Search Results (375)

Background/Objectives: Plant-derived diuretics are attracting increasing interest due to their promising efficacy and improved safety profile compared with synthetic drugs. This study aimed to characterize the phytochemical composition of Astragalus boeticus (A. boeticus) extracts, evaluate their diuretic activity, and assess the oral safety of their main phenolic compound. Methods: Aqueous (AQE) and hydroethanolic (EtOHE) extracts were analyzed using LC–MS/MS, while in silico toxicity prediction of trans-resveratrol was performed using ProTox-II and ADMETlab 2.0. Diuretic activity was evaluated in male Wistar rats (n = 24) divided into four groups: control (distilled water, 10 mL/kg), furosemide (10 mg/kg), AQE (300 mg/kg), and EtOHE (300 mg/kg). Urine and plasma samples were collected after 15 days to determine electrolyte concentrations, creatinine level, creatinine clearance, and hepatic enzyme profile. Results: LC–MS/MS profiling identified fourteen phenolic compounds, with trans-resveratrol (270 µg/g in AQE) being the most abundant, followed by cyanidin-3-O-glucoside and gentisic acid. In silico assessments revealed no hepatotoxic, mutagenic, or neurotoxic effects of trans-resveratrol. Both extracts significantly enhanced urinary output, chloride excretion, and creatinine clearance, while maintaining stable renal and hepatic biochemical parameters, indicating potent diuretic activity without toxicity. Conclusions: A. boeticus extracts demonstrate strong diuretic potential associated with a favorable safety profile, likely linked to their phenolic composition dominated by trans-resveratrol. These findings support the use of A. boeticus as a natural and safe diuretic source. Further investigation is recommended to elucidate its pharmacological mechanisms and therapeutic relevance. Full article

Background: Neoadjuvant chemoradiotherapy (nCRT) is the standard treatment for locally advanced rectal cancer, but only 15–30% of patients achieve a pathological complete response. Single nucleotide polymorphisms represent stable genetic markers with potential predictive value for treatment response. This systematic review synthesizes current evidence on the association between SNPs and the response to nCRT in rectal cancer. Methods: PubMed and Web of Science databases were searched for relevant English studies. Two reviewers independently screened the titles and abstracts using the DistillerSR tool. Full-text articles were assessed for their eligibility. Data extraction followed the PRISMA guidelines, and the risk of bias was assessed. Results: Thirty-two studies (4116 patients) assessed 304 SNPs across 126 genes in 407 analyses. DNA repair genes (XRCC1, XRCC3, ERCC1, ERCC2) and folate metabolism genes (MTHFR, TYMS) were most frequently investigated. Only two SNPs demonstrated predictive value in multiple studies: rs25487 (XRCC1) and rs1801133 (MTHFR); however, the associations were inconsistent. The remaining SNPs showed isolated associations in single studies. No SNP demonstrated predictive value across independent cohorts. Conclusions: Current evidence does not support the clinical use of individual SNPs to predict nCRT response in rectal cancer patients. Although XRCC1 and MTHFR polymorphisms have been extensively studied, their predictive utility remains inconclusive. Future research should prioritize large, multicenter prospective studies with standardized treatment and outcome definitions, and consider polygenic risk models or integrated multi-omic approaches. Full article

Large Language Models (LLMs) are emerging technologies and a growing research trend in Artificial General Intelligence (AGI), which envisions a future where machines can think and learn like humans across a wide range of tasks. Information generated by LLMs is essentially the prediction of next tokens in Natural Language Processing (NLP) tasks. However, the generated content is always subject to issues of truthfulness and hallucinations. The information and knowledge integrity of LLM-generated content therefore remains subjective. Exploring recent literature on the integrity of LLMs in a systematic manner is both timely and essential. Moreover, ensuring the reliability of LLMs in real-world applications is critical. Various approaches have been explored to promote information and knowledge integrity in LLMs, including adversarial training, data augmentation, and calibration methods. However, beyond these techniques, other strategies also contribute to maintaining knowledge integrity. This paper specifically focuses on three such approaches: knowledge distillation, semantic integrity, and provenance tracking, which play essential roles in ensuring that LLMs generate accurate, consistent, and trustworthy information. Knowledge distillation enhances model efficiency by transferring knowledge from larger models to smaller ones while preserving essential learning without compromising knowledge integrity. This reduces hallucinations. Semantic integrity safeguards consistency and strengthens the robustness of generated outputs. It is concurrently checking the meaningfulness of the outputs with the context. Provenance tracking improves transparency and trustworthiness through mechanisms such as data lineage and explainability, thereby ensuring the credibility of the LLM-generated responses. This review suggests that knowledge distillation, semantic integrity, and provenance tracking can enhance the reliability of LLM outputs, with prior studies reporting reductions in hallucination rates, improvements in robustness, and gains in factual consistency. Full article

