Search Results (138)

Generative image steganography is a key technology for secure information transmission, but existing deep learning-based generative steganographic methods suffer from an extremely high bit error rate (BER) and degraded steganographic image quality in low-bit-rate embedding tasks in which secret information needs duplication or padding to match the model input size. In addition, it is difficult to balance BER reduction and imperceptibility of stego-images. To address these issues, this paper proposes a novel generative image steganography algorithm based on flip watermarking, with the core novelty of designing a mirror flipping preprocessing mechanism to achieve a redundant watermark and eliminate information errors caused by duplication or padding, and constructing an end-to-end Mini-Hide steganographic framework to integrate flip watermarking with generative steganography for the first time. Specifically, the proposed method first converts the binary bitstream of secret information into a square matrix, and performs vertical, horizontal and vertical–horizontal mirror flipping on the matrix to form a redundant basic watermark, which is then expanded to a secret image with the same size as the cover image. After that, the secret image is preprocessed by a preparation network and then input into an encoding network together with the cover image to generate a stego-image. Finally, the generated stego-image is input into the decoding network to extract the secret image. Subsequently, the inverse operation of flip watermarking is performed on the extracted secret image to recover the original binary bitstream. Extensive experiments are conducted on the public COCO dataset ($256\times 256$ pixels) with BER, PSNR, and SSIM, and the proposed method is compared with state-of-the-art generative steganographic methods. Quantitative results show that the proposed method achieves a $0\%$ BER for secret information of $8\times 8$ to $64\times 64$ bits, and the BER is only $0.00002\%$ for $256\times 256$-bit secret information; the PSNR of stego-images reaches 37.75 dB, and the SSIM hits 0.96, which are 7.07 dB and 0.02 higher than those of the classic HiDDeN method ($64\times 64$ bit) respectively. We also validated the flip watermark module by integrating into other methods; the results also show that the PSNR of FNNS-D is improved by 13.12 dB ($256\times 256$), and the BER of SteganoGAN is reduced by $99.99\%$ ($256\times 256$ bit). In addition, the proposed method breaks the embedding size limit of HiDDeN (≤$64\times 64$ bit) and supports up to $256\times 256$-bit secret information embedding with stable performance. This work significantly reduces the BER of generative image steganography while improving the visual quality of stego-images, provides a new preprocessing and optimization scheme for low-BER generative steganographic algorithm design, and also offers a universal lightweight module for performance improvement of existing steganographic methods, which has important theoretical and practical significance for enhancing the security and reliability of covert information transmission in the field of information security. Full article

Reliable and up-to-date measurements of public space remain scarce in small and medium-sized towns (SMSTs), where conventional geospatial datasets are often outdated, inconsistent, or inaccessible. This study presents a low-cost and fully reproducible computational pipeline that integrates nadir RGB imagery captured by a DJI Mini 3 UAV with a lightweight instance-segmentation model (Ultralytics YOLOv12-seg) and GIS-based post-processing to derive class-specific surface indicators at the neighborhood scale. The workflow consists of four components: autonomous UAV acquisition over three representative zones of Sesquilé, Colombia; planar mosaic generation and georeferencing using ad hoc ground control points; fine-tuning of a YOLOv12-seg model trained on locally annotated images; and transformation of predicted masks into OSM and GeoPackage geometries for metric analysis. The trained model achieved stable convergence with mask mAP50 ≈ 0.85 and mAP50–95 ≈ 0.70, supported by balanced precision–recall behavior across classes. Spatial outputs exhibit coherent morphological contrasts between the analyzed zones. Buildings occupy 48.17% of the mapped area, vegetation 25.88%, and transport- and plaza-related public space (roadways, sidewalks, and hardscape areas) 25.95%. These proportions capture a clear gradient from a dense urban core to less consolidated peripheral sectors. Results demonstrate that very-high-resolution UAV imagery, combined with open-source deep-learning tools and structured GIS post-processing, can reliably produce operational public-space indicators for SMSTs at low cost. The methodology provides an accessible and scalable framework for evidence-based urban assessment in municipalities with limited technical and financial resources. Full article

