Data-Driven Modelling and Analysis of Attention-Working Memory Interplay

Master Thesis (2025)
Author(s)

S.M. Ohkawa (TU Delft - Mechanical Engineering)

Contributor(s)

M. Jafarian – Mentor (TU Delft - Team Matin Jafarian)

D. Boskos – Graduation committee member (TU Delft - Team Dimitris Boskos)

M.L. van de Ruit – Graduation committee member (TU Delft - Biomechatronics & Human-Machine Control)

Saskia Haegens – Mentor

More Info
expand_more
Publication Year
2025
Language
English
Graduation Date
07-04-2025
Awarding Institution
Programme
Mechanical Engineering, Systems and Control
Downloads counter
183
Reuse Rights

Other than for strictly personal use, it is not permitted to download, forward or distribute the text or part of it, without the consent of the author(s) and/or copyright holder(s), unless the work is under an open content license such as Creative Commons.

Abstract

In this project, a data-driven modelling algorithm for learning new dynamical models from experimental magnetoencephalography (MEG) data is introduced. This algorithm provides a contrast to existing hypothesis-driven modelling techniques in neuronal dynamics, and is useful for generating new insights from data when hypotheses for the neural mechanisms underlying a process are not readily available. The algorithm utilises universal differential equations (UDEs), combining white-box modelling with machine learning techniques. The algorithm is applied to a single-subject human MEG dataset to produce an oscillator network model. The model captures the frequency-domain behaviour of and interaction between several brain regions of interest during completion of a working memory (WM) task. The machine learning techniques are used to identify the role of attention mechanisms in these interaction dynamics, providing neuroscientists with data-driven insights into the brain dynamics underlying the attention-WM interplay.

Files

MSc_Thesis_Ohkawa.pdf
(pdf | 30.4 Mb)
License info not available