Integrating deep learning techniques for personalized learning pathways in higher education.

The rapid improvement of artificial intelligence (AI) in the educational domain has opened new possibilities for enhancing the learning experiences for students. This research discusses the critical need for personalized education in higher education by integrating deep learning (DL) techniques to create customized learning pathways for students. This research intends to bridge the gap between constant educational content and dynamic student needs. This research presents an AI-driven adaptive learning platform implemented across four different courses and 300 students at a university in Faisalabad-Pakistan. A controlled experiment compares student outcomes between those using the AI platform and those undergoing traditional instruction. Quantitative results demonstrate a 25 % improvement in grades, test scores, and engagement for the AI group, with a statistical significance of a p-value of 0.00045. Qualitative feedback highlights enhanced experiences attributed to personalized pathways. The DL analysis of student performance data highlights key parameters, including enhanced learning outcomes and engagement metrices over time. Surveys reveal increased satisfaction compared to one-size-fits-all content. Unlike prior AI research lacking rigorous validation, our methodology and significant results deliver a concrete framework for institutions to implement personalized, AI-driven education at scale. This data-driven approach builds on previous attempts by tying adaptations to actual student needs, yielding measurable improvements in key outcomes. Overall, this work empirically validates that AI platforms leveraging robust analytics to provide customized and adaptive learning can significantly enhance student academic performance, engagement, and satisfaction compared to traditional approaches. These findings have insightful consequences for the future of higher education. The research contributes to the growing demand for AI in education research and provides a practical framework for institutions seeking to implement more adaptive and student-centric teaching methodologies.

[Using Cloud Healthcare to Improve Home Learning Efficacy in Congenital Heart Disease Infants].

BACKGROUND: During the COVID-19 pandemic, visitation restrictions in line with infection control policies curtailed opportunities for family members to learn essential caregiving skills in the intensive care unit. This limitation decreased satisfaction among family members, possibly indicating their increased difficulties in care due to the lack of face-to-face guidance. Thus, increasing family member understanding of and ability to apply learning content without direct interaction presents a significant and urgent challenge. Moreover, because of lack of caregiving confidence, some family members may be reluctant to facilitate the discharge of critically ill patients, causing delays in discharge planning. These challenges underscore the obstacles faced by nursing health education during the pandemic. PURPOSE: This study was designed to utilize cloud technology to enhance the knowledge and skills of families caring for infants with congenital heart disease at home and to assess their satisfaction with the associated homecare learning platform. RESOLUTION: Based on our hospital's cloud-based health education platform, a series of personalized instructional video materials was developed for families of infants with congenital heart disease. These materials cover comprehensively the entire treatment process, from diagnosis to post-discharge home care skills, for these patients. To facilitate autonomous learning, the videos in this series were made accessible to the families anytime, anywhere via personal devices such as smartphones and tablets. Concurrently, a chatbot tool was integrated to provide guidance on inpatient care for infants with congenital heart disease, including fundamental aspects of newborn care, with the aim of equipping parents and caregivers with the knowledge and skills necessary to provide basic post-discharge care. To ensure the families acquired personalized care skills, after completing the learning modules, practical bedside training sessions incorporating knowledge and skills assessments were organized for family members. RESULTS: After project implementation, the average knowledge score for family members increased significantly from 79.1 to 100 (perfect score). The proportion of family members proficient in executing caregiving techniques autonomously also rose impressively from 30% to 95%. Furthermore, average overall satisfaction with cloud-based technology-assisted caregiving learning among the family members rose 31.4% from 3.5 to 4.6. CONCLUSIONS: This project represents a viable solution to providing clinical nursing guidance independent of the constraints of time and location, and effectively enhances homecare-skill-related learning outcomes in family members, especially with regard to caring for infants with congenital heart disease.

Personalized strategies for academic success in learning anatomy: Exploring metacognitive and technological adaptation in medical students.

