Analysis and Prediction of Student Performance Based on Moodle Log Data using Machine Learning Techniques

During the COVID-19 Pandemic, many universities in Thailand were mostly locked down and classrooms were also transformed into a fully online format. It was challenging for teachers to manage online learning and especially to track student behavior since the teacher could not observe and notify students. To alleviate this problem, one solution that has become increasingly important is the prediction of student performance based on their log data. This study, therefore, aims to analyze student behavior data by applying Predictive Analytics through Moodle Log for approximately 54,803 events. Six Machine Learning Classifiers (Neural Network, Random Forest, Decision Tree, Logistic Regression, Linear Regression, and Support Vector Machine) were applied to predict student performance. Further, we attained a comparison of the effectiveness of early prediction for four stages at 25%, 50%, 75%, and 100% of the course. The prediction models could guide future studies, motivate self-preparation and reduce dropout rates. In the experiment, the model with 5-fold cross-validation was evaluated. Results indicated that the Decision Tree performed best at 81.10% upon course completion. Meanwhile, the SVM had the best result at 86.90% at the first stage, at 25% of the course, and Linear Regression performed with the best efficiency at the middle stages at 70.80%, and 80.20% respectively. The results could be applied to other courses and on a larger e-learning systems log that has similar student activity conditions and this could contribute to more accurate student performance prediction © 2023, International Journal of Emerging Technologies in Learning.All Rights Reserved.

Initial trust formation on shared autonomous vehicles: Exploring the effects of personality-, transfer- and performance-based stimuli

Building initial trust is critical for the acceptance of shared autonomous vehicles (SAVs). Initial trust determines whether this emerging mobility solution will be accepted when it is available in the market. This study examines the initial trust formation process in the context of SAVs using the elaboration likelihood model and trust transfer theory. It investigates the effects of different personality-based, transfer-based, and performance-based factors on initial trust and adoption intention. A structural equation modelling is conducted in Singapore based on valid survey design principles, sampling protocols, and data analysis procedures. Results show that among three trust-building paths, the performance-based factors which include SAV capability and interaction quality are the most important. The transfer-based (i.e., trust in shared mobility) and personality-based factor (i.e., trust propensity) rank second and third, respectively. Six moderators such as covid history and shared mobility experience are also tested to investigate significant differences in the results. Based on these findings, this study offers theoretical and policy implications for scholars and practitioners.

A drug recommender system Based on Collaborative Filtering for Covid-19 patients

The epidemic caused by a new mutation of the coronavirus family called Covid-19 has created a global crisis involving all the world's countries. This disease has become a severe danger to everyone due to its unknown nature, high spread, and inability to detect the infected. In this regard, one of the important issues facing patients with Covid-19 is the prescription of Drugs according to the severity of the disease and considering the records of underlying diseases in people. In recent years, recommender systems have been developed significantly along with the advancement in information technology and artificial intelligence, which is one of its applications in various fields of medical sciences. Among them, we can refer to recommending systems for the prevention, control, and treatment of diseases. In this research, using the collaborative filtering approach as one of the types of recommender systems as well as the K-means clustering algorithm, a Drug recommendation system for patients with Covid-19 in the treatment stage of the disease is presented. The results of this research show that this recommender system has an acceptable performance based on the evaluation criteria of precision, recall, and F1-score compared to the opinions of experts in this field. © 2023 IEEE.

Data Analysis on Instruction Delivery Technology: Determining the Factors Influencing the System Adaptation of Learning Management System

To assess the status of its performance based on expectations and feedback specifically from the educators who are users of Fr. Saturnino Urios University's (FSUU) learning management system (LMS). The researchers investigated and undermined gaps in training and learning using the analytical report. The finding showed that LMS's purpose is not only to deliver online education but also to provide a wide range of services like acting as a platform for online courses and content and learning activities both asynchronous and synchronous instructions. An LMS may provide classroom management as well as facilitation in the perspective and paradigm of higher education with an instructor-led training system or in the context of a flipped classroom, which ushered in the inevitable arrival of a new normal in part because of this global pandemic, COVID 19. Recent LMSs contain clever algorithms that automatically recommend courses based on a user's ability profile and extract metadata from various learning resources to produce such effective recommendations, improving s their accuracy. One of the various resources available to instructors to aid in teaching and learning is FSUU Learn. Furthermore, due to its numerous and versatile instructional elements, it is promising even after the epidemic and in face-to-face learning. The purpose of this study is to determine the elements that affect faculty and teachers at the university's acceptance of the LMS FSUU Learn as well as whether their usage of ICT affects their acceptance of other LMS FSUU Learn features during the peak of pandemic. The results revealed that the actual usage is 67% while the behavioral intention to use the FSUU Learn is 56.8%. The variables used in the study were able to predict 62% of the variance that could explain the acceptance of the FSUU Learn based on the perception of the faculty/teacher users. © 2023 IEEE.

