Explore the vast range of titles available.

With the increasing use of Artificial Intelligence (AI) technologies in education, the number of published studies in the field has increased. However, no large-scale reviews have been conducted to comprehensively investigate the various aspects of this field. Based on 4,519 publications from 2000 to 2019, we attempt to fill this gap and identify trends and topics related to AI applications in education (AIEd) using topic-based bibliometrics. Results of the review reveal an increasing interest in using AI for educational purposes from the academic community. The main research topics include intelligent tutoring systems for special education; natural language processing for language education; educational robots for AI education; educational data mining for performance prediction; discourse analysis in computer-supported collaborative learning; neural networks for teaching evaluation; affective computing for learner emotion detection; and recommender systems for personalized learning. We also discuss the challenges and future directions of AIEd.

Artificial Intelligence (AI) plays an increasingly important role in language education; however, the trends, research issues, and applications of AI in language learning remain largely under-investigated. Accordingly, the present paper, using bibliometric analysis, investigates these issues via a review of 516 papers published between 2000 and 2019, focusing on how AI was integrated into language education. Findings revealed that the frequency of studies on AI-enhanced language education increased over the period. The USA and Arizona State University were the most active country and institution, respectively. The 10 most popular topics were: (1) automated writing evaluation; (2) intelligent tutoring systems (ITS) for reading and writing; (3) automated error detection; (4) computer-mediated communication; (5) personalized systems for language learning; (6) natural language and vocabulary learning; (7) web resources and web-based systems for language learning; (8) ITS for writing in English for specific purposes; (9) intelligent tutoring and assessment systems for pronunciation and speech training; and (10) affective states and emotions. The results also indicated that AI was frequently used to assist students in learning writing, reading, vocabulary, grammar, speaking, and listening. Natural language processing, automated speech recognition, and learner profiling were commonly applied to develop automated writing evaluation, personalized learning, and intelligent tutoring systems.

Innovative information and communication technologies have reformed higher education from the traditional way to smart learning. Smart learning applies technological and social developments and facilitates effective personalized learning with innovative technologies, especially smart devices and online technologies. Smart learning has attracted increasing research interest from the academia. This study aims to comprehensively review the research field of smart learning by conducting a topic modeling analysis of 555 smart learning publications collected from the Scopus database. In particular, it seeks answers to (1) what the major research topics concerning smart learning were, and (2) how these topics evolved. Results demonstrate several major research issues, for example, Interactive and multimedia learning, STEM (science, technology, engineering, and mathematics) education, Attendance and attention recognition, Blended learning for smart learning, and Affective and biometric computing. Furthermore, several emerging topics were identified, for example, Smart learning analytics, Software engineering for e-learning systems, IoT (Internet of things) and cloud computing, and STEM education. Additionally, potential inter-topic directions were highlighted, for instance, Attendance and attention recognition and IoT and cloud computing, Semantics and ontology and Mobile learning, Feedback and assessment and MOOCs (massive open online courses) and course content management, as well as Blended learning for smart learning and Ecosystem and ambient intelligence.

As a human-friendly system, the artificial intelligence (AI) robot is one of the critical applications in promoting precision education. Alongside the call for humanity-oriented applications in education, AI robot-supported precision education has developed into an active field, with increasing literature available. This study aimed to comprehensively analyze directions taken in the past in this research field to interpret a roadmap for future work. By adopting structural topic modeling, the Mann-Kendall trend test, and keyword analysis, we investigated the research topics and their dynamics in the field based on literature collected from Web of Science and Scopus databases up to 2021. Results showed that AI robots and chatbots had been widely used in different subject areas (e.g., early education, STEM education, medical, nursing, and healthcare education, and language education) for promoting collaborative learning, mobile/game-based learning, distance learning, and affective learning. However, a limited practice in developing true human-centered AI (HCAI)-supported educational robots is available. To advance HCAI in education and its application in educational robots for precision education, we suggested involving humans in AI robot design, thinking of individual learners, testing, and understanding the learner-AI robot interaction, taking an HCAI multidisciplinary approach in robot system development, and providing sufficient technical support for instructors during robot implementation.

