Learning Portfolio Research Articles

Transparent Machine Learning Model to Understand Drug Permeability through the Blood-Brain Barrier.

The blood-brain barrier (BBB) selectively regulates the passage of chemical compounds into and out of the central nervous system (CNS). As such, understanding the permeability of drug molecules through the BBB is key to treating neurological diseases and evaluating the response of the CNS to medical treatments. Within the last two decades, a diverse portfolio of machine learning (ML) models have been regularly utilized as a tool to predict, and, to a much lesser extent, understand, several functional properties of medicinal drugs, including their propensity to pass through the BBB. However, the most numerically accurate models to date lack in transparency, as they typically rely on complex blends of different descriptors (or features or fingerprints), many of which are not necessarily interpretable in a straightforward fashion. In fact, the "black-box" nature of these models has prevented us from pinpointing any specific design rule to craft the next generation of pharmaceuticals that need to pass (or not) through the BBB. In this work, we have developed a ML model that leverages an uncomplicated, transparent set of descriptors to predict the permeability of drug molecules through the BBB. In addition to its simplicity, our model achieves comparable results in terms of accuracy compared to state-of-the-art models. Moreover, we use a naive Bayes model as an analytical tool to provide further insights into the structure-function relation that underpins the capacity of a given drug molecule to pass through the BBB. Although our results are computational rather than experimental, we have identified several molecular fragments and functional groups that may significantly impact a drug's likelihood of permeating the BBB. This work provides a unique angle to the BBB problem and lays the foundations for future work aimed at leveraging additional transparent descriptors, potentially obtained via bespoke molecular dynamics simulations.

Equitable teacher education in a virtual world: the promise of learning-oriented assessment

ABSTRACT This study reports teacher perceptions towards learning-oriented assessment (LOA) in an English language teaching certification course (Kompetanse for Kvalitet, KfK). The course was delivered online during emergency remote teaching caused by the COVID-19 pandemic. Equitable practices in instruction and assessment aimed at collaboration, dialogue, group engagement, and active involvement based on LOA practices. Even though using assessment to promote learning has been gaining prominence, applying LOA in online learning has recently gained momentum. Thus, the study reports on how an online implementation of LOA is perceived by participants of a teacher education program concerning their learning. Data collection tools included a questionnaire (n = 132) and randomly sampled reflective writings (n = 23) submitted as part of the learner portfolio. Data were analyzed qualitatively through thematic analysis and quantitatively on SPSS using descriptive statistics and Factor Analysis with Varimax rotation. Findings indicated that LOA was perceived positively, offering opportunities to improve language and skills, link course content with teaching practice, and reflect on learning. Using LOA in post-COVID times empowered course participants to identify and monitor their progress and skills. The study has implications for teacher educators integrating LOA and technology in professional development to maintain equity and cultivate efficient learning.

BILSTM Model for Machine Learning Stock Prediction and Portfolio Construction in the Context of Covid-19 Pandemic

BILSTM Model for Machine Learning Stock Prediction and Portfolio Construction in the Context of Covid-19 Pandemic

이해중심 교육과정에 기반한 국어과 의사소통 역량 단원 실행 연구

Objectives This study aims to implement the unit of Korean Language Education Communicative Competency, focusing on discussions using generative AI. Methods This study formed a theoretical background by examining the characteristics of understanding by design, the concept and process of discussions, the utilization of generative AI for discussions, Critical Reflection on the Discussion Unit in the Korean Language Textbook, and the structuring of units based on Korean Language Education Communicative Competency. After establishing a research procedure based on the ADDIE model, constructing an implementation model, selecting measurement tools, organizing a research group, and establishing a plan for effectiveness verification, this study was conducted by applying the unit design developed by Ryu (2023). Results Utilizing the Wilcoxon signed-rank test, the study confirms a significant improvement in the study group's communicative competency in all sub-factors from pre-test to post-test. Through reflective discussions and analysis of learner portfolios using analytical rubrics, it is confirmed that by engaging in discussion activities utilizing generative AI based on inclusiveness and initiative, the communicative competency and discussion skills of the research group have positively improved. Conclusions Hopefully, this study will have implications for the role of Korean Language Education to respond to changes in the future educational environment and contribute to the research and practice of competency-based Korean language education.

Developing an electronic portfolio of learning for family medicine training in South Africa.

