Learning Technology Research Articles

Describing youth participatory evaluation of educational interventions as a key domain of the social determinants of health: protocol for a scoping review

IntroductionYouth participatory evaluation is one model for monitoring global outcomes and assessing interventions to improve young people’s health equity and well-being while embracing principles of participation and empowerment. Little is...

Enhanced Self-Checkout System for Retail Based on Improved YOLOv10.

With the rapid advancement of deep learning technologies, computer vision has shown immense potential in retail automation. This paper presents a novel self-checkout system for retail based on an improved YOLOv10 network, aimed at enhancing checkout efficiency and reducing labor costs. We propose targeted optimizations for the YOLOv10 model, incorporating the detection head structure from YOLOv8, which significantly improves product recognition accuracy. Additionally, we develop a post-processing algorithm tailored for self-checkout scenarios, to further enhance the application of the system. Experimental results demonstrate that our system outperforms existing methods in both product recognition accuracy and checkout speed. This research not only provides a new technical solution for retail automation but offers valuable insights into optimizing deep learning models for real-world applications.

Fault Impulse Inference and Cyclostationary Approximation: A feature-interpretable intelligent fault detection method for few-shot unsupervised domain adaptation

With the advancement of intelligent detection for rotating machinery, numerous domain adaptation methods have been devised to transfer detection knowledge from one source domain working condition to another target domain working condition, involving extensive transfer scenarios including labeled, few-shot labeled, and unlabeled target conditions. Yet, learning from sparsely labeled signals in the source domain working condition and transferring to unlabeled target conditions, termed few-shot unsupervised domain adaptation (FUDA), is closer to reality but almost unexplored. Diverging from the intuition of combining existing transfer and few-shot learning technologies, this paper pioneers a novel single learning principle focusing on the cyclostationary mechanism (CT) of fault signals. In its implementation, named cyclically enhanced cyclostationary variational autoencoder (CCTVAE), the CT principle motivates the encoder to infer domain-shared representations with fault impulses, and the decoder approximates the cyclostationary structure containing the clear fault and working condition information. Then, auxiliary samples for few-shot expansion are generated by adjusting cyclic parameters of the posterior distribution of representations. Experimentally, CCTVAE achieves commendable results on simulated and real fault datasets. Even for compound faults, domain-shared representations and generated auxiliary signals manifest interpretable fault-indicating spectral lines in the frequency domain, underscoring method reliability.

Online Teaching and Learning Technology Tools for Analytical-Numerical Methods in Engineering

The COVID-19 pandemic has forced the synchronized and asynchronized teaching and learning (TnL) to sustain educational programs. It is difficult to change the modality of most STEM courses because the TnL of many laboratory skills does not transform to an online learning environment. The complication of virtual lab skills is the motivation of this paper to focus on the online Analytical Numerical Method course (ANM) integrated with technology tools and apps. The methodology of online TnL for Analytical numerical Methods involves the scientific and mathematical thinking skills in experimental approaches. These approaches employ varied education processes such as heutagogy, peeragogy, and cybergogy. Online ANM is looking for educator 4.0 tools to facilitate the outline of synchronous and asynchronous TnL activities. The apps and tools are suitable for most aspects of ANM course. The implementation strategies integrated Mathematics, IT and engineering. As expected, without STEM approaches and without online TnL technology tools, creating learner engagement through information and communication technology cannot be achieved. The result and discussion of SEM-AMOS model enhance online teaching and learning ANM based on student feedback, questionnaires and survey. Diagram, table and data presentation reveal an unexpected result supported by virtual lab and variants of virtual laboratory. This paper will provide a guidance to educator 4.0 practitioners to modify the current curriculum in line with the latest technological developments and requirements in online TnL.

