An AI-powered platform to enhance and personalize e-learning

Researchers at the Autonomous University of Madrid have recently created an innovative AI-powered platform that could improve remote learning, allowing educators to securely monitor students and verify that they attend required online classes or exams.

An early prototype of this platform, called Demo-edBB, will be presented at the AAAI-23 Conference on Artificial Intelligence in February 2022, in Washington, and a version of the paper is available at the arXiv preprint server.

“Our research group, the BiDA-Laboratory at the Autonomous University of Madrid, has substantial experience with biometric signals and systems, behavior analysis, and AI applications, with more than 300 articles published in the last two decades,” Roberto Daza García, one of the researchers who carried out the study.

“In recent years, virtual education has grown significantly, becoming the main foundation of one of the most important educational institutions and generating new and valuable opportunities for learning. Therefore, our group has recently been working on new technologies for e-learning, ultimately leading the development of a platform that combines biometric and behavior analysis tools”.

EdBB, the platform created by the BiDA-Lab team, was specifically designed to improve online student assessment processes, while making them more secure. The platform is based on various technologies, including biometric identification tools that recognize users based on their behavior (eg, keyboarding patterns or “keystrokes”) or physiological data (eg. , facial recognition tools), as well as algorithms trained to detect specific behaviors (for example, attention, stress, etc.). Until now, the researchers developed a demo version of their platform, called edBB-demo, but now they are working on the full version.

“Our platform captures different sensors from the average student’s computer (webcam, keyboard, audio, metadata, etc.) and applies different technologies on real timefor identification of users, suspicious events, estimation of behavior, etc., to later translate them into reports for teachers”, explained Daza García.

“It can capture all student sensors in a secure and transparent way, while allowing them to use any other online education platform. edBB-Demo combines some of the most important advances in remote biometric and behavioral understanding from the latest decade”.

The platform created by this team of researchers is based on a multimodal learning framework, a model that can analyze different types of data, including images, videos, audio signals, and metadata. The demo version of the platform was trained on a database of learn and test sessions, each lasting more than 20 minutes, with 60 different students.

“One of the biggest concerns for educational institutions is how to prove that remote students do in fact attend an online assessment,” said Daza García. “The edBB-Platform’s biometric and behavioral detection technologies can ensure greater security in this important task, while also detecting a student’s behavior, which could improve the learning process and even pave the way for new technologies estimate attention or stress levels of students. We are convinced that these new technologies will be essential in the future to offer a more personalized education for each student.”

The demo version of edBB has four key capabilities, namely it can authenticate users with high levels of accuracy, recognize human actions in videos, estimate a student’s heart rate using webcam footage, and estimate the students’ attention by analyzing their facial expressions. The data set used to train the framework was recently made available online and could therefore be used to train other machine learning models.

The platform created by this team of researchers could soon help advance remote learning, allowing educators to reliably and securely verify the identity of e-learners. Additionally, it could make it easier to personalize online learning by identifying potential issues that are hindering a student’s learning, such as inattention or high stress levels.

“We believe that this is a broad area that has a promising future with many challenges to face, so now we want to continue to improve the edBB-platformadded Daza Garcia. “We want to continue developing the lines of research we are currently working on, as well as new cognitive load estimation systems, using multimodal facial analysis and new multimodal architectures to identify the dynamics of the student’s keyboard or mouse. In addition, we want to expand our research fields in estimation of visual attention, gaze tracking, response prediction, etc.”

© 2022 Science X Network