Multi-Armed Bandit-Based User Network Node Selection.

In the scenario of an integrated space-air-ground emergency communication network, users encounter the challenge of rapidly identifying the optimal network node amidst the uncertainty and stochastic fluctuations of network states. This study introduces a Multi-Armed Bandit (MAB) model and proposes an optimization algorithm leveraging dynamic variance sampling (DVS). The algorithm posits that the prior distribution of each node's network state conforms to a normal distribution, and by constructing the distribution's expected value and variance, it maximizes the utilization of sample data, thereby maintaining an equilibrium between data exploitation and the exploration of the unknown. Theoretical substantiation is provided to illustrate that the Bayesian regret associated with the algorithm exhibits sublinear growth. Empirical simulations corroborate that the algorithm in question outperforms traditional ε-greedy, Upper Confidence Bound (UCB), and Thompson sampling algorithms in terms of higher cumulative rewards, diminished total regret, accelerated convergence rates, and enhanced system throughput.

The impact of teaching presence on students' online learning experience: evidence from 334 Chinese universities during the pandemic.

Teaching presence is the core role of teachers in online education and is the most promising mechanism for developing online learning communities. Drawing on the theoretical framework of teaching presence, and based on data from an online survey of university students from 334 Chinese universities, this study constructs a framework for teaching presence and compares the differences in teaching presence among different student groups, and further explores the impact of teaching presence on students' online learning experience and its heterogeneity in terms of gender and discipline. The study finds that teaching presence includes three dimensions: instructional design and organization, facilitating interaction, and direct instruction, and there are differences among different groups. Teaching presence has a significant impact on the online learning experience, among which facilitating interaction is the most important influencing factor. Heterogeneity examination reveals that the direct instruction dimension has a greater impact on the online learning experience of female students and students in science and engineering, while the facilitating interaction dimension has a greater impact on the experience of male students and students in science and engineering. For the development of online teaching, it is necessary to help online teachers comprehensively improve teaching presence, adopt different teaching strategies and improvement measures for different student groups, and pay attention to collecting and analyzing student behavioral data for teachers to reflect on and improve teaching.

Student Satisfaction and Physical Health Effects of Online Learning Among Medical and Paramedical Undergraduates in Northern India: A Cross-Sectional Study.

BACKGROUND: Online modality of pedagogy was introduced in many medical institutes globally, especially during the COVID-19 pandemic. However, these techniques were not evaluated, either with respect to effectiveness or student satisfaction in terms of promoting successful educational outcomes. The current study was conducted to identify determinants of student satisfaction with respect to online learning, in the post-pandemic era. METHODS: A pilot-tested and validated online questionnaire was administered to 370 medical/paramedical students who attended online classes during the pandemic. The students were selected randomly from four different streams of a medical university, representing all the years of study. The questionnaire included Likert-type questions and was divided into two parts: socio-demographic profile and satisfaction with online learning. RESULTS: The response rate was 81.4%. Overall satisfaction with online learning among students was 35.9% and the areas of most satisfaction for students were user-friendliness of the online portal (65.5%), self-directed responsibilities assigned to pupils (49.9%), faculty accessibility/availability (48.8%) and timely evaluation, test and feedback (47.9%). The areas of most dissatisfaction were lack of personal effect as compared to offline learning (n=71, 23.6%), effect on social life (n=54, 17.9%), and feeling of not belonging to the online session (n=38, 12.6%). Multiple regression analysis demonstrated that having previous exposure to online courses and having a separate room led to more satisfaction, whereas the emergence of health problems led to poor satisfaction with the course. The duration of previous exposure to online courses was not a statistically significant predictor of satisfaction. One or more health problems were reported by 176 (58.5%) of the respondents. Some of the common health problems reported were eye strain (72.8%), headache (56.1%), insomnia (47.2%), stress (35.2%), muscle fatigue (22.6) and tingling sensation (10.6%). CONCLUSION: Adopting a combination of online and offline approaches, i.e., blended pedagogy, involving different methods to involve students and their feedback are important to ensure student satisfaction.