Domain Transfer-Based Hypergraph Convolutional Network for Posture Anomaly Detection in Physical Education Teaching

Human skeleton-based posture anomaly detection has been widely applied in the field of physical education teaching. The existing spatio-temporal graph convolutional networks (ST-GCN) can fully utilize the local and global information of the human skeleton for action recognition, but the entire model requires a large amount of computation and the modeling of high-order relationships between joint points of the human skeleton is insufficient. To this end, this paper proposes a novel domain adaptive hypergraph convolutional network for basketball posture anomaly analysis by exploiting 2D skeleton information. First, we designed an effective hypergraph convolution feature extraction network to improve the high-order dependency modeling. To further improve the performance of the hypergraph convolutional network, we introduce domain adaptive learning technology to supervise the feature extraction learning of the target domain (2D skeleton) through the source domain (3D skeleton). At last, we construct a basketball action teaching analysis dataset for model evaluation. We conducted a large number of comparative experiments on the public dataset NTU RGB+D and our self-built dataset. All the results showed that our proposed hypergraph convolutional model effectively extracts features of 2D human skeletons, and by introducing domain adaptive learning, the performance of basketball anomaly detection is further improved.

A comprehensive review of the application of NLP technology in language learning

The rapid development of Natural Language Processing (NLP) technology has provided new perspectives and tools for the acquisition of second languages. As our world becomes increasingly interconnected, the role of NLP in facilitating language learning has become more prominent. This paper reviews the multifaceted applications of NLP technology in language learning, including auxiliary teaching functions such as reading assistance, writing feedback, oral interaction, and personalized learning. These applications have significantly enhanced language learners' abilities in vocabulary acquisition, grammatical application, pronunciation accuracy, and reading comprehension through real-time feedback, enhanced interactivity, and promotion of cultural understanding. Despite the immense potential of NLP technology in second language learning, challenges such as technical accuracy, cultural adaptability, and data privacy exist. This paper proposes strategies, such as ensuring technical accuracy, curating diverse datasets and safeguarding data privacy to address these challenges. Looking forward, the future development of NLP technology in second language education holds great promise. As NLP continues to evolve, it is expected to contribute to more personalized, effective, and accessible language learning solutions. This paper aims to provide valuable references and insights for educators, technology developers, and policymakers, enabling them to harness the transformative potential of NLP in language education and to navigate the future of educational technology with confidence and foresight.

Ecopedagogy and Environmental Literacy in Research Trends in Indonesia

This study analyzes the trend and development of eco-pedagogy literacy in Indonesia from 2016 to 2024. The method used was a Systematic Literature Review (SLR) with the PRISMA protocol, analyzing 27 articles that met the inclusion criteria. The results of this study showed 1) a significant increase in the number of publications related to eco pedagogy literacy, especially publications in 2023, 2) Qualitative research with high school students as subjects and questionnaires as research tools are often used, 3) Problem-Based Learning (PBL) and Contextual Learning (CL) are the most common learning strategies applied in eco pedagogy. In addition, environmental awareness is the theme most often associated with ecopedagogy literacy in Indonesia. The study also revealed that the Research and Development (RnD) approach is rarely applied, so there are opportunities for developing innovative learning modules and educational media that are more interactive in introducing eco-pedagogy. This research contributes to understanding how environmental education can be strengthened through eco pedagogy and encourages further research that focuses on using technology in learning to improve environmental literacy. As such, the findings are highly relevant to supporting the development of more sustainable education programs in Indonesia.

Systematic Review of Adapting Immersive Technology in Enhancing Teaching and Learning for Students in Higher Education

