Filter Bank Common Spatial Pattern (FBCSP) in Brain-Computer Interface
Citations
1,966 citations
1,675 citations
Cites background or methods from "Filter Bank Common Spatial Pattern ..."
...To address whether these ConvNets can reach competitive decoding accuracies, we performed a statistical comparison of their decoding accuracies to those achieved with decoding based on filter bank common spatial patterns (FBCSP) [Ang et al., 2008; Chin et al., 2009], a method that is widely used in EEG decoding and has won several EEG decoding competitions such as BCI competition IV datasets 2a and 2b....
[...]
..., 2008] and a highpass filter was one of the suggested methods to remove eye artefacts; indeed this was the method the winners of the competition used [Ang et al., 2008]....
[...]
...…datasets special care to avoid decoding eye-related signals was requested from the publishers of the datasets [Brunner et al., 2008] and a highpass filter was one of the suggested methods to remove eye artefacts; indeed this was the method the winners of the competition used [Ang et al., 2008]....
[...]
...filters is therefore typically applied to the whole set of relevant electrodes as a basic step in many successful examples of EEG decoding [Ang et al., 2008; Blankertz et al., 2008; Rivet et al., 2009]....
[...]
...FBCSP [Ang et al., 2008; Chin et al., 2009] is a widely used method to decode oscillatory EEG data, for example, with respect to movement-related information, that is, the decoding problem we focus on in this study....
[...]
862 citations
Cites methods or result from "Filter Bank Common Spatial Pattern ..."
...Various classification algorithms can be used, but the study in (Ang et al., 2008) showed that FBCSP that employed the Naïve Bayesian Parzen Window (NBPW) classifier (Ang and Quek, 2006) yielded better results on the BCI Competition III Dataset IVa....
[...]
...FILTER BANK COMMON SPATIAL PATTERN The Filter Bank Common Spatial Pattern (FBCSP) algorithm (Ang et al., 2008) is illustrated in Figure 1....
[...]
...The Filter Bank Common Spatial Pattern (FBCSP) algorithm (Ang et al., 2008) is illustrated in Figure 1....
[...]
...Based on the study in (Ang et al., 2008), k = 4 is used....
[...]
...In this paper, the Filter Bank Common Spatial Pattern (FBCSP) algorithm is presented to enhance the performance of the CSP algorithm by performing autonomous selection of discriminative subject-specific frequency range for band-pass filtering of the EEG measurements (Ang et al., 2008)....
[...]
747 citations
Cites methods from "Filter Bank Common Spatial Pattern ..."
...is based on the filter bank common spatial pattern (FBCSP) variant (Ang et al., 2008)....
[...]
553 citations
References
45,034 citations
26,531 citations
"Filter Bank Common Spatial Pattern ..." refers background in this paper
...The SVM implementation in the Matlab Bioinformatics toolbox is used in this paper....
[...]
...Spatial Patterns of using FBCSPf on BCI Competition dataset IVa for subjects (a) ‘aa’, (b) ‘al’, (c) ‘av’, (d) ‘aw’, and (e) ‘ay’ respectively 2396 2008 International Joint Conference on Neural Networks (IJCNN 2008) NBPW FLD CART KNN SVM RNFS DENFIS AVG 60 65 70 75 80 85 A cc u ra cy (% ) Test accuracy MIBIF1 MIBIF2 MIBIF3 MIBIF4 MIFS FRFS2 MINBPW MIRSR Fig....
[...]
...The results also show that the FBCSP with MIBIF4 and NBPW as well as SVM yield a superior test accuracy of 81.1(2.2%, whereas FLD yields 80.9(2.1%....
[...]
...Specifically, the FBCSP with MIBIF4 and NBPW yields a test accuracy of 90.3(0.7%; whereas FLD yields 89.9(0.9%, and SVM yields 90.0(0.8%....
[...]
...The Support Vector Machine (SVM) [27] is a linear discriminant that maximizes the separation between two classes based on the assumption that it improves the classifier’s generalization capability....
[...]
14,825 citations
12,243 citations
"Filter Bank Common Spatial Pattern ..." refers methods in this paper
...The k-nearest neighbor (k-NN) [29] is a classifier that assigns the class label of a new data based on the class with the most occurrences in a set of k nearest training data points usually computed using a distance measure such as the Euclidean distance....
[...]