Search Results (4,795)

The identification of scenes poses a notable challenge within the realm of image processing. Unlike object recognition, which typically involves relatively consistent forms, scene images exhibit a broader spectrum of variability. This research introduces an approach that combines image and text data to improve scene recognition performance. A model for tagging images is employed to extract textual descriptions of objects within scene images, providing insights into the components present. Subsequently, a pre-trained encoder converts the text into a feature set that complements the visual information derived from the scene images. These features offer a comprehensive understanding of the scene’s content, and a dynamic integration network is designed to manage and prioritize information from both text and image data. The proposed framework can effectively identify crucial elements by adjusting its focus on either text or image features depending on the scene’s context. Consequently, the framework enhances scene recognition accuracy and provides a more holistic understanding of scene composition. By leveraging image tagging, this study improves the image model’s ability to analyze and interpret intricate scene elements. Furthermore, incorporating dynamic integration increases the accuracy and functionality of the scene recognition system. Full article

Traffic flow prediction is a prominent research area in intelligent transportation systems, significantly contributing to urban traffic management and control. Existing methods or models for traffic flow prediction predominantly rely on a fixed-graph structure to capture spatial correlations within a road network. However, the fixed-graph structure can restrict the representation of spatial information due to varying conditions such as time and road changes. Drawing inspiration from the attention mechanism, a new prediction model based on the mixed-graph neural network is proposed to dynamically capture the spatial traffic flow correlations. This model uses graph convolution and attention networks to adapt to complex and changeable traffic and other conditions by learning the static and dynamic spatial traffic flow characteristics, respectively. Then, their outputs are fused by the gating mechanism to learn the spatial traffic flow correlations. The Transformer encoder layer is subsequently employed to model the learned spatial characteristics and capture the temporal traffic flow correlations. Evaluated on five real traffic flow datasets, the proposed model outperforms the state-of-the-art models in prediction accuracy. Furthermore, ablation experiments demonstrate the strong performance of the proposed model in long-term traffic flow prediction. Full article

Traditional maritime target element resolution, relying on manual experience and uniform sampling, lacks accuracy and efficiency in non-uniform sampling, missing data, and noisy scenarios. While large language models (LLMs) offer a solution, their general knowledge gaps with maritime needs limit direct application. This paper proposes a fine-tuned LLM-based adaptive optimization method for non-uniform sampling maritime target element resolution, with three key novelties: first, selecting Doubao-Seed-1.6 as the base model and conducting targeted preprocessing on maritime multi-source data to address domain adaptation gaps; second, innovating a “Prefix tuning + LoRA” hybrid strategy (encoding maritime rules via Prefix tuning, freezing 95% of base parameters via LoRA to reduce trainable parameters to <0.5%) to balance cost and performance; third, building a non-uniform sampling-model collaboration mechanism, where the fine-tuned model dynamically adjusts the sampling density via semantic understanding to solve random sampling’s “structural information imbalance”. Experiments in close, away, and avoid scenarios (vs. five control models including original LLMs, rule-only/models, and ChatGPT-4.0) show that the proposed method achieves a comprehensive final score of 0.8133—37.1% higher than the sub-optimal data-only model (0.5933) and 87.7% higher than the original general model (0.4333). In high-risk avoid scenarios, its Top-1 Accuracy (0.7333) is 46.7% higher than the sub-optimal control, and Scene-Sensitive Recall (0.7333) is 2.2 times the original model; in close and away scenarios, its Top-1 Accuracy reaches 0.8667 and 0.9000, respectively. This method enhances resolution accuracy and adaptability, promoting LLM applications in navigation. Full article

