Atopic dermatitis (AD) is a chronic inflammatory skin disorder that is significantly contributed to by epigenetics. We developed a machine learning-based framework to identify DNA methylation biomarkers associated with AD classification and severity. Genome-wide methylation data from peripheral blood were processed using four feature selection algorithms: coarse approximation linear function (CALF), elastic net (EN), minimum redundancy maximum relevance (mRMR), and recursive feature elimination with cross-validation (RFECV). The integrative framework identified a central panel of 8 CpG sites that achieved an area under the curve (AUC) of 1.00 in the test set. This panel demonstrated high disease specificity, showing poor classification performance for systemic lupus erythematosus (AUC = 0.46), Crohn’s disease (AUC = 0.50), and oral squamous cell carcinoma (AUC = 0.58). Severity prediction using RFECV-selected 63 CpG sites (RFE63) achieved high accuracy across classifiers, with Random Forest (accuracy = 0.94) outperforming the others. The functional enrichment of CpG-associated genes highlighted key immune-related transcriptional regulators, including STAT5A, RUNX1, MEIS1, and PAX4. These genes are linked to chromatin remodeling, T helper cell differentiation, and interleukin-2 regulation, which are critical in AD pathogenesis and severity. Our findings demonstrate the utility of machine learning-integrated epigenomics in identifying robust, disease-specific biomarkers for AD diagnosis and monitoring, offering new insights into the molecular mechanisms underlying childhood AD. However, further validation in large-scale independent cohorts is required to confirm their clinical robustness and generalizability.

Machine translation with large language models has recently attracted growing attention due to its flexibility and strong zero-shot and few-shot capabilities. However, most prompt-based LLM translation methods rely on linear generation or shallow self-refinement, implicitly committing to a single reasoning path. Such designs are brittle when translating long and syntactically complex sources, where reliable translation often requires structured planning and hypothesis exploration. In this paper, we propose TransGoT, a novel machine translation framework inspired by the graph-of-thoughts paradigm, which formulates translation as a structured, multi-stage reasoning process over a graph of intermediate thoughts. TransGoT explicitly decomposes translation into constraint identification, draft generation, and culture- and style-aware refinement, enabling systematic exploration and aggregation of alternative translation hypotheses. To better adapt graph-based reasoning to translation, we design two key mechanisms: (1) Uncertainty-driven thought transformation. Unlike general reasoning tasks, translation uncertainty is often localized and unevenly distributed across tokens, making holistic regeneration inefficient. We therefore design uncertainty-driven thought transformation, which leverages model-internal confidence signals to guide targeted token-level revision; (2) Dispersion-adaptive thought scoring. It emphasizes evaluation criteria with stronger inter-candidate variance to enable robust multi-criteria thought selection. We evaluate TransGoT on the WMT22 benchmarks and experimental results demonstrate that TransGoT consistently outperforms strong LLM-based translation baselines, validating the effectiveness of structured graph-based reasoning for machine translation.

Large Language Model (LLM) inference engines are becoming critical system infrastructure, yet their increasing architectural complexity makes defects difficult to be diagnosed and repaired. Existing reliability studies predominantly focus on model behavior or training frameworks, leaving inference engine bugs underexplored, especially in settings where execution-based debugging is impractical. We present a static, issue-centric approach for automated root cause analysis and repair suggestion generation for LLM inference engines. Based solely on issue reports and developer discussions, we construct a real-world defect dataset and annotate each issue with a semantic root cause category and affected system module. Leveraging text-based representations, our framework performs root cause classification and coarse-grained module localization without requiring code execution or specialized runtime environments. We further integrate structured repair patterns with a large language model to generate interpretable and actionable repair suggestions. Experiments on real-world issues concerning vLLMs demonstrate that our approach achieves effective root cause identification and module localization under limited and imbalanced data. A cross-engine evaluation further shows promising generalization to TensorRT-LLM. Human evaluation confirms that the generated repair suggestions are correct, useful, and clearly expressed. Our results indicate that static, issue-level analysis is a viable foundation for scalable debugging assistance in LLM inference engines. This work highlights the feasibility of static, issue-level defect analysis for complex LLM inference engines and explores automated debugging assistance techniques. The dataset and implementation will be publicly released to facilitate future research.

