Please use this identifier to cite or link to this item:
https://www.um.edu.mt/library/oar/handle/123456789/107628
Title: | Effective data acquisition for machine learning algorithm in EEG signal processing |
Other Titles: | Soft computing : theories and applications : proceedings of SoCTA 2016 |
Authors: | Bonello, James Garg, Lalit Garg, Gaurav Audu, Eliazar Elisha |
Keywords: | Electroencephalography -- Data processing Signal processing -- Data processing Machine learning -- Medical applications Computer communication systems Epilepsy -- Diagnosis |
Issue Date: | 2018 |
Publisher: | Springer |
Citation: | Bonello, J., Garg, L., Garg, G., & Audu, E. E. (2018). Effective data acquisition for machine learning algorithm in EEG signal processing. In M. Pant, K. Ray, T. K. Sharma, S. Rawat, & A. Bandyopadhyay (Eds.), Soft Computing: Theories and Applications: Proceedings of SoCTA 2016, Vol. 2 (pp. 233-244). Singapore: Springer. |
Abstract: | The aim of this paper is to demonstrate that small dataset can be used in machine learning for seizure monitoring and detection using smart organization of multichannel EEG sensor data. This reduces training time and improves computational performance in terms of space and time complexities on hardware implementations. The proposed approach has been tested and validated using CHB-MIT dataset containing EEG recordings of 24 clinically verified seizure and non-seizure pediatric patients. The predictability is discussed in terms of the latency and the required length of data for the proposed approach over the state-of-the-art method in the field of EEG-based seizure prediction. |
URI: | https://www.um.edu.mt/library/oar/handle/123456789/107628 |
ISBN: | 9789811056994 |
Appears in Collections: | Scholarly Works - FacICTCIS |
Files in This Item:
File | Description | Size | Format | |
---|---|---|---|---|
Effective data acquisition for machine learning algorithm in EEG signal processing 2018.pdf Restricted Access | 542.14 kB | Adobe PDF | View/Open Request a copy |
Items in OAR@UM are protected by copyright, with all rights reserved, unless otherwise indicated.