The proliferation of electronic health records necessitates secure and privacy-preserving data sharing frameworks to combat escalating cybersecurity threats in healthcare. Current systems face critical limitations including centralized data repositories vulnerable to breaches, static consent mechanisms, and inadequate audit capabilities. This paper introduces an integrated blockchain and federated learning framework that enables privacy-preserving collaborative AI across healthcare institutions without centralized data pooling. The proposed approach combines federated distillation for heterogeneous model collaboration with dynamic differential privacy that adapts noise injection to data sensitivity levels. A novel threshold key-sharing protocol ensures decentralized access control, while a dual-layer Quorum blockchain establishes immutable audit trails for all data sharing transactions. Experimental evaluation on clinical datasets (Mortality Prediction and Clinical Deterioration from eICU-CRD) demonstrates that our framework maintains diagnostic accuracy within 3.6% of centralized approaches while reducing communication overhead by 71% and providing formal privacy guarantees. For Clinical Deterioration prediction, the framework achieves 96.9% absolute accuracy on the Clinical Deterioration task with FD-DP at $ϵ$ = 1.0, representing only 0.14% degradation from centralized performance. The solution supports HIPAA-aligned technical safeguards, mitigates inference and membership attacks, and enables secure cross-institutional data sharing with real-time auditability. This work establishes a new paradigm for privacy-preserving healthcare AI that balances data utility, regulatory requirements, and protection against emerging threats in distributed clinical environments. Full article

AI-generated phishing emails present a growing cybersecurity threat, exploiting human psychology with high-quality, context-aware language. This paper introduces a novel two-stage detection framework that combines deep learning with psychological analysis to address this challenge. A new dataset containing 2995 GPT-o1-generated phishing emails, each labelled with Cialdini’s six persuasion principles, is created across five organisational sectors—forming one of the largest and most behaviourally annotated corpora in the field. The first stage employs a fine-tuned DistilBERT model to predict the presence of persuasion principles in each email. These confidence scores then feed into a lightweight dense neural network at the second stage for final binary classification. This interpretable design balances performance with insight into attacker strategies. The full system achieves 94% accuracy and 98% AUC, outperforming comparable methods while offering a clearer explanation of model decisions. Analysis shows that principles like authority, scarcity, and social proof are highly indicative of phishing, while reciprocation and likeability occur more often in legitimate emails. This research contributes an interpretable, psychology-informed framework for phishing detection, alongside a unique dataset for future study. Results demonstrate the value of behavioural cues in identifying sophisticated phishing attacks and suggest broader applications in detecting malicious AI-generated content. Full article

Pyruvate:ferredoxin oxidoreductase (PFOR) is a key Achilles’ heel in anaerobic pathogens. We integrate electronic-structure calculations (DFT), cheminformatic QSAR metrics, and residue-resolved docking to distill a concise “recognition code” and translate it into practical design rules. Using nitazoxanide (Nita; ΔG_(bind) ≈ −10.0 kcal·mol⁻¹) as a well-established reference, productive binding requires a conserved triad: a hydrogen-bond donor addressing Thr-997 and Cys-840, a π–π stack with Phe-869, and a recurrent π–σ contact to Thr-997 that orients the scaffold. Deacetylation to tizoxanide unmasks the phenolic donor and raises local electrophilicity, yet it also slightly loosens pocket packing (−9.6 kcal·mol⁻¹). Strategic halogenation introduces a σ-hole interaction near Pro-29, tightening pose geometry without disrupting the donor network; the lead analogue yields −10.1 kcal·mol⁻¹, and two others match the reference by preserving the triad and hydrophobic belt. The result is a minimal, testable recipe—retain the phenolic donor, enforce Thr-997/Cys-840 and Phe-869, and add a calibrated halogen σ-hole—offering falsifiable predictions to surpass nitazoxanide and guiding synthesis and biophysical validation in targeted PFOR inhibition. Full article