Workplace-based assessment has become increasingly crucial in the postgraduate training of specialists in South Africa, particularly for family physicians. The development of a Portfolio of Learning (PoL) has been a central focus within the discipline of family medicine for over a decade. Initially, a paper-based portfolio was adopted to collect evidence of learning for 50 out of 85 agreed exit-level outcomes. Stellenbosch University led the conversion of this portfolio into an electronic format, known as e-PoL, utilising Scorion software. The e-PoL was successfully implemented in the Western and Eastern Cape regions and was subsequently adopted nationally under the coordination of the South African Academy of Family Physicians. In 2023, the e-PoL underwent a redesign to gather evidence of learning for 22 entrustable professional activities (EPAs). Key insights from this development process underscore the importance of the PoL in supporting assessment-for-learning rather than merely assessment-of-learning. This necessitates features for feedback and interaction, ensuring that the PoL functions beyond a mere repository of forms. Additionally, the e-PoL should facilitate triangulation, aggregation, and saturation of data points to effectively measure EPAs. Furthermore, the PoL has not only documented learning but has also played a pivotal role in guiding the development of clinical training by explicitly outlining expectations for both registrars and supervisors. While the initial design and development costs are significant, operational costs become affordable when shared across all training programmes.

Co-design in electronic portfolio for learning: pilot validation of the Co-PIRS Model

Co-design in electronic portfolio for learning: pilot validation of the Co-PIRS Model

Developing and Implementing a Competency-Based Veterinary Medicine Program at the Université de Montréal.

This article outlines the comprehensive reform of the Doctorate in Veterinary Medicine (DVM) program at the Université de Montréal, with a focus on the integration of a competency-based approach within the existing curriculum. The primary purpose of this reform was to enhance student competency and address specific deficiencies in competencies as revealed by annual outcomes assessment surveys. The authors developed a competency framework with seven competencies and specific elements, providing a foundation for the educational redesign. This framework guided the creation of learning-assessment situations (LAS) aimed at promoting active and contextualized learning throughout the program. The competency development and assessment pathway (CDAP) matrix was established to align LAS within the traditional program structure and track student progress. A learning portfolio and a competency certification process were introduced to support student learning and assess competency achievement. The authors discuss change management, including the paradigm shift towards programmatic assessment, and provide insights into the evolution of the program post-implementation. Preliminary outcomes assessment reveals positive changes in how teaching staff and students perceive the program. Despite challenges related to human resource constraints, the authors emphasize the significance of this reform, which aligns with current trends in medical education. This paper underscores the importance of tailoring educational approaches to specific institutional environments while maintaining programmatic rigor and quality assurance.

A scoping review on the use of reflection and reflective portfolio learning in veterinary education.

In veterinary education, reflection and reflective portfolio learning aim to enhance professional development. Although reflection and reflective portfolio learning are widely used in teaching and healthcare, their demonstrable impact on veterinary education is unclear. Although the benefits are uncertain, reflection may provide potential for self-development and help to prepare students for clinical practice. The aim of this work was to review research into reflective practice and reflective portfolio learning, to find evidence for its use in teaching, to confirm how it is best implemented to optimise professional development and to identify gaps for future research. This scoping review was conducted according to the Joanna Briggs Institute guidelines adhering to review methodology. Ten databases were searched and screened for reflection and portfolio learning as a primary source of data. Of 29,933 texts identified by title and/or abstract, 51 final works were screened in full. Of these, 16 papers that gathered evidence on reflection were included. The results confirmed a growing evidence base for reflection in the veterinary field. In total, six works demonstrated a positive impact on professional development. Written reflective assignments were the most common methods of implementation, with 11 papers referencing their use. Other methods included group discussion and facilitated reflection. This review identified numerous gaps for research, including validating the methods of implementation, exploring the efficacy of methods other than written reflection, examining how reflection is used at different stages of the veterinary career and study of different models of reflection to identify which are most useful.

Investigating the Learning Outcomes of Non-cognitive Abilities in University Admissions Across Countries: A Study Through Learning Portfolios

Investigating the Learning Outcomes of Non-cognitive Abilities in University Admissions Across Countries: A Study Through Learning Portfolios

Evidence of learning in workplace-based assessments in a Family Medicine Training Programme.

Learning portfolios (LPs) provide evidence of workplace-based assessments (WPBAs) in clinical settings. The educational impact of LPs has been explored in high-income countries, but the use of portfolios and the types of assessments used for and of learning have not been adequately researched in sub-Saharan Africa. This study investigated the evidence of learning in registrars' LPs and the influence of the training district and year of training on assessments. A cross-sectional study evaluated 18 Family Medicine registrars' portfolios from study years 1-3 across five decentralised training sites affiliated with the University of the Witwatersrand. Descriptive statistics were calculated for the portfolio and quarterly assessment (QA) scores and self-reported clinical skills competence levels. The competence levels obtained from the portfolios and university records served as proxy measures for registrars' knowledge and skills. The total LP median scores ranged from 59.9 to 81.0, and QAs median scores from 61.4 to 67.3 across training years. The total LP median scores ranged from 62.1 to 83.5 and 62.0 to 67.5, respectively in QAs across training districts. Registrars' competence levels across skill sets did not meet the required standards. Higher skills competence levels were reported in the women's health, child health, emergency care, clinical administration and teaching and learning domains. The training district and training year influence workplace-based assessment (WPBA) effectiveness. Ongoing faculty development and registrar support are essential for WPBA.Contribution:This study contributes to the ongoing discussion of how to utilise WPBA in resource-constrained sub-Saharan settings.

