Search Results (105,713)

To address the challenge of model selection in large-scale traffic flow prediction tasks, this paper proposes a dynamic multi-model selection framework based on Deep Contextual Bandits (DCB). Centered on the optimal combination of sub-models, the framework leverages contextual information of road segments to select dynamically among candidate predictors, achieving more efficient and accurate traffic flow prediction. Several mechanisms are introduced to improve strategy learning and convergence, including a baseline network, experience replay, double-model estimation, and prioritized experience sampling. A clustering-based strategy is further designed to reduce the search space and enhance the generalization and transferability. Experiments on real-world traffic datasets demonstrate that the proposed framework significantly outperforms traditional static fusion methods, reinforcement learning (RL) baselines, and mainstream spatiotemporal prediction models. In particular, the framework yields a 1.0% improvement in R² and a 3.2% reduction in MAE compared to state-of-the-art baselines, while reducing inference time by 43.1%. Moreover, the proposed framework shows strong capability in adaptive model selection under varying contexts, with ablation studies confirming the effectiveness of its key components. Full article

The detection of defects in key transmission-line equipment under complex environments often suffers from insufficient accuracy and reliability due to background interference and multi-scale feature variations. To address this issue, this paper proposes an improved defect detection model based on YOLOv11, named DCDW-YOLOv11. The model introduces deformable convolution C2f_DCNv3 in the backbone network to enhance adaptability to geometric deformations of targets, and incorporates the convolutional block attention module (CBAM) to highlight defect features while suppressing background interference. In the detection head, a dynamic head structure (DyHead) is adopted to achieve cross-layer multi-scale feature fusion and collaborative perception, along with the WIoU loss function to optimize bounding box regression and sample weight allocation. Experimental results demonstrate that on the transmission-line equipment defect dataset, DCDW-YOLOv11 achieves an accuracy, recall, and mAP of 94.4%, 92.8%, and 96.3%, respectively, representing improvements of 2.8%, 7.0%, and 4.4% over the original YOLOv11, and outperforming other mainstream detection models. The proposed method can provide high-precision and highly reliable defect detection support for intelligent inspection of transmission lines in complex scenarios. Full article

This paper explores the application of predictive maintenance (PdM) to address paraffin deposition in sucker rod pump systems used for oil production. System maintenance has become critical for enhancing efficiency and reducing costs, while PdM, supported by advanced analytics and sensors, enables downtime prediction and maintenance optimization. Paraffin deposition is a significant problem in the oil industry, as it diminishes production capacity and increases expenses. This paper presents the use of the SCADA system, which enables the collection and analysis of data in real time. Furthermore, it proposes diagnostic methods for early detection of paraffin deposition using predictive maintenance, offering timely warnings to prevent production delays. While the proposed framework relies on interpretable statistical and physics-informed predictive models, the results indicate that further improvements could be achieved by integrating advanced artificial intelligence techniques to enhance adaptability, automation, and decision support in predictive maintenance systems. Full article

Cancer immunoprevention leverages the immune system’s surveillance mechanisms to mitigate tumor development. Vaccines that constitute a tumor antigen and an immune adjuvant are perceived as immunoprevention modalities. However, relevant tumor antigens are unknown for non-viral cancers, which constitute most human cancers. Our group has recently shown that SA–4–1BBL, a novel agonist of CD137 receptor, but not antibodies, shows immunoprevention efficacy against various tumors. Advanced bioinformatics analyses of bulk RNA-seq data were conducted to elucidate mechanisms underlying cancer immunoprevention. Mice received subcutaneous injections of SA–4–1BBL or agonistic 3H3 antibody, and the injection-site tissue (IS) and draining lymph nodes (LN) were analyzed for differential gene expression. SA–4–1BBL induced a compartmentalized and temporally dynamic immune program characterized by early effector activation at IS and sustained immune regulation in draining LN. K-means clustering of 4564 DEGs identified eight functionally distinct clusters. IS-enriched clusters contained activation genes for CD4⁺ T and NK cells, including Cd28, Klra1, Cd4, Cd40, and Cd40l, while LN clusters were enriched for regulatory genes (Tnfaip3, Irf5, Col1a2) that ensure immune priming and homeostatic restraint for a balanced response. SA–4–1BBL generated a more selective and durable activation of adaptive immunity, TCR signaling, Th1/Th2 differentiation, and NK cytotoxicity. 3H3 activated broader innate inflammatory programs, including Toll-like receptor and neurodegeneration-linked pathways. IMPRes analysis showed that SA–4–1BBL activates sequential immune-regulatory circuits centered on Stat1, Cd247, and Ifng and modulates the CD151–TGF-β axis. These findings demonstrate that SA–4–1BBL elicits a balanced immune response, ensuring both safety and efficacy in preventing cancer development. Full article