Recent advances in generative artificial intelligence (AI) technologies have been significantly driven by models such as generative adversarial networks (GANs), variational autoencoders (VAEs), and denoising diffusion probabilistic models (DDPMs). Although architects recognize the potential of generative AI in design, personal barriers often restrict their access to the latest technological developments, thereby causing the application of generative AI in architectural design to lag behind. Therefore, it is essential to comprehend the principles and advancements of generative AI models and analyze their relevance in architecture applications. This paper first provides an overview of generative AI technologies, with a focus on probabilistic diffusion models (DDPMs), 3D generative models, and foundation models, highlighting their recent developments and main application scenarios. Then, the paper explains how the abovementioned models could be utilized in architecture. We subdivide the architectural design process into six steps and review related research projects in each step from 2020 to the present. Lastly, this paper discusses potential future directions for applying generative AI in the architectural design steps. This research can help architects quickly understand the development and latest progress of generative AI and contribute to the further development of intelligent architecture.

The increasing availability of real-world clinical compliance data provides unprecedented opportunities to model medication behaviors dynamically and personalize treatment strategies. However, the complex, heterogeneous, and often incomplete nature of these data presents significant modeling challenges, particularly for capturing medication nonadherence, patient-specific therapeutic dynamics, and drug interaction effects. Existing approaches, including statistical regression models and rule-based decision systems, often fail to capture the high-dimensional, temporally-evolving, and probabilistic characteristics inherent in medication trajectories, limiting their effectiveness in precision medicine and policy simulation contexts. To address these limitations, we propose a novel intelligent computing framework that unifies probabilistic graphical modeling, deep temporal inference, and domain-informed strategy design. Our approach is instantiated in the Hierarchical Therapeutic Transformer (HTT), a Bayesian transformer-based model that captures therapeutic state transitions via structured latent variables and medication-aware attention mechanisms. Furthermore, we introduce the Pharmacovigilant Inductive Strategy (PIS), a training paradigm that integrates pharmacological priors, adaptive quantification, and entropy-driven curriculum learning to enhance robustness and generalizability. Our method effectively models dose-response variability, accounts for clinical data missingness, and generalizes across cohorts through a hierarchical latent prior framework. Experimental evaluations demonstrate that our system achieves state-of-the-art performance in predicting adherence patterns and clinical outcomes across diverse datasets, aligning with current advances in medication adherence modeling and probabilistic health informatics. This work provides a rigorous, interpretable, and scalable foundation for real-time decision support in pharmacotherapy, contributing to the broader goals of personalized medicine, drug safety monitoring, and computational clinical reasoning.

Personalized language learning (PLL), a popular approach to precision language education, plays an increasingly essential role in effective language education to meet diverse learner needs and expectations. Research on PLL has become an active sub-field of research on technology-enhanced language learning and artificial intelligence applications in education. Based on the PLL literature from the Web of Science and Scopus databases, this study identified trends and prominent research issues within the field from 2000 to 2019 using structural topic modeling and bibliometrics. Trend analysis of articles demonstrated increasing interest in PLL research. Journals such as Educational Technology ＆ Society and Computers ＆ Education had contributed much to PLL research. PLL associated closely with mobile learning, game-based learning, and online/web-based learning. Moreover, personalized feedback and recommendations were important issues in PLL. Additionally, there was an increasing interest in adopting learning analytics and artificial intelligence in PLL research. Results obtained could help practitioners and scholars better understand the trends and status of PLL research and become aware of the hot topics and future directions.