Vision Transformers (ViTs), inspired by their success in natural language processing, have recently gained attention for heart sound classification (HSC). However, most of the existing studies on HSC rely on single-stream architectures, overlooking the advantages of multi-resolution features. While multi-stream architectures employing early or late fusion strategies have been proposed, they often fall short of effectively capturing cross-modal feature interactions. Additionally, conventional fusion methods, such as concatenation, averaging, or max pooling, frequently result in information loss. To address these limitations, this paper presents a novel attention fusion-based two-stream Vision Transformer (AFTViT) architecture for HSC that leverages two-dimensional mel-cepstral domain features. The proposed method employs a ViT-based encoder to capture long-range dependencies and diverse contextual information at multiple scales. A novel attention block is then used to integrate cross-context features at the feature level, enhancing the overall feature representation. Experiments conducted on the PhysioNet2016 and PhysioNet2022 datasets demonstrate that the AFTViT outperforms state-of-the-art CNN-based methods in terms of accuracy. These results highlight the potential of the AFTViT framework for early diagnosis of cardiovascular diseases, offering a valuable tool for cardiologists and researchers in developing advanced HSC techniques. Full article

Tau protein, a neuron-enriched microtubule-associated protein encoded by the MAPT gene, plays pivotal roles in microtubule stabilisation, axonal transport, and synaptic plasticity. Aberrant post-translational modifications (PTMs), hyperphosphorylation, acetylation, ubiquitination, oxidative stress and neuroinflammation disrupt tau’s normal functions, drive its mislocalization, and promote aggregation into neurofibrillary tangles, a hallmark of Alzheimer’s disease (AD) and related tauopathies. Over the past two decades, tau-targeted therapies have advanced into clinical development, yet most have failed to demonstrate efficacy in human trials. This review synthesises mechanistic insights into tau biology and pathology, highlighting phosphorylation and acetylation pathways, aggregation-prone motifs, and immune-mediated propagation. We analyse the current therapeutic landscape, including kinase and phosphatase modulators, O-GlcNAcase inhibitors, aggregation blockers, immunotherapies, and microtubule-stabilising agents, while examining representative clinical programs and the reasons underlying their limited success. By combining mechanistic understanding with clinical experience, this review outlines emerging opportunities for rational treatment development, aiming to inform future tau-targeted strategies for AD and other tauopathies. Full article

Background: Drug–drug interactions (DDIs) involve pharmacokinetic or pharmacodynamic changes that occur when multiple drugs are co-administered, potentially leading to reduced efficacy or adverse effects. As polypharmacy becomes more prevalent, especially among patients with chronic diseases, scalable and accurate DDI prediction has become increasingly important. Although numerous computational approaches have been proposed to predict DDIs using various modalities such as chemical structure and biological networks, the intrinsic heterogeneity of these data complicates unified modeling; Methods: We address this challenge with a multimodal deep learning framework that integrates three complementary, heterogeneous modalities: (i) chemical structure, (ii) BioBERT-derived semantic embeddings (a domain-specific large language model, LLM), and (iii) pharmacological mechanisms through the CTET proteins. To incorporate indirect biological pathways within the PPI network, we apply a random walk with restart (RWR) algorithm. Results: Across features combinations, fusing structural feature with BioBERT embedding achieved the highest classification accuracy (0.9655), highlighting the value of readily available data and the capacity of domain-specific language models to encode pharmacological semantics from unstructured texts. Conclusions: BioBERT embeddings were particularly informative, capturing subtle pharmacological relationships between drugs and improving prediction of potential DDIs. Beyond predictive performance, the framework is readily applicable to real-world clinical workflows, providing rapid DDI references to support the polypharmacy decision-making. Full article

