Search Results (25,709)

As the threat from malicious UAVs continues to intensify, accurate identification of individual UAVs has become a critical challenge in regulatory and security domains. Existing single-signal analysis methods suffer from limited recognition accuracy. To address this issue, this paper proposes a high-precision individual identification method for UAVs based on FFS-SPWVD and DIR-YOLOv11. The proposed method first employs a frame-by-frame search strategy combined with the smoothing pseudo-Wigner–Ville distribution (SPWVD) algorithm to obtain effective time–frequency feature representations of flight control signals. Building on this foundation, the YOLOv11n network is adopted as the baseline architecture. To enhance the extraction of time–frequency texture features from UAV signals in complex environments, a Multi-Branch Auxiliary Multi-Scale Fusion Network is incorporated into the neck network. Meanwhile, partial space–frequency selective convolutions are introduced into selected C3k2 modules to alleviate the increased computational burden caused by architectural modifications and to reduce the overall number of model parameters. Experimental results on the public DroneRFb-DIR dataset demonstrate that the proposed method effectively extracts flight control frames and performs high-resolution time–frequency analysis. In individual UAV identification tasks, the proposed approach achieves 96.17% accuracy, 97.82% mAP50, and 95.29% recall, outperforming YOLOv11, YOLOv12, and YOLOv13. This study demonstrates that the proposed method achieves both high accuracy and computational efficiency in individual UAV recognition, providing a practical technical solution for whitelist identification and group size estimation in application scenarios such as border patrol, traffic control, and large-scale events. Full article

Image deraining is a crucial preprocessing task for enhancing the robustness of high-level vision systems under adverse weather conditions. However, most of the existing methods are limited to a single RGB color space, and it is difficult to effectively separate high-frequency rain streaks from low-frequency backgrounds, resulting in color distortion and detail loss in the restored image. Therefore, a rain removal network that combines dual-color space and frequency domain priors is proposed. Specifically, the devised network employs a dual-branch Transformer architecture to extract color and structural features from the RGB and YCbCr color spaces, respectively. Meanwhile, a Hybrid Attention Feedforward Block (HAFB) is constructed. HAFB achieves feature enhancement and regional focus through a progressive perception selection mechanism and a multi-scale feature extraction architecture, thereby effectively separating rain streaks from the background. Furthermore, a Wavelet-Gated Cross-Attention module is designed, including a Wavelet-Enhanced Attention Block (WEAB) and a Dual Cross-Attention module (DCA). This design enhances the complementary fusion of structural information and color features through frequency-domain guidance and bidirectional semantic interaction. Finally, experimental results on multiple datasets (i.e., Rain100L, Rain100H, Rain800, Rain12, and SPA-Data) demonstrate that the proposed method outperforms other approaches. Full article

This study presents the results of an investigation into the carbothermic synthesis of silicon carbide (SiC) from microsilica and petroleum coke. The research combines thermodynamic modeling with experimental validation conducted in an ore-thermal furnace. Thermodynamic calculations were performed using the HSC Chemistry 10 software package to evaluate the influence of temperature and the SiO₂/C ratio on phase formation and the conditions of SiC synthesis. The results show that the synthesis process exhibits a strong dependence on temperature and is largely governed by the carbon balance of the charge. At an SiO₂/C ratio of 1, the system is carbon-rich, which promotes effective reduction of silicon dioxide. However, at elevated temperatures, these conditions intensify gas-phase reactions and lead to increased silicon losses. The most favorable conditions for silicon carbide formation were achieved at an SiO₂/C ratio of 1.5, which is close to the stoichiometric value. This conclusion is confirmed by the maximum degree of SiC recovery obtained under experimental conditions. In contrast, at an SiO₂/C ratio of 2, carbon deficiency results in incomplete reduction in SiO₂ and a lower yield of the target product. The phase composition of the synthesized samples was analyzed by X-ray diffraction, revealing β-SiC as the dominant crystalline phase. The morphology and structure of the materials were examined using scanning electron microscopy, which confirmed the formation of SiC particles and aggregates with characteristic features. A comparison between calculated and experimental results demonstrates that thermodynamic modeling adequately describes the main trends of the process and can be effectively applied to optimize SiC synthesis conditions during the processing of technogenic silica-containing waste. Full article