Researching the Prospects for Change that COVID Disruption has Brought to High Stakes Testing and Accountability Systems

This paper explores the disruption that COVID has brought to the normal functioning of performance-based accountability systems and asks whether this has created new possibilities for those organising against the use of high stakes testing in education. Drawing on a sequence of research projects1 exploring primary schools' responses to the pandemic in England during 2020-21, this article considers the ways in which the pandemic creates new conditions for dismantling high stakes testing and accountability regimes, and the role of research in making the case for change. © 2022, Arizona State University. All rights reserved.

Preparing Middle Grades Candidates for edTPA in Uncertain Times

Teacher candidates in North Carolina must earn a passing score on the edTPA assessment to get certified. The middle grades education program at Western Carolina University integrates aspects of the edTPA assessment throughout pre-student teaching coursework and field experiences to prepare candidates for this high-stakes assessment. Some of the edTPA practice assignments serve as key assessments that help the middle grades program faculty evaluate the program and make decisions about curriculum. The pivot to remote and blended learning formats on campus and in partner middle level schools affected the implementation of the edTPA-related assignments. The authors share some of the challenges of implementing edTPA practice portfolios during the pandemic as well as insights gleaned from their assessment of the data.

Use of Interdisciplinary Approach in Performance-based Assessment in the New Normal

This descriptive research study aimed to assess the management of the existing policies, guidelines, and procedures on the implementation of the interdisciplinary approach in performance-based assessment (IAPA) before and during Coronavirus disease (COVID-19) as a basis for proposing improvements for its implementation in the “new normal”. 30 senior high school science teachers and school leaders from 5 private and 5 public schools in Metro Manila, Philippines, participated in this study. The participants assessed the management of existing policies, guidelines, and procedures on the IAPA’s implementation using a survey questionnaire and identified its strengths and weaknesses using an interview guide. The researchers developed the instruments used for data collection but subjected to experts’ validation and reliability test. Results reveal that the management of IAPA was effective and that it benefits students and teachers in many ways. However, it has also weaknesses, which are associated with the role of school leaders in the implementation of the policies, guidelines, and/or procedures, especially during the new normal education setting. The study provides suggestions for improving IAPA implementation in the new normal covering both the face-to-face and online learning modalities. © 2022 The Author(s).

Prediction of Students’ Performance Based on Their Learning Experiences and Assessments: Statistical and Neural Network Approaches

The education approaches in the higher education have been evolved due to the impact of covid-19 pandemic. The predicting of students’ final performance has become more crucial as various new learning approaches have been adopted in the teaching. This paper proposes a statistical and neural network model to predict students’ final performance based on their learning experiences and assessments as the predictor variables. Students’ learning experiences were obtained through educational data analytic platform on a module that delivered the mixed-mode education strategy using Flipped classroom, asynchronous and cognitive learning in combination with the revised Bloom’s taxonomy. Statistical evaluations including multiple regressions, ANOVA correlations are performed to evaluate the appropriateness of the input variables used for the later Neural Network output prediction. The Levenberg-Marquardt algorithm is employed as the training rule for the Neural Network model. The performance of neural network model is further verified to prevent the overfitting issue. The Neural Network model has achieved a high prediction accuracy justifying the students’ final performance through utilising the aforementioned pedagogical practises along with limitations. © 2022, Springer Nature Switzerland AG.