Glutamine metabolism has emerged as one of the most critical bioenergetic and biosynthetic programs sustaining leukemic cell growth, survival, stemness and therapeutic resistance. In both acute and chronic leukemias, including acute myeloid leukemia (AML) and acute lymphoblastic leukemia (ALL), malignant cells display a strong dependency on extracellular glutamine to support mitochondrial respiration, anabolic biosynthesis and redox homeostasis. This dependency is reinforced by oncogenic signaling networks, post-transcriptional metabolic regulation and microenvironmental adaptation within the bone marrow niche. Therapeutic strategies targeting glutamine utilization, including glutaminase inhibition, transporter blockade and enzymatic glutamine depletion, have demonstrated robust antileukemic activity in preclinical models, and early clinical efforts have begun to explore glutamine-directed interventions in myeloid neoplasms. However, metabolic plasticity, microenvironment-derived nutrient buffering and systemic toxicity remain significant limitations to clinical translation. This review provides a detailed synthesis of the biochemical framework of glutamine metabolism in leukemia, the molecular mechanisms enforcing glutamine addiction, the downstream functional consequences on proliferation, redox balance and leukemic stem cell biology, the current landscape of therapeutic strategies and emerging directions aimed at overcoming resistance and improving clinical efficacy. Full article

Urban areas face rising risks from extreme heat due to climate change, intensifying thermal stress and exacerbating social inequalities. Urban climate refuges—cool, accessible indoor and outdoor public spaces that maintain their ordinary functions—are increasingly adopted as a local adaptation measure to protect vulnerable populations during heat events. This study aims to develop and test a SWOT–CAME analytical framework to evaluate and compare the maturity, equity, and implementation logic of urban climate refuge networks in three European cities with contrasting climates and governance traditions: Barcelona, Amsterdam, and Copenhagen. A qualitative multiple-case design is combined with a transparent indicator set (coverage, accessibility, and typology mix) derived from official municipal sources and planning documents. Results show differentiated pathways: Barcelona represents an institutionalized network model; Amsterdam illustrates an emerging coordinated public-health approach; and Copenhagen reflects an ecosystem-based orientation where green–blue infrastructure provides substantial passive cooling capacity but requires clearer heat-specific operational protocols. The discussion highlights the need for hybrid adaptation strategies that combine nature-based solutions with operational governance and targeted support for vulnerable groups. The paper concludes with a transferable framework for cities seeking to integrate climate refuges into resilience and climate-justice agendas. Full article

Aquaculture of molluscs and crustaceans represents an important and expanding sector within global food production. The intensification of these systems has been accompanied by an increased prevalence and severity of infectious diseases, which continue to constrain productivity and sustainability. Current disease management approaches include biosecurity measures, husbandry practices, therapeutics, and selective breeding, which have shown limited efficacy against many emerging pathogens affecting invertebrate species. Unlike finfish, aquatic invertebrates lack adaptive immunity and rely exclusively on innate immune mechanisms, limiting the effectiveness of traditional vaccine strategies. There is growing interest in immunostimulants that enhance innate defenses and support immune priming or trans-generational immune priming (TGIP). This review summarises the current understanding of immune defence mechanisms in molluscs and crustaceans and examines recent progress in the development of immunomodulators and prophylactic interventions aimed at improving health outcomes and disease resilience in invertebrate aquaculture. Full article

