Search Results (219)

Garlic, as an important economic crop, plays a crucial role in the global agricultural production system. Accurate identification of garlic cultivation areas is of great significance for agricultural resource allocation and industrial development. Traditional crop identification methods face challenges of insufficient accuracy and spatial fragmentation in complex agricultural landscapes, limiting their effectiveness in precision agriculture applications. This study, focusing on Kaifeng City, Henan Province, developed an integrated technical framework for garlic identification that combines deep learning edge detection, multi-source feature optimization, and spatial constraint optimization. First, edge detection training samples were constructed using high-resolution Jilin-1 satellite data, and the DexiNed deep learning network was employed to achieve precise extraction of agricultural field boundaries. Second, Sentinel-1 SAR backscatter features, Sentinel-2 multispectral bands, and vegetation indices were integrated to construct a multi-dimensional feature space containing 28 candidate variables, with optimal feature subsets selected through random forest importance analysis combined with recursive feature elimination techniques. Finally, field boundaries were introduced as spatial constraints to optimize pixel-level classification results through majority voting, generating field-scale crop identification products. The results demonstrate that feature optimization improved overall accuracy from 0.91 to 0.93 and the Kappa coefficient from 0.8654 to 0.8857 by selecting 13 optimal features from 28 candidates. The DexiNed network achieved an F1-score of 94.16% for field boundary extraction. Spatial optimization using field constraints effectively eliminated salt-and-pepper noise, with successful validation in Kaifeng’s garlic. Full article

Efficient and explainable vehicle damage inspection is essential due to the increasing complexity and volume of vehicular incidents. Traditional manual inspection approaches are not time-effective, prone to human error, and lead to inefficiencies in insurance claims and repair workflows. Existing deep learning methods, such as CNNs, often struggle with generalization, require large annotated datasets, and lack interpretability. This study presents a robust and interpretable deep learning framework for vehicle damage classification, integrating Vision Transformers (ViTs) and ensemble detection strategies. The proposed architecture employs a RetinaNet backbone with a ViT-enhanced detection head, implemented in PyTorch using the Detectron2 object detection technique. It is pretrained on COCO weights and fine-tuned through focal loss and aggressive augmentation techniques to improve generalization under real-world damage variability. The proposed system applies the Weighted Box Fusion (WBF) ensemble strategy to refine detection outputs from multiple models, offering improved spatial precision. To ensure interpretability and transparency, we adopt numerous explainability techniques—Grad-CAM, Grad-CAM++, and SHAP—offering semantic and visual insights into model decisions. A custom vehicle damage dataset with 4500 images has been built, consisting of approximately 60% curated images collected through targeted web scraping and crawling covering various damage types (such as bumper dents, panel scratches, and frontal impacts), along with 40% COCO dataset images to support model generalization. Comparative evaluations show that Hybrid ViT-RetinaNet achieves superior performance with an F1-score of 84.6%, mAP of 87.2%, and 22 FPS inference speed. In an ablation analysis, WBF, augmentation, transfer learning, and focal loss significantly improve performance, with focal loss increasing F1 by 6.3% for underrepresented classes and COCO pretraining boosting mAP by 8.7%. Additional architectural comparisons demonstrate that our full hybrid configuration not only maintains competitive accuracy but also achieves up to 150 FPS, making it well suited for real-time use cases. Robustness tests under challenging conditions, including real-world visual disturbances (smoke, fire, motion blur, varying lighting, and occlusions) and artificial noise (Gaussian; salt-and-pepper), confirm the model’s generalization ability. This work contributes a scalable, explainable, and high-performance solution for real-world vehicle damage diagnostics. Full article