Navigating performance-based assessments in unprecedented times: Adaptations, challenges, and strategies

This chapter focuses on the implementation of performance-based assessments (PBAs) at the Auburn University Harrison School of Pharmacy (AUHSOP) during the COVID-19 pandemic, when shifts were made to a fully remote delivery of the pharmacy curriculum in March 2020 and then altered to a hybrid delivery in the fall semester in which students returned to campus in a limited capacity. In addition to describing adaptations made due to curriculum delivery changes for each professional year, the chapter will provide specific challenges encountered while planning and implementing PBAs with a focus on factors related to students, standardized persons (SPs), and logistics. Student and SP perceptions of remote PBA delivery will be presented as well as strategies for improvement of future PBA events. (PsycInfo Database Record (c) 2022 APA, all rights reserved)

Nursing Home COVID Relief Under QIP's Performance-Based Formula: Does Performance Actually Matter, and Should It?

The Quality Incentive Program (QIP) distributed US$2 billion to nursing homes (NHs) that met performance goals primarily related to their COVID-19 infection rates. We examine how QIP affected 15,331 NHs with different facility and community attributes, and the extent to which QIP payments per resident-week (QIP$) were associated with NHs' COVID-related attributes. We find that QIP$ was primarily determined by county (not facility) infection rates. QIP distributed US$2 billion to NHs for months in which they experienced virtually no COVID-19 cases; US$0 was distributed for months in which they experienced more than 300,000 cases. We find that QIP$ was larger for smaller, nonprofit NHs located in more rural and economically distressed communities. Regression analyses reveal that recipients of larger QIP$ maintained greater supplies of personal protective equipment, conducted more staff testing, and limited admissions of infected residents, and that greater staff testing and limited admissions are also associated with NHs' sustained success in receiving QIP payments. Policymakers should consider whether performance-based payment systems are optimal for addressing public health emergencies.

Student Performance Based on Student Final Exam Prediction

The Covid-19 pandemic situation has made changes to the education system. Educational institutions carried out the shift from the face-To-face learning model to the distance learning model to adapt to the pandemic situation to maintain educational activities' sustainability. Despite changes in learning models, education providers certainly want to maintain academic quality by producing graduates with superior academics, practical knowledge, and innovative thinking. The problem currently faced is how education providers can monitor students' performance to complete their studies correctly. Therefore, a grade prediction is needed that helps students, lecturers, and administrators of educational institutions maintain and improve academic quality. This study compares the techniques. This study shows that the Naïve Bayes method provides a higher level of accuracy than the KNN method, which is 96%. © 2021 IEEE.

Machine Learning for Exhibition Recommendation in a Museum's Virtual Tour Application

The museum visit is having a crisis during the COVID-19 pandemic. SMBII Museum in Palembang has a remarkable decrease of visitors up to 90%. A strategy is needed to increase museum visits and enable educational and tourism roles in a pandemic situation. This paper evaluates the machine learning model for exhibition recommendations given to visitors through virtual tour applications. Exploring unfamiliar museum exhibitions to visitors through virtual museum applications will be tedious. If virtual collections are ancient and do not display any interest, they will quickly lead to boredom and reluctance to explore virtual museums. For this reason, an effective method is needed to provide suggestions or recommendations that meet the interests of visitors based on the profiles of museum visitors, making it easier for visitors to find exciting exhibition rooms for learning and tourism. Machine learning has proven its effectiveness for predictions and recommendations. This study evaluates several machine learning classifiers for exhibition recommendations and development of virtual tour applications that applied machine learning classifiers with the best performance based on the model evaluation. The experimental results show that the KNN model performs best for exhibition recommendations with cross-validation accuracy = 89.09% and F-Measure = 90.91%. The SUS usability evaluation on the exhibition recommender feature in the virtual tour application of SMBII museum shows average score of 85.83. The machine learning-based recommender feature usability is acceptable, making it easy and attractive for visitors to find an exhibition that might match their interests. © 2022. All Rights Reserved.

Experimental study on the influence of abusive management on the job performance based on Internet technology

Against the background of the COVID-19, the global economic situation is not optimistic. The Job performance of employees is the basis of corporate interests, and the choice of management style will directly affect employees' work mentality and behavior. Based on the survey data of 963 employees in high-tech enterprises across China, this paper uses the hierarchical regression method to explore the influence mechanism of abusive management (AS) on job performance (JP). Common method deviation (CMV) showed no obvious common method bias problem in the data collected in this study. The results showed that there was significant negative correlation between abusive management and job performance (β=-0.023, mathrm{p} < 0.05). The relationship between abusive management and job performance was partially mediated by job insecurity (JI). After adding job insecurity as mediating variable between AS and JP, the effect of abusive management on job performance changes from β=-0.042 (p<0.05) to β=-0.029 (p <0.05). The bootstrap method was also used in this study to test the mediating effect. Self-efficacy (SE) and job insecurity had significant interaction, and the coefficient is β=-0.112(\mathrm{p} < 0.05). So, SE moderated the relationship between job insecurity and job performance. © 2021 IEEE.