Migraine and epilepsy are common neurological disorders that share overlapping symptoms, such as visual disturbances and altered consciousness, making accurate diagnosis challenging. Although their underlying mechanisms differ, both conditions involve recurrent irregular brain activity, and traditional EEG-based diagnosis relies heavily on clinical interpretation, which may be subjective and insufficient for clear differentiation. To address this challenge, this study introduces an automated EEG classification framework combining Dual Tree Complex Wavelet Transform (DTCWT) for feature extraction with a Random Subspace Ensemble Classifier for multi-class discrimination. EEG data recorded under photic and nonphotic stimulation were analyzed to capture both temporal and frequency characteristics. DTCWT proved effective in modeling the non-stationary nature of EEG signals and extracting condition-specific features, while the ensemble classifier improved generalization by training multiple models on diverse feature subsets. The proposed system achieved an average accuracy of 99.50%, along with strong F-measure, AUC, and Kappa scores. Notably, although previous studies suggest heightened EEG activity in migraine patients during flash stimulation, findings here indicate that flash stimulation alone does not reliably distinguish migraine from epilepsy. Overall, this research highlights the promise of advanced signal processing and machine learning techniques in enhancing diagnostic precision for complex neurological disorders. Full article

Objectives: Acute obstructive pyelonephritis (AOP) is a urological emergency that combines bacterial infection with upper urinary tract obstruction. This retrospective study focuses on the microbial etiology and causes of obstruction, clinical manifestations, antibacterial therapy, drainage type, and outcomes in patients diagnosed with AOP at a tertiary urology center between 1 January 2020 and 30 December 2024. Methods: One hundred patients with a mean age of 61.30 years were included in this retrospective study, which examines demographic data, comorbidities, clinical features, pathogens involved, antimicrobial regimens, and hospital outcomes. Results: Urolithiasis was the most frequent cause of obstruction (62%), followed by ureteral stenosis (14%) and tumors (11%). AOPs were mainly produced by Escherichia coli (58%), followed by Klebsiella spp. (21%); 18% of all identified bacteria were ESBL-producing Gram-negative bacilli, and 29% were MDR bacteria. The most used IV antibiotics were fluoroquinolones (52%), followed by cephalosporins (19%) and carbapenems (18%). Carbapenems were administered to all patients with AOP caused by ESBL-producing pathogens and to 62% of those with MDR bacteria. The duration of antibiotic therapy was individualized based on clinical response. Switch to oral administration was made after 4.3 ± 1.5 days, and the antibiotic treatment lasted 10.8 ± 3.2 days. Conclusions: The results of the present study support integrating evidence-based guidelines with regional patterns of bacterial susceptibility to optimize therapeutic approaches and reduce severe outcomes in patients with AOP, most of whom have multiple comorbidities. Full article

Sentiment analysis of Arabic text, particularly on social media platforms, presents a formidable set of unique challenges that stem from the language’s complex morphology, its numerous dialectal variations, and the frequent and nuanced use of emojis to convey emotional context. This paper presents SiAraSent, a hybrid framework that integrates traditional text representations, emoji-aware features, and deep contextual embeddings based on Arabic transformers. Starting from a strong and fully interpretable baseline built on Term Frequency–Inverse Definition Frequency (TF–IDF)-weighted character and word N-grams combined with emoji embeddings, we progressively incorporate SinaTools for linguistically informed preprocessing and AraBERT for contextualized encodings. The framework is evaluated on a large-scale dataset of 58,751 Arabic tweets labeled for sentiment polarity. Our design works within four experimental configurations: (1) a baseline traditional machine learning architecture that employs TF-IDF, N-grams, and emoji features with an Support Vector Machine (SVM) classifier; (2) an Large-language Model (LLM) feature extraction approach that leverages deep contextual embeddings from the pre-trained AraBERT model; (3) a novel hybrid fusion model that concatenates traditional morphological features, AraBERT embeddings, and emoji-based features into a high-dimensional vector; and (4) a fully fine-tuned AraBERT model specifically adapted for the sentiment classification task. Our experiments demonstrate the remarkable efficacy of our proposed framework, with the fine-tuned AraBERT architecture achieving an accuracy of 93.45%, a significant 10.89% improvement over the best traditional baseline. Full article