Diaphorobacter nitroreducens is a Gram-negative bacterium ubiquitously found in wastewater, recognized for its ecological adaptability and potential applications in environmental, biomedical, and industrial processes. Central to its adaptability is the nfrB gene, which encodes a cyclic di-3′,5′-guanylate (c-di-GMP)-activated glycosyltransferase. This enzyme facilitates the secretion of biofilm-associated extracellular polymeric substances (EPS), essential for its survival and functionality in diverse environments. Using complete EMJH media as a selective medium, D. nitroreducens was successfully isolated from soil and water samples from Estero de Paco, Manila, Philippines, enabling downstream analyses of its nfrB gene. Phylogenetic analyses revealed that the nfrB gene tree deviates significantly from the canonical 16S rRNA gene tree, with D. nitroreducens clustering alongside members of the Enterobacteriaceae family. This deviation suggests the potential influence of horizontal gene transfer, adaptive evolution, or lineage-specific pressures on nfrB evolution. Structural analysis of NfrB through Alphafold 3 prediction demonstrated a conserved N-terminal region across taxa, except for the outgroup Zymomonas mobilis. Conversely, the C-terminal region, housing the catalytic domain, showed considerable diversity, reflecting adaptive modifications across bacterial lineages. Despite this variability, the putative binding site for cyclic di-3′,5′-guanylate remained conserved, indicating a balance between functional conservation and adaptive diversification. These findings not only deepen the existing understanding of bacterial signaling and glycosylation mechanisms but also provide insights into the evolutionary dynamics of glycosyltransferases. Furthermore, the study underscores the potential of NfrB as a target for innovative applications, including the design of novel biocatalysts and the development of informed strategies for bacterial management in environmental, industrial, and biotechnological contexts. Full article

Anomaly detection of catenary support components (CSCs) is an important component in railway condition monitoring systems. However, because the abnormal features of CSCs loosening are not obvious, and the current CNN models and visual Transformer models have problems such as limited remote modeling capabilities and secondary computational complexity, it is difficult for existing deep learning anomaly detection methods to effectively exert their performance. The state space model (SSM) represented by Mamba is not only good at long-range modeling, but also maintains linear computational complexity. In this paper, using the state space model (SSM), we proposed a new visual state space reconstruction network (VSM-UNet) for the detection of CSC loosening anomalies. First, based on the structure of UNet, a visual state space block (VSS block) is introduced to capture extensive contextual information and multi-scale features, and an asymmetric encoder–decoder structure is constructed through patch merging operations and patch expanding operations. Secondly, the CBAM attention mechanism is introduced between the encoder–decoder structure to enhance the model’s ability to focus on key abnormal features. Finally, a stable abnormality score calculation module is designed using MLP to evaluate the degree of abnormality of components. The experiment shows that the VSM-UNet model, learning strategy and anomaly score calculation method proposed in this article are effective and reasonable, and have certain advantages. Specifically, the proposed method framework can achieve an AUROC of 0.986 and an FPS of 26.56 in the anomaly detection task of looseness on positioning clamp nuts, U-shaped hoop nuts, and cotton pins. Therefore, the method proposed in this article can be effectively applied to the detection of CSCs abnormalities. Full article

Acoustic imaging systems are essential for underwater target recognition and localization, but forward-looking sonar (FLS) imagery faces challenges due to seabed variability, resulting in low resolution, blurred images, and sparse targets. To address these issues, we introduce RCF-YOLOv8, an enhanced detection framework based on YOLOv8, designed to improve FLS image analysis. Key innovations include the use of CoordConv modules to better encode spatial information, improving feature extraction and reducing misdetection rates. Additionally, an efficient multi-scale attention (EMA) mechanism addresses sparse target distributions, optimizing feature fusion and improving the network’s ability to identify key areas. Lastly, the C2f module with high-quality feature fusion (C2f-Fusion) optimizes feature extraction from noisy backgrounds. RCF-YOLOv8 achieved a 98.8% mAP@50 and a 67.6% mAP@50-95 on the URPC2021 dataset, outperforming baseline models with a 2.4% increase in single-threshold accuracy and a 10.4% increase in multi-threshold precision, demonstrating its robustness for underwater detection. Full article