Personalization of learning is an educational strategy rooted in metacognition and is significant in academic training. This is especially true in medical contexts. This study explored the relationship between the metacognitive profile of students of human anatomy, the classification of questions according to their difficulty, and the anatomical domain. It also covered the integration of educational technologies to create personalized learning environments. The identification of metacognitive profiles ("Active", "Pragmatic", "Theoretical", and "Reflective") has been highlighted as a critical influence on students' responses to different pedagogical approaches. Personalized adaptation based on these profiles has shown potential for improving grades and increasing student satisfaction and engagement with learning. The results revealed variations in student performance in relation to different pedagogical approaches, learning units, and evaluation modalities. The "Experience" evaluation modality, personalized according to metacognitive profiles, level of competence, and learning objectives, resulted in higher average scores. However, there was significant variability in the results. Those findings confirm the effectiveness of metacognitive adaptation in improving academic performance. Furthermore, they provide a solid basis for formulating personalized and effective pedagogical strategies in medical education. They recognize the influence of metacognitive profiles on student performance and contribute to advancing medical pedagogy.

Thematic evolution of smart learning environments, insights and directions from a 20-year research milestones: A bibliometric analysis.

Smart learning environments (SLEs) have been developed to create an effective learning environment gradually and sustainably by applying technology. Given the growing dependence on technology daily, SLE will inevitably be incorporated into the teaching and learning process. Without transforming technology-enhanced learning environments into SLE, they are restricted to adding sophistication and lack pedagogical benefits, leading to wasteful educational investments. SLE research has grown over time, particularly during the COVID-19 pandemic in 2020-2021, which fundamentally altered the "landscape" of technology use in education. This study aims to discover how the stages of SLE transform from time to time by applying two bibliometric analysis approaches: publication performance analysis and science mapping. The dataset was created by extracting bibliometric data from Scopus, including 427 articles, 162 publication sources (journals and proceeding), and 1080 authors from 2002 to 2022. Three kinds of SLE research subjects were identified by keyword synthesis: SLE features, technological innovation, and adaptive learning systems. Adaptive learning and personalized learning are consistently used interchangeably to demonstrate the significance of supporting the diversity of student and teacher conditions. Learning analytics, essential to employing big data technology for educational data mining, is a new theme being considered increasingly in the future to achieve adaptive and personalized learning. The 20-year SLE research milestone, broken down into five stages with various focuses on goals and served as the foundation for creating a maturity model of SLE.

Pharmacology education in the medical curriculum: Challenges and opportunities for improvement.

The knowledge and application of pharmacology is essential for safe prescribing and administration of drugs. In this narrative review, the challenges to pharmacology education in the medical curricula were broadly identified to include issues around content and pedagogies. The increasing number of approved drugs and drug targets, expanding field of pharmacology and the often-changing treatment guidelines and board-defined competencies can make pharmacology education in the medical curriculum daunting. There has been a consensus around the deployment of innovative medical curricula with emphasis on vertical and horizontal integration. This strategy, effective as it has been, presents new challenges to pharmacology education. As a discipline often perceived by students to be hard-to-learn, the future of pharmacology education must include heavy reliance on active learning strategies. The continuing utilization of problem-based, team-based and case-based learning can be complemented with personalized learning which aims to identify the learning gaps in individual students. Technology-inspired student engagement can foster pharmacology learning and retention. Early exposure to pharmacology from premedical preparation through an enduring across-the-level integration can be an effective way to enhance pharmacology learning in the medical curricula.

Improving Athletic Trainers' Knowledge of Clinical Documentation through Novel Educational Interventions: A Randomized Controlled Trial.

