Search Results (18,795)

General large language models (LLMs) often suffer from semantic misinterpretation, information redundancy, and hallucinated content when applied to educational question-answering tasks. These issues hinder their effectiveness in supporting students’ specialized course learning and self-directed study. To address these challenges, this study proposes an intelligent tutoring model that integrates a knowledge graph with a large language model (KG-CQ). Focusing on the Data Structures (C Language) course, the model constructs a course-specific knowledge graph stored in a Neo4j graph database. It incorporates modules for knowledge retrieval, domain-specific question answering, and knowledge extraction, forming a closed-loop system designed to enhance semantic comprehension and domain adaptability. A total of 30 students majoring in Educational Technology at H University were randomly assigned to either an experimental group or a control group, with 15 students in each. The experimental group utilized the KG-CQ model during the answering process, while the control group relied on traditional learning methods. A total of 1515 data points were collected. Experimental results show that the KG-CQ model performs well in both answer accuracy and domain relevance, accompanied by high levels of student satisfaction. The model effectively promotes self-directed learning and provides a valuable reference for the development of knowledge-enhanced question-answering systems in educational settings. Full article

Preformed porous media (PPM) technology has emerged as a transformative approach to enhance heat and mass transfer in vacuum freeze-drying (VFD) of agricultural and food products. This review systematically analyzes recent advances in PPM research, with particular focus on spray freeze-drying (SFD) as the dominant technique for precision pore architecture control. Empirical studies confirm PPM’s efficacy: drying time reductions of 20–50% versus conventional VFD while improving product quality (e.g., 15% higher ginsenoside retention in ginseng, 90% enzyme activity preservation). Key innovations include gradient porous structures and multi-technology coupling strategies that fundamentally alter transfer mechanisms through: resistance mitigation via interconnected macropores (50–500 μm, 40–90% porosity), pseudo-convection effects enabling 30% faster vapor removal, and radiation enhancement boosting absorption by 40–60% and penetration depth 2–3 times. While inherent VFD limitations (e.g., low thermal conductivity) persist, we identify PPM-specific bottlenecks: precision regulation of pore structures (<5% size deviation), scalable fabrication of gradient architectures, synergy mechanisms in multi-field coupling (e.g., microwave-PPM interactions). The most promising advancements include 3D-printed gradient pores for customized transfer paths, intelligent monitoring-feedback systems, and multiscale modeling bridging pore-scale physics to macroscale kinetics. This review provides both a critical assessment of current progress and a forward-looking perspective to guide future research and industrial adoption of PPM-enhanced VFD. Full article

The optimization of beamforming in multi-base station (multi-BS) reconfigurable intelligent surface (RIS)-aided systems is a challenging task due to its high computational complexity. This paper first demonstrates that an optimized multi-BS system exhibits superior communication performance compared to a centralized large-scale single-BS system. To efficiently solve the complex beamforming problem in the multi-BS environment, this paper proposes a novel optimization solver based on a graph neural network (GNN) that models the physical structure of the system. Experimental results show that the proposed GNN solver finds solutions of higher quality, achieving a 42% performance increase with 45% less total computational complexity compared to a conventional iterative optimization method. Furthermore, when compared to other complex AI models such as transformer and Bi-LSTM, the proposed GNN achieves similar state-of-the-art performance while having less than 1% of the parameters and a fraction of the computational cost. These findings demonstrate that the GNN is a powerful, efficient, and practical solution for beamforming optimization in multi-BS RIS-aided systems, satisfying the demands for performance, computational efficiency, and model compactness. Full article

As technologies become increasingly diverse and complex, Intelligent Massage Systems (IMS) are evolving from traditional mechanically executed modes toward personalized and predictive health interventions. However, the field still lacks a unified grading standard for intelligence, making it difficult to quantitatively assess a system’s overall intelligence level. To address this gap, this paper proposes a task-driven six-level (L0–L5) classification framework and constructs a Massage-Driven Task (MDT) model that decomposes the massage process into six subtasks (S1–S6). Building on this, we design a three-dimensional evaluation scheme comprising a Functional Delegation Structure (FDS), an Anomaly Perception Mechanism (APM), and a Human–Machine Interaction Boundary (HMIB), and we select eight key performance indicators to quantify IMS intelligence across the perception–decision–actuation–feedback closed loop. We then determine indicator weights via the Delphi method and the Analytic Hierarchy Process (AHP), and obtain dimension-level scores and a composite intelligence score S0 using normalization and weighted aggregation. Threshold intervals for L0–L5 are defined through equal-interval partitioning combined with expert calibration, and sensitivity is verified on representative samples using ±10% data perturbations. Results show that, within typical error ranges, the proposed grading framework yields stable classification decisions and exhibits strong robustness. The framework not only provides the first reusable quantitative basis for grading IMS intelligence but also supports product design optimization, regulatory certification, and user selection. Full article