‘유아교육과정’ 교과목 수업 개선 실천

This study explored the student agency changes of prospective early childhood teachers revealed in the process of improving the ‘Early Childhood Education Curriculum’ subject at S University in the metropolitan area. The research participants were 56 students from the Department of Early Childhood Education at S University and one professor who is the researcher oneself for the purpose of improving the 'Early Childhood Education Curriculum' class, the early childhood education curriculum theory lectures, on-site field classes, and TBL(Team Based Learning) were used to provide education to children. Research materials include kindergarten visit reports, research participants' PPT for early childhood education program presentation and key summaries, learning portfolios, class improvement reflection sheets, and researchers' research notes. The data collected during the research process was categorized based on specific concepts and reclassified based on the research problem through inductive content analysis. Excitement was mainly showed when the exercise of student agency was executed and field visit to kindergartens, and unfamiliarity was expressed through TBL early childhood education program presentations and discussion classes and learning portfolio experiences. Second, after improving the ‘Early Childhood Education Curriculum’ class, it is said that students came to recognize themselves as learners who formed student agency at the intersection of reflection and practice. I found autonomy like a compass through TBL, and through kindergarten field-related classes, they found themselves as a valuable resource as a early childhood teacher who lacked understanding of the connection between early childhood education theory and practice. Based on this study, we hope to become a systematic turning point in teaching-learning methods for improving theoretical classes to train high-quality pre-service early childhood teachers.

Castle Oaks Learning Portfolio: How we stand tall to end injustices and become allies to walk the path of Truth and Reconciliation

Students in F3A, F4A, 34A, F45, F5A and F5B at Castle Oaks Public School are learning how to stand tall and how to use their voices to advocate for equitable services and resources for Indigenous children. We are learning how we can listen, learn and honour the Truth in order to be allies and walk the path of Reconciliation. With our Reconciliation Ambearristers, we are learning how we can stand tall to end inequities and create a fair, safe and caring world for all children. We created a learning portfolio to showcase our learning thus far.

The impact of Methodological choices on Machine Learning Portfolios

The impact of Methodological choices on Machine Learning Portfolios

Exploring the Acceptance and User Satisfaction of AI-Driven e-Learning Platforms (Blackboard, Moodle, Edmodo, Coursera and edX): An Integrated Technology Model

As e-learning platforms gain traction globally, understanding students’ perceptions and intentions towards these platforms is paramount, especially within the context of Saudi universities, where e-learning is rapidly emerging as a transformative educational tool for sustainable development. This study examined the influence of different AI-based social learning networks, personal learning portfolios, and personal learning environments on Saudi university students’ perceived usefulness and ease of use regarding AI-driven platforms (Blackboard, Moodle, Edmodo, Coursera and edX). Furthermore, the study explored the direct effects of these perceptions on students’ satisfaction and intentions to use e-learning. The study also delved into the moderating effects of individual characteristics like readiness for self-directed e-learning, self-efficacy, and personal innovativeness on students’ e-learning intentions. A cross-sectional design was employed, collecting self-reported data from a strong sample of Saudi university students using stratified random sampling. The study targeted 500 students from different universities in Saudi Arabia. Results underscored the significant influence of AI-based social learning networks, personal learning portfolios, and personal learning environments on perceived usefulness and ease of use. Both perceived usefulness and ease of use also significantly and positively influenced satisfaction, influencing students’ attitudes toward e-learning but not their intention to use it. Student characteristics, especially self-efficacy, showed notable impacts on e-learning intentions. However, their interaction with satisfaction yielded insignificant effects on intentions.

Exploring the effects of cross-cultural collaborating on bilingual digital storytelling on students’ intercultural learning

ABSTRACT As intercultural learning has been increasingly regarded as essential in higher education, researchers have promoted it through integration of digital storytelling into cultural exchange activities. However, most studies have focused on the utilization of only one language whereas the effects of multilingual digital storytelling on students’ intercultural learning is understudied. To help bridge this gap, in this study, the effects of creating bilingual digital stories with students in an English-speaking country on the intercultural learning of students in a Chinese-speaking country were investigated. Data included students’ learning portfolios and reflective essays and were analyzed utilizing content analysis and matrix coding query. The findings revealed that the students became more critically aware of their own and others’ cultural diversity and sensitive to the uses of both English and Chinese language and multimedia resources for communication with people from different cultural backgrounds. They also reported multiple advantages associated with their cross-cultural online interactions, specifically in the domains of language acquisition and cultural understanding. However, they also highlighted challenges, notably the difficulties in coordinating meeting schedules and overcoming communication barriers. Implications and limitations are also discussed.

