130,494 research outputs found
Processing and Understanding Moodle Log Data and Their Temporal Dimension
No full textThe increased adoption of online learning environments has resulted in the availability of vast amounts of educational log data, which raises questions that could be answered by a thorough and accurate examination of students’ online learning behaviours. Event logs describe something that occurred on a platform and provide multiple dimensions that help to characterize what actions students take, when, and where (in which course and in which part of the course). Temporal analysis has been shown to be relevant in learning analytics (LA) research, and capturing time-on-task as a proxy to model learning behaviour, predict performance, and prevent drop-out has been the subject of several studies. In Moodle, one of the most used learning management systems, while most events are logged at their beginning, other events are recorded at their end. The duration of an event is usually calculated as the difference between two consecutive records assuming that a log records the action’s starting time. Therefore, when an event is logged at its end, the difference between the starting and the ending event identifies their sum, not the duration of the first. Moreover, in the pursuit of a better user experience, increasingly more online learning platforms’ functions are shifted to the client, with the unintended effect of reducing significant logs and conceivably misinterpreting student behaviour. The purpose of this study is to present Moodle’s logging system to illustrate where the temporal dimension of Moodle log data can be difficult to interpret and how this knowledge can be used to improve data processing. Starting from the correct extraction of Moodle logs, we focus on factors to consider when preparing data for temporal dimensional analysis. Considering the significance of the correct interpretation of log data to the LA community, we intend to initiate a discussion on this domain understanding to prevent the loss of data-related knowledge
Time-on-Task Estimation by data-driven Outlier Detection based on Learning Activities
No full textTemporal analysis has been demonstrated to be relevant in Learning Analytics research, and capturing time-on-task, i.e., the amount of time spent by students in quality learning, as a proxy to model learning behaviour, predict performance, and avoid drop-out has been the focus of a number of investigations. Nonetheless, most studies do not provide enough information on how their data were prepared for their findings to be easily replicated, even though data pre-processing decisions have an impact on the analysis' outcomes and can lead to inaccurate predictions. One of the key aspects in the preparation of learning data for temporal analysis is the detection of anomalous values of temporal duration of students' activities. Most of the works in the literature address this problem without taking into account the fact that different activities can have very different typical execution times. In this paper, we propose a methodology for estimating time-on-task that starts with a well-defined data consolidation and then applies an outlier detection strategy to the data based on a distinct study of each learning activity and its peculiarities. Our real-world data experiments show that the proposed methodology outperforms the current state of the art, providing more accurate time estimations for students' learning tasks
Amplification of coupling for Yukawa potentials
No full textIt is well known that Yukawa potentials permit bound states in the Schrodinger equation only if the ratio of the exchanged mass to bound mass is below a critical multiple of the coupling constant. However, arguments suggested by the Darwin term imply a more complex situation. By numerically studying the Dirac equation with a Yukawa potential we investigate this "amplification" effect.69
Advancing Colorectal Cancer Diagnosis: Integrating Synthetic Data and Machine Learning for Microbiome Analysis
No full textThis work highlights the importance of the gut microbiota in colorectal health, especially during AP-to-CRC transition. Synthetic data augmentation enlarged and balanced a multidimensional OTU table for machine learning categorization. The OTU table refinement used SVM and LG for sample validation and several statistical tests to assure synthetic data realism. In addition, deep learning feature extraction with LRP identified 64 unique bacterial taxa that were assessed for their ability to distinguish AP and CRC samples in diverse datasets. Fusobacterium was important in LRP and SHAP studies, consistent with its connection with CRC. SHAP analysis using XGBoost discovered differentiated features like Parvimonas, Alistipes, and Ruminococcus in stool and biopsy datasets. Classifying the saliva dataset with 100% accuracy is noteworthy. © 2025 by The Institute of Electrical and Electronics Engineers, Inc. All rights reserved
Visual Analytics for Session-based Time-Windows Identification in Virtual Learning Environments
No full textDue to the flexibility of online learning courses, students organise and manage their own learning time by deciding when, what, and how to study. Each individual has distinctive learning habits that identify their behaviours and set them apart from others. To explore how students behave over time, in this work we seek to identify adequate time-windows that could be used to investigate the temporal behaviour of students in online learning environments. We first propose a novel perspective to identify various types of sessions based on individual requirements. Most of the works in the literature address this problem by setting an arbitrary session timeout threshold. In this paper we propose an algorithm that helps us in determining the most suitable threshold for the session. Then, based on the identified sessions, we determine time-windows using data-driven methods. To this end, we created a visual tool that assists data scientists and researchers in determining the optimal settings for the session identification and locating suitable time-windows
Fermion-fermion bound state condition for scalar exchanges
No full textThe condition for the existence of a bound state between two fermions exchanging massive scalars is derived. For low scalar mass, we reproduce the scalar field model result. The high scalar mass result exhibits a somewhat different inequality condition.78
Session-Based Time-Window Identification in Virtual Learning Environments
No full textStudents organize and manage their own learning time, choosing when, what, and how to study due to the flexibility of online learning. Each person has unique learning habits that define their behaviours and distinguish them from others. To investigate the temporal behaviour of students in online learning environments, we seek to identify suitable time-windows that could be used to investigate their temporal behaviour. First, we present a novel perspective for identifying different types of sessions based on individual needs. The majority of previous works address this issue by establishing an arbitrary session timeout threshold. In this paper, we propose an algorithm for determining the optimal threshold for a given session. Second, we use data-driven methods to support investigators in determining time-windows based on the identified sessions. To this end, we developed a visual tool that assists data scientists and researchers to determine the optimal settings for session identification and locating suitable time-windows. Notes for Research • In this paper we tackle the problem of identifying appropriate time-windows that could be used to investigate the temporal behaviour of students in online learning environments and to better adapt analysis techniques to a given dataset. • Previous research has often identified time-windows intuitively or based on personal experience and viewpoints. In contrast to previous research, we propose a method to support investigators in identifying time-windows objectively using a data-driven approach based on the concept of session, which we have reformulated in three different forms to meet various individual requirements. • We also introduce an algorithm for estimating the duration of inactivity, i.e., off-task activity, during online learning. • To identify time-windows, we developed a visual tool, whose whole source code is freely available, to assist data scientists and researchers in determining the optimal settings for the session identification and locating suitable time-windows
- …