Coronaviruses, including avian infectious bronchitis virus (IBV), utilize host cellular pathways to evade the host immune response. The aryl hydrocarbon receptor (AhR), a key antiviral regulator exploited by mammalian coronaviruses like SARS-CoV-2, remains unclear in avian coronavirus pathogenesis. This study examined AhR’s involvement during IBV infection using H1299 and Vero cells with pharmacological modulation (AhR antagonist CH223191/agonist kynurenine) and shRNA-mediated silencing. Viral replication was quantified through plaque assays, qRT-PCR, and Western blot. The results reveal IBV-induced AhR activation, driving downstream CYP1A1 expression and pro-inflammatory cytokine production. CH223191 treatment reduced IBV titers, RNA loads, and N protein expression dose-dependently, while kynurenine showed no effect. AhR knockdown similarly reduced N protein expression, confirming its proviral role. An IBV-encoded noncoding RNA was identified as a modulator of AhR activation, suggesting viral balancing of immune evasion and replication efficiency. These results establish AhR as a conserved host factor co-opted by IBV, and highlight AhR antagonism as a promising therapeutic strategy. By bridging insights from avian and mammalian coronaviruses, this work informs strategies to address IBV’s genetic variability and supports development of broad-spectrum antiviral therapies. Full article

The Flaviviruses Dengue virus (DENV), West Nile virus (WNV), Zika virus (ZIKV), and Yellow Fever virus (YFV), are mosquito-borne viruses that represent a persistent challenge to global health due to the emergence and re-emergence of outbreaks of significant magnitudes. Their positive-sense RNA genome, about 11,000 nucleotides long, encodes structural and nonstructural proteins. These viruses evolve rapidly through mutations and genetic recombination, which can lead to more virulent and transmissible strains. Although whole-genome sequencing is ideal for studying their evolution and geographic spread, its cost is a limitation. We investigated the genetic variability of DENV, ZIKV, WNV, and YFV to identify genomic regions that accurately reflect the phylogeny of the complete coding sequence and evaluated the utility of these regions in reconstructing the geographic dispersal patterns of viral genotypes and lineages. Publicly available sequences from GenBank were examined to assess variability, reconstruct phylogenies, and identify the most informative genomic regions. Once representative regions were identified, they were used to infer the global phylogeographic structure of each virus. The virus depicted distinct variation patterns, but conserved regions of high and low variability were common to all. Highly variable regions of ~2700 nt offered greater resolution in phylogenetic trees, improving the definition of internal branches and statistical support for nodes. In some cases, combined multiple highly variable regions enhanced phylogenetic accuracy. Phylogeographic reconstruction consistently grouped sequences by genotype and geographic origin, with temporal structuring revealing evolutionarily distinct clusters that diverged over decades. These findings highlight the value of targeting genomic regions for phylogenetic and phylogeographic analysis, providing an efficient alternative for genomic surveillance. Full article

Low-light image enhancement aims to restore images captured under extreme low-light conditions. Existing methods demonstrate that fusing Fourier transform magnitude and phase information within the RGB color space effectively improves enhancement results. Meanwhile, recent advances have demonstrated that certain color spaces based on human visual perception, such as Hue–Value–Intensity (HVI), are superior to RGB for enhancing low-light images. However, these methods neglect the key impact of the coupling relationship between spatial and frequency-domain features on image enhancement. This paper proposes a spatial–frequency-domain multi-scale fusion for low-light image enhancement by exploring the intrinsic relationships among the three channels of HVI space, which consists of a dual-path parallel processing architecture. In the spatial domain, a specifically designed multi-scale feature extraction module systematically captures comprehensive structural information. In the frequency domain, our model establishes deep coupling between spatial features and Fourier transform features in the I-channel. The effectively fused features from both domains synergistically drive an encoder–decoder network to achieve superior image enhancement performance. Extensive experiments on multiple public benchmark datasets show that the proposed method significantly outperforms state-of-the-art approaches in both quantitative metrics and visual quality. Full article