The low-altitude airspace of bird flocks is gradually shared by unmanned aerial vehicles (UAVs), posing safety risks that necessitate accurate trajectory forecasting. However, existing vision-based methods often treat trajectory prediction and UAV detection as separate tasks, assume light-tailed Gaussian noise, and rely on heavy backbones. These limitations, when applied to bird trajectory forecasting, limit uncertainty calibration and embedded deployment in ground-based monocular surveillance. In this work, we propose a unified framework for low-altitude monitoring. Its core, Mini-BirdFormer, combines a lightweight Transformer encoder with a Student-t mixture density head to model heavy-tailed flight dynamics and produce calibrated uncertainty. Experiments on a real-world dataset show the model achieves strong long-horizon performance with only 1.05 million parameters, attaining a minADE of 0.785 m and reducing negative log-likelihood from 1.25 to −2.01 (lower is better) compared with a Gaussian Long Short-Term Memory (LSTM) baseline. Crucially, it enables low-latency inference on resource-constrained platforms at 616 FPS. Additionally, a system-level extension supports zero-shot UAV detection via open-vocabulary learning, attaining 92% recall without false alarms. Results demonstrate that combining heavy-tailed probabilistic modeling with a compact backbone provides a practical, deployable approach for monitoring shared airspace. Full article

The regulatory framework governing EU electricity markets is highly complex, fragmented across multiple normative acts and sensitive to citation accuracy and contextual completeness. While Large Language Models (LLMs) offer promising capabilities for regulatory question answering (QA), their tendency to hallucinate legal references and omit critical conditions makes them unreliable for compliance-sensitive domains. This paper presents the design of a domain-specific Retrieval-Augmented Generation (RAG) system for EU electricity market regulations, explicitly engineered to deliver source-grounded, traceable and low-hallucination answers. The answering component is based on Google’s gemini-2.5-flash model. The Open AI’s gpt-4o-mini model is responsible for both relevant document selection before building the RAG prompt and playing the judge LLM role for Retrieval Augmented Generation Assessment (RAGAS) evaluation. We build a legal corpus comprising multiple core EU regulatory acts related to REMIT and market operation and propose a regulatory QA architecture that integrates: (i) three chunking strategies (article-based, structure-aware, sliding window), (ii) two embedding models and (iii) a novel LLM-based document selection agent that restricts retrieval to the most relevant normative acts before vector search, improving contextual focus and retrieval precision. Using a fixed benchmark of regulatory questions and a reproducible evaluation protocol, we quantitatively assess system performance with RAGAS metrics and classical information-retrieval measures. While all configurations achieve strong faithfulness (up to 0.96), answer relevancy varies substantially with embedding and chunking choices. The findings confirm that retrieval engineering, particularly embedding selection, chunking strategy and pre-retrieval document filtering, has a high impact for building reliable regulatory AI systems. The sliding window strategy combined with bge-small-en-v1.5 delivered the strongest rank-sensitive retrieval performance, achieving the highest Precision@10 and NDCG@10. In contrast, article-level chunking with the same model yielded a modest improvement in Recall@10, indicating a clear trade-off between recall and precision-oriented ranking quality in legal corpora. Full article

KANECS is a 3D multigroup neutronics code based on the Simplified Spherical Harmonics (SP_N) approximation and the Continuous Galerkin Finite Element Method (CGFEM). In this work, the code is extended to solve the time-dependent neutron kinetics by implementing a fully implicit backward Euler scheme for the neutron transport equation and an implicit exponential integration for delayed neutron precursors. These schemes ensure unconditional stability and minimize temporal discretization errors, making the method suitable for fast transients. The new formulation transforms each time step into a transient fixed-source problem, which is solved efficiently using the GMRES solver with ILU preconditioning. The kinetics module is validated against established benchmark problems, including TWIGL, the C5G2 MOX benchmark, and both 2D and 3D mini-core rod-ejection transients. KANECS shows close agreement with the reference solutions from well-known neutron transport codes, with consistent accuracy in normalized power evolution, spatial power distributions, and steady-state eigenvalues. The results confirm that KANECS provides a reliable and accurate framework for solving neutron kinetics problems. Full article

Hyperspectral reconstruction (SR) refers to the computational process of generating high-dimensional hyperspectral images (HSI) from low-dimensional observations. However, the superior performance of most supervised learning-based reconstruction algorithms is predicated on the availability of fully labeled three-dimensional data. In practice, this requirement demands complex optical paths with dual high-precision registrations and stringent calibration. To address this gap, we extend the fully supervised paradigm to a semi-supervised setting and propose SSHSR, a semi-supervised SR method for scenarios with limited spectral annotations. The core idea is to leverage spectrally aware mini-patches (SA-MP) as guidance and form region-level supervision from averaged spectra, so it can learn high-quality reconstruction without dense pixel-wise labels over the entire image. To improve reconstruction accuracy, we replace the conventional fixed-form Tikhonov physical layer with an optimizable version, which is then jointly trained with the deep network in an end-to-end manner. This enables the collaborative optimization of physical constraints and data-driven learning, thereby explicitly introducing learnable physical priors into the network. We also adopt a reconstruction network that combines spectral attention with spatial attention to strengthen spectral–spatial feature fusion and recover fine spectral details. Experimental results demonstrate that SSHSR outperforms existing state-of-the-art (SOTA) methods on several publicly available benchmark datasets, as well as on remote sensing and real-world scene data. On the GDFC remote sensing dataset, our method yields a 6.8% gain in PSNR and a 22.1% reduction in SAM. Furthermore, on our self-collected real-world scene dataset, our SSHSR achieves a 6.0% improvement in PSNR and a 11.9% decrease in SAM, confirming its effectiveness under practical conditions. Additionally, the model has only 1.59 M parameters, which makes it more lightweight than MST++ (1.62 M). This reduction in parameters lowers the deployment threshold while maintaining performance advantages, demonstrating its feasibility and practical value for real-world applications. Full article

