Frequency detection for SSVEP-based BCI using deep canonical correlation analysis
01 Oct 2016-pp 001983-001987
TL;DR: To the best knowledge, this is the first time to apply deep CCA (DCCA) to the task of frequency component extraction in SSVEP and it demonstrates that DCCA extracts more robust feature, which has significantly higher signal to noise ratio (SNR) compared to those of CCA.
Abstract: Canonical correlation analysis (CCA) has been successfully used for extracting frequency components of steady-state visual evoked potential (SSVEP) in electroencephalography (EEG). Recently, a few efforts on CCA-based SSVEP methods have been made to demonstrate the benefits for brain computer interface (BCI). Most of these methods are limited to linear CCA. In this paper consider a deep extension of CCA where input data are processed through multiple layers before their correlations are computed. To our best knowledge, it is the first time to apply deep CCA (DCCA) to the task of frequency component extraction in SSVEP. Our empirical study demonstrates that DCCA extracts more robust feature, which has significantly higher signal to noise ratio (SNR) compared to those of CCA, and it results in better performance in classification with the averaged accuracy of 92%.
Citations
More filters
TL;DR: It is suggested that the STE-DW algorithm can be used as a reliable identification algorithm for training-free SSVEP-based BCIs, because of the good balance between ease of use, recognition accuracy, ITR and user applicability.
Abstract: The past decade has witnessed rapid development in the field of brain–computer interfaces (BCIs). While the performance is no longer the biggest bottleneck in the BCI application, the tedious train...
52 citations
TL;DR: A nonlinear feature extraction method based on deep multiset CCA (DMCCA) is proposed for SSVEP recognition to fully utilize the real EEG and constructed sine–cosine signals.
36 citations
TL;DR: In this article, a novel data-driven fault diagnosis method by combining deep canonical variate analysis and Fisher discriminant analysis (DCVA-FDA) is proposed for complex industrial processes.
Abstract: In this article, a novel data-driven fault diagnosis method by combining deep canonical variate analysis and Fisher discriminant analysis (DCVA-FDA) is proposed for complex industrial processes. Inspired by the recently developed deep canonical correlation analysis, a new nonlinear canonical variate analysis (CVA) called DCVA is first developed by incorporating deep neural networks into CVA. Based on DCVA, a residual generator is designed for the fault diagnosis process. FDA is applied in the feature space spanned by residual vectors. Then, a Bayesian inference classifier is performed in the reduced dimensional space of FDA to label the class of process data. A continuous stirred-tank reactor and an industrial benchmark of the Tennessee Eastman process are carried out to test the performance of DCVA-FDA fault diagnosis. The experimental results demonstrate that the proposed DCVA-FDA fault diagnosis is able to significantly improve the fault diagnosis performance when compared to other methods also examined in this article.
34 citations
TL;DR: It is argued that spatiotemporal beamforming can serve several synchronous visual BCI paradigms even without attempting to optimizing their electrode sets and investigated whether interactions between beamformer outputs could be employed to increase accuracy.
Abstract: Brain-Computer Interfaces (BCIs) decode brain activity with the aim to establish a direct communication channel with an external device. Albeit they have been hailed to (re-)establish communication in persons suffering from severe motor- and/or communication disabilities, only recently BCI applications have been challenging other assistive technologies. Owing to their considerably increased performance and the advent of affordable technological solutions, BCI technology is expected to trigger a paradigm shift not only in assistive technology but also in the way we will interface with technology. However, the flipside of the quest for accuracy and speed is most evident in EEG-based visual BCI where it has led to a gamut of increasingly complex classifiers, tailored to the needs of specific stimulation paradigms and use contexts. In this contribution, we argue that spatiotemporal beamforming can serve several synchronous visual BCI paradigms. We demonstrate this for three popular visual paradigms even without attempting to optimizing their electrode sets. For each selectable target, a spatiotemporal beamformer is applied to assess whether the corresponding signal-of-interest is present in the preprocessed multichannel EEG signals. The target with the highest beamformer output is then selected by the decoder (maximum selection). In addition to this simple selection rule, we also investigated whether interactions between beamformer outputs could be employed to increase accuracy by combining the outputs for all targets into a feature vector and applying three common classification algorithms. The results show that the accuracy of spatiotemporal beamforming with maximum selection is at par with that of the classification algorithms and interactions between beamformer outputs do not further improve that accuracy.