CONTEXT: Athletic trainers (ATs) have reported the need for more educational resources about clinical documentation. OBJECTIVE: To investigate the effectiveness of passive and active educational interventions to improve practicing ATs' clinical documentation knowledge. DESIGN: Randomized control trial, sequential explanatory mixed methods study. SETTING: Online module(s), knowledge assessment and interviews. PATIENTS OR OTHER PARTICIPANTS: We emailed 18,981 practicing ATs across employment settings, of which 524 ATs were enrolled into a group [personalized learning pathway (PLP=178), passive reading list (PAS=176), control (CON=170)] then took the knowledge assessment. There were 364 ATs who did not complete the intervention and/or post-knowledge assessment; therefore, complete responses from 160 ATs (PLP=39, PAS=44, CON=77; age=36.6±11.2y, years certified=13.9±10.7y) were analyzed. MAIN OUTCOME MEASURE(S): Knowledge assessment (34 items) and interview guides (12-13 items) were developed, validated, and piloted with ATs prior to study commencement. We summed correct responses (1 point each, 34 points maximum) and calculated percentages and pre- and post-knowledge mean change scores. Differences among groups (PLP, PAS, CON) and time (pre- intervention, post-intervention) were calculated using a 3X2 repeated-measures ANOVA (P≤.05) with post hoc Tukey HSD. Semi-structured interviews were conducted (PLP=15, PAS=14), recorded, transcribed, and analyzed following the consensual qualitative research tradition. RESULTS: No differences in the pre-knowledge assessment were observed between-groups. We observed a group x time interaction (F2,157 = 15.30, P<.001; partial eta-squared=0.16). The PLP exhibited greater mean change (M=3.0±2.7) than PAS (M=1.7±3.0, P=.049) and CON (M=0.4±2.2, P<.001). Descriptively, ATs scored lowest on legal (61.3%±2.1%), value of the AT (63.7%±4.3%), and health information technology (65.3%±3.7%) items. Whereas ATs described being confident in their documentation knowledge, they also identified key content (eg, legal considerations, strategies) they deemed valuable. CONCLUSIONS: The educational interventions improved ATs' knowledge of clinical documentation and provided valuable resources for their clinical practice; however, targeted continuing education is needed to address knowledge gaps.

Designing Optimal, Data-Driven Policies from Multisite Randomized Trials.

Optimal treatment regimes (OTRs) have been widely employed in computer science and personalized medicine to provide data-driven, optimal recommendations to individuals. However, previous research on OTRs has primarily focused on settings that are independent and identically distributed, with little attention given to the unique characteristics of educational settings, where students are nested within schools and there are hierarchical dependencies. The goal of this study is to propose a framework for designing OTRs from multisite randomized trials, a commonly used experimental design in education and psychology to evaluate educational programs. We investigate modifications to popular OTR methods, specifically Q-learning and weighting methods, in order to improve their performance in multisite randomized trials. A total of 12 modifications, 6 for Q-learning and 6 for weighting, are proposed by utilizing different multilevel models, moderators, and augmentations. Simulation studies reveal that all Q-learning modifications improve performance in multisite randomized trials and the modifications that incorporate random treatment effects show the most promise in handling cluster-level moderators. Among weighting methods, the modification that incorporates cluster dummies into moderator variables and augmentation terms performs best across simulation conditions. The proposed modifications are demonstrated through an application to estimate an OTR of conditional cash transfer programs using a multisite randomized trial in Colombia to maximize educational attainment.

Validity of the UCEEM in use: How Does it Triangulate with Qualitative Data in Measuring the Effect of an Educational Intervention?

Objectives: Improving medical student placements relies on being able to reliably evaluate how students experience clinical learning environments. The Undergraduate Clinical Education Environment Measure (UCEEM) is an increasingly used validated tool designed to allow such evaluations. This study aims to further characterize how the UCEEM relates to qualitative evaluation. methods: Students on placement at one hospital were invited to complete the UCEEM before and after the implementation of an innovative new placement structure. Additionally, focus groups were employed to collect qualitative data on their experiences. a novel protocol to triangulate the output of the UCEEM with the qualitative data was developed. Results: The UCEEM showed good internal consistency (Cronbach's Alpha 0.79-0.91) and internal correlation. Implementation of the intervention created significant improvements in the overall UCEEM scores (P = .008) and in the "Learning in and through work and quality of supervision" (P = .048), "Preparedness for student entry" (P = .033) and "Workplace interaction patterns and student inclusion" (P = .039) domains. The triangulation of qualitative data with UCEEM output showed that the UCEEM allowed evaluation of some perceptions not reached through open questioning. However, mixed interpretations of UCEEM items by students led to the conflation of themes and challenges in deriving the meaning behind the score. This appeared to be the case for 14 of the 24 UCEEM items. Conclusion: This investigation adds to the literature supporting the UCEEM as a validated tool. It also elucidates the limitations and relationships to qualitative data that investigators need to be aware of in its use.

