Search Results (256)

E-learning content and participants in the learning process are usually annotated with metadata. Complicated metadata models are necessary for organizing personalized learning, so an ontological metadata representation is used. Since ontologies represent static knowledge, changes in e-learning systems and related description metadata require frequent changes to corresponding ontologies. Only a few professionals in the educational domain have some expertise in ontology development. So, maximal possible automation is of great importance for the development and maintenance of knowledge models, needed for intelligent e-learning environments. Ontology learning is an approach for automatic ontology development and evolution, affected significantly by recent advances in Artificial Intelligence and Language Models. The main objective of this study is to explore and analyze ontology learning approaches and techniques and the specifics of their use in an intelligent e-learning environment. It examines and summarizes recent scientific research to reveal the degree of development and the extent to which ontology learning is applied to support personalized tutoring. The paper outlines trends and challenges of ontology learning from textual e-learning content and comprehensively discusses ontology learning and its applications in intelligent e-learning. It also describes a use case concerning the implementation and practical usage of ontology learning. Full article

Machine tools are the major consumers of industrial energy, but their energy efficiency remains low, posing a serious challenge to sustainable manufacturing. The current literature predominantly focuses on isolated subsystems or specific operational phases (e.g., cutting parameters), lacking systematic evaluations of how different methodologies interact within the Life Cycle Assessment (LCA) framework. This paper provides a critical synthesis of three core methodologies—modeling methods, system parameter optimization, and machine learning (ML)—across the design/production, usage, and recycling stages. Unlike descriptive reviews, this study highlights the scientific contribution by defining the applicability boundaries and complementary mechanisms of these approaches. The analysis reveals that while modeling lays the theoretical basis for eco-design and remanufacturing assessments, and optimization effectively resolves multi-objective trade-offs, these static methods struggle with the dynamic complexity of real-time operations where ML excels. However, ML is identified to be constrained by high data dependency and poor generalization in heterogeneous environments. Consequently, this review shows that the ‘cross-application’ of modeling methods and machine learning to construct hybrid models is essential for addressing complex nonlinear relationships and achieving accurate energy prediction throughout the entire life cycle. Finally, future directions such as transfer learning and digital twins are proposed to overcome current generalization bottlenecks, providing a theoretical foundation for the industry’s transition from passive energy assessment to active, intelligent energy management. Full article

This article proposes an interpretable adaptive control model for dynamically regulating task difficulty in Artificial intelligence (AI)-augmented reading-comprehension learning systems. The model adjusts, on the fly, the level of task complexity associated with reading comprehension and post-text analytical tasks based on learner performance, with the objective of maintaining an optimal difficulty level. Grounded in adaptive control theory and learning theory, the proposed algorithm updates task difficulty according to the deviation between observed learner performance and a predefined target mastery rate, modulated by an adaptivity coefficient. A simulation study involving heterogeneous learner profiles demonstrates stable convergence behavior and a strong positive correlation between task difficulty and learning performance (r = 0.78). The results indicate that the model achieves a balanced trade-off between learner engagement and cognitive load while maintaining low computational complexity, making it suitable for real-time integration into intelligent learning environments. The proposed approach contributes to AI-supported education by offering a transparent, control-theoretic alternative to heuristic difficulty adjustment mechanisms commonly used in e-learning systems. Full article

With the increasingly prominent demand for building energy efficiency and occupant-centric design, accurate and reliable personal thermal comfort models (PTCMs) are playing an important role in various residential and energy applications (e.g., building energy-saving design, indoor environmental regulation, and health and well-being improvement). In recent years, data-driven and artificial intelligence (AI) technologies have attracted considerable attention in the field of personal thermal comfort modeling. This study systematically reviews recent progress in data-driven personal thermal comfort modeling, emphasizing contact-based and non-contact data collection ways, correlation analysis of feature data, modeling methods based on machine learning and deep learning. Considering the high cost and limited scale of collection experiments, as well as noise, ambiguity, and individual differences in subjective feedback, special attention is put on the data-efficient thermal comfort modeling in data scarcity scenarios using a transfer learning (TL) strategy. Characteristics and suitable occasions of four transfer methods (model-based, instance-based, feature-based, and ensemble methods) are summarized to provide a deep perspective for practical applications. Furthermore, integration of PTCM into building environment control is summarized from aspects of the integration framework, modeling method, control strategy, actuator, and control effect. Performance of the integrated systems is analyzed in terms of improving personal thermal comfort and promoting building energy efficiency. Finally, several challenges faced by PTCMs and future directions are discussed. Full article

