Bibtex
Cite as text
@Article{,
Year= "2021",
Volume= "Schriftenreihe der Wissenschaftlichen Gesellschaft für Arbeits- und Betriebsorganisation (WGAB) e.V.",
Pages= "243-260",
Journal = "WGAB",
Title= "Neuro-adaptive tutoring systems - Neurophysiological-based recognition of affective-emotional and cognitive states of learners for intelligent neuro-adaptive tutoring systems ",
Author= "Katharina Lingelbach M.Sc.
Applied Neurocognitive Systems
Fraunhofer Institute for Industrial Engineering IAO
Department of Psychology, Applied Neurocognitive Psychology Lab University of Oldenburg
Sabrina Gado M.Sc. Psychologie
Fraunhofer Institute for Industrial Engineering IAO Stuttgart
Prof. Dr.-Ing. Prof. e. h. Wilhelm Bauer
Fraunhofer Institute for Industrial Engineering IAO Stuttgart
",
Doi= "https://doi.org/10.30844/wgab_2021_15",
Abstract= "Monitoring learners’ mental states via a passive Brain-Computer Interface (BCI) allows to continuously estimate current abilities, available cognitive resources, and motivation. It bears the great potential to adapt educational contents, learning speed, and format to the learner’s needs via an intelligent tutoring system. We present a neurophysiological-based approach to continuously monitor learners’ current affective-emotional and cognitive states by measuring and decoding brain activity via a passive BCI. In two studies (N = 8 and N = 7), we investigate whether we can a) predict learners’ affective and cognitive states during a learning or training session, b) provide continuous feedback of recognized states to the learner and, thereby, c) increase performance and intrinsic motivation. Oscillatory power measures in the alpha (8 – 12 Hz) and theta (4 – 7 Hz) frequency band served as features for the prediction and visualization. Our results reveal that machine learning algorithms can distinguish different states of cognitive workload and affect. The approach contributes to the development of closed-loop neuro-adaptive tutoring systems which allow to monitor learners’ states, provide feedback, and adapt their parameters for an optimal learner-training fit and effective and positive learning experience. ",
}
Katharina Lingelbach M.Sc.
Applied Neurocognitive Systems
Fraunhofer Institute for Industrial Engineering IAO
Department of Psychology, Applied Neurocognitive Psychology Lab University of Oldenburg
Sabrina Gado M.Sc. Psychologie
Fraunhofer Institute for Industrial Engineering IAO Stuttgart
Prof. Dr.-Ing. Prof. e. h. Wilhelm Bauer
Fraunhofer Institute for Industrial Engineering IAO Stuttgart(2021): Neuro-adaptive tutoring systems - Neurophysiological-based recognition of affective-emotional and cognitive states of learners for intelligent neuro-adaptive tutoring systems . Schriftenreihe der Wissenschaftlichen Gesellschaft für Arbeits- und Betriebsorganisation (WGAB) e.V.(2021), S. 243-260. Online: https://doi.org/10.30844/wgab_2021_15 (Abgerufen 14.08.24)
Open Access
Monitoring learners’ mental states via a passive Brain-Computer Interface (BCI) allows to continuously estimate current abilities, available cognitive resources, and motivation. It bears the great potential to adapt educational contents, learning speed, and format to the learner’s needs via an intelligent tutoring system. We present a neurophysiological-based approach to continuously monitor learners’ current affective-emotional and cognitive states by measuring and decoding brain activity via a passive BCI. In two studies (N = 8 and N = 7), we investigate whether we can a) predict learners’ affective and cognitive states during a learning or training session, b) provide continuous feedback of recognized states to the learner and, thereby, c) increase performance and intrinsic motivation. Oscillatory power measures in the alpha (8 – 12 Hz) and theta (4 – 7 Hz) frequency band served as features for the prediction and visualization. Our results reveal that machine learning algorithms can distinguish different states of cognitive workload and affect. The approach contributes to the development of closed-loop neuro-adaptive tutoring systems which allow to monitor learners’ states, provide feedback, and adapt their parameters for an optimal learner-training fit and effective and positive learning experience.
.