Objectives: This study presents the development of a bilingual, expert-evaluated question–answer (Q&A) dataset, named PMR-Q&A, designed for training large language models (LLMs) in the field of Physical Medicine and Rehabilitation (PMR). Methods: The dataset was created through a systematic and semi-automated framework that converts unstructured scientific texts into structured Q&A pairs. Source materials included eight core reference books, 2310 academic publications, and 323 theses covering 15 disease categories commonly encountered in PMR clinical practice. Texts were digitized using layout-aware optical character recognition (OCR), semantically segmented, and distilled through a two-pass LLM strategy employing GPT-4.1 and GPT-4.1-mini models. Results: The resulting dataset consists of 143,712 bilingual Q&A pairs, each annotated with metadata including disease category, reference source, and keywords. A representative subset of 3000 Q&A pairs was extracted for expert validation to evaluate the dataset’s reliability and representativeness. Statistical analyses showed that the validation sample accurately reflected the thematic and linguistic structure of the full dataset, with an average score of 1.90. Conclusions: The PMR-Q&A dataset is a structured and expert-evaluated resource for developing and fine-tuning domain-specific large language models, supporting research and educational efforts in the field of physical medicine and rehabilitation. Full article

Selenoprotein N (SelN or SELENON) is a selenium-containing protein of the endoplasmic/sarcoplasmic reticulum (ER/SR), encoded by the SEPN1 gene. In skeletal muscle, SelN is particularly important for regulating SR calcium homeostasis. It acts as a calcium sensor, modulating the activity of the sarcoplasmic reticulum calcium pump (SERCA) through a redox-dependent mechanism. Loss-of-function mutations in the SEPN1 gene give rise to a spectrum of skeletal muscle disorders collectively referred to as SEPN1-related myopathies (SEPN1-RM). Histopathologically, SEPN1-RM is characterized by the presence of minicores, which are localized regions within muscle fibers exhibiting mitochondrial depletion (i.e., cores) and sarcomeric disarray. As no effective therapy is currently available for SEPN1-RM, understanding SelN biology through loss-of-function models remains essential for elucidating disease mechanisms and identifying potential therapeutic targets. This review examines the current knowledge on SelN function and the pathological mechanisms underlying SEPN1 loss-of-function, with a particular focus on the connection between calcium handling, oxidative/ER stress, and muscle dysfunction. It also highlights emerging strategies aimed at restoring SelN activity or mitigating downstream defects, outlining potential therapeutic avenues for SEPN1-RM. Full article

High-entropy alloys (HEAs) present a vast compositional design space, characterized by four core effects—high configurational entropy, sluggish diffusion, severe lattice distortion, and the cocktail effect—which collectively underpin their exceptional potential for both structural and hydrogen storage applications. This mini-review synthesizes recent advances in the compositional design of HEAs with emphasis on structural materials and hydrogen storage. Firstly, it provides an overview of the definition of HEAs and the roles of principal alloying elements, then synthesizes solid solution formation rules based on representative descriptors—atomic size mismatch, electronegativity difference, valence electron concentration, mixing enthalpy, and mixing entropy—together with their applicability limits and common failure scenarios. A brief introduction is provided to the preparation methods of arc melting and powder metallurgy, which have a strong interaction with the composition. The design–structure–property links are then consolidated for structural materials (mechanical properties) and for hydrogen storage materials (hydrogen storage performance). Furthermore, the rules for the combined design of control systems for HEAs and the associated challenges were further discussed, and the future development prospects of HEAs in structural materials and hydrogen storage were also envisioned. Full article