Being, becoming and sustaining: learning professional learning in teacher education

ABSTRACT In this study, we are exploring the development of professional learning of nearly qualified teachers, here referred to as prospective teachers, during their subject teacher education at a Finnish university. From a teacher educator stance, we aim to understand how teacher education practices can support prospective teachers’ professional learning. The research question guiding our study is: How are prospective teachers portraying their professional learning by making use of a self-reflective portfolio? The data analysed consists of self-reflective learning portfolios written by prospective subject teachers as a course assignment in a course in general didactics. Drawing on a practice theoretical perspective, the analysis highlights how activities and assignments supporting both individual and collegial learning can be arranged during pre-service teacher education, and how prospective teachers can achieve a sense of collaborative and dialogic professional learning. The results contribute to discussions about promoting sustainable professional learning for both prospective and in-service teachers.

Interactive Website: Dynamic Virtual Classroom Creation Training

The integration of Information and Communication Technology (ICT) in teaching in the current era of the industrial revolution opens opportunities to enhance the learning experience and provide a more inclusive, innovative, and engaging education. One of the latest trends receiving attention in the field of education is the implementation of Interactive Websites through the Google Sites platform. Therefore, BDK Ambon, as an educational and training institution, conducts Multimedia Learning Training. In this training, the facilitator, represented by the trainer, conducts research with the aim of describing the training process for creating Google Sites as a Learning Portfolio. The research is carried out in Southeast Maluku Regency, involving 35 teachers. This research employs a descriptive survey method divided into three stages: the preparation stage, the implementation stage, and the evaluation stage. The research findings revealed that 90% of the teachers were unfamiliar with how to use Google Sites as a learning portfolio, as observed during the preparation phase. However, during the implementation phase of the training, the participants enthusiastically engaged in the training activities, and by the end of the session, they were capable of creating and utilizing Google Sites to support learning. Moving on to the evaluation phase, the results showed that all participants were categorized above the established standard. The scores of all participants fell into the categories of fairly competent, competent, and highly competent. This demonstrates the effectiveness of the multimedia learning training and its ability to provide positive benefits for teachers. Looking ahead, it is necessary to conduct similar training in order to enable all teachers in the BDK Ambon working area to utilize and leverage technology to its fullest potential.

Machine learning portfolios for US stock prices: Directional forecasting before and during the COVID-19 pandemic

Machine learning portfolios for US stock prices: Directional forecasting before and during the COVID-19 pandemic

Machine-Learning-Based Rotating Detonation Engine Diagnostics: Evaluation for Application in Experimental Facilities

Real-time monitoring of combustion behavior is a crucial step toward actively controlled rotating detonation engine (RDE) operation in laboratory and industrial environments. Various machine learning methods have been developed to advance diagnostic efficiencies from conventional postprocessing efforts to real-time methods. This work evaluates and compares conventional techniques alongside convolutional neural network (CNN) architectures trained in previous studies, including image classification, object detection, and time series classification, according to metrics affecting diagnostic feasibility, external applicability, and performance. Real-time, capable diagnostics are deployed and evaluated using an altered experimental setup. Image-based CNNs are applied to externally provided images to approximate dataset restrictions. Image classification using high-speed chemiluminescence images and time series classification using high-speed flame ionization and pressure measurements achieve classification speeds enabling real-time diagnostic capabilities, averaging laboratory-deployed diagnostic feedback rates of 4–5 Hz. Object detection achieves the most refined resolution of 20 μs in postprocessing. Image and time series classification require the additional correlation of sensor data, extending their time-step resolutions to 80 ms. Comparisons show that no single diagnostic approach outperforms its competitors across all metrics. This finding justifies the need for a machine learning portfolio containing a host of networks to address specific needs throughout the RDE research community.

Effects of Learning Portfolios in General Education Courses on Undergraduates' Self-Regulated Learning Abilities, Ego-Resilience, and Self-Directed Learning Readiness

Learning portfolios have garnered attention in education since the mid-1990s. Despite this, there is a lack of comprehensive research on their effect, particularly regarding their affective factors. This study aims to design a course using learning portfolios in general education and to verify its effects on self-regulated learning, ego-resilience, and self-directed learning readiness. The research involved a total of 226 Korean and Chinese international students from one Korean university. They were surveyed before and after participating in the learning portfolio course. The self-regulated learning abilities, ego-resilience, and self-directed learning readiness of both participating and non-participating groups were measured and analyzed. The findings indicated that learning portfolios significantly enhanced self-regulated learning abilities, ego-resilience, and self-directed learning readiness among Korean undergraduates. Conversely, these activities had no notable impact on the self-regulated learning abilities, ego-resilience, and self-directed learning readiness of Chinese international students. Based on these results, implications were suggested for integrating learning portfolio activities into general education.