This study presents a novel cyber-resilient, data-driven optimisation framework for real-time energy management in electric vehicle (EV)-integrated smart grids. The proposed framework integrates a hybrid optimisation engine—combining genetic algorithms and reinforcement learning—with a real-time analytics module to enable adaptive scheduling under uncertainty. It accounts for dynamic electricity pricing, EV mobility patterns, and grid load fluctuations, dynamically reallocating charging demand in response to evolving grid conditions. Unlike existing GA/RL schedulers, this framework uniquely integrates adaptive optimisation with resilient forecasting under incomplete data and lightweight blockchain-inspired cyber-defence, thereby addressing efficiency, accuracy, and security simultaneously. To ensure secure and trustworthy EV–grid communication, a lightweight blockchain-inspired protocol is incorporated, supported by an intrusion detection system (IDS) for cyber-attack mitigation. Empirical evaluation using European smart grid datasets demonstrates a daily peak demand reduction of 9.6% (from 33 kWh to 29.8 kWh), with a 27% decrease in energy delivered at the original peak hour and a redistribution of demand that increases delivery at 19:00 h by nearly 25%. Station utilisation became more balanced, with weekly peak normalised utilisation falling from 1.0 to 0.7. The forecasting module achieved a mean absolute error (MAE) of 0.25 kWh and a mean absolute percentage error (MAPE) below 20% even with up to 25% missing data. Among tested models, CatBoost outperformed LightGBM and XGBoost with an RMSE of 0.853 kWh and $R^2$ of 0.416. The IDS achieved 94.1% accuracy, an AUC of 0.97, and detected attacks within 50–300 ms, maintaining over 74% detection accuracy under 50% novel attack scenarios. The optimisation runtime remained below 0.4 s even at five times the nominal dataset scale. Additionally, the study outlines a conceptual extension to support location-based planning of charging infrastructure. This proposes the alignment of infrastructure roll-out with forecasted demand to enhance spatial deployment efficiency. While not implemented in the current framework, this forward-looking integration highlights opportunities for synchronising infrastructure development with dynamic usage patterns. Collectively, the findings confirm that the proposed approach is technically robust, operationally feasible, and adaptable to the evolving demands of intelligent EV–smart grid systems. Full article

A smart irrigation system based on soil moisture sensors supported by photovoltaic energy is an innovation to address water use efficiency in the agricultural sector, especially in remote areas. This technology utilizes photovoltaic panels as a renewable energy source to operate water pumps, while soil moisture sensors provide real-time data that is used to automatically manage irrigation according to plant needs. This technology not only increases the efficiency of water and energy use but also supports environmental conservation by reducing dependence on fossil fuels. This research was conducted using a Systematic Literature Review (SLR) approach guided by the PRISMA framework to analyze trends, benefits, and challenges in implementing this technology. The analysis results show that this system offers various advantages, including energy efficiency, reduced carbon emissions, and ease of management through the integration of Internet of Things (IoT) technology. Several challenges remain, such as high initial investment costs, limited network access, and obstacles. Technical matters related to installation and maintenance. Various solutions have been proposed, including providing subsidies for small farmers, implementing radiofrequency modules, and using modular designs to simplify implementation. This study contributes to the development of a conceptual framework that can be adapted to various geographic and socio-economic conditions. Potential further developments include the integration of artificial intelligence and additional sensors to increase efficiency and support the sustainability of the agricultural sector globally. 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

This paper presents a modification of an image encryption algorithm combining chaos and the Fibonacci matrix by integrating artificial intelligence via a Generative Pre-Trained Transformer (GPT). The goal is to improve the robustness of the algorithm by dynamically adapting the parameters of the chaotic system and generating cryptographic keys based on image characteristics. The proposed methodology includes two main innovations: the implementation of GPT for automated generation of the initial parameters of the chaotic system, which allows for greater variability and security in encryption, and the use of GPT for dynamic determination of the Fibonacci Q-matrix, which provides additional complexity and increased resistance to attacks. The method is realized in the MATLAB (R2023a) environment through integration with OpenAI API and the MATLAB–Python interface for requesting GPT models. The efficiency and reliability of the modified algorithm are compared with those of standard chaotic encryption algorithms, and its robustness to various cryptographic attacks is also studied. Full article