Hand rehabilitation requires consistent, repetitive exercises that can often reduce patient motivation, especially in home-based therapy. This study introduces ReHAb Playground, a deep learning-based system that merges real-time gesture recognition with 3D hand tracking to create an engaging and adaptable rehabilitation experience built in the Unity Game Engine. The system utilizes a YOLOv10n model for hand gesture classification and MediaPipe Hands for 3D hand landmark extraction. Three mini-games were developed to target specific motor and cognitive functions: Cube Grab, Coin Collection, and Simon Says. Key gameplay parameters, namely repetitions, time limits, and gestures, can be tuned according to therapeutic protocols. Experiments with healthy participants were conducted to establish reference performance ranges based on average completion times and standard deviations. The results showed a consistent decrease in both task completion and gesture times across trials, indicating learning effects and improved control of gesture-based interactions. The most pronounced improvement was observed in the more complex Coin Collection task, confirming the system’s ability to support skill acquisition and engagement in rehabilitation-oriented activities. ReHAb Playground was conceived with modularity and scalability at its core, enabling the seamless integration of additional exercises, gesture libraries, and adaptive difficulty mechanisms. While preliminary, the findings highlight its promise as an accessible, low-cost rehabilitation platform suitable for home use, capable of monitoring motor progress over time and enhancing patient adherence through engaging, game-based interactions. Future developments will focus on clinical validation with patient populations and the implementation of adaptive feedback strategies to further personalize the rehabilitation process. Full article

Ryanodine receptor 1-related myopathies (RYR1-RM) are caused by RYR1 gene variants and comprise a wide spectrum of histopathological manifestations. Here, we focus on patients carrying RYR1 variants and muscle histopathology consistent with central core disease (CCD) or multi-minicore disease (MmD). RNA-sequencing analyses of skeletal muscle biopsies obtained from both CCD and MmD patients and from healthy controls were performed to better understand the molecular pathways activated by RYR1 variants. Our analyses revealed that, beyond the well-established role of RYR1 in calcium homeostasis, broader cellular pathways are implicated. In CCD, differentially expressed genes were enriched for pathways related to oxidative stress response, SMAD signalling, and apoptosis, consistent with the role of intracellular calcium dysregulation in promoting mitochondrial dysfunction and cell death. In contrast, MmD patients exhibited enrichment of pathways related to immune activation. This was corroborated by the upregulation of GTPase-regulating genes and the down-regulation of transcriptional repressors such as ZFP36 and ATN1. When considering all RYR1-RM patients collectively, Wnt signalling, immune-related pathways, and oxidative phosphorylation emerged as shared enriched pathways, indicating possible convergent mechanisms across histopathological phenotypes. Our study suggests that complex gene regulation driven by RYR1 variants may be a unifying feature in CCD and MmD, offering new insight into potential therapeutic targets. Full article

Background: Although the participation of children with autism spectrum disorder (ASD) in team sports presents challenges, group-based physical activities could offer specific benefits for their core symptoms. Therefore, the aim of this systematic review was to analyze the benefits of mini-basketball for children with ASD. Methods: A systematic review was conducted following PRISMA guidelines and was registered in PROSPERO (CRD420251144800). Four databases (Web of Science, SPORTDiscus, PubMed, and Scopus) were searched to select randomized controlled trials reporting the effects of mini-basketball interventions on children with ASD from their inception to August 2025. Results: Eight randomized controlled trials involving 436 participants (aged 3–12 years, 87.3% male) met the inclusion criteria. All studies were conducted in China using 12-week interventions (40–45 min, 2–5 days/week at moderate intensity). The quality was rated as good in two studies and fair in six. Five studies assessed social responsiveness, with four showing significant pre–post reductions in the experimental groups and all demonstrating superior outcomes versus those of the controls. One study reported significant reductions in repetitive behaviors, self-injurious behaviors, and restricted behaviors compared to that of the controls. Joint attention improvements were observed through eye-tracking measures, with increased fixation counts, shorter time to first fixation, and more accurate gaze shifts. Physical fitness benefits included improved shuttle run times and standing long jump performance. Finally, one study demonstrated better inhibition control and improvements in sleep quality, including increased sleep duration and efficiency. Conclusions: Mini-basketball interventions can improve social responsiveness and related outcomes in children with ASD. These findings support mini-basketball as a feasible, safe, and effective intervention that could be integrated with existing therapeutic approaches. Full article

