Skip to main content

Research Repository

Advanced Search

Automated tonic-clonic seizure detection using random forests and spectral analysis on electroencephalography data.

Stewart, Craig; Fung, Wai Keung; Fough, Nazila; Prabhu, Radhakrishna

Authors

Wai Keung Fung



Contributors

Maurizio Valle
Editor

Dirk Lehmhus
Editor

Christian Gianoglio
Editor

Edoardo Ragusa
Editor

Lucia Seminara
Editor

Stefan Bosse
Editor

Ali Ibrahim
Editor

Klaus-Dieter Thoben
Editor

Abstract

Artificial intelligence (AI) has a potential for impact in the diagnosis of neurological conditions, the academic consensus generally has a positive outlook regarding how AI can improve the care of stroke victims and those who suffer from neuro-degenerative conditions such as dementia. When combined with Internet of Things technology, this could facilitate a new paradigm for epilepsy treatment. These technologies have applications in improving the welfare of epileptics, epilepsy being a common neurological condition that can result in premature death without a quick response. As such it is important for the system to avoid false negatives. This investigation focused on how machine learning algorithms can be utilised to identify these events through Electroencephalography (EEG) data. The UCI/Bonn dataset, a classic benchmark for automated epilepsy detection systems was identified and utilised. This investigation focused on the random forest algorithm. Given that EEG neurological data represents time series data and machine learning excels at this task, automation could be achievable via a wearable device. From there, Fast Fourier Transforms (FFT) were applied to identify if spectral features of EEG signals would aid identification of seizures. This method achieved an accuracy of 99%, precision of 98% and a recall of 100% in 12.2 milliseconds time to classify and one second of EEG data. These results show that random forests combined with FFT are a viable technique for attaining high recall when detecting grand mal epileptic seizures in short periods of time. CHB-MIT dataset was utilized for parity also showing good performance.

Citation

STEWART, C., FUNG, W.K., FOUGH, N. and PRABHU, R. 2022. Automated tonic-clonic seizure detection using random forests and spectral analysis on electroencephalography data. In Valle, M., Lehmhus, D., Gianoglio, C. et al. (eds.) Advances in system-integrated intelligence: proceedings of the 6th International conference on system-integrated intelligence 2022 (SysInt 2022), 7-9 September 2022, Genova, Italy. Lecture notes in networks and systems (LNNS), 546. Cham: Springer [online], pages 679-688. Available from: https://doi.org/10.1007/978-3-031-16281-7_64

Presentation Conference Type Conference Paper (published)
Conference Name 6th International conference on System-integrated intelligence 2022 (SysInt 2022)
Start Date Sep 7, 2022
End Date Sep 9, 2022
Acceptance Date Jul 5, 2022
Online Publication Date Sep 4, 2022
Publication Date Dec 31, 2022
Deposit Date Sep 14, 2022
Publicly Available Date Sep 5, 2023
Publisher Springer
Peer Reviewed Peer Reviewed
Pages 679-688
Series Title Lecture notes in network and systems (LNNS)
Series Number 546
Series ISSN 2367-3370; 2367-3389
Book Title Advances in system-integrated intelligence: proceedings of the 6th International conference on system-integrated intelligence 2022 (SysInt 2022), 7-9 September 2022, Genova, Italy
ISBN 9783031162800
DOI https://doi.org/10.1007/978-3-031-16281-7_64
Keywords Epilepsy; Seizure detection; Random forest; Fast Fourier Transform (FFT); Artificial intelligence (AI); IOT
Public URL https://rgu-repository.worktribe.com/output/1752980

Files




You might also like



Downloadable Citations