This study is grounded in the macro-context of smart agriculture and global food security. Due to population growth and climate change, precise and efficient monitoring of crop distribution and growth is vital for stable production and optimal resource use. Remote sensing combined with deep learning enables multi-scale agricultural monitoring from field identification to disease diagnosis. However, current models face three deployment bottlenecks: high complexity hinders operation on edge devices; scarce labeled data causes overfitting in small-sample cases; and there is insufficient generalization across regions, crops, and imaging conditions. These issues limit the large-scale adoption of intelligent agricultural technologies. To tackle them, this paper proposes a lightweight crop recognition model, MAF-RecNet. It aims to achieve high accuracy, efficiency, and strong generalization with limited data through structural optimization and attention mechanism fusion, offering a viable path for deployable intelligent monitoring systems. Built on a U-Net with a pre-trained ResNet18 backbone, MAF-RecNet integrates multiple attention mechanisms (Coordinate, External, Pyramid Split, and Efficient Channel Attention) into a hybrid attention module, improving multi-scale feature discrimination. On the Southern Hebei Farmland dataset, it achieves 87.57% mIoU and 95.42% mAP, outperforming models like SegNeXt and FastSAM, while maintaining a balance of efficiency (15.25 M parameters, 21.81 GFLOPs). The model also shows strong cross-task generalization, with mIoU scores of 80.56% (Wheat Health Status Dataset in Southern Hebei), 90.20% (Global Wheat Health Dataset), and 84.07% (Corn Health Status Dataset). Ablation studies confirm the contribution of the attention-enhanced skip connections and decoder. This study not only provides an efficient and lightweight solution for few-shot agricultural image recognition but also offers valuable insights into the design of generalizable models for complex farmland environments. It contributes to promoting the scalable and practical application of artificial intelligence technologies in precision agriculture. Full article

Self-supervised contrastive learning has demonstrated remarkable effectiveness in learning visual representations without labeled data, yet its application to 3D local feature learning from point clouds remains underexplored. Existing methods predominantly focus on complete object shapes, neglecting the critical challenge of recognizing partial observations commonly encountered in real-world 3D perception. We propose a momentum contrastive learning framework specifically designed to learn discriminative local features from randomly sampled point cloud regions. By adapting the MoCo architecture with PointNet++ as the feature backbone, our method treats local parts of point cloud as fundamental contrastive learning units, combined with carefully designed augmentation strategies including random dropout and translation. Experiments on ShapeNet demonstrate that our approach effectively learns transferable local features and the empirical observation that approximately 30% object local part represents a practical threshold for effective learning when simulating real-world occlusion scenarios, and achieves comparable downstream classification accuracy while reducing training time by 16%. Full article

Flood events driven by climate variability and change pose significant risks for socio-economic activities in the Awash Basin, necessitating advanced forecasting tools. This study benchmarks five deep learning (DL) architectures, Convolutional Neural Network (CNN), Long Short-Term Memory (LSTM), Gated Recurrent Unit (GRU), Bidirectional LSTM (BiLSTM), and a Hybrid CNN–LSTM, for daily discharge forecasting for the Hombole catchment in the Upper Awash Basin (UAB) using 40 years of hydrometeorological observations (1981–2020). Rainfall, lagged discharge, and seasonal indicators were used as predictors. Model performance was evaluated against two baseline approaches, a conceptual HBV rainfall–runoff model as well as a climatology, using standard and hydrological metrics. Of the two baselines (climatology and HBV), the climatology showed limited skill with large bias and negative NSE, whereas the HBV model achieved moderate skill (NSE = 0.64 and KGE = 0.82). In contrast, all DL models substantially improved predictive performance, achieving test NSE values above 0.83 and low overall bias. Among them, the Hybrid CNN–LSTM provided the most balanced performance, combining local temporal feature extraction with long-term memory and yielding stable efficiency (NSE ≈ 0.84, KGE ≈ 0.90, and PBIAS ≈ −2%) across flow regimes. The LSTM and GRU models performed comparably, offering strong temporal learning and robust daily predictions, while BiLSTM improved flood timing through bidirectional sequence modeling. The CNN captured short-term variability effectively but showed weaker representation of extreme peaks. Analysis of peak-flow metrics revealed systematic underestimation of extreme discharge magnitudes across all models. However, a post-processing flow-regime classification based on discharge quantiles demonstrated high extreme-event detection skill, with deep learning models exceeding 89% accuracy in identifying extreme-flow occurrences on the test set. These findings indicate that, while magnitude errors remain for rare floods, DL models reliably discriminate flood regimes relevant for early warning. Overall, the results show that deep learning models provide clear improvements over climatology and conceptual baselines for daily streamflow forecasting in the UAB, while highlighting remaining challenges in peak-flow magnitude prediction. The study indicates promising results for the integration of deep learning methods into flood early-warning workflows; however, these results could be further improved by adopting a probabilistic forecasting framework that accounts for model uncertainty. Full article

