Με τη χρηματοδότηση της Ευρωπαϊκής Ένωσης. Οι απόψεις και οι γνώμες που διατυπώνονται εκφράζουν αποκλειστικά τις απόψεις των συντακτών και δεν αντιπροσωπεύουν κατ'ανάγκη τις απόψεις της Ευρωπαϊκής Ένωσης ή του Ευρωπαϊκού Εκτελεστικού Οργανισμού Εκπαίδευσης και Πολιτισμού (EACEA). Η Ευρωπαϊκή Ένωση και ο EACEA δεν μπορούν να θεωρηθούν υπεύθυνοι για τις εκφραζόμενες απόψεις. Μελέτη περίπτωσης 2: Αναγνώριση ενεργειών των μαθητών/τριών για τη βελτίωση της ανατροφοδότησης των εκπαιδευτικών κατά τη διάρκεια της τηλεκπαίδευσης General information Dimitriadou, E., & Lanitis, A. (2024). Student action recognition for improving teacher feedback during tele-education. IEEE Transactions on Learning Technologies, 17, 569– 584. https://doi.org/10.1109/tlt.2023.3301094 The aim of the research was to develop and evaluate a student action recognition system, reviewing students' behaviour participation and disaffection, intended to support teacher feedback during distance education. This system was designed to monitor student actions in online courses while protecting student privacy and providing real-time feedback to educators about student engagement without direct visual contact. Description of case An AI system was developed to recognise specific student actions using deep neural network architectures like GoogleNet, Inception-v3, and Faster R-CNN. The system used videos of student actions, processed locally on student devices, to train these networks. The effectiveness of the system was assessed through a comprehensive user evaluation involving students, parents, and educators, who provided feedback via online questionnaires and interviews. Lessons learned The results indicated that the system was effective in recognising student actions and was well-received by all stakeholders. Educators, in particular, found it useful for improving interaction and engagement in online settings. The system was well accepted due to the personal data protection measures applied. Implications for practice The AI system could enhance the effectiveness of online learning and distance education by providing insights into student behaviour, thus facilitating better educational outcomes. Μελέτη περίπτωσης 3: Διασφάλιση της ακαδημαϊκής ακεραιότητας και της εμπιστοσύνης σε διαδικτυακά περιβάλλοντα μάθησης: Μια διαχρονική μελέτη ενός συστήματος παρακολούθησης που βασίζεται σε ΤΝ σε ιδρύματα τριτοβάθμιας εκπαίδευσης. General information Fidas, C., Belk, M., Constantinides, A., Portugal, D., Martins, P., Pietron, A. M., Pitsillides, A., & Avouris, N. (2023). Ensuring academic integrity and trust in online learning environments: A longitudinal study of an AI-Centered proctoring system in tertiary educational institutions. Education Sciences, 13(6), 566. https://doi.org/10.3390/educsci13060566 The research aimed to enhance the credibility of online examinations in HE by identifying scenarios/cases that threaten the credibility of online exams and proposing AI-driven solutions to address these threats. A longitudinal study involving stakeholders from three European HE institutions was conducted. Description of case The researchers designed and implemented an intelligent system titled TRUSTID. The system incorporates advanced biometric technologies for identity verification and continuous monitoring. Students first register their biometric data, such as facial and vocal characteristics, which TRUSTID continuously uses to verify the student's identity throughout the exam. The system is privacy-friendly, allowing students to securely control their personal biometric information. Additionally, TRUSTID monitors behavioural patterns and physical examination contexts, detecting unusual activities
RkJQdWJsaXNoZXIy NzYwNDE=