Amid China’s shift from a model of urban “incremental expansion” to one focused on “stock optimization”, the renewal of streetscapes has taken center stage as a critical approach to improving the human experience within urban environments. However, empirical insight into how visual interventions affect aesthetic perception across different road types remains notably limited. This study addresses that gap through a spatiotemporal investigation of Zhengzhou’s streetscape transformations between 2017 and 2022. Major roads were categorized into four functional types—freeway, under-freeway, regular road, and tunnel—to better capture perceptual variation. Leveraging a Fully Convolutional Network (FCN), we extracted nine visual components from historical street views and paired them with crowd-sourced “beauty” ratings from the MIT Place Pulse 2.0 dataset. Statistical analyses, including paired t-tests and Kernel Density Estimation (KDE), indicated marked improvements in perceived beauty following renewal, with the exception of tunnel segments. Through Random Forest (RF) regression and SHapley Additive exPlanations (SHAP) interpretation, greening emerged as the most influential driver of aesthetic enhancement—most prominently on regular roads (SHAP = 2.246). The impact of renewal was found to be context-specific: green belts were most effective in under-freeway areas (SHAP = +0.8), while improvements to pavement (SHAP = +0.97) and street vitality were key for regular roads. Notably, SHAP analysis revealed non-linear relationships, such as diminishing perceptual returns when green coverage exceeded certain thresholds. These findings inform a “visual renewal–perceptual response” framework, offering data-driven guidance for adaptive, human-centered upgrades in high-density urban settings. Full article

The yak represents a distinct domestic animal species that predominantly inhabits the Qinghai–Tibet Plateau and adjacent areas, possessing considerable value in both scientific and economic contexts. Compared to animals that mainly dwell on plains, such as cattle, the sperm maturation process in yak exhibits a certain degree of species specificity to adapt to their unique reproductive needs in high-altitude environments. Serving as the main storage site for functionally competent sperm, the cauda epididymis plays an integral role in mediating their post-testicular maturation. MiRNAs are vital regulatory molecules in the epididymis, influencing sperm maturation by modulating gene expression after transcription. To investigate the unique regulatory mechanisms of sperm maturation in yak, this study compared the miRNA expression profiles in the cauda epididymis of yak and cattle using high-throughput small RNA (sRNA) sequencing. The comparative analysis identified and characterized sRNA populations in the cauda epididymis of yak and cattle, revealing a similar length distribution that peaked at 22 nt and a predominance of known miRNAs. Notably, eight miRNAs were found to be highly expressed in both species. Furthermore, the first-nucleotide bias differed significantly between known and novel miRNAs within each species. A total of 31 differentially expressed (DE) miRNAs were identified, with 11 upregulated and 20 downregulated in yak compared to cattle. Among these, bta-miR-1298 exhibited the most significant upregulation, while bta-miR-2344 displayed the most pronounced downregulation. Bioinformatic analysis linked the predicted target genes of these miRNAs to numerous critical signaling pathways, including calcium signaling, the mitogen-activated protein kinase (MAPK) signaling pathway, the Ras-associated protein 1 (Rap1) signaling pathway, and the cyclic guanosine monophosphate-protein kinase G (cGMP-PKG) signaling pathway. Furthermore, eight significantly DE miRNAs, including bta-miR-2443, bta-miR-503-3p, bta-miR-6517, bta-miR-2440, bta-miR-2431-3p, bta-miR-2436-3p, bta-miR-6523a, and bta-miR-6775, were predicted to target genes involved in various aspects of sperm structural and functional maturation. These aspects include flagellum formation, sperm motility, chromatin remodeling, acrosome reaction, acrosome structure, sperm capacitation, chemotaxis, and nuclear chromatin condensation. Multiple miRNAs and their corresponding predicted target genes were analyzed by quantitative real-time PCR (qPCR), demonstrating an inverse correlation between miRNA expression and target gene levels. These findings reveal a distinct, species-specific miRNA signature in the yak cauda epididymis, which suggests a potential contribution to regulating the epididymal luminal environment and the process of sperm maturation. This study provides preliminary foundational data for elucidating the differences in sperm maturation mechanisms between yak and cattle, and offers potential novel targets for improving reproductive efficiency in plateau livestock. Full article