The enhanced long-range navigation (eLoran) system serves as an important backup method for the global navigation satellite system (GNSS) system. In long-distance transmission scenarios, the signal propagation delay of the eLoran system is affected by fluctuations in meteorological factors along the path. Regarding these issues, such as the potential timing system errors caused by meteorological factors and the limitation on the accuracy of the timing system, in this paper, an innovative prediction model is proposed to predict the propagation delay data by fusing the propagation delay data of multiple differential reference stations on the path and the path-weighted meteorological data. By collecting and processing actual data, four types of prediction tasks were designed. Comparative analyses of the prediction performance of eight common models were conducted on a unified dataset. The results show that the Pucheng–Zhengzhou path-weighted ten-factor back-propagation neural network (PZWT-BPNN) model performs the best, achieving a balance between prediction accuracy and training efficiency. This model effectively suppresses the timing errors caused by meteorological fluctuations and improves the prediction accuracy of the propagation delay of the system, providing corresponding technical support for key fields such as low-altitude economy and transportation.

In logistics systems, the organization of information retrieval plays a key role in human interaction with technical systems to ensure decision-making speed, route optimization, planning, and resource allocation. At the same time, the efficiency of the logistics system when simultaneously processing large volumes of data and constantly updating it is determined by the speed of processing user requests and the accuracy of the responses provided by the system. Within the retrieval-augmented generation architecture, a hybrid information retrieval method has been proposed, based on the combined use of a vector-graph data representation structure and large language model. Experiments showed that the hybrid method achieved best accuracy rates of 0.24–0.25 (among all considered methods) with enhanced scalability capabilities (when the number of nodes increases fourfold, the time increases only twofold—from 0.09 s to 0.20 s) due to the limitation of the graph traversal area when implementing the graph component of the hybrid search. An optimal range of 30–50 nodes to be traversed was also identified, balancing precision and query processing speed. The findings are of practical value to logistics system developers and supply chain managers aiming to implement high-precision, natural language-based information retrieval in dynamic operational environments.

Renewable energy sources like wind turbines and solar panels are integrated into modern power grids as Distributed Energy Resources (DERs). These DERs can operate independently or as part of microgrids. Interconnecting multiple microgrids creates Networked Microgrids (NMGs) that increase reliability, resilience, and independent power generation. However, the trustworthiness of individual DERs remains a critical challenge in NMGs, particularly when integrating previously deployed or geographically distributed units managed by entities with varying expertise. Assessing DER trustworthiness ensuring reliability and security is essential to prevent system-wide instability. Thisresearch addresses this challenge by proposing a lightweight trust metric generation system capable of processing structured and semi-structured DER data to produce key trust indicators. The system employs a Small Language Model (SLM) with approximately 16 million parameters for textual data understanding and metric extraction, followed by a regression head to output bounded trust scores. Designed for deployment in computationally constrained environments, the SLM requires only 64.6 MB of disk space and 200–250 MB of memory that is significantly lesser than larger models such as DeepSeek R1, Gemma-2, and Phi-3, which demand 3–12 GB. Experimental results demonstrate that the SLM achieves high correlation and low mean error across all trust metrics while outperforming larger models in efficiency. When integrated into a full neural network-based trust framework, the generated metrics enable accurate prediction of DER trustworthiness. These findings highlight the potential of lightweight SLMs for reliable and resource-efficient trust assessment in NMGs, supporting resilient and sustainable energy systems in smart cities.

AI-based audio generation has advanced rapidly, enabling deepfake audio to reach levels of naturalness that closely resemble real recordings and complicate the distinction between authentic and synthetic signals. While numerous CNN- and Transformer-based detection approaches have been proposed, most adopt a model-centric perspective in which the spectral representation remains fixed. Parallel data-centric efforts have explored alternative representations such as scalograms and CQT, yet the field still lacks a unified framework that jointly evaluates the influence of model architecture, its hyperparameters (e.g., learning rate, number of epochs), and the spectral representation along with its own parameters (e.g., representation type, window size). Moreover, there is no standardized approach for benchmarking custom architectures against established baselines under consistent experimental conditions. FakeVoiceFinder addresses this gap by providing a systematic framework that enables direct comparison of model-centric, data-centric, and hybrid evaluation strategies. It supports controlled experimentation, flexible configuration of models and representations, and comprehensive performance reporting tailored to the detection task. This framework enhances reproducibility and helps clarify how architectural and representational choices interact in synthetic audio detection.

