Spatial Filtering Based on Canonical Correlation Analysis for Classification of Evoked or Event-Related Potentials in EEG Data

Spüler, Martin; Walter, Armin; Rosenstiel, Wolfgang; Bogdan, Martin

doi:10.1109/tnsre.2013.2290870

Cited by 74 publications

(48 citation statements)

References 26 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In contrast, down-sampled data does not provide advantage in terms of accuracy. Rather, a sampling rate between 20 and 40 Hz, as typically used in P300 detection algorithms using EEG [5,6,22,23], yielded slightly lower recognition rates compared with sampling the data at higher rates.…”

Section: Discussionmentioning

confidence: 98%

“…The highest accuracies were achieved equally with two different sets of model functions. The first set was based on empirical estimates constructing reference signals according to [6] and the second set was designed to compose the temporal evolution of the signal. Using the latter method, CCA constructs a spatial filter matrix and concurrently determines brain dynamics.…”

Section: Discussionmentioning

confidence: 99%

“…Similarly, CCA was used to detect steady-state visual evoked potentials for BCI control [14,15]. The classification of ERPs obtained from CCA by building reference functions from trial averages in combination with a linear discriminant classifier was first introduced by Spüler et al [6] and recently compared with other spatial filters [26], revealing a superior performance compared to PCA. In the present paper we adapted this approach for recognizing sequences of events by a simple correlation measure and showed that alternative model functions can be used in this framework as reference signals as well.…”

Section: Discussionmentioning

confidence: 99%

“…However, to exploit the strength of CCA, we intend to model a set of multiple distinct reference functions. One approach was introduced by Spüler et al [6], who calculated the average signal across all standard trials as M s mean ∈ R n×c and across all target trials in a set of training data as M t mean ∈ R n×c , where c is the number of channels to be involved. The advantage of this method is that the reference functions are directly calculated from the brain data representing one time course for each channel with reduced noise.…”

Section: Model Functions For Erpsmentioning

confidence: 99%

“…An appropriate combination of these channels enhances the signal strength and reduces the noise. Such channel weightings are also known as spatial filter coefficients which were applied to analyze P300 potentials, taking varying approaches to estimating the coefficients, e.g., independent component analysis (ICA) [3], common spatial patterns (CSP) [4], spatial whitening [5], canonical correlation analysis (CCA) [6], and others [7,8]. A quite simple example of a spatial filter is averaging the signal across all channels, weighting all channels equally.…”

Section: Introductionmentioning

confidence: 99%

See 4 more Smart Citations

An Efficient Decoder for the Recognition of Event-Related Potentials in High-Density MEG Recordings

et al. 2016

View full text Add to dashboard Cite

Brain-computer interfacing (BCI) is a promising technique for regaining communication and control in severely paralyzed people. Many BCI implementations are based on the recognition of task-specific event-related potentials (ERP) such as P300 responses. However, because of the high signal-to-noise ratio in noninvasive brain recordings, reliable detection of single trial ERPs is challenging. Furthermore, the relevant signal is often heterogeneously distributed over several channels. In this paper, we introduce a new approach for recognizing a sequence of attended events from multi-channel brain recordings. The framework utilizes spatial filtering to reduce both noise and signal space considerably. We introduce different models that can be used to construct the spatial filter and evaluate the approach using magnetoencephalography (MEG) data involving P300 responses, recorded during a BCI experiment. Compared to the accuracy achieved in the BCI experiment performed without spatial filtering, the recognition rate increased significantly to up to 95.3% on average (SD: 5.3%). In combination with the data-driven spatial filter construction we introduce here, our framework represents a powerful method to reliably recognize a sequence of brain potentials from high-density electrophysiological data, which could greatly improve the control of BCIs.

show abstract

Section: Discussionmentioning

confidence: 98%

Section: Discussionmentioning

confidence: 99%

Section: Discussionmentioning

confidence: 99%

Section: Model Functions For Erpsmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

An Efficient Decoder for the Recognition of Event-Related Potentials in High-Density MEG Recordings

et al. 2016

View full text Add to dashboard Cite

show abstract

Effects of Stimulus Sequences on Brain-Computer Interfaces Using Code-Modulated Visual Evoked Potentials: An Offline Simulation

Thielen

2023

Lecture Notes in Computer Science

View full text Add to dashboard Cite

Brain-computer interfaces (BCIs) translate brain activity into computer commands opening a novel non-muscular channel for communication and control. Before BCIs can be used effectively, they require extensive calibration of their machine learning algorithms using labeled training data. This tedious calibration process is not only timeconsuming and costly but also restricts the exploration and optimization of stimulus parameters that could greatly enhance BCI performance. To overcome the challenge of acquiring large training datasets, a simulation framework was developed to eliminate the need for recording calibration data. Unlike previous studies, this simulation framework incorporates a biologically plausible forward model of the code-modulated visual evoked potential (c-VEP). By utilizing synthetic data generated by this improved simulation framework, an offline study was conducted to systematically compare five different stimulus conditions: almost perfect autocorrelation (APA) sequence, de Bruijn sequence, Golay sequence, Gold code, and m-sequence. The results of the study revealed that the Golay sequence achieved the highest grand average performance, followed by the APA sequence, m-sequence, Gold code, and finally the de Bruijn sequence. Furthermore, when the stimulus sequence was optimized for individual participants, typically the Golay and APA sequences exhibited the highest classification accuracy, leading to a significant improvement in overall accuracy as compared to using the Golay sequence for all participants. This research represents an important initial step towards optimizing stimulus parameters for BCIs using simulated data. This approach has the potential to accelerate the development and optimization of BCIs, resulting in more effective applications that can be tailored to individual users.

show abstract

Comparing Methods for Decoding Movement Trajectory from ECoG in Chronic Stroke Patients

Spüler

Grimm²,

Gharabaghi³

et al. 2015

Biosystems &Amp; Biorobotics

View full text Add to dashboard Cite

Spatial Filtering Based on Canonical Correlation Analysis for Classification of Evoked or Event-Related Potentials in EEG Data

Cited by 74 publications

References 26 publications

An Efficient Decoder for the Recognition of Event-Related Potentials in High-Density MEG Recordings

An Efficient Decoder for the Recognition of Event-Related Potentials in High-Density MEG Recordings

Effects of Stimulus Sequences on Brain-Computer Interfaces Using Code-Modulated Visual Evoked Potentials: An Offline Simulation

Comparing Methods for Decoding Movement Trajectory from ECoG in Chronic Stroke Patients

Contact Info

Product

Resources

About