Secret image sharing (SIS) is an image protection technique based on cryptography. However, traditional SIS schemes have limited noise resistance, making it difficult to ensure reconstructed image quality. To address this issue, this paper proposes a robust SIS scheme based on QR codes, which enables the efficient and lossless reconstruction of the secret image without pixel expansion. Moreover, the proposed scheme maintains high reconstruction quality under noisy conditions. In the sharing phase, the scheme compresses the length of shares by optimizing polynomial computation and improving the pixel allocation strategy. Reed–Solomon coding is then incorporated to enhance the anti-noise capability during the sharing process, while achieving meaningful secret sharing using QR codes as carriers. In the reconstruction phase, the scheme further improves the quality of the reconstructed secret image by combining image inpainting algorithms with the error-correction capability of Reed–Solomon codes. The experimental results show that the scheme can achieve lossless reconstruction when the salt-and-pepper noise density is less than $d\le 0.02$, and still maintains high-quality reconstruction when $d\le 0.13$. Compared with the existing schemes, the proposed method significantly improves noise robustness without pixel expansion, while preserving the visual meaning of the QR code carrier, and achieves a secret sharing strategy that combines robustness and practicality. Full article

Traditional median filtering with a fixed window easily leads to edge blurring and adaptive median filtering requires manual presetting of the maximum window parameter and has insufficient retention of details when dealing with high-density salt-and-pepper noise. Aiming at these problems, this paper proposes a hybrid decision-making adaptive median filtering algorithm with dual-window detection in collaboration with particle swarm optimization (PSO). The algorithm quickly locates suspected noise points through a 3 × 3 small window and enhances noise identification accuracy by using a PSO dynamically optimized 5–35-pixel large window. Meanwhile, a hybrid decision-making mechanism based on local statistical properties was introduced to dynamically select median filtering, weighted average based on spatial distance, or pixel preservation strategy to balance noise suppression and detail preservation, and the PSO algorithm was used to automatically find the optimal parameters of the large window’s size to avoid the manual parameter-tuning process. Experiments were conducted on standard grayscale and color images and compared with four traditional methods and two more advanced methods. The experiments showed that the algorithm improved the peak signal-to-noise ratio (PSNR) value by 2–4 dB and the structural similarity index measure (SSIM) metric by 0.05–0.2 under high salt-and-pepper noise density compared with the traditional methods, which effectively improved the contradiction between noise suppression and detail retention in traditional filtering algorithms and provided a highly efficient and intelligent solution for image denoising in high-noise scenarios. Full article

Hyperspectral classification of wetland environments remains challenging due to high spectral similarity, class imbalance, and blurred boundaries. To address these issues, we propose a novel Multi-Branch Channel-Gated Swin Transformer network (MBCG-SwinNet). In contrast to previous CNN-based designs, our model introduces a Swin Transformer spectral branch to enhance global contextual modeling, enabling improved spectral discrimination. To effectively fuse spatial and spectral features, we design a residual feature interaction chain comprising a Residual Spatial Fusion (RSF) module, a channel-wise gating mechanism, and a multi-scale feature fusion (MFF) module, which together enhance spatial adaptivity and feature integration. Additionally, a DenseCRF-based post-processing step is employed to refine classification boundaries and suppress salt-and-pepper noise. Experimental results on three UAV-based hyperspectral wetland datasets from the Yellow River Delta (Shandong, China)—NC12, NC13, and NC16—demonstrate that MBCG-SwinNet achieves superior classification performance, with overall accuracies of 97.62%, 82.37%, and 97.32%, respectively—surpassing state-of-the-art methods. The proposed architecture offers a robust and scalable solution for hyperspectral image classification in complex ecological settings. Full article

Objectives: This study introduces an automated classification system for noisy kidney ultrasound images using an ensemble of deep neural networks (DNNs) with transfer learning. Methods: The method was tested using a dataset with two categories: normal kidney images and kidney images with stones. The dataset contains 1821 normal kidney images and 2592 kidney images with stones. Noisy images involve various types of noises, including salt and pepper noise, speckle noise, Poisson noise, and Gaussian noise. The ensemble-based method is benchmarked with state-of-the-art techniques and evaluated on ultrasound images with varying quality and noise levels. Results: Our proposed method demonstrated a maximum classification accuracy of 99.43% on high-quality images (the original dataset images) and 99.21% on the dataset images with added noise. Conclusions: The experimental results confirm that the ensemble of DNNs accurately classifies most images, achieving a high classification performance compared to conventional and individual DNN-based methods. Additionally, our method outperforms the highest-achieving method by more than 1% in accuracy. Furthermore, our analysis using Gradient-weighted Class Activation Mapping indicated that our proposed deep learning model is capable of prediction using clinically relevant features. Full article