Cross-project software vulnerability detection must cope with pronounced domain shift and severe class imbalance, while the target project is typically unlabeled. Existing unsupervised domain adaptation techniques either focus on marginal alignment and overlook class-conditional mismatch, or depend on noisy pseudolabels, which can induce negative transfer in imbalanced settings. To address these challenges we propose DAP2ER, a progressive domain adaptation framework that couples adversarial domain confusion with entropy regularization and prototype-guided high-confidence pseudolabel optimization. Specifically, DAP2ER constructs source class prototypes, selects reliable target samples via confidence-aware pseudolabeling, and performs class-conditional alignment by pulling target features toward the corresponding prototypes. A progressive weighting schedule gradually increases the strength of domain and self-training objectives, stabilizing optimization in early epochs. Experiments on two real-world vulnerability datasets demonstrate that DAP2ER consistently outperforms strong baselines, improving the F1-score by up to 21 percentage points and achieving substantial gains in AUC for bidirectional transfer. Full article

As the critical component of the gastrointestinal tract, which lives in trillions of gut microorganisms, in a healthy state, the host interacts with the gut microbiota and is symbiotic. The species Limosilactobacillus reuteri, Ligilactobacillus salivarius, and Lactobacillus johnsonii are indigenous gut commensal bacteria that are mainly found in the digestive tracts. These three bacteria possess a variety of characteristics that reflect their ability to adapt to the gastrointestinal environment. Herein, we summarize the current progress of research on the probiotic properties of these strains in terms of their ability to protect against harmful pathogens, maintain intestinal health, and improve disease outcomes. These bacteria can impact the intestinal barrier function and enhance intestinal immunity through various mechanisms, such as upregulating the tight-junction protein expression and mucin secretion of intestinal epithelial cells, adjusting and balancing the gut microbiota, and blocking pro-inflammatory cytokine production. They have been shown to ameliorate intestinal inflammation in animal models and provide protective effects against various healthy issues in humans, including diarrhea, constipation, colorectal cancer, obesity, and liver diseases. However, the detailed mechanisms of certain strains remain unclear. Full article

Federated learning (FL) has emerged as a promising paradigm for privacy-preserving distributed intelligence in modern urban transportation systems, where vehicles collaboratively train global models without sharing raw data. However, the dynamic nature of vehicular environments introduces critical challenges, including unstable participation, data heterogeneity, and the potential for malicious behavior. Conventional FL frameworks lack effective trust management and adaptive incentive mechanisms capable of maintaining fairness and reliability under these fluctuating conditions. This paper presents a reputation-aware federated learning framework that integrates multi-dimensional reputation evaluation, dynamic incentive control, and malicious client detection through an adaptive feedback mechanism. Each vehicular client is assessed based on data quality, stability, and behavioral consistency, producing a reputation score that directly influences client selection and reward allocation. The proposed feedback controller self-tunes the incentive weights in real time, ensuring equitable participation and sustained convergence performance. In parallel, a penalty module leverages statistical anomaly detection to identify, isolate, and penalize untrustworthy clients without compromising benign contributors. Extensive simulations conducted on real-world datasets demonstrate that the proposed framework achieves higher model accuracy and greater robustness against poisoning and gradient manipulation attacks compared to existing baseline methods. The results confirm the potential of our trust-regulated incentive mechanism to enable reliable federated learning in smart cities transportation systems. Full article