Examining the Impact of Assistive Technology on Psychological Health, Family Education, and Curriculum Research in Japan: Insights from Artificial Intelligence.

This study aims to analyze the effect of psychological health based on artificial intelligence agent technology on the implementation effect of Japanese family education. By combining mobile agent technology and education thought, the system structure and working mechanism of the education support system of agents are studied to build personalized support for the family education system based on mobile agents. A total of 320 Japanese middle school students were randomly divided into an experimental group and a control group, with 160 cases in each group. The control group received traditional family health education, while the experimental group received mental health education based on the Agent Technology family education system. The basic information and mental health scores of the two groups of students were compared. The results showed that there were no remarkable differences in the number of male and female cases, weight, height, average age, grade, home address, or family situation between groups (p > 0.05). The psychological health level of the experimental group was considerably superior to that of the control group regarding obsessional symptoms, interpersonal tension and sensitivity, depression, anxiety, learning pressure, maladaptation, emotional imbalance, and psychological imbalance (p < 0.05). In summary, compared with traditional family education, family education of the mental health education system based on agent technology can better improve the level of middle school students' mental health, which can improve student forced symptoms, interpersonal tension and sensitivity, depression, anxiety, learning pressure, maladjustment, emotional imbalance, psychological imbalance, and many other psychological states. Furthermore, personalized support for family education systems based on mobile agents has the advantages of autonomy, responsiveness, initiative, and mobility, which provides a new idea for family education.

The Charm or Chasm of Digital Personalized Learning in Education: Teachers' Reported Use, Perceptions and Expectations.

Although digital personalized learning (DPL) is assumed to be beneficial for the student as well as the teacher, the implementation process of DPL tools can be challenging. Therefore, the aim of our study is to scrutinize teachers' perceptions towards the implementation of DPL in the classroom. A total of 370 teachers from primary and secondary education (students aged 6-18 years old) were questioned through an online survey. An overview of descriptive results is presented regarding (1) teachers' reported technology use, (2) their perceptions towards adaptivity and dashboards in DPL tools and (3) their expectations of support in view of implementing DPL. Based on a cluster analysis, three teacher clusters are distinguished. Results reveal all three clusters had positive perceptions towards DPL. Nevertheless, there is great variety in reported use of DPL tools.

Research on the correlation between the preference of personalized learning resource recommendation system and self-directed learning level of medical students / 中华医学教育探索杂志

Objective:To understand the preferences of medical students for the performance, function and recommendation method of personalized learning resource recommendation system, as well as the correlation with the self-directed learning ability of medical students, so as to provide a reference for further building an effective learning platform and learning resource tool.Methods:A total of 482 first-year to third-year medical students in a medical university were selected as the research subjects. The electronic self-directed learning scale and the self-designed medical education learning resources recommendation system of performance, function and recommendation method scale were used to conduct a questionnaire survey. Pearson correlation analysis was used to explore the correlation between the performance, function and recommendation method preference of medical students' information resource recommendation system and self-directed learning ability.Results:Medical students had high demand and preference for learning [(4.35±0.58) points], accuracy [(4.32±0.62) points] and timeliness [(4.32±0.62) points] of learning resource recommendation system. In terms of the function of the recommendation system, the following [(4.10±0.71) points] and sharing [(3.94±0.82) points], and searching [(4.35±0.59) points], feedback [(4.09±0.73) points] and publication [(3.80±0.88) points] in the interactive function were all highly rated. For the preference of recommendation methods, the scores of discipline connection [(4.07±0.66) points] and time line [(4.02±0.74) points] were higher. The dimensions with high relevance to self-directed learning included timeliness ( r=0.367), social attributes ( r=0.361), and the basis of similar groups ( r=0.316). Conclusion:Medical students are familiar with and have a positive attitude towards the performance, functions and recommendation methods of the learning resource recommendation system, and have a cognitive foundation for the construction of the learning resource recommendation system and related resource platforms. This system has a certain correlation with the self-directed learning ability of medical students. Promoting the construction of medical education information resources is conducive to promoting the development of self-directed learning ability of medical students.