As an auxin-responsive gene, Gretchen Hagen 3 (GH3) maintains hormonal homeostasis by conjugating excess auxin with amino acids in plant stress-related signaling pathways. GH3 genes have been characterized in many plant species, but the characteristics of pepper (Capsicum annuum L.) GH3 (CaGH3) gene family members in response to multiple stimulants are largely unknown. In this study, we systematically identified the CaGH3 gene family at the genome level and identified eight members on four chromosomes in pepper. CaGH3s were divided into two groups (I and III) and shared conserved motifs, domains, and gene structures. Moreover, CaGH3s had close evolutionary relationships with tomato (Solanum lycopersicum L.), and the promoters of most CaGH3 genes contained hormone and abiotic stress response elements. A protein interaction prediction analysis demonstrated that the CaGH3-3/3-6/3-7/3-8 proteins were possibly core members of the CaGH3 family interaction. In addition, qRT-PCR results showed that CaGH3 genes were differentially expressed in pepper tissues and could be induced by phytohormones (IAA, ABA, and MeJA) and abiotic stresses (salt, low temperature, and drought) with different patterns. In addition, CaGH3-5 and CaGH3-7 were cloned, and the sequences showed a high degree of conservation. Moreover, the results of subcellular localization indicated that they were located in the membrane and chloroplast. Notably, after overexpressing CaGH3-7 in tomato, RNA-seq was performed on wild-type and transgenic lines, and the differentially expressed genes were mainly enriched in response to external stimuli. This study not only lays the foundation for a comprehensive understanding of the function of the CaGH3 gene family during plant growth and stress responses but also provides potential genetic resources for pepper resistance breeding. 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

AT-hook motif nuclear-localized (AHL) genes play critical roles in chromatin remodeling and gene transcription regulation, profoundly influencing plant growth, development, and stress responses. While AHL genes have been extensively characterized in multiple plant species, their biological functions in pepper (Capsicum annuum L.) remain largely uncharacterized. In this study, we identified 45 CaAHL genes in the pepper genome through bioinformatics approaches. Comprehensive analyses were conducted to examine their chromosomal distribution, phylogenetic relationships, and the structural and functional features of their encoded proteins. Phylogenetic clustering classified the CaAHL proteins into six distinct subgroups. Transcriptome profiling revealed widespread expression of CaAHL genes across diverse tissues—including roots, stems, leaves, flowers, seeds, pericarp, placenta, and fruits—at various developmental stages. Quantitative real-time PCR further demonstrated that CaAHL1, CaAHL33, and CaAHL23 exhibited consistently high expression throughout flower bud development, whereas CaAHL36 showed preferential upregulation at early bud development stages. Expression profiling under hormone treatments and abiotic stresses indicated that CaAHL36 and CaAHL23 are auxin-inducible but are repressed by ABA, cold, heat, salt, and drought stress. Subcellular localization assays in Nicotiana benthamiana leaf epidermal cells showed that both CaAHL36 and CaAHL23 were predominantly localized in the nucleus, with faint expression also detected in the cytoplasm. Collectively, this study provides foundational insights into the CaAHL gene family, laying the groundwork for future functional investigations of these genes in pepper. Full article

