Evaluating quantum neural network filtered motor imagery brain-computer interface using multiple classification techniques
- Submitting institution
-
Middlesex University
- Unit of assessment
- 11 - Computer Science and Informatics
- Output identifier
- 806
- Type
- D - Journal article
- DOI
-
10.1016/j.neucom.2014.12.114
- Title of journal
- Neurocomputing
- Article number
- -
- First page
- 161
- Volume
- 170
- Issue
- -
- ISSN
- 0925-2312
- Open access status
- Out of scope for open access requirements
- Month of publication
- July
- Year of publication
- 2015
- URL
-
http://eprints.mdx.ac.uk/17368/
- Supplementary information
-
-
- Request cross-referral to
- -
- Output has been delayed by COVID-19
- No
- COVID-19 affected output statement
- -
- Forensic science
- No
- Criminology
- No
- Interdisciplinary
- No
- Number of additional authors
-
4
- Research group(s)
-
-
- Citation count
- 11
- Proposed double-weighted
- No
- Reserve for an output with double weighting
- No
- Additional information
- The raw brain signal (EEG) acquired non-invasively during mental imagination performed by a brain-computer interface (BCI) user is naturally embedded with noise while the actual noise-free EEG is still unattainable. This paper compares the enrichment in information when filtering raw/noisy EEG signals using a Recurrent Quantum Neural Network (RQNN) model and a standard filtering model, both investigated over multiple classification techniques on several datasets. This is significant because this is the first RQNN for filtering physiological signals using concepts from quantum mechanics. Results show that RQNN is a flexible technique to suit different classifiers for real-time EEG filtering.
- Author contribution statement
- -
- Non-English
- No
- English abstract
- -