Corrigendum: Video playback speed influence on learning effect from the perspective of personalized adaptive learning: A study based on cognitive load theory.

[This corrects the article DOI: 10.3389/fpsyg.2022.839982.].

Students' adaptive deep learning path and teaching strategy of contemporary ceramic art under the background of Internet.

With the rapid expansion of Internet technology, this research aims to explore the teaching strategies of ceramic art for contemporary students. Based on deep learning (DL), an automatic question answering (QA) system is established, new teaching strategies are analyzed, and the Internet is combined with the automatic QA system to help students solve problems encountered in the process of learning. Firstly, the related theories of DL and personalized learning are analyzed. Among DL-related theories, Back Propagation Neural Network (BPNN), Convolutional Neural Network (CNN), Long Short-Term Memory (LSTM), and Gated Recurrent Unit (GRU) are compared to implement a single model and a mixed model. Secondly, the collected student questions are selected and processed, and experimental parameters in different models are set for comparative experiments. Experiments reveal that the average accuracy and Mean Reciprocal Rank (MRR) of traditional retrieval methods can only reach about 0.5. In the basic neural network, the average accuracy of LSTM and GRU structural models is about 0.81, which can achieve better results. Finally, the accuracy of the hybrid model can reach about 0.82, and the accuracy and MRR of the Bidirectional Gated Recurrent Unit Network-Attention (BiGRU-Attention) model are 0.87 and 0.89, respectively, achieving the best results. The established DL model meets the requirements of the online automatic QA system, improves the teaching system, and helps students better understand and solve problems in the ceramic art courses.

Video Playback Speed Influence on Learning Effect From the Perspective of Personalized Adaptive Learning: A Study Based on Cognitive Load Theory.

Following the COVID-19 pandemic, online learning has become a new mode of learning that students must adapt to. However, the mechanisms by which students receive and grasp knowledge in the online learning mode remain unknown. Cognitive load theory (CLT) offers instructions to students considering the knowledge of human cognition. Therefore, this study considers the CLT to explore the internal mechanism of learning under the online mode in an experimental study. We recruited 76 undergraduates and randomly assigned them to four groups in which they will watch videos at four different kinds of speed (1.0× or 1.25× or 1.5× or 2× speed). The study observed and analyzed how video playback speed affected students' learning and cognitive load to obtain the following results: (1) Video playback speed significantly influenced the students' learning effect. The best effect was observed at the speed of 1.25× and 1.5×. (2) The speed that affected the learning effect best differed according to the students' learning abilities. High-level group students performed best at the speed of 1.5×, whereas low-level group students performed best at the speed of 1.25×. (3) The 1.5× speed showed significant differences in the learning effect by students' majors. This indicates that the cognitive load of liberal arts students increased greatly at this speed. (4) A change in playback speed has a significant impact on the cognitive load. Accelerated playback speed increases the cognitive load of students. The highest learning effect is observed under medium cognitive load.

Personalized and Adaptive Context-Aware Mobile Learning: Review, challenges and future directions.