Medical students' preferences for asynchronous online or face-to-face learning strategies in learning gross anatomy and neuroanatomy during the COVID-19 pandemic.

Gross anatomy and neuroanatomy are fundamental subjects in medical education. However, learning different anatomical terms and understanding the complexity of the subjects are often challenging for medical students. At National Taiwan University, the 2020-2021 cohort adopted a face-to-face (F2F) learning strategy for gross anatomy and neuroanatomy lecture and laboratory courses until May 17, 2021. After the aforementioned date, the same cohort learned the rest of the gross anatomy and neuroanatomy courses via asynchronous online learning. This study aimed to evaluate the benefits of and students' preferences for F2F and asynchronous online learning strategies in learning gross anatomy and neuroanatomy. A survey with closed-ended and open-ended questions was used to quantitatively and qualitatively explore medical students' learning preferences for two teaching strategies in gross anatomy and neuroanatomy. The results identified different learning preferences among students in learning gross anatomy and neuroanatomy-satisfied with both learning strategies, satisfied with only F2F learning strategy, satisfied with only asynchronous online learning strategy, and satisfied with neither learning strategy. The survey results with closed-ended and open-ended questions showed that medical students preferred F2F learning for anatomical laboratory courses but favored asynchronous online learning for neuroanatomical laboratory courses. In addition, medical students considered peer discussion more critical in learning gross anatomy than neuroanatomy. These findings provide valuable information about medical students' preference for gross anatomy and neuroanatomy courses, which anatomy teachers can consider when planning to enhance their curriculum in the future.

Physics-Informed Online Learning for Temperature Prediction in Metal AM.

In metal additive manufacturing (AM), precise temperature field prediction is crucial for process monitoring, automation, control, and optimization. Traditional methods, primarily offline and data-driven, struggle with adapting to real-time changes and new process scenarios, which limits their applicability for effective AM process control. To address these challenges, this paper introduces the first physics-informed (PI) online learning framework specifically designed for temperature prediction in metal AM. Utilizing a physics-informed neural network (PINN), this framework integrates a neural network architecture with physics-informed inputs and loss functions. Pretrained on a known process to establish a baseline, the PINN transitions to an online learning phase, dynamically updating its weights in response to new, unseen data. This adaptation allows the model to continuously refine its predictions in real-time. By integrating physics-informed components, the PINN leverages prior knowledge about the manufacturing processes, enabling rapid adjustments to process parameters, geometries, deposition patterns, and materials. Empirical results confirm the robust performance of this PI online learning framework in accurately predicting temperature fields for unseen processes across various conditions. It notably surpasses traditional data-driven models, especially in critical areas like the Heat Affected Zone (HAZ) and melt pool. The PINN's use of physical laws and prior knowledge not only provides a significant advantage over conventional models but also ensures more accurate predictions under diverse conditions. Furthermore, our analysis of key hyperparameters-the learning rate and batch size of the online learning phase-highlights their roles in optimizing the learning process and enhancing the framework's overall effectiveness. This approach demonstrates significant potential to improve the online control and optimization of metal AM processes.

Development of an AI predictive model to categorize and predict online learning behaviors of students in Thailand.

This qualitative study has three objectives: (1) to develop a predictive AI model to categorize the online learning behavior of Thai students who study through a Thai Massive Open Online Course (MOOC); (2) to categorize students' online behavior in a Thai MOOC; and (3) to evaluate the prediction accuracy of the developed predictive AI models. Data were collected from 8000 learners enrolled in the KMUTT015 course on the Thai MOOC platform. The k-means clustering algorithm classified learners enrolled in the Thai MOOC platform based on their online learning behaviors. The decision tree algorithm was used to assess the accuracy of the AI model prediction capability. The study finds the predictive AI model successfully categorizes learners based on their learning behaviors and predicts their future online learning behaviors in the online learning environment. The k-means clustering algorithm yields three groups of learners in the Thai MOOC platform: High Active Participants (HAP), Medium Active Participants (MAP), and Lurking participants. The findings also indicate high predictive accuracy rates for each behavioral group (HAP cluster = 0.98475, Lurking participants cluster = 0.967625, and MAP cluster = 0.955375), indicating the proficiency of the AI predictive model in forecasting learner behavior. The results of this study will benefit the design of online courses that respond to the needs of students with different online learning characteristics and help them achieve a high level of academic performance.