Investigation of Using Sky Openness Ratio as Predictor for Navigation Performance in Urban-like Environment to Support PBN in UTM.

One of the causes of positioning inaccuracies in the Unmanned Aircraft System (UAS) is navigation error. In urban environment operations, multipaths could be the dominant contributor to navigation errors. This paper presents a study on how the operation environment affects the lateral (horizontal) navigation performance when a self-built UAS is going near different types of urban obstructions in real flight tests. Selected test sites are representative of urban environments, including open carparks, flight paths obstructed by buildings along one or both sides, changing sky access when flying towards corners formed by two buildings or dead ends, and buildings with reflective glass-clad surfaces. The data was analysed to obtain the horizontal position error between Global Positioning System (GPS) position and ground truth derived from Real Time Kinematics (RTK), with considerations for (1) horizontal position uncertainty estimate (EPH) reported by the GPS receiver, (2) no. of visible satellites, and (3) percentage of sky visible (or sky openness ratio, SOR) at various altitudes along the flight paths inside the aforementioned urban environments. The investigation showed that there is no direct correlation between the measured horizontal position error and the reported EPH; thus, the EPH could not be used for the purpose of monitoring navigation performance. The investigation further concluded that there is no universal correlation between the sky openness ratio (SOR) seen by the UAS and the resulting horizontal position error, and a more complex model would need to be considered to translate 3D urban models to expected horizontal navigation uncertainty for the UAS Traffic Management (UTM) airspace.

Designing PISA-Like Mathematics Task Using a COVID-19 Context (PISAComat)

New changes to the school curriculum by enacting a minimum competency assessment (MCA) with PISA criteria in 2021 have led to confusion over the form of MCA questions among teachers and students due to limited learning resources at schools. This study aimed to produce valid and practical PISA COVID-19 mathematics tasks (PISAComat) potentially affecting mathematics literacy. This study involved 27 secondary-level students aged 15 years old with different levels of mathematics skills. Design research in the form of development studies was chosen as the core framework of this research assisted with the online learning platform. Data were analyzed descriptively through observations, tests, interviews, and document reviews. A set of PISAComat on quantity and change & relationship at the level of reasoning was gained after a formative evaluation. The formative process was conducted through zoom meetings and intensive communication at WhatsApp Group (WAG) to produce valid and practical PISAComat. After being tested in the classroom, the resulting PISAComat had been potentially effective in promoting students' mathematics literacy and life skills during the COVID-19 pandemic.

Understanding Quality Paradigm Shifts in the Evolving Pharmaceutical Landscape: Perspectives from the USP Quality Advisory Group.

Recent changes in the pharmaceutical industry have led to significant paradigm shifts in the pharmaceutical quality environment. Globalization of the pharmaceutical industry, increasingly rapid development of novel therapies, and adoption of new manufacturing techniques have presented numerous challenges for the established regulatory framework and quality environment and are impacting the approaches utilized to ensure the quality of pharmaceutical products. Regulators, industry, and standards-setting organizations have begun to recognize the need to rely more on integrated risk-based approaches and to create more nimble and flexible standards to complement these efforts. They also increasingly have recognized that quality needs to be built into systems and processes throughout the lifecycle of the product. Moreover, the recent COVID-19 crisis has emphasized the need to adopt practices that better promote global supply chain resilience. In this paper, the USP Quality Advisory Group explores the various paradigm shifts currently impacting pharmaceutical quality and the approaches that are being taken to adapt to this new environment. Broad adoption of the Analytical Procedure Lifecycle approach, improved data management, and utilization of digital technologies are identified as potential solutions that can help meet the challenges of these quality paradigm shifts. Further discussion and collaboration among stakeholders are needed to pursue these and other solutions that can ensure a continued focus on quality while facilitating pharmaceutical innovation and development.