Sentiment analysis is essential for understanding consumer opinions, yet selecting the optimal models and embedding methods remains challenging, especially when handling ambiguous expressions, slang, or mismatched sentiment–rating pairs. This study provides a comprehensive comparative evaluation of sentiment classification models across three paradigms: traditional machine learning, pre-transformer deep learning, and transformer-based models. Using the Amazon Magazine Subscriptions 2023 dataset, we evaluate a range of embedding techniques, including static embeddings (GloVe, FastText) and contextual transformer embeddings (BERT, DistilBERT, etc.). To capture predictive confidence and model uncertainty, we include categorical cross-entropy as a key evaluation metric alongside accuracy, precision, recall, and F1-score. In addition to detailed quantitative comparisons, we conduct a systematic qualitative analysis of misclassified samples to reveal model-specific patterns of uncertainty. Our findings show that FastText consistently outperforms GloVe in both traditional and LSTM-based models, particularly in recall, due to its subword-level semantic richness. Transformer-based models demonstrate superior contextual understanding and achieve the highest accuracy (92%) and lowest cross-entropy loss (0.25) with DistilBERT, indicating well-calibrated predictions. To validate the generalisability of our results, we replicated our experiments on the Amazon Gift Card Reviews dataset, where similar trends were observed. We also adopt a resource-aware approach by reducing the dataset size from 25 K to 20 K to reflect real-world hardware constraints. This study contributes to both sentiment analysis and sustainable AI by offering a scalable, entropy-aware evaluation framework that supports informed, context-sensitive model selection for practical applications. Full article

Discrete prompts are the main method for interacting with Large Language Models (LLMs) due to their interpretability and cross-model compatibility. However, optimizing them for fine-grained tasks such as Aspect-Based Sentiment Analysis (ABSA) remains challenging, particularly due to error propagation from fixed prediction orders. This problem comes from two issues: errors that cascade in the sequence and the need for intensive human involvement in the prompt design. To solve these problems, we present LM-SODP, a Reinforcement Learning (RL) framework that automatically finds a better discrete prompt and decides a better order to make predictions for ABSA. Our method is based on a distilled GPT-2. It improves how the model uses task-specific information and reduces uncertainty by optimizing the prompts. This reduces the output entropy. LM-SODP also independently finds a better execution sequence for the subtasks in ABSA. Experiments on public datasets show that our method leads to stable improvements under different conditions. By using the optimized prompts, LM-SODP can effectively guide LMs with limited computational resources. It also maintains good performance across different domains and opens new avenues for automated prompt token generation. Full article

To ensure the effectiveness of online teaching, educators must understand students’ learning progress. This study proposes LWKD-ViT, a framework designed to accurately capture students’ emotions during online courses. The framework is built on a lightweight facial expression recognition (FER) model with modifications to the fusion block. In addition, knowledge distillation (KD) is integrated into the online course platform to enhance performance. The framework follows a defined process involving face detection, tracking, and clustering to extract facial sequences for each student. An improved model, MobileViT-Local, developed by the authors, extracts emotion features from individual frames of students’ facial video streams for classification and prediction. Students’ facial images are captured through their device cameras and analyzed in real time on their devices, eliminating the need to transmit videos to the teacher’s computer or a remote server. To evaluate the performance of MobileViT-Local, comprehensive tests were conducted on benchmark datasets, including RAFD, RAF-DB, and FER2013, as well as a self-built dataset, SCAUOL. Experimental results demonstrate the model’s competitive performance and superior efficiency. Due to the use of knowledge distillation, the proposed model achieves a prediction accuracy of 94.96%, surpassing other mainstream models. It also exhibits excellent performance, with optimal FLOPs of 0.265 G and a compact size of 4.96 M, while maintaining acceptable accuracy. Full article