Accurate and timely diagnosis of rice leaf diseases is crucial for smart agriculture leveraging vision sensors. However, existing lightweight convolutional neural networks (CNNs) often struggle in complex field environments, where small lesions, cluttered backgrounds, and varying illumination complicate recognition. This paper presents I-GhostNetV3, an incrementally improved GhostNetV3-based network for RGB rice leaf disease recognition. I-GhostNetV3 introduces two modular enhancements with controlled overhead: (1) Adaptive Parallel Attention (APA), which integrates edge-guided spatial and channel cues and is selectively inserted to enhance lesion-related representations (at the cost of additional computation), and (2) Fusion Coordinate-Channel Attention (FCCA), a near-neutral SE replacement that enables efficient spatial–channel feature fusion to suppress background interference. Experiments on the Rice Leaf Bacterial and Fungal Disease (RLBF) dataset show that I-GhostNetV3 achieves 90.02% Top-1 accuracy with 1.831 million parameters and 248.694 million FLOPs, outperforming MobileNetV2 and EfficientNet-B0 under our experimental setup while remaining compact relative to the original GhostNetV3. In addition, evaluation on PlantVillage-Corn serves as a supplementary transfer sanity check; further validation on independent real-field target domains and on-device profiling will be explored in future work. These results indicate that I-GhostNetV3 is a promising efficient backbone for future edge deployment in precision agriculture. Full article

Aiming at the problem that fault characteristics cannot be effectively expressed due to the low pixel proportion of the hot spot target and background interference when detecting hot spot faults in complex environments, a photovoltaic module hot spot fault detection method integrating U-Net and YOLOv8 is proposed. Firstly, the U-Net segmentation network is introduced to remove pseudo-high-brightness heat sources in the background and highlight the contour features of the photovoltaic panels, laying a good foundation for the subsequent photovoltaic hot spot fault detection tasks. Secondly, a detection network is built based on the YOLOv8 framework. Aiming at the problems that it is difficult to extract the hot spot features of photovoltaic panels of different sizes and to balance the reasoning speed and detection accuracy, a detection network based on deformable convolution and GhostNet is designed. Furthermore, to enhance the adaptability of the convolutional neural network to multi-scale hot spot targets, deformable convolution (DCN) is introduced into the YOLOv8 network. By adaptively adjusting the shape and size of the receptive field, the detection accuracy is further improved. Then, aiming at the issue that it is difficult to balance accuracy and speed in the detection network, the C2f_Ghost module is designed to simplify the network parameters and improve the model inference speed. To verify the effectiveness of the algorithm, a comparison is made with SSD, YOLOv5, YOLOv7, and YOLOv8. The results show that the proposed algorithm can accurately detect hot spot faults, with an accuracy of up to 88.5%. Full article

As a key technology in the intelligent interpretation of remote sensing, remote sensing image change detection aims to automatically identify surface changes from images of the same area acquired at different times. Although vision foundation models have demonstrated outstanding capabilities in image feature representation, their inherent patch-based processing and global attention mechanisms limit their effectiveness in perceiving multi-scale targets. To address this, we propose a multi-scale remote sensing image change detection network based on a vision foundation model, termed SAM-MSCD. This network integrates an efficient parameter fine-tuning strategy with a cross-temporal multi-scale feature fusion mechanism, significantly improving change perception accuracy in complex scenarios. Specifically, the Low-Rank Adaptation mechanism is adopted for parameter-efficient fine-tuning of the Segment Anything Model (SAM) image encoder, adapting it for the remote sensing change detection task. A bi-temporal feature interaction module(BIM) is designed to enhance the semantic alignment and the modeling of change relationships between feature maps from different time phases. Furthermore, a change feature enhancement module (CFEM) is proposed to fuse and highlight differential information from different levels, achieving precise capture of multi-scale changes. Comprehensive experimental results on four public remote sensing change detection datasets, namely LEVIR-CD, WHU-CD, NJDS, and MSRS-CD, demonstrate that SAM-MSCD surpasses current state-of-the-art (SOTA) methods on several key evaluation metrics, including the F1-score and Intersection over Union(IoU), indicating its broad prospects for practical application. Full article