34 citations
01 Jan 2018
TL;DR: This paper proposes a deep learning model that uses a hybrid architecture based on Convolutional and Recurrent Neural Networks to classify SSVEP signals in the time domain directly and achieves accuracy higher than the state-of-the-art method: canonical correlation analysis in the frequency domain.
Abstract: Steady-State Visual Evoked Potential (SSVEP) is one of the popular methods of brain-computer interfacing (BCI). It is used to translate the Electroencephalogram (EEG) signals into actions or choices. The main challenge in processing the SSVEP signal recognition is finding an appropriate intermediate representation to facilitate the classification task afterwards. In the literature, frequency domain analysis was extensively adopted as an intermediate representation for SSVEP classification. In this presented paper, we propose a deep learning model that uses a hybrid architecture based on Convolutional and Recurrent Neural Networks to classify SSVEP signals in the time domain directly. We achieved accuracy 93.59% compared to 87.40% for the state-of-the-art method: canonical correlation analysis in the frequency domain. The proposed architecture facilitates the real-time classification of SSVEP signals in the time domain for real-time applications such as robot cars and exoskeletons.
26 citations
Cites background from "Frequency detection for SSVEP-based..."
...maximize the correlation between the two sets of datasets [6]....
[...]
References
More filters
TL;DR: The concept of correlation and regression may be applied not only to ordinary one-dimensional variates but also to variates of two or more dimensions as discussed by the authors, where the correlation of the horizontal components is ordinarily discussed, whereas the complex consisting of horizontal and vertical deviations may be even more interesting.
Abstract: Concepts of correlation and regression may be applied not only to ordinary one-dimensional variates but also to variates of two or more dimensions. Marksmen side by side firing simultaneous shots at targets, so that the deviations are in part due to independent individual errors and in part to common causes such as wind, provide a familiar introduction to the theory of correlation; but only the correlation of the horizontal components is ordinarily discussed, whereas the complex consisting of horizontal and vertical deviations may be even more interesting. The wind at two places may be compared, using both components of the velocity in each place. A fluctuating vector is thus matched at each moment with another fluctuating vector. The study of individual differences in mental and physical traits calls for a detailed study of the relations between sets of correlated variates. For example the scores on a number of mental tests may be compared with physical measurements on the same persons. The questions then arise of determining the number and nature of the independent relations of mind and body shown by these data to exist, and of extracting from the multiplicity of correlations in the system suitable characterizations of these independent relations. As another example, the inheritance of intelligence in rats might be studied by applying not one but s different mental tests to N mothers and to a daughter of each
6,122 citations
"Frequency detection for SSVEP-based..." refers background in this paper
...multidimensional variables [10], and its goal is to find the maximal correlation coefficient between those two sets....
[...]
Proceedings Article•
16 Jun 2013TL;DR: DCCA is introduced, a method to learn complex nonlinear transformations of two views of data such that the resulting representations are highly linearly correlated and Parameters of both transformations are jointly learned to maximize the (regularized) total correlation.
Abstract: We introduce Deep Canonical Correlation Analysis (DCCA), a method to learn complex nonlinear transformations of two views of data such that the resulting representations are highly linearly correlated. Parameters of both transformations are jointly learned to maximize the (regularized) total correlation. It can be viewed as a nonlinear extension of the linear method canonical correlation analysis (CCA). It is an alternative to the nonparametric method kernel canonical correlation analysis (KCCA) for learning correlated nonlinear transformations. Unlike KCCA, DCCA does not require an inner product, and has the advantages of a parametric method: training time scales well with data size and the training data need not be referenced when computing the representations of unseen instances. In experiments on two real-world datasets, we find that DCCA learns representations with significantly higher correlation than those learned by CCA and KCCA. We also introduce a novel non-saturating sigmoid function based on the cube root that may be useful more generally in feedforward neural networks.