Autonomous vehicles (AVs) rely on a heterogeneous sensor suite of RGB cameras, LiDAR, GPS/IMU, and emerging event-based dynamic vision sensors (DVS) to perceive and navigate complex environments. However, these sensors can be deceived by realistic cyberattacks, undermining safety. In this work, we systematically implement seven attack vectors in the CARLA simulator—salt and pepper noise, event flooding, depth map tampering, LiDAR phantom injection, GPS spoofing, denial of service, and steering bias control—and measure their impact on a state-of-the-art end-to-end driving agent. We then equip each sensor with tailored defenses (e.g., adaptive median filtering for RGB and spatial clustering for DVS) and integrate a unsupervised anomaly detector (EfficientAD from anomalib) trained exclusively on benign data. Our detector achieves clear separation between normal and attacked conditions (mean RGB anomaly scores of 0.00 vs. 0.38; DVS: 0.61 vs. 0.76), yielding over 95% detection accuracy with fewer than 5% false positives. Defense evaluations reveal that GPS spoofing is fully mitigated, whereas RGB- and depth-based attacks still induce 30–45% trajectory drift despite filtering. Notably, our research-focused evaluation of DVS sensors suggests potential intrinsic resilience advantages in high-dynamic-range scenarios, though their asynchronous output necessitates carefully tuned thresholds. These findings underscore the critical role of multi-modal anomaly detection and demonstrate that DVS sensors exhibit greater intrinsic resilience in high-dynamic-range scenarios, suggesting their potential to enhance AV cybersecurity when integrated with conventional sensors. Full article

Background: Casein kinase I-like (CKL) protein is a member of the serine/threonine kinase CKI family and plays a pivotal regulatory role in various eukaryotic cellular processes, including stress responses. Objectives: This study aims to systematically identify the CKL gene family in the tomato genome and investigate its responsiveness to abiotic stress. Methods: Members of SlCKL were identified through genome-wide bioinformatics analysis, and their physicochemical properties, chromosomal localization, gene structure, conserved domains, phylogenetic relationships, cis-acting elements, cross-species collinearity, and tissue expression profiles were comprehensively analyzed. The expression patterns of SlCKL genes under abiotic stress were validated using real-time quantitative PCR. Results: A total of 16 SlCKL genes were identified and classified into three subfamilies (I–III), which are unevenly distributed across nine chromosomes, predominantly clustered at the ends. The gene structure, motifs, and functional domains exhibit high conservation. Collinearity analysis revealed stronger synteny between tomato and Arabidopsis thaliana or pepper compared to rice, maize, or tobacco, suggesting a common ancestral origin. The tissue expression profile indicates that SlCKLs are preferentially transcribed in roots. Promoter analysis and qRT-PCR validation demonstrated differential responses of SlCKLs to various abiotic stresses, such as drought, salt, heat, cold, and ABA treatment. Conclusions: This study represents the first systematic identification of the tomato SlCKL gene family, elucidating its evolutionary relationships, structural characteristics, tissue-specific expression patterns, and differential responsiveness to abiotic stress, thereby providing a critical foundation for further investigation into the molecular mechanisms underlying CKL-mediated abiotic stress adaptation in tomatoes. Full article

Titanium dioxide nanoparticles (TiO₂-NPs) were synthesized using the molten salt method and systematically characterized. TiO₂-NPs were evaluated for their capacity to promote the growth of Capsicum annuum cultivars together with the plant growth-promoting microorganisms (PGPMs) Bacillus thuringiensis (Bt) and Trichoderma harzianum (Th). The variables analyzed included physiological parameters and antioxidant responses. The capacity of TiO₂-NPs to scavenge free radicals was also investigated, along with their biocompatibility, using Artemia salina as an in vivo model. The results demonstrated that TiO₂-NPs exhibited a nanocuboid-type morphology, negative surface charge, and small surface area. It was noted that TiO₂-NPs enhanced the CFU and spore production of Bt (1.56–2.92 × 10⁸ CFU/mL) and Th (2.50–3.90 × 10⁸ spores/mL), respectively. It was observed that TiO₂-NPs could scavenge DPPH, ABTS, and H₂O₂ radicals (IC₅₀ 48.66–109.94 μg/mL), while not compromising the viability of A. salina at 50–300 μg/mL. TiO₂-NPs were determined to enhance the root length and fresh and dry weights of chili peppers. Similarly, TiO₂-NPs in synergy with Bt and Th increased the activity of β-1,3-Glucanase (2.45 nkat/g FW) and peroxidase (69.90 UA/g FW) enzyme activity, and increased the TPC (29.50 GA/g FW). The synergy of TiO₂-NPs with the PGPMs consortium also upregulated the total chlorophyll content: 210.8 ± 11.4 mg/mg FW. The evidence from this study unveils the beneficial application of TiO₂-NPs with Bt and Th as an efficient approach to promote the physiology and antioxidant responses of chili peppers. Full article