Semi-supervised joint classification of Hyperspectral Images (HSIs) and LiDAR-derived Digital Surface Models (DSMs) remains challenging due to scarcity of labeled pixels, strong intra-class variability, and the heterogeneous nature of spectral and elevation features. In this work, we propose a Hybrid Mamba–Graph Fusion Network (HMGF-Net) with Multi-Stage Pseudo-Label Refinement (MS-PLR) for semi-supervised hyperspectral–LiDAR classification. The framework employs a spectral–spatial HSI backbone combining 3D–2D convolutions, a compact LiDAR CNN encoder, Mamba-style state-space sequence blocks for long-range spectral and cross-modal dependency modeling, and a graph fusion module that propagates information over a heterogeneous pixel graph. Semi-supervised learning is realized via a three-stage pseudolabeling pipeline that progressively filters, smooths, and re-weights pseudolabels based on prediction confidence, spatial–spectral consistency, and graph neighborhood agreement. We validate HMGF-Net on three benchmark hyperspectral–LiDAR datasets. Compared with a set of eight state-of-the-art (SOTA) baselines, including 3D-CNNs, SSRN, HybridSN, transformer-based models such as SpectralFormer, multimodal CNN–GCN fusion networks, and recent semi-supervised methods, the proposed approach delivers consistent gains in overall accuracy, average accuracy, and Cohen’s kappa, especially in low-label regimes (10% labeled pixels). The results highlight that the synergy between sequence modeling and graph reasoning in combination with carefully designed pseudolabel refinement is essential to maximizing the benefit of abundant unlabeled samples in multimodal remote sensing scenarios. Full article

Background/Objectives: Hepatocellular carcinoma (HCC) shows marked molecular and histopathological heterogeneity. Among the alterations most strongly associated with clinical outcome are mutations in TP53 and CTNNB1, as well as the presence of microvascular invasion (MVI). Although these factors are well established as prognostic indicators, how their molecular effects relate to tumor morphology remains unclear. In this work, we studied transcriptomic changes linked to TP53 and CTNNB1 mutational status and to MVI, and examined whether these changes are reflected in routine histology. Methods: RNA sequencing data from HCC samples annotated for mutations and vascular invasion were analyzed using differential expression analysis combined with machine learning-based feature selection to characterize the underlying transcriptional programs. In parallel, we trained a weakly supervised multitask deep learning model on hematoxylin and eosin-stained whole-slide images using slide-level labels only, without spatial annotations, to assess whether these features could be inferred from global histological patterns. Results: Distinct gene expression profiles were observed for TP53-mutated, CTNNB1-mutated, and MVI-positive tumors, involving pathways related to proliferation, metabolism, and invasion. Image-based models were able to capture morphological patterns associated with these states, achieving above-random discrimination with variable performance across tasks. Conclusions: Taken together, these results support the existence of coherent biological programs underlying key risk determinants in HCC and indicate that their phenotypic effects are, at least in part, detectable in routine histopathology. This provides a rationale for integrative morpho-molecular approaches to risk assessment in HCC. Full article

DNA sequence classification is a fundamental problem in bioinformatics, playing an indispensable role in gene annotation and disease prediction. Whereas most deep learning models, such as CNNs, BiLSTM networks, and GRUs, have been found individually optimal, each of these methods excels in modeling a specific aspect of sequence data: local motifs, long-range dependencies, and efficient temporal modeling of the sequences. Here, we present and evaluate an ensemble model that integrates CNN, BiLSTM, and GRU architectures via a majority voting combination scheme so that their complementary strengths can be harnessed. We trained and evaluated each standalone and the integrated model on a DNA dataset comprising 4380 sequences falling under five functional categories. The ensemble model achieved a classification accuracy of 90.6% with precision, recall, and F1 score equal to 0.91, thereby outperforming the state-of-the-art techniques by large margins. Although previous studies have tried analyzing each Deep Learning method individually for DNA classification tasks, none have attempted a systematic combination of CNN, BiLSTM, and GRU based on their ability to extract features simultaneously. The current research aims at presenting a novel method that combines these architectures based on a Majority Voting strategy and proves how their combination is better at extracting local patterns and long dependency information when compared individually. In particular, the proposed ensemble model smoothed the high recall of BiLSTM with the high precision of CNN, leading to more robust and reliable classification. The experiments involved a publicly available DNA sequence data set of 4380 sequences distributed over 5 classes. Our results emphasized the prospect of hybrid ensemble deep learning as a strong approach for complex genomic data analysis, opening ways toward more accurate and interpretable bioinformatics research. Full article