Background: Metabolic associated steatohepatitis (MASH) represents a severe subtype of metabolic associated fatty liver disease (MASLD), with an increased risk of progression to cirrhosis and hepatocellular carcinoma. The nomenclature shift from nonalcoholic steatohepatitis (NASH)/nonalcoholic fatty liver disease (NAFLD) to MASH/MASLD, underscores the pivotal role of metabolic factors in disease progression. Diagnosis of MASH currently hinges on liver biopsy, a procedure whose invasive nature limits its clinical utility. This study aims to identify and validate metabolism-related genes (MRGs) markers for the non-invasive diagnosis of MASH. Methods: This study extracted multiple datasets from the GEO database to identify metabolism-related differentially expressed genes (MRDEGs). Protein-Protein Interaction (PPI) network and machine learning algorithms, including Least Absolute Shrinkage and Selection Operator (LASSO) regression, Support Vector Machine-Recursive Feature Elimination (SVM-RFE), and Random Forest (RF), were applied to screen for signature MRDEGs. The diagnostic performance of these MRDEGs was evaluated using the Receiver Operating Characteristic (ROC) curve and further validated using independent external datasets. Additionally, enrichment analysis was performed to uncover key driver pathways in MASH. The infiltration levels of various immune cell types were assessed using single sample Gene Set Enrichment Analysis (ssGSEA). Finally, Spearman correlation analysis confirmed the association between signature genes and immune cells. Results: We successfully identified seven signature MRDEGs, including CYP7A1, GCK, AKR1B10, HPRT1, GPD1, FADS2, and ENO3, through PPI network analysis and machine learning algorithms. The gene model displayed exceptional diagnostic performance in the training and validation cohorts, as evidenced by the area under ROC curve (AUC) exceeding 0.9. Further enrichment analysis revealed that signature MEDEGs were primarily involved in multiple biological pathways related to glucose and lipid metabolism. Immune infiltration analysis indicated a significant increase in the infiltration levels of activated CD8 T cells, gamma-delta T cells, natural killer cells, and CD56bright NK cells in patients with MASH. Conclusion: This study successfully identified seven signature MRDEGs as significant diagnostic biomarkers for MASH. The findings not only offer novel strategies for non-invasive diagnosis of MASH but also highlight the substantial role of immune cell infiltration in the progression of MASH.

The pretrained large language models have been widely tested for their performance on some challenging tasks including arithmetic, commonsense, and symbolic reasoning. Recently how to combine LLMs with prompting techniques has attracted lots of researchers to propose their models to automatically solve math word problems. However, most research works focus on solving math problems at the elementary school level and few works aim to solve problems in science disciplines, e.g., Physics. In this exploratory study, we discussed the potential pedagogical benefits of using ChatGPT in physics and demonstrated how to prompt ChatGPT in solving physics problems. The results suggest that ChatGPT is able to solve some physics calculation problems, explain solutions, and generate new exercises at a human level.

The accurate identification of pulmonary nodules is critical for the early diagnosis of lung diseases; however, this task remains challenging due to inadequate feature representation and limited localization sensitivity. Current methodologies often utilize channel attention mechanisms and intersection over union (IoU)-based loss functions. Yet, they frequently overlook spatial context and struggle to capture subtle variations in aspect ratios, which hinders their ability to detect small objects. In this study, we introduce an improved YOLOV11 framework that addresses these limitations through two primary components: a spatial squeeze-and-excitation (SSE) module that concurrently models channel-wise and spatial attention to enhance the discriminative features pertinent to nodules and explicit aspect ratio penalty IoU (EAPIoU) loss that imposes a direct penalty on the squared differences in aspect ratios to refine the bounding box regression process. Comprehensive experiments conducted on the LUNA16, LungCT, and Node21 datasets reveal that our approach achieves superior precision, recall, and mean average precision (mAP) across various IoU thresholds, surpassing previous state-of-the-art methods while maintaining computational efficiency. Specifically, the proposed SSE module achieves a precision of 0.781 on LUNA16, while the EAPIoU loss boosts mAP@50 to 92.4% on LungCT, outperforming mainstream attention mechanisms and IoU-based loss functions. These findings underscore the effectiveness of integrating spatially aware attention mechanisms with aspect ratio-sensitive loss functions for robust nodule detection.