1,502 citations
"Frequency detection for SSVEP-based..." refers background or methods in this paper
...In [8], they noted that DCCA might particularly have an advantage when the number of output units equal to the top components of two...
[...]
...A deep extension of CCA was introduced in [8], referred to as deep canonical correlation analysis (DCCA)....
[...]
...This model learns the complex nonlinear transformations of two sets of data to give high linear correlation between their representations [8]....
[...]
TL;DR: A recognition approach is proposed based on the extracted frequency features for an SSVEP-based brain computer interface (BCI) that were higher than those using a widely used fast Fourier transform (FFT)-based spectrum estimation method.
Abstract: Canonical correlation analysis (CCA) is applied to analyze the frequency components of steady-state visual evoked potentials (SSVEP) in electroencephalogram (EEG). The essence of this method is to extract a narrowband frequency component of SSVEP in EEG. A recognition approach is proposed based on the extracted frequency features for an SSVEP-based brain computer interface (BCI). Recognition Results of the approach were higher than those using a widely used fast Fourier transform (FFT)-based spectrum estimation method
826 citations
"Frequency detection for SSVEP-based..." refers methods in this paper
...powerful method for discriminating the frequency component of SSVEP from possible frequencies [3, 4]....
[...]
...multiple-channel EEG signals using CCA and select one of them which shows the maximum value to be target frequency [3]....
[...]
...The feasibility of using CCA for SSVEP BCI was first introduced by [3], where CCA was shown to be better than the Fourier transform-based method....
[...]
TL;DR: The positive characteristics of the proposed SSVEP-based BCI system are that channel selection and parameter optimization are not required, the possible use of harmonic frequencies, low user variation and easy setup.
Abstract: In recent years, there has been increasing interest in using steady-state visual evoked potential (SSVEP) in brain–computer interface (BCI) systems. However, several aspects of current SSVEP-based BCI systems need improvement, specifically in relation to speed, user variation and ease of use. With these improvements in mind, this paper presents an online multi-channel SSVEP-based BCI system using a canonical correlation analysis (CCA) method for extraction of frequency information associated with the SSVEP. The key parameters, channel location, window length and the number of harmonics, are investigated using offline data, and the result used to guide the design of the online system. An SSVEP-based BCI system with six targets, which use nine channel locations in the occipital and parietal lobes, a window length of 2 s and the first harmonic, is used for online testing on 12 subjects. The results show that the proposed BCI system has a high performance, achieving an average accuracy of 95.3% and an information transfer rate of 58 ± 9.6 bit min−1. The positive characteristics of the proposed system are that channel selection and parameter optimization are not required, the possible use of harmonic frequencies, low user variation and easy setup.
694 citations
"Frequency detection for SSVEP-based..." refers background in this paper
...signals, and it is important to prove the confidence of the method [12]....
[...]
TL;DR: This paper reviews the literature on SSVEP-based BCIs and comprehensively reports on the different RVS choices in terms of rendering devices, properties, and their potential influence on BCI performance, user safety and comfort.
Abstract: Brain-computer interface (BCI) systems based on the steady-state visual evoked potential (SSVEP) provide higher information throughput and require shorter training than BCI systems using other brain signals. To elicit an SSVEP, a repetitive visual stimulus (RVS) has to be presented to the user. The RVS can be rendered on a computer screen by alternating graphical patterns, or with external light sources able to emit modulated light. The properties of an RVS (e.g., frequency, color) depend on the rendering device and influence the SSVEP characteristics. This affects the BCI information throughput and the levels of user safety and comfort. Literature on SSVEP-based BCIs does not generally provide reasons for the selection of the used rendering devices or RVS properties. In this paper, we review the literature on SSVEP-based BCIs and comprehensively report on the different RVS choices in terms of rendering devices, properties, and their potential influence on BCI performance, user safety and comfort.
563 citations
"Frequency detection for SSVEP-based..." refers background in this paper
...Especially, due to its advantages such as easy system configuration, little user training and relatively high information transfer rate, the BCI with SSVEP has been adopted in many studies as a promising BCI paradigm [2]....
[...]