The integration of immersive technology into educational settings has garnered substantial interest as a potential means to improve teaching and learning (TnL)experiences. The dynamic landscape of education demands innovative approaches to engage, motivate, and empower both educators and learners. Immersive technology, including Virtual Reality (VR), Augmented Reality (AR), as well as Mixed Reality (MR), provides uncommon probabilities to transcend traditional classroom boundaries and provide interactive and immersive learning experiences. However, to harness the full potential of immersive technology, a clear understanding of the conceptual frameworks guiding its implementation is essential. This study utilizes the PRISMA approach. Furthermore, the systematic search of academic databases using the Web of Science (WoS) as well as the Scopus database resulted in an extensive selection of studies, reviews and articles related to immersive learning. Following the implementation of an advanced search approach utilizing keywords (1. Immersive learning, 2. AR, as well as 3. Technology Impact on TnL), the systematic review process yielded a diverse array of articles. These articles were identified and included in the review due to their exploration of the conceptual frameworks that underlie the integration of immersive technology in the field of education. Additionally, the review reveals common themes and emerging trends within the field, shedding light on the diverse approaches to leveraging immersive technology for TnL. The final finding data is (n: 29), which reviews identified key themes. Expect validation to be divided into three themes, which are (1) Immersive learning, (2) AR, and (3) Technology Impact on TnL. Meanwhile, the findings emphasize the importance of well-defined theoretical foundations and best practices when implementing immersive technology for educational purposes. The review underscores the importance of ongoing research as well as innovation in the domain of immersive technology to fully exploit its potential for enhancing TnL experiences. In essence, this systematic review adds to the continued conversation about the efficient utilization of immersive technology in education and paves the way for further exploration and advancement in this field.

Generative artificial intelligence tools for diverse learning styles in design education

The integration of Artificial Intelligence (AI) is transforming design education by automating processes and enhancing learning. Early exposure to AI offers students a competitive edge in critical thinking and problem-solving. AI tools can inspire space planning, improve workflow, reduce cognitive load, and foster creativity. This study explores how the VARK model, which categorizes learning styles into Visual, Auditory, Reading/Writing, and Kinesthetic, influences student engagement with AI tools. In an interior design classroom study involving 32 sophomore students, AI tools were used to create floor plans and generate 3D images. The study assessed the correlation between learning styles and technology acceptance. Results revealed no strong correlations between individual learning styles and perceived ease of use, perceived usefulness, or actual use of AI tools. However, visual and kinesthetic learners displayed higher engagement, suggesting that these modalities may benefit more from AI-enhanced design education. The study also confirmed that perceived ease of use and usefulness are critical factors in technology acceptance, aligning with the Technology Acceptance Model (TAM). The findings suggest that AI tools can be broadly effective across diverse learning styles, with a universal perception of their utility in design education. This research highlights the potential of AI to support creative problem-solving and prepare students for future challenges in a digital design landscape. While learning styles influence engagement, AI tools’ usability and educational benefits are consistently recognized, demonstrating their transformative potential in design education.

A Technology-Based Intervention Impacts Quality of Life for Low-Income Older Adults by Reducing Loneliness and Improving Healthcare Self-Efficacy and Self-Rated Health.

This paper describes a technology program aimed at developing technical skills and confidence, reducing social isolation and loneliness, and increasing healthcare self-management and self-efficacy among older adults. We conducted a mixed-methods study using surveys collected at baseline and 12months from 90 older adults. Focus group data (n = 7) collected at 12months were examined for convergence with key quantitative outcomes, emergent value-related themes, and evaluation of program structure and staff. Outcome data showed improvements in loneliness (Cohen's d = -0.24, p = .004) (validated by qualitative data), self-rated health (d = 0.23, p = .011), and healthcare self-efficacy (d = 0.31, p = .004). Participants with higher healthcare self-efficacy (β = 0.24, p = .03) and higher negative emotions (β = 0.28, p = .01) had greater frequency of internet use to search for health information. Qualitative findings described program mechanisms supporting increases in self-efficacy, including increased technology use and confidence, and values statements demonstrating the meaningfulness of learning technology and its impact on multiple domains of quality of life.

Artificial intelligence and machine learning in disorders of consciousness.

As artificial intelligence and machine learning technologies continue to develop, they are being increasingly used to improve the scientific understanding and clinical care of patients with severe disorders of consciousness following acquired brain damage. We here review recent studies that utilized these techniques to reduce the diagnostic and prognostic uncertainty in disorders of consciousness, and to better characterize patients' response to novel therapeutic interventions. Most papers have focused on differentiating between unresponsive wakefulness syndrome and minimally conscious state, utilizing artificial intelligence to better analyze functional neuroimaging and electroencephalography data. They often proposed new features using conventional machine learning rather than deep learning algorithms. To better predict the outcome of patients with disorders of consciousness, recovery was most often based on the Glasgow Outcome Scale, and traditional machine learning techniques were used in most cases. Machine learning has also been employed to predict the effects of novel therapeutic interventions (e.g., zolpidem and transcranial direct current stimulation). Artificial intelligence and machine learning can assist in clinical decision-making, including the diagnosis, prognosis, and therapy for patients with disorders of consciousness. The performance of these models can be expected to be significantly improved by the use of deep learning techniques.