The Priority-Flood algorithm, widely recognized for its computational efficiency in hydrological analysis, serves as the fundamental method for depression identification in DEMs, and the efficiency of the Priority-Flood algorithm hinges largely on the core component—priority queue implementation. Existing studies have focused predominantly on reducing the amount of data processed by queues, with few systematic reports on concrete queue implementations and corresponding performance analyses. In this study, six priority queues in the Priority-Flood algorithm are compared: a mini-heap (Heap), an AVL tree, a red-black tree (RBTree), a pairing heap (PairingHeap), a skip list (SkipList), and the Hash Heap (HHeap) structure proposed herein. Using multiscale DEM datasets as benchmarks, the results show that HHeap consistently outperforms the other structures across all scales, with particular advantages in ultralarge queues and in scenarios with high data duplication, rendering it the most effective choice for priority queues. The pairing heap approach typically ranks second in terms of overall runtime, whereas the AVL tree exhibits stable performance across scales; min-heap shows pronounced weaknesses under large-scale data conditions. This study provides empirical evidence to guide efficient priority queue selection and implementation and offers a viable technical pathway for ultralarge-scale terrain analysis. Future work will explore integrating HHeap with learning-based sorting and parallelization to further enhance processing performance and robustness in massive DEM contexts. Full article

Background: Neurodegenerative diseases, including spastic paraplegia type 11 (SPG11), are complex disorders characterized by progressive neurological decline and significant metabolic disturbances. Spatacsin, the protein encoded by the SPG11 gene, plays a critical role in autophagy and lysosomal homeostasis, which are essential for neuronal health. Its impairment leads to defective cellular clearance and neurodegeneration. Recently, personalized and precision nutrition have emerged as promising approaches to enhance clinical outcomes by tailoring dietary interventions to individual genetic, metabolic, and phenotypic profiles. Objectives: This mini scoping review aimed to synthesize current evidence on the application of personalized and precision nutrition in SPG11 and to explore how insights from related neurodegenerative diseases could inform the development of future dietary and metabolic interventions for this rare disorder. Methods: Following PRISMA-ScR guidelines, a scoping review was conducted using PubMed, Scopus, and Web of Science databases (2020–2024). Eligible studies included investigations addressing nutritional, genomic, or metabolic interventions in neurodegenerative diseases. Of 30 screened papers, nine met the inclusion criteria, primarily focusing on nutritional and metabolic interventions related to neurodegenerative and neuromuscular conditions. Results: To date, no dietary intervention trials have been conducted specifically for SPG11. However, evidence from studies on related neurodegenerative diseases suggests that antioxidant, mitochondrial-supportive, and microbiota-targeted dietary approaches may beneficially influence key pathological processes such as oxidative stress, lipid dysregulation, and autophagy—core mechanisms that are also central to SPG11 pathophysiology. Conclusions: Although current evidence remains preliminary, personalized nutrition is a promising supplementary strategy for managing neurodegenerative diseases, including SPG11. Future research should incorporate systems-based approaches that combine dietary, metabolic, and neuroimaging assessments, with sex and comorbidity-stratified analyses, multi-omics profiling, and predictive modeling. These frameworks could help design safe, effective, and personalized nutritional interventions aimed at enhancing metabolic resilience and slowing disease progression in SPG11. Full article

A multimodal interactive system, HortiVQA-PP, is proposed for horticultural scenarios, with the aim of achieving precise identification of pests and their natural predators, modeling ecological co-occurrence relationships, and providing intelligent question-answering services tailored to agricultural users. The system integrates three core modules: semantic segmentation, pest–predator co-occurrence detection, and knowledge-enhanced visual question answering. A multimodal dataset comprising 30 pest categories and 10 predator categories has been constructed, encompassing annotated images and corresponding question–answer pairs. In the semantic segmentation task, HortiVQA-PP outperformed existing models across all five evaluation metrics, achieving a precision of 89.6%, recall of 85.2%, F1-score of 87.3%, $mAP@50$ of 82.4%, and IoU of 75.1%, representing an average improvement of approximately 4.1% over the Segment Anything model. For the pest–predator co-occurrence matching task, the model attained a multi-label accuracy of 83.5%, a reduced Hamming Loss of 0.063, and a macro-F1 score of 79.4%, significantly surpassing methods such as ASL and ML-GCN, thereby demonstrating robust structural modeling capability. In the visual question answering task, the incorporation of a horticulture-specific knowledge graph enhanced the model’s reasoning ability. The system achieved 48.7% in BLEU-4, 54.8% in ROUGE-L, 43.3% in METEOR, 36.9% in exact match (EM), and a GPT expert score of 4.5, outperforming mainstream models including BLIP-2, Flamingo, and MiniGPT-4 across all metrics. Experimental results indicate that HortiVQA-PP exhibits strong recognition and interaction capabilities in complex pest scenarios, offering a high-precision, interpretable, and widely applicable artificial intelligence solution for digital horticulture. Full article