Skip to main content

LUP Student Papers

LUND UNIVERSITY LIBRARIES

Statistics and Machine Learning for Classification of Emotional and Semantic Content of EEG

Keding, Oskar LU and Ohlin, David (2021) In Master’s Theses in Mathematical Sciences FMSM01 20211
Mathematical Statistics
Abstract
Interpreting EEG measurements is of great relevance, both for developing underlying neuroscientific theory and improving existing applications. In this study, two networks with different approaches to time-frequency analysis and feature selection are compared on simulated and real data for semantic and emotional perception. The first network uses the Morlet wavelet transform to achieve adaptable feature selection. The second network uses a convolutional net to analyse reassigned spectrograms, in hope of improving component localisation. The result shows relatively good performance of the Morlet network with easily interpretable features, especially when combined with Grad-CAM, a method for visualising the gradients of the network to locate... (More)
Interpreting EEG measurements is of great relevance, both for developing underlying neuroscientific theory and improving existing applications. In this study, two networks with different approaches to time-frequency analysis and feature selection are compared on simulated and real data for semantic and emotional perception. The first network uses the Morlet wavelet transform to achieve adaptable feature selection. The second network uses a convolutional net to analyse reassigned spectrograms, in hope of improving component localisation. The result shows relatively good performance of the Morlet network with easily interpretable features, especially when combined with Grad-CAM, a method for visualising the gradients of the network to locate relevant data regions. The network using reassigned spectrograms performs less well, but comparisons with methods for ordinary spectrograms suggest that this is due to poor performance of the more traditional image-processing methods used, making it difficult to determine the effect of reassignment. Testing on novel data shows lower, but statistically significant, classification performance for emotional content, likely due both to methodological shortcomings and to the intrinsic difficulty of the problem. The study explores the use of transfer learning and finds promising results both in the accuracy on new subjects with models trained on data from others and in boosting training on single subjects by initialisation with transferred weights. Finally, the Morlet network is applied to analyse similarities between perception and memory retrieval, with significant results for networks trained on memory data and tested on perception data. (Less)
Please use this url to cite or link to this publication:
author
Keding, Oskar LU and Ohlin, David
supervisor
organization
course
FMSM01 20211
year
type
H2 - Master's Degree (Two Years)
subject
keywords
Machine Learning, machine, learning, neural, network, statistics, EEG, emotion, semantic, emotional, signal, processing, reassignment, time-frequency, spectrogram, brain processing, bci, CNN, convolutional
publication/series
Master’s Theses in Mathematical Sciences
report number
LUTFMS-3408-2021
ISSN
1404-6342
other publication id
2021:E8
language
English
additional info
Link to Github:
https://github.com/ohlindavid/ExjobbEEG
id
9043034
date added to LUP
2021-05-12 09:34:36
date last changed
2021-06-03 15:23:09
@misc{9043034,
  abstract     = {{Interpreting EEG measurements is of great relevance, both for developing underlying neuroscientific theory and improving existing applications. In this study, two networks with different approaches to time-frequency analysis and feature selection are compared on simulated and real data for semantic and emotional perception. The first network uses the Morlet wavelet transform to achieve adaptable feature selection. The second network uses a convolutional net to analyse reassigned spectrograms, in hope of improving component localisation. The result shows relatively good performance of the Morlet network with easily interpretable features, especially when combined with Grad-CAM, a method for visualising the gradients of the network to locate relevant data regions. The network using reassigned spectrograms performs less well, but comparisons with methods for ordinary spectrograms suggest that this is due to poor performance of the more traditional image-processing methods used, making it difficult to determine the effect of reassignment. Testing on novel data shows lower, but statistically significant, classification performance for emotional content, likely due both to methodological shortcomings and to the intrinsic difficulty of the problem. The study explores the use of transfer learning and finds promising results both in the accuracy on new subjects with models trained on data from others and in boosting training on single subjects by initialisation with transferred weights. Finally, the Morlet network is applied to analyse similarities between perception and memory retrieval, with significant results for networks trained on memory data and tested on perception data.}},
  author       = {{Keding, Oskar and Ohlin, David}},
  issn         = {{1404-6342}},
  language     = {{eng}},
  note         = {{Student Paper}},
  series       = {{Master’s Theses in Mathematical Sciences}},
  title        = {{Statistics and Machine Learning for Classification of Emotional and Semantic Content of EEG}},
  year         = {{2021}},
}