Nursing students' engagement in online learning.

Reliance on digital technology may have implications for our social and economic wellbeing, including factors such as health, environmental quality, social interaction, and educational levels. Although there may be concerns, it is important to acknowledge that digital technology also offers immediate, cost-effective and accessible solutions that are transforming various services. The COVID-19 pandemic, through the disruption of educational systems worldwide, has accelerated the transformation of higher education, leading to changes in the way it is perceived. However, there is a lack of understanding regarding the relationship between digital poverty, digital literacy, and students' online experiences. This article aims to explore the engagement of nursing students in online learning post COVID.

Adaptive EMG decomposition in dynamic conditions based on online learning metrics with tunable hyperparameters.

OBJECTIVE: Robustness to non-stationary conditions is essential to develop stable and accurate wearable neural interfaces. APPROACH: We propose a novel adaptive electromyography (EMG) decomposition algorithm that builds on blind source separation methods by leveraging the Kullback-Liebler divergence and kurtosis of the signals as metrics for online learning. The proposed approach provides a theoretical framework to tune the adaptation hyperparameters and compensate for non-stationarities in the mixing matrix, such as due to dynamic contractions, and to identify the underlying motor neuron (MN) discharges. The adaptation is performed in real-time (~22 ms of computational time per 100-ms batches). MAIN RESULTS: The proposed adaptation algorithm significantly improved all decomposition performance metrics with respect to the absence of adaptation in a wide range of motion of the wrist (80°). The rate of agreement, sensitivity, and precision were ≥ 90% in ≥ 80% of the cases in both simulated and experimentally recorded data, according to a two- source validation approach. SIGNIFICANCE: The findings demonstrate the feasibility of accurately decoding MN discharges in real-time during dynamic contractions from wearable systems mounted at the wrist and forearm. Moreover, the study proposes an experimental validation method for EMG decomposition in dynamic tasks.

Impact of online learning during COVID-19 pandemic on digital device related ocular health.

Objective: The aim of this study was to evaluate the impact of the COVID-19 pandemic on ocular health related to digital device usage among university students in Lebanon. Design: A cross-sectional design was utilized to examine the association between the pandemic and ocular health. Participants: A total of 255 university students in Lebanon participated in the study, selected based on their enrollment during the pandemic. Methods: An online survey assessed participants' digital device usage, awareness of digital eye strain, and experienced symptoms. The study addressed the relationship between symptom frequency and screen time, especially in their connection to the pandemic and online learning. Results: Prior to the pandemic, the majority of participants (73.0 %) were unaware of digital eye strain. Following the transition to online learning, nearly half of the participants (47.0 %) reported using digital devices for 12 or more hours. The majority (92.0 %) experienced a substantial increase in daily digital device usage for learning, with an average increase of 3-5 h. Symptoms of digital eye strain, including headache, burning of eyes, blurry vision, sensitivity to light, worsening of vision and dryness of the eyes intensified in both frequency and severity during the pandemic and online learning period. Conclusions: The study emphasizes the importance of promoting healthy habits and implementing preventive measures to reduce the prevalence of digital eye strain symptoms among university students. Healthcare professionals and public health authorities should educate individuals on strategies to alleviate digital eye strain, considering the persistent reliance on digital devices beyond the pandemic.

An efficient, reliable and valid assessment for affective states during online learning.