This study proposes a functional framework to enhance the efficiency and effectiveness of e-learning content creation by systematically integrating generative artificial intelligence (AI) technologies. While previous research on e-learning has primarily focused on systems and infrastructure, little attention has been given to content creation. To address this gap, we present a five-step methodology: (1) conducting a systematic literature review of existing e-learning development frameworks; (2) proposing a content-specific framework centered on instructors and technical support roles; (3) outlining a detailed task-based content creation process; (4) identifying and classifying commercial AI tools applicable to each functional unit; and (5) comparing the tools based on their strengths, limitations, and suitability. The proposed framework includes eight key functional stages, ranging from lesson planning to editing, automation, and final review. For each stage, AI tools such as ChatGPT, Synthesia, MidJourney, and Grammarly are evaluated and mapped to the corresponding workflow phase. The findings suggest that integrating AI tools into content creation can significantly reduce production time and cost, improve instructional quality, and lower e-learning sector entry barriers. This study contributes a conceptual model and practical strategies for leveraging AI in scalable, high-quality digital education environments. Full article

Design education involves complex historical knowledge structures that often impose a high extraneous cognitive load on students. This study proposes and evaluates an intelligent instructional system that integrates Retrieval-Augmented Generation (RAG) with anthropomorphic digital humans to function as scalable cognitive scaffolding. We developed a locally deployed architecture utilizing the Qwen3-30B Large Language Model (LLM) for reasoning, BGE-Large-Zh for high-precision semantic embedding, and LiveTalking for real-time audiovisual generation. To validate the system’s pedagogical efficacy, a multi-center randomized controlled trial (RCT) was conducted across three universities ($N = 150$). The experimental group utilized the RAG-enhanced digital human system, while the control group received traditional instruction. Quantitative results demonstrate that the system significantly improved learning outcomes ($p<0.001, Cohen’s d=1.14$) and classroom engagement ($p<0.001, d=1.39$). Crucially, measurements using the Paas Mental Effort Rating Scale revealed a significant reduction in mental effort ($p<0.001, d=1.71$) for the experimental group. Instructional efficiency analysis (E) confirmed that the system successfully converted reduced extraneous load into germane learning gains (Experimental $E=+0.72$ vs. Control $E=-0.68$). These findings validate the technical feasibility and educational value of combining localized RAG architectures with embodied AI, offering a replicable framework for reducing cognitive load in intensive learning environments. Full article

This paper proposes E-MOTE (Emotion-aware Teacher Education Framework), an ethically grounded conceptual model aimed at enhancing teacher education through the integrated use of the Facial Action Coding System (FACS), Artificial Intelligence (AI), and Virtual Reality (VR). As a conceptual and design-oriented proposal, E-MOTE is presented as a structured blueprint for future development and empirical validation, not as an implemented or evaluated system. Grounded in neuroscientific and educational research, E-MOTE seeks to strengthen teachers’ emotional awareness, teacher noticing, and social–emotional learning competencies. Rather than reporting empirical findings, this article offers a theoretically structured framework and an operational blueprint for the design of emotion-aware teacher training environments, establishing a structured foundation for future empirical validation. E-MOTE articulates three core contributions: (1) it clarifies the multi-layered construct of emotion-aware teaching by distinguishing between emotion detection, perception, awareness, and regulation; (2) it proposes an integrated AI–FACS–VR architecture for real-time and post hoc feedback on teachers’ perceptual performance; and (3) it outlines a staged experimental blueprint for future empirical validation under ethically governed conditions. As a design-oriented proposal, E-MOTE provides a structured foundation for cultivating emotionally responsive pedagogy and inclusive classroom management, supporting the development of perceptual micro-skills in teacher practice. Its distinctive contribution lies in proposing a shift from predominantly macro-behavioral simulation toward the deliberate cultivation of perceptual micro-skills through FACS-informed analytics integrated with AI-driven simulations. Full article