Binary code similarity detection (BCSD) plays an important role in software security. Recent deep learning-based methods have made great progress. Existing methods based on a single feature, such as semantics or graph structure, struggle to handle changes caused by the architecture or compilation environment. Methods fusing semantics and graph structure suffer from insufficient learning of the function, resulting in low accuracy and robustness. To address this issue, we proposed Fus, a method that integrates semantic information from the pseudo-C code and structural features from the Abstract Syntax Tree (AST). The pseudo-C code and AST are robust against compilation and architectural changes and can represent the function well. Our approach consists of three steps. First, we preprocess the assembly code to obtain the pseudo-C code and AST for each function. Second, we employ a Siamese network with CodeBERT models to extract semantic embeddings from the pseudo-C code and Tree-Structured Long Short-Term Memory (Tree LSTM) to encode the AST. Finally, function similarity is computed by summing the respective semantic and structural similarities. The evaluation results show that our method outperforms the state-of-the-art methods in most scenarios. Especially in large-scale scenarios, its performance is remarkable. In the vulnerability search task, Fus achieves the highest recall. It demonstrates the accuracy and robustness of our method. Full article

This article offers a new perspective on Miriam’s red jewel in Nathaniel Hawthorne’s The Marble Faun (1860), interpreting it as a symbol of Jewish femininity, diasporic memory, and aesthetic resistance. Although the jewel has received little critical attention, this study suggests that it plays a central role in shaping Miriam’s identity and in articulating broader cultural anxieties around gender, ethnicity, and visibility. Through intertextual readings of Shakespeare’s Jessica and Walter Scott’s Rebecca and Rowena, the essay situates Miriam within a literary tradition of Jewish women whose identities are mediated through symbolic adornments. In addition to literary analysis, the article draws on visual art history—particularly Carol Ockman’s interpretation of Jean-Auguste-Dominique Ingres’s 1848 portrait of Baronne de Rothschild—to explore how 19th-century visual culture contributed to the eroticization and exoticization of Jewish women. By placing Hawthorne’s portrayal of Miriam in dialogue with such visual representations, the essay highlights how the red jewel functions as a site of encoded cultural meaning. The analysis is further informed by feminist art theory (Griselda Pollock) and postcolonial critique (Edward Said), offering an interdisciplinary approach to questions of identity, marginalization, and symbolic resistance. While not claiming to offer a definitive reading, this article aims to open new interpretive possibilities by foregrounding the jewel’s narrative and symbolic significance. In doing so, it contributes to ongoing conversations in Hawthorne studies, Jewish cultural history, and the intersections of literature and visual art. Full article

Hyperspectral image classification (HSIC) involves analyzing high-dimensional data that contain substantial spectral redundancy and spatial noise, which increases the entropy and uncertainty of feature representations. Reducing such redundancy while retaining informative content in spectral–spatial interactions remains a fundamental challenge for building efficient and accurate HSIC models. Traditional deep learning methods often rely on redundant modules or lack sufficient spectral–spatial coupling, limiting their ability to fully exploit the information content of hyperspectral data. To address these challenges, we propose SGFNet, which is a spectral-guided fusion network designed from an information–theoretic perspective to reduce feature redundancy and uncertainty. First, we designed a Spectral-Aware Filtering Module (SAFM) that suppresses noisy spectral components and reduces redundant entropy, encoding the raw pixel-wise spectrum into a compact spectral representation accessible to all encoder blocks. Second, we introduced a Spectral–Spatial Adaptive Fusion (SSAF) module, which strengthens spectral–spatial interactions and enhances the discriminative information in the fused features. Finally, we developed a Spectral Guidance Gated CNN (SGGC), which is a lightweight gated convolutional module that uses spectral guidance to more effectively extract spatial representations while avoiding unnecessary sequence modeling overhead. We conducted extensive experiments on four widely used hyperspectral benchmarks and compared SGFNet with eight state-of-the-art models. The results demonstrate that SGFNet consistently achieves superior performance across multiple metrics. From an information–theoretic perspective, SGFNet implicitly balances redundancy reduction and information preservation, providing an efficient and effective solution for HSIC. Full article