Automatic Modulation Recognition (AMR) is a critical technology for intelligent wireless communication systems, but the deployment of high-performance deep learning models is often hindered by their substantial computational and memory requirements. To address this challenge, this paper proposes a multi-level knowledge distillation network, namely MLD-Net, for creating a lightweight and powerful AMR model. Our approach employs a large Transformer-based network as a teacher to guide the training of a compact and efficient Reformer-based student model. The knowledge contained in the large model is transferred across three distinct granularities: at the output level, to convey high-level predictive distributions; at the feature level, to align intermediate representations; and at the attention level, to propagate relational information about signal characteristics. This comprehensive distillation strategy empowers the student model to effectively emulate the teacher’s complex reasoning processes. Experimental results on the RML2016.10A benchmark dataset demonstrate that MLD-Net achieves state-of-the-art performance, outperforming other baseline models across a wide range of signal-to-noise ratios while requiring only a fraction of the parameters. Extensive ablation study further confirms the collaborative contribution of each distillation level, validating that the proposed MLD-Net is an effective solution for developing lightweight and efficient AMR networks for edge deployment. Full article

Background: Dopamine (DA) is a key biomarker for neurodegenerative diseases such as Parkinson’s. However, detailed insights into how DA release in the brain changes with aging remain challenging. Integrating machine learning with DA sensing platforms has proven more effective in tracking age-dependent DA dynamics than using the sensing platforms alone. Method: This study presents a machine learning framework to automatically detect and quantify dopamine (DA) release using the near-infrared catecholamine nanosensors (nIRCats) dataset of acute mouse brain tissue across three age groups (4, 8.5, and 12 weeks), focusing on the dorsolateral (DLS) and dorsomedial striatum (DMS). 251 image frames from the dataset were analyzed to extract features for training a CatBoost regression model. To enhance speed while maintaining much of the predictive accuracy, the model was distilled into a kernelized Ridge regression model. Results: The model achieved validation Mean Squared Error (MSE) of 0.004 and R² value of 0.79. When the acceptable prediction range was expanded to include values within ±10% of the actual DA release and mouse age, model performance improved to a validation MSE of 0.001 and R² value of 0.97. Conclusions: These results demonstrate that the proposed approach can accurately and automatically predict spatial and age-dependent dopamine dynamics; a crucial requirement for optimizing deep brain stimulation therapies for neurodegenerative disorders such as Parkinson’s disease (PD) and depression. Full article

Autonomous driving in dense urban environments requires accurate trajectory forecasting supported by interpretable contextual evidence. This study presents a multimodal framework that performs driving scene context (DSC)-aware trajectory prediction while providing risk-aware explanations to reveal the contextual cues behind predicted motion. The framework integrates temporal object states—trajectories, velocities, yaw angles, and motion status—with semantic information from forward-facing camera imagery, and is composed of four modules: object behavioral feature extraction, scene context extraction, DSC-augmented trajectory prediction, and risk-aware reasoning using a multimodal large language model (MLLM). Experiments on the Rank2Tell dataset demonstrate the feasibility and applicability of the proposed approach, achieving an ADE of 10.972, an FDE of 13.701, and an RMSE of 8.782. Additional qualitative evaluation shows that DeepSeek-R1-Distill-Qwen-7B generates the most coherent and contextually aligned explanations among the tested models. These findings indicate that combining DSC-aware prediction with interpretable reasoning provides a practical and transparent solution for autonomous driving in complex urban environments. Full article

This paper presents AdaLite, a knowledge distillation framework for monocular depth estimation designed for efficient deployment on resource-limited devices, without relying on quantization or pruning. While large-scale depth estimation networks achieve high accuracy, their computational and memory demands hinder real-time use. To address this problem, a large model is adopted as a teacher, and a compact encoder–decoder student with few trainable parameters is trained under a dual-supervision scheme that aligns its predictions with both teacher feature maps and ground-truth depths. AdaLite is evaluated on the NYUv2, SUN-RGBD and KITTI benchmarks using standard depth metrics and deployment-oriented measures, including inference latency. The distilled model achieves a 94% reduction in size and reaches 1.02 FPS on a Raspberry Pi 2 (2 GB CPU), while preserving 96.8% of the teacher’s accuracy (${\delta }_1$) and providing over 11× faster inference. These results demonstrate the effectiveness of distillation-driven compression for real-time depth estimation in resource-limited environments. The code is publically available. Full article