Real-time visual inference on resource-constrained hardware remains a core challenge for edge computing and embedded artificial intelligence systems. Recent deep learning architectures, particularly Vision Transformers (ViTs) and Detection Transformers (DETRs), achieve high detection accuracy but impose substantial computational and memory demands that limit their deployment on low-power edge platforms such as NVIDIA Jetson and Raspberry Pi devices. This paper presents a systematic review of model compression and optimization strategies—specifically quantization, pruning, and knowledge distillation—applied to lightweight object detection architectures for edge deployment. Following PRISMA (Preferred Reporting Items for Systematic Reviews and Meta-Analyses) guidelines, peer-reviewed studies were analyzed from Scopus, IEEE Xplore, and ScienceDirect to examine the evolution of efficient detectors from convolutional neural networks to transformer-based models. The synthesis highlights a growing focus on real-time transformer variants, including Real-Time DETR (RT-DETR) and low-bit quantized approaches such as Q-DETR, alongside optimized YOLO-based architectures. While quantization enables substantial theoretical acceleration (e.g., up to 16× operation reduction), aggressive low-bit precision introduces accuracy degradation, particularly in transformer attention mechanisms, highlighting a critical efficiency-accuracy tradeoff. The review further shows that Quantization-Aware Training (QAT) consistently outperforms Post-Training Quantization (PTQ) in preserving performance under low-precision constraints. Finally, this review identifies critical open research challenges, emphasizing the efficiency–accuracy tradeoff and the high computational demands imposed by Transformer architectures. Future directions are proposed, including hardware-aware optimization, robustness to imbalanced datasets, and multimodal sensing integration, to ensure reliable real-time inference in practical agricultural edge computing environments. Full article

Sulfamethoxazole (SMX), a widely used antibiotic, poses potential threats to ecosystems and human health due to its persistence and residues in aquatic environments. This study developed a novel intelligent water treatment system, namely Intelligent Pulsed Electrochemical Activation of NaClO₂ (IPEA_NaClO2), which integrates a FeCuC-Ti₄O₇ composite electrode with machine learning (ML) to achieve efficient SMX removal and energy consumption optimization. Six key operational parameters—initial SMX concentration, NaClO₂ dosage, reaction temperature, reaction time, pulsed potential, and pulsed frequency—were systematically investigated to evaluate their effects on removal efficiency and electrical specific energy consumption (E-SEC). Under optimized conditions (SMX 10 mg L⁻¹, NaClO₂ 60~90 mM, pulsed frequency 10 Hz, temperature 313 K) for 60 min, the IPEA_NaClO2 system achieved an SMX removal efficiency of 89.9% with a low E-SEC of 0.66 kWh m⁻³. Among the ML models compared (back-propagation neural network, BPNN; gradient boosting decision tree, GBDT; random forest, RF), BPNN exhibited the best predictive performance for both SMX removal efficiency and E-SEC, with a coefficient of determination (R²) approaching 1 on the test set. Practical application tests demonstrated that the system maintained excellent stability across different water matrices, achieved a bacterial inactivation rate of 98.99%, and significantly reduced SMX residues in a simulated agricultural irrigation system. This study provides a novel strategy for the intelligent control and efficient removal of refractory organic pollutants in complex water bodies. Full article

The opto-mechanical automated manufacturing process, characterized by stringent process constraints, dynamic disturbances, and conflicting optimization objectives, presents significant control challenges for traditional scheduling and control approaches. We formulate the scheduling problem within a closed-loop control paradigm and propose a novel bi-level intelligent control framework integrating Deep Reinforcement Learning (DRL) and Bayesian Optimization (BO). The core of our approach is a bi-level intelligent control framework. An inner DRL agent acts as an adaptive controller, generating control actions (scheduling decisions) by perceiving the system state and learning a near-optimal policy through a carefully designed reward function, while an outer BO loop automatically tunes the DRL’s hyperparameters and reward weights for superior performance. This synergistic BO-DRL mechanism facilitates intelligent and adaptive decision-making. The proposed method is extensively evaluated against standard meta-heuristics, including Genetic Algorithm (GA) and Particle Swarm Optimization (PSO), on a complex 20-jobs × 20-machines flexible job shop scheduling benchmark specific to opto-mechanical automated manufacturing. The experimental results demonstrate that our BO-DRL algorithm significantly outperforms these benchmarks, achieving reductions in makespan of 13.37% and 25.51% compared to GA and PSO, respectively, alongside higher machine utilization and better on-time delivery. Furthermore, the algorithm exhibits enhanced convergence speed, superior robustness under dynamic disruptions (e.g., machine failures, urgent orders), and excellent scalability to larger problem instances. This study confirms that integrating DRL’s perceptual decision-making capability with BO’s efficient parameter optimization yields a powerful and effective solution for intelligent scheduling in high-precision manufacturing environments. Full article

As edge computing becomes increasingly central to modern digital infrastructure, it also creates opportunities for sophisticated malware attacks that traditional security systems struggle to address. This study proposes a natural language processing (NLP) framework integrated with ensemble learning into next-generation firewalls (NGFWs) to detect and mitigate malware attacks in edge computing environments. The approach leverages unstructured threat intelligence (e.g., cybersecurity reports, logs) by applying NLP techniques, such as TF-IDF vectorization, to convert textual data into structured insights. This process uncovers hidden patterns and entity relationships within system logs. By combining Random Forest (RF) and Logistic Regression (LR) in a soft voting ensemble, the proposed model achieves 95% accuracy on a cyber threat intelligence dataset augmented with synthetic data to address class imbalance, and 98% accuracy on the CSE-CIC-IDS2018 dataset. The study was validated using ANOVA to assess statistical robustness and confusion matrix analysis, both of which confirmed low error rates. The system enhances detection rates and adaptability, providing a scalable defense layer optimized for resource-constrained, latency-sensitive edge environments. Full article