The current study aims to develop an efficient, reliable and valid assessment, the affective states for online learning scale (ASOLS), for measuring learners' affective states during online learning using a sample of 173 young learners. The assessment consists of 15 items which assess five affective states, including concentration, motivation, perseverance, engagement, and self-initiative. To improve efficiency, five items (one for each affective state) are randomly selected and presented every 30 min during online learning. In addition, 14 among the participants were further invited to perform on-site online learning, and their affective states were validated by observations conducted by two psychologists. The ASOLS was found to be reliable and valid, with high internal consistency reliabilities and good construct, convergent and criterion validity. Confirmatory factor analyses showed that the hypothesized five-factor structure demonstrated a satisfactory fit to the data. Moreover, engagement was found to be positively associated with learning performance. Our findings suggest that the ASOLS provides a useful tool for teachers to identify students in upper primary and junior secondary schools with deficits in affective states and offer appropriate remedy or support. It can also be used to evaluate the effectiveness of interventions aimed at enhancing students' affective states during online learning.

Peer creation and sharing of mnemonics in collaborative documents for pathology education: a pilot study.

BACKGROUND: Mnemonic techniques are memory aids that could help improve memory encoding, storage, and retrieval. Using the brain's natural propensity for pattern recognition and association, new information is associated with something familiar, such as an image, a structure, or a pattern. This should be particularly useful for learning complex medical information. Collaborative documents have the potential to revolutionize online learning because they could increase the creativity, productivity, and efficiency of learning. The purpose of this study was to investigate the feasibility of combining peer creation and sharing of mnemonics with collaborative online documents to improve pathology education. METHODS: We carried out a prospective, quasi-experimental, pretest-posttest pilot study. The intervention group was trained to create and share mnemonics in collaborative documents for pathological cases, based on histopathological slides. The control group compared analog and digital microscopy. RESULTS: Both groups consisted of 41 students and did not reveal demographic differences. Performance evaluations did not reveal significant differences between the groups' pretest and posttest scores. Our pilot study revealed several pitfalls, especially in instructional design, time on task, and digital literacy, that could have masked possible learning benefits. CONCLUSIONS: There is a gap in evidence-based research, both on mnemonics and on CD in pathology didactics. Even though, the combination of peer creation and sharing of mnemonics is very promising from a cognitive neurobiological standpoint, and collaborative documents have great potential to promote the digital transformation of medical education and increase cooperation, creativity, productivity, and efficiency of learning. However, the incorporation of such innovative techniques requires meticulous instructional design by teachers and additional time for students to become familiar with new learning methods and the application of new digital tools to promote also digital literacy. Future studies should also take into account validated high-stakes testing for more reliable pre-posttest results, a larger cohort of students, and anticipate technical difficulties regarding new digital tools.

Positive affect and self-care mediate the relationship between trait emotional intelligence and academic engagement in Lebanese undergraduates: Lessons learned from an online setting.

This study examined the impact of positive psychology variables, namely trait emotional intelligence (EI), positive affect and self-care, on academic engagement (AE) in an online learning environment during COVID-19. The study involved 717 undergraduates in Lebanon and utilised structural equation modelling for data analysis. The results demonstrated that positive affect and self-care mediated the relationship between trait EI and AE. In women, both self-care and positive affect were mediators, whereas in men, positive affect was the only mediator. For students who received a mix of synchronous and asynchronous lessons, both self-care and positive affect mediated the relationship between trait EI and AE. However, for those who received only synchronous lessons, positive affect was the sole mediator. Furthermore, AE significantly predicted academic performance (AP) in both models. These findings suggest the importance of interventions that enhance trait EI, positive emotions and self-care to improve AE and ultimately AP in online learning.

The effect of Chinese vocational college students' perception of feedback on online learning engagement: academic self-efficacy and test anxiety as mediating variables.

Enhancing learning engagement is a critical challenge in online education. While previous research underscores the importance of feedback, recent studies have shifted focus to students' perceptions of feedback, which significantly impact learning performance. However, empirical evidence on how these perceptions affect online learning outcomes is limited. Drawing on Self-Determination Theory, this study addresses this gap by employing SEM to analyze the relationships among feedback perception, academic self-efficacy, test anxiety, and online learning engagement. A total of 402 Chinese vocational college students (ages 18-19) completed questionnaires, with statistical analysis conducted using SPSS and Mplus. The study found that perception of feedback directly influences online learning engagement and indirectly affects it through academic self-efficacy and test anxiety, with a total effect value of 0.416. The findings offer valuable insights for educators and suggest directions for future research on feedback perception and online learning engagement.

