This Doctoral research is part of several imec-icon projects (joint projects between industry and academia). The main research objective is to measure and optimise latent variables. This objective is pursued in different technology-enhanced learning contexts.
The imec-icon project LECTURE+ (LEarning in remote Classrooms through Technology-enhanced UseR Engagement) developed and investigated a hybrid virtual classroom. This is a relatively new learning space in which face-to-face and remote learners are synchronously connected, for example, to follow a lecture or a training. Retention and engagement are fundamental weaknesses of distance education compared to conventional education (Boyle et al., 2010). Therefore, fostering engagement in an attempt to decrease drop-out is a key challenge in distance learning. The project’s first objective is to measure engagement. To this end, two approaches are taken: the first approach relies one on computer vision techniques only, the second approach is multimodal as it includes other data sources as well. A second objective of the project is to investigate how the engagement of face-to-face and remote learners compares in the hybrid virtual classroom.

The COSMO (COgnitive Support during Manufacturing Operations) project takes place in another context: assembly work. In assembly, different technological evolutions have resulted in more rapid and diversified manufacturing processes, which may increase the complexity for the operator, and the according cognitive load. That is why we investigate technology-enhanced support by means of Augmented Reality (AR) instructions, in an aim to reduce operators’ perceived complexity, stress and error-making. The project investigates how AR compares to more traditional instructional media, namely oral and paper instructions. Next to that, we also examine technology-enhanced adaptive support through personalised instructions, in the sense that the instructions are adapted to the learner, through AR and VR (Virtual Reality).

The imec project Load Remediation 4.0 (LoRem 4.0) pursues a measurement model for cognitive load employing physiological data (EEG, EOG, skin temperature and skin conductance).