Autonomous vehicles (AVs) are expected to operate safely and efficiently in complex urban environments characterized by dynamic and uncertain elements such as pedestrians, cyclists and adverse weather. Although current neural network-based decision-making algorithms, fuzzy logic and reinforcement learning have shown promise, they often struggle to handle ambiguous situations, such as partially hidden road signs or unpredictable human behavior. This paper proposes a new hybrid decision-making framework combining multi-agent reinforcement learning (MARL) and explainable artificial intelligence (XAI) to improve robustness, adaptability and transparency. Each agent of the MARL architecture is specialized in a specific sub-task (e.g., obstacle avoidance, trajectory planning, intention prediction), enabling modular and cooperative learning. XAI techniques are integrated to provide interpretable rationales for decisions, facilitating human understanding and regulatory compliance. The proposed system will be validated using CARLA simulator, combined with reference data, to demonstrate improved performance in safety-critical and ambiguous driving scenarios. Full article

Small-scale farms produce more than one-third of the world’s food supply, making them a crucial contributor to global food security. In this study, an artificial intelligence of things (AIoT) framework is introduced for smart small-scale farm management. For plant disease detection, the lightweight MobileViT model, which integrates vision transformer and convolutional modules, was utilized to efficiently capture both global and local image features. Data augmentation and transfer learning were employed to enhance the model’s overall performance. MobileViT resulted in a test accuracy of 99.5%, with per-class precision, recall, and f1-score ranging between 0.92 and 1.00 considering the benchmark Plant Village dataset (14 species–38 classes). MobileViT was shown to outperform several standard deep convolutional networks, including MobileNet, ResNet and Inception, by 2–12%. Additionally, an LLM-powered interactive chatbot was integrated to provide farmers with instant plant care suggestions. For plant environment management, the powerful, cost-effective ESP32 microcontroller was utilized as the core processing unit responsible for collecting sensor data (e.g., soil moisture), controlling actuators (e.g., water pump for irrigation), and maintaining connectivity with Google Firebase Cloud. Finally, a mobile application was developed to integrate the AI and IoT system capabilities, hence providing users with a reliable platform for smart plant disease detection and environment management. Each system component was each tested individually, before being incorporated into the mobile application and tested in real-world scenarios. The presented AIoT-based solution has the potential to enhance crop productivity within small-scale farms while promoting sustainable farming practices and efficient resource management. Full article

This article explores various applications and advancements in the fields of energy management (EM), cybersecurity (CS), and automation across multiple sectors, including smart grids (SGs), the Internet of things (IoT), trading, e-commerce, and autonomous systems. A variety of innovative solutions and methodologies are discussed, such as enhanced impedance methods for simulation stability, decision support systems for resource allocation, and advanced algorithms for detecting cyber-physical threats. The integration of artificial intelligence (AI) and machine learning (ML) techniques is highlighted, particularly in addressing challenges such as fault tolerance, economic distribution in cyber-physical systems (CPSs), and protection coordination in complex environments. Additionally, the development of robust algorithms for real-time monitoring and control demonstrates significant potential for improving system efficiency and resilience against various types of attacks. Full article

In industrial inspection and experimental data-acquisition scenarios, the accuracy and efficiency of digital tubes, which are commonly used display components, directly affect the intelligence of the system. However, models trained on data from specific environments may experience a significant drop in recognition accuracy when applied to different environments derived from impacts of various specific scenarios (e.g., temperature changes, changes in light intensity, changes in rate, and color contrast between equipment displays and environments, among others), which may affect model accuracy. To ensure recognition accuracy, we may need to collect data from specific environments to retrain the model for each specific environment, but manual annotation is often inefficient. To address these issues, this article proposes a solution integrating image processing with deep learning within specific scenarios, encompassing the entire workflow from data acquisition to model training. Employing image processing techniques to provide high-quality training data for models, we construct a semi-supervised adversarial learning framework based on an improved self-training algorithm. The framework employs the k-means clustering algorithm for stratified sampling preparation, adds the Squeeze-and-Excitation B Block to the Convolutional Neural Network backbone, and employs the Adversarial Generative Adversarial Network to generate adversarial examples for adversarial training, thus enhancing both classification accuracy and robustness. Full article