Efficient emergency load transfer is crucial for ensuring the power system’s safe operation and reliable power supply. However, traditional load transfer methods that rely on human experience have limitations, such as slow response times and low efficiency, which make it difficult to address complex and diverse fault scenarios effectively. Therefore, this paper proposes an emergency load transfer method based on knowledge graphs to achieve intelligent management and efficient retrieval of emergency knowledge. Firstly, a named entity recognition model based on ERNIE-BiGRU-CRF is constructed to automatically extract key entities and relationships from the load transfer plan texts, obtaining information such as fault names, fault causes, and operation steps. Secondly, a power system emergency load transfer knowledge graph is constructed based on the extracted structured knowledge, which is efficiently stored using a graph database and enables the visualization and interactive query of knowledge. Finally, real power system fault cases prove that the proposed method can effectively improve the retrieval efficiency of fault knowledge and provide intelligent support for online emergency load transfer decisions. Full article

This scoping review paper provides an overview of the evolution, the current stage, and the future prospects of fracture studies on composite laminates. A fundamental understanding of composite materials is presented by highlighting the roles of the fiber and matrix, outlining the applications of various synthetic fibers used in current structural sectors. Challenges posed by interlaminar delamination, one of the critical failure modes, are highlighted. This paper systematically discusses the fracture behavior of these laminates under mixed-mode and complex loading conditions. Standardized fracture toughness testing methods, including Mode I Double Cantilever Beam (DCB), Mode II End-Notched Flexure (ENF) and Mixed-Mode Bending (MMB), are initially discussed, which is followed by a decade-wide chronological analysis of fracture mechanics approaches. Key advancements, including toughening mechanisms, Cohesive Zone Modeling (CZM), Virtual Crack Closure Technique (VCCT), Extended Finite Element Method (XFEM) and Digital Image Correlation (DIC), are analyzed. The review also addresses recent trends in fracture studies, such as bio-inspired architecture, self-healing systems, and artificial intelligence in fracture predictions. By mapping the trajectory of past innovations and identifying unresolved challenges, such as scale integration, dataset standardization for AI, and manufacturability of advanced architectures, this review proposes a strategic research roadmap. The major goal is to enable unified multi-scale modeling frameworks that merge physical insights with data learning, paving the way for next-generation composite laminates optimized for resilience, adaptability, and environmental responsibility. Full article

Intelligent sensors with embedded AI are key to modern cyber-physical systems. They find applications in industrial automation, medical diagnostics and healthcare, smart cities, and autonomous systems. Despite their significant potential, they face several hardware challenges related to computing power, energy consumption, communication capabilities, and security, which limit their effectiveness. This article analyzes factors influencing the production and deployment of AI sensors. The key limitations are energy efficiency, computing power, scalability, and integration of AI sensors in real-time conditions. Among the main problems are the high requirements for data processing, the limitations of traditional microprocessors, and the balance between performance and energy consumption. To meet these challenges, the article presents several practical and innovative approaches, including the development of specialized microprocessors and optimized architectures for “edge computing,” which promise radical reductions in latency and power consumption. Through a synthesis of current research and practical examples, the article emphasizes the need for intermediate hardware–software solutions and standardization for mass deployment of AI sensors. Full article

The pursuit of universal, symmetric semantic representations within large language models (LLMs) faces a fundamental challenge: the inherent asymmetry of natural languages. Different languages exhibit vast disparities in syntactic structures, lexical choices, and cultural nuances, making the creation of a truly shared, symmetric embedding space a non-trivial task. This paper aims to address this critical problem by introducing a novel framework to forge robust and symmetric multilingual sentence embeddings. Our approach, named DACL (Dynamic Asymmetric Contrastive Learning), is anchored in two powerful asymmetric learning paradigms: Contrastive Learning and Dynamic Curriculum Learning (DCL). We extend Contrastive Learning to the multilingual context, where it asymmetrically treats semantically equivalent sentences from different languages (positive pairs) and sentences with distinct meanings (negative pairs) to enforce semantic symmetry in the target embedding space. To further refine this process, we incorporate Dynamic Curriculum Learning, which introduces a second layer of asymmetry by dynamically scheduling training instances from easy to hard. This dual-asymmetric strategy enables the model to progressively master complex cross-lingual relationships, starting with more obvious semantic equivalences and advancing to subtler ones. Our comprehensive experiments on benchmark cross-lingual tasks, including sentence retrieval and cross-lingual classification (XNLI, PAWS-X, MLDoc, MARC), demonstrate that DACL significantly outperforms a wide range of established baselines. The results validate our dual-asymmetric framework as a highly effective approach for forging robust multilingual embeddings, particularly excelling in tasks involving complex linguistic asymmetries. Ultimately, this work contributes a novel dual-asymmetric learning framework that effectively leverages linguistic asymmetry to achieve robust semantic symmetry across languages. It offers valuable insights for developing more capable, fair, and interpretable multilingual LLMs, emphasizing that deliberately leveraging asymmetry in the learning process is a highly effective strategy. Full article