Is YouTube a reliable source of information for temporomandibular joint ankylosis?

PURPOSE: In the digital era, the internet is the go-to source of information, and patients often seek insights on medical conditions like TMJ ankylosis. YouTube, a popular platform, is widely used for this purpose. However, YouTube's lack of regulation means it can host unreliable content. Hence, the primary objective of this study is to assess the scientific quality of YouTube videos concerning TMJ ankylosis. MATERIALS AND METHODS: This study analyzed 59 TMJ ankylosis-related videos. Two Oral and Maxillofacial Surgery specialists assessed these videos. Data on the video source, duration, upload date, the time elapsed since upload, total views, likes, dislikes and comments, Interaction index, and viewing rate were collected and analyzed. Video quality was assessed using the Global Quality Scale (GQS) and the Quality Criteria for Consumer Health Information (DISCERN), comparing health professionals and non-health professionals. RESULTS: Health professional's videos were better in terms of GQS 3.21 ± 0.94 and DISCERN score 3.03 ± 0.75 as compared to the non-health professional videos GQS 3.0 ± 1.04, and DISCERN 2.81 ± 1.13. Health professional group videos had more reliability and better quality than the non-health professional group (p < 0.01). CONCLUSION: YouTube should not be relied on as a trustworthy source for high-quality and reliable information regarding TMJ ankylosis videos. Healthcare professionals must be prepared to address any ambiguous or misleading information and to prioritize building trustworthy relationships with patients through accurate diagnostic and therapeutic processes.

An Al-BERT-Bi-GRU-LDA algorithm for negative sentiment analysis on Bilibili comments.

The number of online self-learning users has been increasing due to the promotion of various lifelong learning programs. Unstructured commentary text related to their real learning experience regarding the learning process is generally published by users to show their opinions and complaints. The article aims to utilize the dataset of real text comments of 10 high school mathematics courses participated by high school students in the Bilibili platform and construct a hybrid algorithm called the Artificial Intelligence-Bidirectional Encoder Representations from Transformers (BERT) + Bidirectional Gated Recurrent Unit (BiGRU) and linear discriminant analysis (LDA) to crunch data and extract their sentiments. A series of tests regarding algorithm comparison were conducted on the educational review datasets. Comparative analysis found that the proposed algorithm achieves higher precision and lower loss rates than other alternative algorithms. Meanwhile, the loss ratio of the proposed algorithm was kept at a low level. At the topic mining level, the topic clustering of negative comments found that the barrage content was very messy and the complexity of the course content was generally reported by the students. Some problems related to videos were also mentioned. The outcomes are promising that the fundamental issues underlined by the students can be effectively resolved to improve curriculum and teaching quality.

Perspectives on dementia care self-learning platform: A focus group study of family and professional caregivers.

OBJECTIVE: To compare perspectives of family and professional caregivers regarding an online self-learning platform. METHODS: Family and professional caregivers were interviewed separately. A thematic analysis was conducted with 12 family caregivers and 13 professional caregivers of people living with dementia in Macao using six semi-structured focus group interviews. RESULTS: Family and professional caregivers had different perspectives regarding the application of online learning program Four main themes emerged from the focus groups, including similarities and differences, namely 1) Need for services; 2) Accessibility to services; 3) Barriers to online learning; 4) Adjustments to the platform. CONCLUSIONS: The psychological assurance offered by an online learning program is imperative to the well-being of family caregivers. By identifying the gap between the needs and abilities of family caregivers and those imagined by professional caregivers, it allows for the development of support programs and interventions tailored to meet the specific needs of family caregivers.

A heutagogical approach to building the residential aged care workforce capability and capacity.

