Interactions Between Pre-Processing and Classification Methods for Event-Related-Potential Classification

Na minha lista:
Detalhes bibliográficos
Publicado no:Neuroinformatics vol. 11, no. 2 (Apr 2013), p. 175
Autor principal: Farquhar, J
Outros Autores: Hill, N J
Publicado em:
Springer Nature B.V.
Assuntos:
Acesso em linha:Citation/Abstract
Full Text
Full Text - PDF
Tags: Adicionar Tag
Sem tags, seja o primeiro a adicionar uma tag!

MARC

LEADER 00000nab a2200000uu 4500
001 1324328057
003 UK-CbPIL
022 |a 1539-2791 
022 |a 1559-0089 
024 7 |a 10.1007/s12021-012-9171-0  |2 doi 
035 |a 1324328057 
045 2 |b d20130401  |b d20130430 
084 |a 23250668 
084 |a 108310  |2 nlm 
100 1 |a Farquhar, J 
245 1 |a Interactions Between Pre-Processing and Classification Methods for Event-Related-Potential Classification 
260 |b Springer Nature B.V.  |c Apr 2013 
513 |a Feature Journal Article 
520 3 |a   Detecting event related potentials (ERPs) from single trials is critical to the operation of many stimulus-driven brain computer interface (BCI) systems. The low strength of the ERP signal compared to the noise (due to artifacts and BCI irrelevant brain processes) makes this a challenging signal detection problem. Previous work has tended to focus on how best to detect a single ERP type (such as the visual oddball response). However, the underlying ERP detection problem is essentially the same regardless of stimulus modality (e.g. visual or tactile), ERP component (e.g. P300 oddball response, or the error-potential), measurement system or electrode layout. To investigate whether a single ERP detection method might work for a wider range of ERP BCIs we compare detection performance over a large corpus of more than 50 ERP BCI datasets whilst systematically varying the electrode montage, spectral filter, spatial filter and classifier training methods. We identify an interesting interaction between spatial whitening and regularised classification which made detection performance independent of the choice of spectral filter low-pass frequency. Our results show that pipeline consisting of spectral filtering, spatial whitening, and regularised classification gives near maximal performance in all cases. Importantly, this pipeline is simple to implement and completely automatic with no expert feature selection or parameter tuning required. Thus, we recommend this combination as a "best-practice" method for ERP detection problems.[PUBLICATION ABSTRACT]   Detecting event related potentials (ERPs) from single trials is critical to the operation of many stimulus-driven brain computer interface (BCI) systems. The low strength of the ERP signal compared to the noise (due to artifacts and BCI irrelevant brain processes) makes this a challenging signal detection problem. Previous work has tended to focus on how best to detect a single ERP type (such as the visual oddball response). However, the underlying ERP detection problem is essentially the same regardless of stimulus modality (e.g., visual or tactile), ERP component (e.g., P300 oddball response, or the error-potential), measurement system or electrode layout. To investigate whether a single ERP detection method might work for a wider range of ERP BCIs we compare detection performance over a large corpus of more than 50 ERP BCI datasets whilst systematically varying the electrode montage, spectral filter, spatial filter and classifier training methods. We identify an interesting interaction between spatial whitening and regularised classification which made detection performance independent of the choice of spectral filter low-pass frequency. Our results show that pipeline consisting of spectral filtering, spatial whitening, and regularised classification gives near maximal performance in all cases. Importantly, this pipeline is simple to implement and completely automatic with no expert feature selection or parameter tuning required. Thus, we recommend this combination as a "best-practice" method for ERP detection problems. 
650 1 2 |a Brain  |x physiology 
650 1 2 |a Brain Mapping 
650 1 2 |a Brain-Computer Interfaces 
650 2 2 |a Electrodes 
650 2 2 |a Electroencephalography  |x methods 
650 1 2 |a Electroencephalography  |x standards 
650 1 2 |a Evoked Potentials  |x physiology 
650 1 2 |a Guidelines as Topic  |x standards 
650 2 2 |a Humans 
650 2 2 |a Signal Processing, Computer-Assisted 
650 2 2 |a Spectrum Analysis 
700 1 |a Hill, N J 
773 0 |t Neuroinformatics  |g vol. 11, no. 2 (Apr 2013), p. 175 
786 0 |d ProQuest  |t Health & Medical Collection 
856 4 1 |3 Citation/Abstract  |u https://www.proquest.com/docview/1324328057/abstract/embedded/L8HZQI7Z43R0LA5T?source=fedsrch 
856 4 0 |3 Full Text  |u https://www.proquest.com/docview/1324328057/fulltext/embedded/L8HZQI7Z43R0LA5T?source=fedsrch 
856 4 0 |3 Full Text - PDF  |u https://www.proquest.com/docview/1324328057/fulltextPDF/embedded/L8HZQI7Z43R0LA5T?source=fedsrch