Improving understanding of EEG measurements using transparent machine learning models

Physiological datasets such as Electroencephalography (EEG) data offer an insight into some of the less well understood aspects of human physiology. This paper investigates simple methods to develop models of high level behavior from low level electrode readings. These methods include using neuron a...

Full description

Bibliographic Details
Main Authors: Roadknight, Chris, Zong, Guanyu, Rattadilok, Prapa
Format: Book Section
Language:English
Published: Springer Nature 2019
Subjects:
Online Access:https://eprints.nottingham.ac.uk/59612/
_version_ 1848799653182570496
author Roadknight, Chris
Zong, Guanyu
Rattadilok, Prapa
author_facet Roadknight, Chris
Zong, Guanyu
Rattadilok, Prapa
author_sort Roadknight, Chris
building Nottingham Research Data Repository
collection Online Access
description Physiological datasets such as Electroencephalography (EEG) data offer an insight into some of the less well understood aspects of human physiology. This paper investigates simple methods to develop models of high level behavior from low level electrode readings. These methods include using neuron activity based pruning and large time slices of the data. Both approaches lead to solutions whose performance and transparency are superior to existing methods.
first_indexed 2025-11-14T20:39:05Z
format Book Section
id nottingham-59612
institution University of Nottingham Malaysia Campus
institution_category Local University
language English
last_indexed 2025-11-14T20:39:05Z
publishDate 2019
publisher Springer Nature
recordtype eprints
repository_type Digital Repository
spelling nottingham-596122020-01-09T03:59:25Z https://eprints.nottingham.ac.uk/59612/ Improving understanding of EEG measurements using transparent machine learning models Roadknight, Chris Zong, Guanyu Rattadilok, Prapa Physiological datasets such as Electroencephalography (EEG) data offer an insight into some of the less well understood aspects of human physiology. This paper investigates simple methods to develop models of high level behavior from low level electrode readings. These methods include using neuron activity based pruning and large time slices of the data. Both approaches lead to solutions whose performance and transparency are superior to existing methods. Springer Nature 2019-10-08 Book Section PeerReviewed application/pdf en cc_by https://eprints.nottingham.ac.uk/59612/1/Improving.pdf Roadknight, Chris, Zong, Guanyu and Rattadilok, Prapa (2019) Improving understanding of EEG measurements using transparent machine learning models. In: Health Information Science. Lecture Notes in Computer Science book series, 11837 . Springer Nature, Switzerland, pp. 134-142. ISBN 9783030329617 Deep Learning; Physiological data; CAPing http://dx.doi.org/10.1007/978-3-030-32962-4_13 doi:10.1007/978-3-030-32962-4_13 doi:10.1007/978-3-030-32962-4_13
spellingShingle Deep Learning; Physiological data; CAPing
Roadknight, Chris
Zong, Guanyu
Rattadilok, Prapa
Improving understanding of EEG measurements using transparent machine learning models
title Improving understanding of EEG measurements using transparent machine learning models
title_full Improving understanding of EEG measurements using transparent machine learning models
title_fullStr Improving understanding of EEG measurements using transparent machine learning models
title_full_unstemmed Improving understanding of EEG measurements using transparent machine learning models
title_short Improving understanding of EEG measurements using transparent machine learning models
title_sort improving understanding of eeg measurements using transparent machine learning models
topic Deep Learning; Physiological data; CAPing
url https://eprints.nottingham.ac.uk/59612/
https://eprints.nottingham.ac.uk/59612/
https://eprints.nottingham.ac.uk/59612/