OBJECTIVE: This paper reports on the design and implementation of an interactive online education package for the diverse Australian residential aged care workforce, in response to the findings of the Royal Commission into Aged Care Quality and Safety. A decade of reports has consistently highlighted the need for an educated workforce to care for the increasingly frail older people with complex care needs living in residential aged care. Cost, availability and timing of education have been identified as barriers to uptake of education for this workforce. METHODS: A heutagogical approach was used to design an evidence-based, modular, online education package for nurses, care workers and allied health practitioners working in the residential aged care sector. The subject matter was developed by experts and the education divided into modules. A key challenge was to design a package that was inclusive of the diversity of educational needs in this workforce. The package does not provide assessments on completion of the modules, relying solely on the motivation of the individual learner. RESULTS: This online education package provides choice and self-determination for users in their learning journey. Collaborating with experts to develop an online education program that is learner-driven, challenges the conventions of education. Users can navigate the package at their pace; choose the modules they have identified as knowledge gaps or are of interest; and complete the education in their own time. CONCLUSION: As expected, most users are care workers and nurses and the five modules of the Dementia program are the most popular.

Ineffective Learning Behaviors and Their Psychological Mechanisms among Adolescents in Online Learning: A Narrative Review.

During the COVID-19 pandemic, many countries and regions experienced a surge in online learning, but the public complained about and questioned its effectiveness. One of the most important reasons for this was the inadequate metacognitive abilities of adolescents. Studies in learning sciences have identified various inefficient learning behaviors among students in online learning, including help abuse, help avoidance, and wheel spinning; all closely related to metacognition. Despite concerns about ecological validity, researchers in psychology have proposed the agenda-based regulation framework, the COPES model, and MAPS model, which may help explain the inefficient learning behaviors among adolescents in online learning. Future studies should aim to verify these theoretical frameworks within the context of online learning and elucidate the causes of inefficient learning behaviors; the design and optimization of online learning systems should be informed by theories in cognitive psychology.

General surgery educational resources for Jordanian medical students.

Background: To outline the resources deemed most beneficial to medical students during their general surgery clerkship, as well as to examine their link to students' general surgery scores and the usage of artificial intelligence in general surgery study. Methods: A retrospective survey of Jordanian medical students from six universities was done between March and June 2023 using a 7-item questionnaire covering questions concerning general surgery study methods and scores. Descriptive statistics were used to evaluate demographic data. Chi-square is used to evaluate categorical data, with a P value <0.05 deemed significant. Results: The average age of respondents was 23.3 years, and 54.2 % of the respondents were females, 47.8 % were from Mutah University. Most students (48.2 %) relied on tutor lectures. Students who studied through instructor lectures had the highest grades (9 % excellent, 17 % very good), followed by students who studied using surgery textbooks (6.8 % and 14.6 %, respectively). The relationship between the study method and academic achievement was statistically significant (P < 0.05). Conclusions: Traditional face-to-face learning with instructor lectures and surgery textbooks is still the most efficient approach to attain the greatest scores. Medical students are still underutilizing artificial intelligence.

Exploring the factors influencing academic learning performance using online learning systems.

-Online learning has become vital and fundamental for learning success in higher education institutions to cope with various learning methodologies or crises such as COVID-19. Therefore, this study investigates factors influencing the academic learning performance among diploma and bachelor's degree students who utilize online e-learning systems in Jordan. Using a conceptual model developed from an extensive previous literature review, the study used a quantitative research methodology to collect data via survey questionnaires. Using PLS-SEM, the empirical analysis of 846 questionnaires collected from Jordanian students demonstrates that task-technology fit and students' satisfaction positively influence learning performance and contribute significantly to student academic success using online learning systems. While the quality of system, service, and information are critical determinants of task-technology fit, student interaction, and instructor interaction are critical determinants of student satisfaction. The study highlights the importance of user-friendly interfaces, effective communication channels, collaboration, and positive learning environments. The findings provide practical insights for universities, online learning system designers, administrators, and instructors to enhance student-learning outcomes. Additionally, system providers can use these findings to address essential successful tools and features needed to create effective and efficient online learning environments. This study highlights practical implications that support higher education institutions' efforts to enhance their online e-learning systems quality and improve student-learning outcomes while helping system providers address essential successful tools and features needed.