Color restoration of mural images based on a reversible neural network: leveraging reversible residual networks for structure and texture preservation

AbstractThe Mogao Grottoes in Dunhuang, a treasure of China's and the world's cultural heritage, contains rich historical and cultural deposits and has left precious relics of the history of human art. Over centuries, the Mogao Caves have been affected by natural and human factors, resulting in irreversible fading and discoloration of many murals. In recent years, deep learning technology has shown great potential in the field of virtual mural color restoration. Therefore, this paper proposes a mural image color restoration method based on a reversible neural network. The method first employs an automatic reference selection module based on structural and texture similarity to choose suitable reference mural images for the faded murals. Then, it utilizes a reversible residual network to extract deep features of the mural images without information loss. Next, a channel refinement module is used to eliminate redundant information in the network channels. Finally, an unbiased color transfer module restores the color of the faded mural images. Compared to other image color restoration methods, the proposed method achieves superior color restoration effects while effectively preserving the original structure and texture details of the mural images. Compared to baseline methods, the Structural Similarity Index (SSIM), Feature Similarity Index (FSIM), and Perception-based Image Quality Evaluator (PIQE) values are improved by 7.97%, 3.46%, and 13.98%, respectively. The color restoration of the Dunhuang Mural holds significant historical, artistic, cultural, and economic values, and plays a positive role in the preservation and inheritance of Chinese culture, as well as in the promotion of cultural exchange and mutual understanding.

Research on risk detection and management based on machine learning

With the rapid advancement in financial risk management, machine learning techniques are playing an increasingly crucial role in credit assessment and risk detection. They provide financial institutions with more scientific and precise platforms and methodologies for risk management. This paper explores various traditional machine learning methods in risk assessment, introduces the XGBoost ensemble learning method, and integrates traditional machine learning with Long Short-Term Memory (LSTM) neural networks to enhance the generalization capability of risk control and credit assessment models. This approach offers new perspectives and improvement directions for risk assessment standards and practices in the financial industry, affirming the potential application of machine learning technologies in future risk management.The results show that the random forest and decision tree have excellent accuracy and recall rates for distinguishing fraudulent transactions. After the introduction of LSTM neural networks, the accuracy and recall rates of fraudulent transaction recognition models reach around 99%, indicating that these models have good adaptability for fraud risk recognition.

An overview of current developments and methods for identifying diabetic foot ulcers: A survey

AbstractDiabetic foot ulcers (DFUs) present a substantial health risk across diverse age groups, creating challenges for healthcare professionals in the accurate classification and grading. DFU plays a crucial role in automated health monitoring and diagnosis systems, where the integration of medical imaging, computer vision, statistical analysis, and gait information is essential for comprehensive understanding and effective management. Diagnosing DFU is imperative, as it plays a major role in the processes of diagnosis, treatment planning, and neuropathy research within automated health monitoring and diagnosis systems. To address this, various machine learning and deep learning‐based methodologies have emerged in the literature to support healthcare practitioners in achieving improved diagnostic analyses for DFU. This survey paper investigates various diagnostic methodologies for DFU, spanning traditional statistical approaches to cutting‐edge deep learning techniques. It systematically reviews key stages involved in diabetic foot ulcer classification (DFUC) methods, including preprocessing, feature extraction, and classification, explaining their benefits and drawbacks. The investigation extends to exploring state‐of‐the‐art convolutional neural network models tailored for DFUC, involving extensive experiments with data augmentation and transfer learning methods. The overview also outlines datasets commonly employed for evaluating DFUC methodologies. Recognizing that neuropathy and reduced blood flow in the lower limbs might be caused by atherosclerotic blood vessels, this paper provides recommendations to researchers and practitioners involved in routine medical therapy to prevent substantial complications. Apart from reviewing prior literature, this survey aims to influence the future of DFU diagnostics by outlining prospective research directions, particularly in the domains of personalized and intelligent healthcare. Finally, this overview is to contribute to the continual evolution of DFU diagnosis in order to provide more effective and customized medical care.This article is categorized under: Application Areas > Health Care Technologies > Machine Learning Technologies > Artificial Intelligence

