Construed as a shift in the distribution or structure of data over time, data drift can adversely affect the performance of machine learning models and data-driven decisions. This study examines two data drift metrics, denoted as dE,PCAand dE,AE, that are derived from unsupervised ML models: the reconstruction error-based metrics of Principal Component Analysis (PCA) and Autoencoders (AE). To investigate the robustness of these metrics, we have systematically accessed time-series datasets from the European Data Portal. Our experiments have examined data versioning through three basic events: creation, update, and deletion. The results are summarised and aggregated for all datasets, and unsupervised analysis based on Robust PCA and AE has been performed to examine patterns within the impact of dataset characteristics on data drift detection and computational efficiency. Our results indicate that both metrics aligned closely in performance with new records, suggesting consistent drift detection under normal conditions with FAIR compliance. However, high-dimensional datasets posed challenges for both PCA and AE models. Update events revealed discrepancies between the two metrics, suggesting that non-linear shifts affected AE-based metrics more than PCA-based ones. Deletion events demonstrated the resilience of these metrics against data loss, but also revealed variability in the reliability of the PCA model; i.e., data drift metrics derived from PCA and AE can be effective but sensitive to certain dataset characteristics.

As one of the fundamental concepts underpinning the FAIR (Findability, Accessibility, Interoperability, and Reusability) guiding principles, data provenance entails keeping track of each version for a given dataset from its original to its latest version. However, standard terms to determine and include versioning information in the metadata of a given dataset are still ambiguous and do not explicitly define how to assess the overlap of information between items along a versioning stream. In this work, we propose a novel approach for automatic versioning of time series datasets, based on the use of parameters from two dimensionality reduction approaches, namely Principal Component Analysis and Autoencoders. That is to say, we systematically detect and measure similarities (information distances) in datasets via dimensionality reduction, encode them as different versions, and then automatically generate provenance metadata via a FAIR versioning service using the W3C DCAT 3.0 nomenclature. We illustrate this approach with two time series datasets and demonstrate how the proposed parameters effectively assess the similarity between different data versions. Our results have shown that the proposed version similarity metrics are robust$(s^{(0,1)}=1)$to the alteration of up to 60% of cells, the removal of up to 60% of rows, and the log-scale transformation of variables. In contrast, row-wise transformations (e.g. converting absolute values to a percentage of a second variable) yield minimal similarity values$(s^{(0,1)} < 0.75)$. Our code and datasets are openly available to enable reproducibility.

Although Mathematics is a fundamental subject for many STEM related areas, undergraduate students find Mathematics a challenging and difficult subject, and they face difficulties in developing logical thinking and problem solving skills. This research-to-practice paper introduces Count With Me!, a novel immersive computer-based educational game that teaches counting principles. The paper analyses and discusses the impact of the game on the learning process and knowledge gain. Twenty-four 1styear undergraduate students took part in the case study. Knowledge tests were employed before and after the students interacted with the educational game. Although addition, multiplication, factorial, and permutation topics were already studied by the students in the high school, the pre-test results showed that some students face difficulties with these topics. The post test results analysis showed a statistically significant knowledge improvement and a high student engagement in playing the game and learning about the Mathematics concepts.

Mathematics is a key subject for success in Computer Science and it continues to be a challenging subject. Use of technology has given rise to a new pedagogy called Flip-Classroom (FC). FC involves creating online multimedia content that is utilized out-of-class in conjunction with in-class learning activities such as individual and collaborative problem solving, group-work and class-discussion. An experiment was conducted to investigate the utility of FC pedagogy and its relationship with student learning. FC pedagogy was implemented in a first year "Introduction to Mathematics for Computing" module and was employed for a number of core topics. A traditional lecture approach was utilized for the remaining topics. In-class quiz based assessments, homework assignments and end of semester examinations have been performed in order to assess the learning performance of the students. The results show that on average students performed better in assessments on topics taught through FC pedagogy. For Continuous Assessment (CA) components this increase was 14% and for the terminal exam this increase was 21%. The results indicate that the FC pedagogy may improve learning. Furthermore the students have indicated their preference in favor of FC pedagogy. This study will be of interest to those considering integrating FC pedagogy into teaching Mathematics.