This study investigates the nonlinear, regime-dependent, and frequency-specific interdependencies between rare earth element (REE) markets and key global critical sectors, including artificial intelligence, semiconductors, clean energy, defense, and advanced manufacturing, under varying levels of geopolitical and financial uncertainty. The main objective is to assess how REE markets transmit and absorb systemic risks across these critical domains. Using a mixed-methods approach combining Quantile-on-Quantile Regression (QQR), Continuous Wavelet Transform (CWT), and Wavelet Transform Coherence (WTC), we examine the dynamic connections between two REE proxies, SOLLIT (Solactive Rare Earth Elements Total Return) and MVREMXTR (MVIS Global Rare Earth Metals Total Return), and major sectoral indices based on a dataset of daily observations from 2018 to 2025. Our results reveal strong evidence of asymmetric, regime-specific risk transmission, with REE markets acting as systemic amplifiers during periods of extreme uncertainty and as sensitive receptors under moderate or localized geopolitical stress. High co-volatility and persistent low-frequency coherence with critical sectors, especially defense, technology, and clean energy, indicate deeply embedded structural linkages and a heightened potential for cross-sectoral contagion. These findings confirm the systemic relevance of REEs and underscore the importance of integrating critical resource exposure into global supply chain risk strategies, sector-specific stress testing, and national security frameworks. This study offers relevant insights for policymakers, risk managers, and institutional investors aiming to anticipate disruptions and strengthen resilience in critical industries. Full article

Methane concentration anomalies during coal mining operations are identified as important factors triggering major safety accidents. This study aimed to address the key issues of insufficient adaptability of existing detection methods in dynamic and complex underground environments and limited characterization capabilities for non-uniform sampling data. Specifically, an intelligent diagnostic model was proposed by integrating the improved Dung Beetle Optimization Algorithm (SGDBO) with Transformer-SVM. A dual-path feature fusion architecture was innovatively constructed. First, the original sequence length of samples was unified by interpolation algorithms to adapt to deep learning model inputs. Meanwhile, statistical features of samples (such as kurtosis and differential standard deviation) were extracted to deeply characterize local mutation characteristics. Then, the Transformer network was utilized to automatically capture the temporal dependencies of concentration time series. Additionally, the output features were concatenated with manual statistical features and input into the LSSVM classifier to form a complementary enhancement diagnostic mechanism. Sine chaotic mapping initialization and a golden sine search mechanism were integrated into DBO. Subsequently, the SGDBO algorithm was employed to optimize the hyperparameters of the Transformer-LSSVM hybrid model, breaking through the bottleneck of traditional parameter optimization falling into local optima. Experiments reveal that this model can significantly improve the classification accuracy and robustness of anomaly curve discrimination. Furthermore, core technical support can be provided to construct coal mine safety monitoring systems, demonstrating critical practical value for ensuring national energy security production. Full article

Since the advent of generative AI, research on AI in Education (AIEd) has experienced explosive growth. This study systematically explores publication dynamics, keyword evolution, and research focuses in AIEd by analyzing 2952 papers from the Web of Science (1990–2024). Using bibliometric methods, 2800 English publications were screened, with analyses conducted via VOSviewer v1.6.20 and Python v3.11.5. Findings show a surge in publications post-2020, reaching 612 in 2023 and 1216 by November 2024. The US and China are leading contributors, with the University of London and the University of California system as core institutions. Keywords evolved from “AI” and “machine learning” (2018–2020) to “ChatGPT” and “ethics” (post-2022), reflecting dual focuses on technological applications and ethical considerations. Notably, 68% of highly cited papers address ethical controversies, while higher education and medical education emerge as primary application domains, involving personalized learning and intelligent tutoring systems. Cross-disciplinary research is evident, with education studies comprising the largest category. The study reveals AIEd’s shift toward socio-technical integration, highlighting generative AI’s transformative role yet identifying gaps in ethical governance and K-12 research. These insights inform policymakers, journals, and institutions, advocating for enhanced interdisciplinary collaboration and long-term impact research to balance innovation with educational ethics. Full article