This study utilized rapeseed straw as the raw material and employed a completely randomized design with four treatments: a distilled water control (CK), individual supplementation of Lactiplantibacillus plantarum (1.0 × 10⁶ CFU/g fresh weight) (Lp), individual supplementation of xylanase (50,000 U/g fresh weight) (XY), and a combined bacterium–enzyme treatment (XYLp). Each treatment was replicated five times, vacuum-sealed, and fermented at 25 °C for 60 days to systematically evaluate the effects of different treatments on the fermentation quality, nutritional composition, and microbial community structure of rapeseed straw silage. The results demonstrated that, compared with the CK group, all additive treatments significantly decreased pH and increased lactic acid (LA) content (p < 0.05). Among them, the Lp group exhibited the lowest pH value (4.27), which was significantly lower than all other treatments except XYLp (p < 0.05). Both the Lp and XYLp groups showed significantly higher LA content than the other groups (p < 0.05). Crude protein (CP) content was significantly higher in all additive treatments than in the CK group (p < 0.05). The XYLp group exhibited the most substantial fiber degradation, with acid detergent fiber (ADF) and neutral detergent fiber (NDF) contents being significantly lower than CK and reaching the lowest values among all treatments (p < 0.05). Both the XY and XYLp groups showed significantly lower hemicellulose and holocellulose contents compared to the CK and Lp groups (p < 0.05). Microbial community analysis revealed that the synergistic bacterium–enzyme treatment significantly enriched fibrolytic genera, including Kosakonia and Pediococcus, and upregulated the expression of key fibrolytic enzymes such as cellulase (EC: 3.2.1.4), β-glucosidase (EC: 3.2.1.21), and endo-1,4-β-xylanase (EC: 3.2.1.8). Functional prediction further indicated that the bacterial–enzyme synergy enhanced fibrous structure degradation and fermentable substrate release by activating carbohydrate metabolism pathways and bacterial secretion systems. These findings suggest that the combined application of Lactiplantibacillus plantarum and xylanase has the potential to be a promising strategy for enhancing fiber degradation and overall fermentation quality in rapeseed straw silage. Full article

Accurate forecasting in heterogeneous spatiotemporal environments requires models that are both generalizable and interpretable, while also preserving cross-scale symmetry between temporal and spatial patterns. Existing deep learning approaches often struggle with limited adaptability to data-scarce regions and lack transparency in capturing cross-scale causal factors. To address these challenges, we propose a novel framework, Cross-Scale Symmetry-Aware Causal Spatiotemporal Modeling with Adaptive Fusion and Region-Knowledge Transfer, which integrates three key innovations. First, a Dynamic Spatio-Temporal Fusion Framework (DSTFF) leverages frequency-aware temporal transformations and adaptive graph attention to capture complex multi-scale dependencies, ensuring temporal–spatial symmetry in representation learning. Second, a Region-Knowledge Enhanced Transfer Learning (RKETL) mechanism distills knowledge across regions through teacher–student distillation, graph-based embeddings, and meta-learning initialization, thereby maintaining structural symmetry between data-rich and data-scarce regions. Third, a Multi-Granularity Causal Inference Prediction Module (MCIPM) uncovers cross-scale causal structures and supports counterfactual reasoning, providing causal symmetry across daily, weekly, and monthly horizons. Comprehensive experiments on multi-regional logistics datasets from China and the U.S. validate the effectiveness of our approach. Across six diverse Chinese regions, our method consistently outperforms state-of-the-art baselines (e.g., PatchTST, TimesNet, FEDformer), reducing MAE by 18.5% to 27.4%. On the U.S. Freight dataset, our model achieves significant performance gains with stable long-horizon accuracy, confirming its strong cross-domain generalization. Few-shot experiments further demonstrate that with only 5% of training data, our framework surpasses the best baseline trained with 20% data. Robustness analyses under input perturbations and uncertainty quantification show that the model maintains low error variance and produces well-calibrated prediction intervals. Furthermore, interpretability is concretely realized through MCIPM, which visualizes the learned causal graphs and quantifies each regional factor’s contribution to forecasting outcomes. This causal interpretability enables transparent understanding of how temporal spatial dynamics interact across scales, supporting actionable decision-making in logistics management and policy planning. Overall, this work contributes a unified spatiotemporal learning framework that leverages symmetry principles across scales and regions to enhance interpretability, transferability, and forecasting accuracy. Full article