AI enhances aquatic resource management by automating species detection, optimizing feed, forecasting water quality, protecting species interactions, and strengthening the detection of illegal, unreported, and unregulated fishing activities. However, these advancements are inconsistently employed, subject to domain shifts, limited by the availability of labeled data, and poorly benchmarked across operational contexts. Recent developments in technology and applications in fisheries genetics and monitoring, precision aquaculture, management, and sensing infrastructure are summarized in this paper. We studied automated species recognition, genomic trait inference, environmental DNA metabarcoding, acoustic analysis, and trait-based population modeling in fisheries genetics and monitoring. We used digital-twin frameworks for supervised learning in feed optimization, reinforcement learning for water quality control, vision-based welfare monitoring, and harvest forecasting in aquaculture. We explored automatic identification system trajectory analysis for illicit fishing detection, global effort mapping, electronic bycatch monitoring, protected species tracking, and multi-sensor vessel surveillance in fisheries management. Acoustic echogram automation, convolutional neural network-based fish detection, edge-computing architectures, and marine-domain foundation models are foundational developments in sensing infrastructure. Implementation challenges include performance degradation across habitat and seasonal transitions, insufficient standardized multi-region datasets for rare and protected taxa, inadequate incorporation of model uncertainty into management decisions, and structural inequalities in data access and technology adoption among smallholder producers. Standardized multi-region benchmarks with rare-taxa coverage, calibrated uncertainty quantification in assessment and control systems, domain-robust energy-efficient algorithms, and privacy-preserving data partnerships are our priorities. These integrated priorities enable transition from experimental prototypes to a reliable, collaborative infrastructure for sustainable wild capture and farmed aquatic systems.

Real-time fine-grained human activity recognition (HAR) remains a challenging problem due to rapid spatial–temporal variations, subtle motion differences, and dynamic environmental conditions. Addressing this difficulty, we propose NovAc-DL, a unified deep learning framework designed to accurately classify short human-like actions, specifically, “pour” and “stir” from sequential video data. The framework integrates adaptive time-distributed convolutional encoding with temporal reasoning modules to enable robust recognition under realistic robotic-interaction conditions. A balanced dataset of 2000 videos was curated and processed through a consistent spatiotemporal pipeline. Three architectures, LRCN, CNN-TD, and ConvLSTM, were systematically evaluated. CNN-TD achieved the best performance, reaching 98.68% accuracy with the lowest test loss (0.0236), outperforming the other models in convergence speed, generalization, and computational efficiency. Grad-CAM visualizations further confirm that NovAc-DL reliably attends to motion-salient regions relevant to pouring and stirring gestures. These results establish NovAc-DL as a high-precision real-time-capable solution for deployment in healthcare monitoring, industrial automation, and collaborative robotics.

This paper presents an in-production Rhetorical Role Labeling (RRL) classifier developed for Hungarian judicial decisions. RRL is a sequential classification problem in Natural Language Processing, aiming to assign functional roles (such as facts, arguments, decision, etc.) to every segment or sentence in a legal document. The study was conducted on a human-annotated sentence-level RRL corpus and compares multiple neural architectures, including BiLSTM, attention-based networks, and a support vector machine as baseline. It further investigates the impact of late chunking during vectorization, in contrast to classical approaches. Results from tests on the labeled dataset and annotator agreement statistics are reported, and performance is analyzed across architecture types and embedding strategies. Contrary to recent findings in retrieval tasks, late chunking does not show consistent improvements for sentence-level RRL, suggesting that contextualization through chunk embeddings may introduce noise rather than useful context in Hungarian legal judgments. The work also discusses the unique structure and labeling challenges of Hungarian cases compared to international datasets and provides empirical insights for future legal NLP research in non-English court decisions.