Examining TPACK Enactment in Elementary Mathematics with Various Learning Technologies

As schools continue to invest more resources into learning technologies and their infrastructure, there is a need to consider ways to support teachers’ professional learning related to the appropriate uses of learning technologies. The construct of TPACK continues to provide a framework for the field to help make sense of the knowledge and skills related to effectively integrating learning technologies into teaching. The article includes three vignettes that describe research-aligned enactments of TPACK using three different learning technologies: an internet-based activity focused on lower-level fluency, an internet-based simulation/game on budgeting, and an internet-based open-ended tool. The three vignettes suggest that TPACK can be enacted regardless of the learning technologies and that the culture and context of schools greatly influences whether and how teachers integrate technology into their mathematics teaching.

Asthma Care Chatbot

Asthma is a chronic respiratory condition affecting millions of people worldwide, characterized by inflammation and narrowing of the airways, leading to symptoms such as coughing, wheezing, and shortness of breath. Managing asthma effectively requires timely intervention and personalized care to alleviate symptoms and prevent exacerbations. In this context, the Asthma Care Chatbot serves as an innovative solution to assist individuals in managing their asthma symptoms more efficiently. Leveraging advancements in technology and machine learning, this chatbot provides personalized recommendations based on user-reported symptoms, age, and gender. By integrating a user-friendly graphical interface, the chatbot aims to enhance accessibility and usability for individuals seeking guidance on managing their asthma condition. This project utilizes a machine learning model trained on a dataset comprising asthma severity data to predict the severity of symptoms reported by users. Through an intuitive interface, users can input their symptoms, demographic information, and receive real-time predictions regarding the severity of their asthma symptoms. Based on the predicted severity level, the chatbot offers tailored recommendations, ranging from self-care measures to prompt medical intervention. Furthermore, the chatbot's performance is evaluated using various metrics such as accuracy, precision, recall, and F1 score, ensuring its reliability and effectiveness in providing accurate predictions. By continuously refining its recommendations based on user feedback and data-driven insights, the Asthma Care Chatbot aims to empower individuals to take proactive steps in managing their asthma condition and improving their quality of life. Asthma Care Chatbot represents a pioneering approach towards personalized asthma management, bridging the gap between individuals and accessible healthcare solutions through the integration of technology and machine learning. By offering personalized guidance and support, the chatbot endeavours to empower individuals in effectively managing their asthma symptoms and promoting better.

Mobile Assisted Language Learning: Ecuadorian Undergraduate Polytechnic Students' Perceptions

Despite the increased use of mobile devices for language learning, little research has examined Ecuadorian university students' perceptions of Mobile-Assisted Language Learning (MALL). This study aims to explore undergraduate polytechnic students' perceptions of using MALL for English skills development. Also, it looks at the different factors associated with the acceptance of technology and identifies those that are more common. This quantitative research design uses a survey adapted from the Technology Adoption Model (TAM). It counts with the participation of 126 Ecuadorian undergraduate polytechnic students taking English as a foreign language classes. Participants were very positive about using MALL applications to learn English during their off-classroom time. The average total mean score was 4.373. It was also determined, through multiple regression analysis, that Perceived Usefulness (t = 6.025, p < 0.000), Social Influence (t = 2.876, p < 0.000), and Perceived Outcomes (t = 3.903, p <0.000) were the highest predictors of MALL acceptance. The two main contributions of this study to the literature are that students feel a connection between their language learning aims and attaining them by using MALL. Perceived Outcome is a high predictor of MALL usage. The findings suggest that Ecuadorian educational practices should increasingly integrate Mobile-Assisted Language Learning (MALL) technologies, as students perceive them as highly useful, especially in improving language skills, fostering social collaboration, and offering personalized, flexible learning experiences that align with their technological readiness and cultural context.