Noises on the field can affect the electromechanical system characteristics in the bearing fault diagnostic process. This paper presents a deep learning-based fault-diagnosis model DRSN–GCE (Deep Relative Shrinkage Network with Gated Convolutions and Enhancements), which is designed to deal with noise and improve noise resistance. In the first step, the data are preprocessed by adding different noises with different ratios of signal to noise and different frequencies to the vibration signals. This simulates the field noise environments. The continuous wavelet transformation (CWT), which converts the time-series signal from one dimension to a time-frequency two-dimensional image, provides rich data input for the deep learning model. Secondly, a convolutional gated layer is added to the deep residual network (DRSN), which suppresses the noise interference. The residual connection structure has also been improved in order to improve the transfer of features. In complex signals, the Gated Convolutional Shrinkage Module is used to improve feature extraction and suppress noise. The experiments on the Case Western Reserve University bearing dataset show that the DRSN–GCE exhibits high diagnostic accuracy and strong noise immunity in various noise environments such as Gauss, Laplace, Salt-and-Pepper, and Poisson. DRSN–GCE is superior to other deep learning models in terms of noise suppression, fault detection accuracy, and rolling bearing fault diagnoses in noisy environments. Full article

Plant cuticular wax serves as a critical component for defense against biotic and abiotic stresses, with its biosynthetic pathway regulated by the ECERIFERUM (CER) gene family. This study presents the first genome-wide identification of 79 CER genes (CalCERs) in pepper (Capsicum annuum L.), which are distributed across all 12 chromosomes. Phylogenetic analysis classified CalCERs into five clades, with clade-specific conservation of exon–intron architectures and protein motifs. Promoter cis-element analysis revealed enrichment of light-responsive elements, abscisic acid (ABA), jasmonic acid (JA), and stress-responsive regulatory motifs, indicating multi-pathway regulation. Transcriptomic data highlighted tissue-specific expression patterns, such as the root-predominant express gene CalCER1-2 and the flower-specific express gene CalCER3-1. Under abiotic stresses (drought, salt, heat, and cold), CalCER4-2 and CalCER6-6 responded rapidly, while most genes showed delayed differential expression. Under biotic stress, CalCER3-1 and CalCER5-3 were upregulated, whereas CalCER2-2 exhibited pathogen-specific suppression, suggesting roles in modulating wax-mediated pathogen resistance. Hormone treatments revealed dynamic responses: CalCER2-2 was persistently ABA-inducible, while CalCER3-1 specifically responded to JA. This study underscores evolutionary conservation and species-specific expansion of the pepper CER family, linking their expression to wax biosynthesis and stress adaptation. These insights provide a foundation for enhancing stress resilience in crops. Future work should employ gene editing and metabolomics to validate functional mechanisms and optimize breeding strategies. Full article

Random noise degrades the quality and reduces the interpretability of Ground Penetrating Radar (GPR) data. The Block Matching Three Dimension (BM3D) algorithm is effective at suppressing Gaussian noise, but ineffective at handling salt-and-pepper noise. On the other hand, the Improved Adaptive Median (IAM) filter is suitable for eliminating salt-and-pepper noise, but performs poorly against Gaussian noise. In this paper, we introduce and implement JBI, a joint denoising algorithm that integrates both BM3D and improved adaptive median filtering, exploiting the advantages of both algorithms to effectively remove both Gaussian and salt-and-pepper noise from GPR data. Applying the proposed joint filter to both synthetic and real field GPR data, infested with various proportions of different noise types, shows that the proposed joint denoising algorithm yields significantly better results than these two filters when used separately, and better than other commonly used denoising filters. Full article