Due to the outbreak of COVID 19, digital learning has become the most efficient learning and teaching technique adopted across the world. The pervasiveness of Personalized and Adaptive Context-Aware Mobile Learning (PACAML) technologies is improving the academic performances of learners by providing an efficient learning platform that supports social interactivity, context sensitivity, connectivity, and individuality in a ubiquitous manner. Several studies have demonstrated the efficacy of PACAML in a modern and innovative educational environment. Based on the recent studies and development of mobile learning technologies, there is clearly a gap in the research that provides a comprehensive body of knowledge on PACAML. In this paper, a review has been conducted on the existing PACAML, analyzing the recent research and development progress using Kitchenham et al. (2009) for systematic reviews. The review was conducted on 25 papers which were selected using the PRISMA technique to put forward the quality criteria that are based on the research aims, objectives and knowledge relevant to the study of PACAML. The results identified the contextual information used in the PACAML studies, the infrastructural requirements of PACAML, the application of PACAML in functional educational settings and the major methodological approaches applied in the studies of PACAML. Finally, the paper presents challenges and future directions that will be of interest to researchers in the educational technologies in the context of PACAML.

Mobile game-based learning as a solution in COVID-19 era: Modeling the pedagogical affordance and student interactions.

The closure of educational institutions due to the COVID-19 pandemic leads imperatively to the utilization of technological advances and the Internet for enabling the continuity of learning. To this direction, Mobile Game-based Learning (MGbL) can be beneficial to teaching and learning; since, from technological perspective, most students prefer to use their mobile devices, such as smartphones or tablets, and from pedagogical perspective, incorporating gaming in educational process can boost students' motivation for learning and improve their learning outcomes. Hence, this study investigates learners' intention to use MGbL as an alternative educational practice during the COVID-19 pandemic, by modeling the pedagogical affordance of this technology and student interactions with it. As a testbed for this research, a MGbL application was used for the instruction of the programming language C# in higher education, during the lockdown period of 2020. The findings reveal that the MGbL technology has a significant and positive impact on student engagement and academic performance.

Building an intelligent recommendation system for personalized test scheduling in computerized assessments: A reinforcement learning approach.

The introduction of computerized formative assessments in the classroom has opened a new area of effective progress monitoring with more accessible test administrations. With computerized formative assessments, all students could be tested at the same time and with the same number of test administrations within a school year. Alternatively, the decision for the number and frequency of such tests could be made by teachers based on their observations and personal judgments about students. However, this often results in rigid test scheduling that fails to take into account the pace at which students acquire knowledge. To administer computerized formative assessments efficiently, teachers should be provided with systematic guidance regarding effective test scheduling based on each student's level of progress. In this study, we introduce an intelligent recommendation system that can gauge the optimal number and timing of testing for each student. We discuss how to build an intelligent recommendation system using a reinforcement learning approach. Then, we present a case study with a large sample of students' test results in a computerized formative assessment. We show that the intelligent recommendation system can significantly reduce the number of testing for the students by eliminating unnecessary test administrations where students do not show significant progress (i.e., growth). Also, the proposed recommendation system is capable of identifying the optimal test time for students to demonstrate adequate progress from one test administration to another. Implications for future research on personalized assessment scheduling are discussed.

Differences in personalized learning practice and technology use in high- and low-performing learner-centered schools in the United States.

The Every Student Succeeds Act supports personalized learning (PL) to close achievement gaps of diverse K-12 learners in the United States. Implementing PL into a classroom entails a paradigm change of the educational system. However, it is demanding to transform traditional practice into a personalized one under the pressure of the annual standardized testing while it is unclear which PL approaches are more likely to result in better academic outcomes than others. Using national survey data of ELA teachers in identified learner-centered schools, this study compared high and low-performing learner-centered schools (determined by their standardized test results) in terms of their use of five PL features (personalized learning plan, competency-based student progress, criterion-referenced assessment, project- or problem-based learning, and multi-year mentoring) and their use of technology for the four functions of planning, learning, assessment, and recordkeeping. Generally, teachers in high-performing schools implemented PL more thoroughly and utilized technology for more functions than those in low-performing schools. Teachers in high-performing schools more frequently considered career goals when creating personal learning plans, shared the project outcomes with the community, and assessed non-academic outcomes. They stayed longer with the same students and developed close relationships with more students. Also, they more frequently used technology for sharing resources and reported having a more powerful technology system than those in low-performing schools. This study informs educators, administrators, and researchers of which PL approaches and technology uses are more likely to result in better academic outcomes measured by standardized assessments.