Robotic grippers play a crucial role in pick-and-place tasks, as their performance directly affects the robot’s operational efficiency, stability, and safety. In industrial applications, such as coal gangue sorting, the target objects have irregular shapes and sharp surfaces, which pose challenges to the gripper’s grasping ability. To solve these problems, an adaptive under-actuated gripper based on rope control is designed. The gripper is simple to control and combines the excellent features of both rigid and flexible grippers. To analyze the characteristics of the gripper, both mathematical analysis and holding force experiments are conducted. The results show that the gripper can generate a greater holding force when grasping larger objects with a constant input air pressure. Furthermore, irregularly shaped testing objects, including coal lumps and ores, are selected to conduct grasping experiments. The gripper achieves a 100% grasping success rate with a load of up to four times the object’s weight suspended beneath it and shows the ability to reliably grasp irregularly shaped objects in high-speed pick-and-place tasks with a payload of four times the object’s weight. Meanwhile, the gripper has a passive anti-collision ability due to the special outer contour of the distal finger when subjected to unexpected, sudden force. Full article

Pansharpening is a fundamental image fusion technique used to enhance the spatial resolution of remote sensing imagery; however, it inevitably introduces spectral distortions that compromise the reliability of downstream analyses. Existing no-reference (NR) quality assessment methods often fail to exclusively isolate these spectral errors from spatial artifacts or lack sensitivity to specific radiometric inconsistencies. To address this gap, this paper proposes a novel No-Reference Multivariate Gaussian-based Spectral Distortion Index (MVG-SDI) specifically designed for pansharpened images. The methodology extracts a hybrid feature set, combining First Digit Distribution (FDD) features derived from Benford’s Law in the hyperspherical color space (HCS) and Color Moment (CM) features. These features are then used to fit Multivariate Gaussian (MVG) models to both the original multispectral and fused images, with spectral distortion quantified via the Mahalanobis distance between their statistical parameters. Experiments on the NBU dataset showed that the MVG-SDI correlates more strongly with standard full-reference benchmarks (such as SAM and CC) than existing NR methods like QNR. Tests with simulated distortions confirmed that the proposed index remains stable and accurate even when facing specific spectral degradations like hue shifts or saturation changes. Full article

Malicious Tor traffic data contains deep domain-specific knowledge, which makes labeling challenging, and the lack of labeled data degrades the accuracy of learning-based detectors. Real-world deployments also exhibit severe class imbalance, where malicious traffic constitutes a small minority of network flows, which further reduces detection performance. In addition, Tor’s fixed 512-byte cell architecture removes packet-size diversity that many encrypted-traffic methods rely on, making feature extraction difficult. This paper proposes an efficient three-stage framework, MAESTRO v1.0, for malicious Tor traffic detection. In Stage 1, MAESTRO extracts multi-scale behavioral signatures by fusing temporal, positional, and directional embeddings at cell, direction, and flow granularities to mitigate feature homogeneity; it then compresses these representations with an autoencoder into compact latent features. In Stage 2, MAESTRO introduces an ensemble-based quality quantification method that combines five complementary anomaly detection models to produce robust discriminability scores for adaptive sample weighting, helping the classifier to emphasize high-quality samples. MAESTRO also trains three specialized GANs per minority class and applies strict five-model ensemble validation to synthesize diverse high-fidelity samples, addressing extreme class imbalance. We evaluate MAESTRO under systematic imbalance settings, ranging from the natural distribution to an extreme 1% malicious ratio. On the CCS’22 Tor malware dataset, MAESTRO achieves 92.38% accuracy, 64.79% recall, and 73.70% F1-score under the natural distribution, improving F1-score by up to 15.53% compared with state-of-the-art baselines. Under the 1% malicious setting, MAESTRO maintains 21.1% recall, which is 14.1 percentage points higher than the best baseline, while conventional methods drop below 10%. Full article