydrogels, due to their excellent biocompatibility, three-dimensional extracellular matrix-like structure, and localized sustained-release properties, can provide support for cell attachment, promote cell proliferation and differentiation, and improve drug utilization efficiency, showing great promise for applications in treating periodontitis as well as promoting periodontal tissue regeneration. This article first introduces the limitations of current periodontitis treatments and the unique advantages of hydrogels in periodontitis treatment and periodontal tissue regeneration, and then provides an overview of the classifications of hydrogels, the active substances they can load, and the characteristics and functions of these active substances. Subsequently, the article introduces the latest advances in the application of several common natural polymer hydrogels in periodontal tissue regeneration. Finally, the article discusses the current limitations of hydrogels in terms of structure and properties, and proposes potential solutions and future development directions in periodontal tissue regeneration. Full article

A surge in environmental pollution compels society to utilize food processing wastes to produce valuable compounds. Enzymatic technology, specifically cellulase-mediated hydrolysis, provides an eco-friendly and effective approach for treating food processing leftovers. The main objective of this review is to explore the significant contributions of cellulase, both in industrial settings and from an environmental perspective. Therefore, this review covers all the aspects of cellulase structural identification, classification, and evolution to its profound applications. The review initially explores cellulases’ structural and functional characteristics based on the catalytic and cellulose-binding domains and discusses cellulases’ evolutionary origin. A thorough understanding of cellulase properties is essential for overcoming the challenges associated with its commercial production for various applications. In this regard, the optimization for cellulase production through several approaches, including rational design, direct evolution, genetic engineering, and fermentation technology, is also reviewed. In addition, it also underscores the significance of agro-industrial biorefineries, which provide scalable and sustainable solutions to meet future demands for food, chemicals, materials, and fuels. Finally, the last sections of the review solely highlight the potential applications of microbial cellulases in bioremediation. In summary, this review outlines the role of cellulase in efficient valorization aimed at producing multiple bioproducts and the enhancement of environmental remediation efforts. Full article

Background: Attention-deficit/hyperactivity disorder (ADHD) is a heterogeneous neurodevelopmental condition that currently relies on subjective clinical judgment for diagnosis, emphasizing the need for objective, clinically applicable tools. Methods: We applied machine learning techniques to parent reports, self-reports, and performance-based measures in a sample of 255 Taiwanese children and adolescents (108 ADHD and 147 controls; mean age = 11.85 years). Models were trained under a nested cross-validation framework to avoid performance overestimation. Results: Most models achieved high classification accuracy (AUCs ≈ 0.886–0.906), while convergent feature importance across models highlighted parent-rated social problems, executive dysfunction, and self-regulation traits as robust predictors. Additionally, ex-Gaussian parameters derived from reaction time distributions on the Continuous Performance Test (CPT) proved more informative than raw scores. Conclusions: These findings support the utility of integrating multi-informant ratings and task-based measures in interpretable ML models to enhance ADHD diagnosis in clinical practice. Full article