Mapping the scientific landscape and evolution of the international journal of surgery: A scientometric analysis (2004-2024)

Aim: The purpose of this study was to analyze the publication characteristics and development of the International Journal of Surgery over its 20-year history. Methods: This study included articles published in IJS during the 20 years from 2004 to 2024. The data were analyzed using the Citespace, VOS viewer, and the ‘Bibliometrix’ package in R software. We studied the dynamics and trend patterns of IJS literature production through descriptive bibliometrics and identified the most prolific authors, publications, institutions, and countries. Bibliometric maps were utilized to visualize published articles’ content and identify the most prolific research terms and topics in IJS, as well as their evolution over time. Results: A total of 5964 publications in the IJS from 2004 to 2023 and 356 publications in 2024 were included in the analysis. The study revealed a positive trend in literature production, although the number of articles published in IJS has slightly decreased recently. The most productive country was China (n=1,211), the most productive institution was Sichuan University (n=151), and the most prolific author was Wang Yang (n=87). The top 15 most cited articles focus primarily on research reporting standard guidelines for surgical studies. Research published in IJS mainly targeted middle-aged and older adults, emphasizing postoperative complications and treatment outcomes. The future research focus in IJS might center on integrating artificial intelligence and deep learning technologies to revolutionize surgical research and practice. Conclusions: The International Journal of Surgery significantly contributes to advances in surgical research. IJS prioritized enhancing patient outcomes and advancing surgical techniques, focusing on middle-aged and older adults, postoperative complications, and treatment outcomes. The journal emphasized robust evidence through retrospective, controlled, and cohort surgical studies. Integrating artificial intelligence and deep learning represented a significant frontier poised to revolutionize surgical care, shaping the future landscape of research and practice.

Enabling personalized smart tourism with location-based social networks

With the rapid advance of mobile internet, communication technology and the Internet of Things (IoT), the tourism industry is undergoing unprecedented transformation. Smart tourism offers users personalized and customized services for travel planning and recommendations. Location-based social networks (LBSNs) play a crucial role in smart tourism industry by providing abundant data sources through their social networking attributes. However, applying LBSNs to smart tourism is a challenge due to the need to deal with complex multi-source information modeling and tourism data sparsity. In this article, to fully harness the potential of LBSNs using deep learning technologies, we propose an knowledge-driven personalized recommendation method for smart tourism. Representation learning techniques can effectively modeling the contextual information (e.g., time, space, and semantics) in LBSNs, while the data augmentation strategy of contrastive learning techniques can explore user personalized travel behaviors and alleviate data sparsity. To demonstrate the effectiveness of the proposed approach, we conducted a case study on trip recommendation. Furthermore, the patterns of human mobility are revealed by exploring the effect of contextual data and tourist potential preferences.

Calculation of Aortic Arch Calcification Degree in Hemodialysis Patients Using Deep Learning

Abdominal Aortic Calcification (AAC) is a common form of vascular calcification closely associated with atherosclerosis and serves as an important marker for measuring increased risk of cardiovascular, cerebrovascular, and peripheral vascular diseases. Particularly in patients with Chronic Kidney Disease (CKD) and those undergoing dialysis, the risk of AAC significantly increases due to a combination of traditional and non-traditional risk factors. Therefore, developing a rapid and accurate method to assess the extent of AAC is crucial for preventing the progression of vascular calcification and the associated risk of cardiovascular diseases. Dialysis patients are required to undergo an abdominal X-ray annually, and the degree of calcification of the abdominal aorta is assessed manually through these X-ray images. However, these methods have limitations in identifying subtle calcifications in the abdominal aorta and the assessment process is time-consuming and depends on the experience and subjective judgment of physicians. To overcome these limitations, we propose a new method that incorporates deep learning technology to improve the accuracy of assessing the extent of AAC. Our method utilizes CNN models and attention modules to enhance the model's ability to recognize features of abdominal aortic calcification.