Analysis the effect of PCA for feature reduction in non-stationary EEG based motor imagery of BCI system

Yu, Xinyang; Chum, Pharino; Sim, Kwee-Bo

doi:10.1016/j.ijleo.2013.09.013

Cited by 106 publications

(40 citation statements)

References 6 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Neuper et al [32] also used the same method for referencing and reported the classification accuracy, in case of kinesthetic motor imagery (MIK), is 67%. Yu et al [67] used several types of spatial filter such as Common Average Reference (CAR), Laplacian (LAP), Common Spatial Pattern (CSP) and no-spatial filter technique in his research. In that experiment Support Vector Machine (SVM) was used as classifier and interestingly the best performance was obtained from CAR method rather than CSP or other method.…”

Section: |P a G Ementioning

confidence: 99%

A Review on the Components of EEG-based Motor Imagery Classification with Quantitative Comparison

Rahman¹,

Joadder²

2017

Appl. Theory Comput. Technol.

View full text Add to dashboard Cite

Motor Imagery (MI) is a voluntary modulation of brain signals for specific action without real limb movement. It is essential to classify MI signal to design a brain computer interface (BCI). BCI involves a number of signal processing steps, and a lot of techniques have been developed for each step. There can be numerous combinations of these techniques at different steps that can be employed to design a BCI. This work focuses on MI-based BCI using EEG signal and reviews the existing techniques. More importantly, a detailed comparative study is performed to explore the important combinations of methods by comparing their performance quantitatively. Often a method, which performs very good in one combination, can be bad performer in other combinations and it is a dilemma for the researchers to select appropriate methods for their desired BCI application.In our performance analysis, we have systematically included the variations of methods in each step of BCI such that it gives idea to BCI researchers how each method in one step fits best with specific combinations of methods in other steps. We have shown that how much each step is sensitive towards overall performance of the BCI system.We hope that this work helps, especially for new researchers, to provide a better guideline for designing more efficient BCI system.

show abstract

Section: |P a G Ementioning

confidence: 99%

A Review on the Components of EEG-based Motor Imagery Classification with Quantitative Comparison

Rahman¹,

Joadder²

2017

Appl. Theory Comput. Technol.

View full text Add to dashboard Cite

show abstract

“…[32,33] This technique projects a dataset into different components that captures the variance of the data, where each component is a linear combination of the features. Moreover, the first component captures the most variance in the dataset, the second component captures the second most variance, and so on.…”

Section: Principal Component Analysismentioning

confidence: 99%

Assessment of feature selection and classification methods for recognizing motor imagery tasks from electroencephalographic signals

Vega

Sajed

Mathewson

et al. 2016

AIR

View full text Add to dashboard Cite

Recognition of motor imagery tasks (MI) from electroencephalographic (EEG) signals is crucial for developing rehabilitation and motor assisted devices based on brain-computer interfaces (BCI). Here we consider the challenge of learning a classifier, based on relevant patterns of the EEG signals; this learning step typically involves both feature selection, as well as a base learning algorithm. However, in many cases it is not clear what combination of these methods will yield the best classifier. This paper contributes a detailed assessment of feature selection techniques, viz., squared Pearson's correlation (R 2 ), principal component analysis (PCA), kernel principal component analysis (kPCA) and fast correlation-based filter (FCBF); and the learning algorithms: linear discriminant analysis (LDA), support vector machines (SVM), and Feed Forward Neural Network (NN). A systematic evaluation of the combinations of these methods was performed in three two-class classification scenarios: rest vs. movement, upper vs. lower limb movement and right vs. left hand movement. FCBF in combination with SVM achieved the best results with a classification accuracy of 81.45%, 77.23% and 68.71% in the three scenarios, respectively. Importantly, FCBF determines, based on the feature set, whether a classifier can be learned, and if so, automatically identifies the subset of relevant and non-correlated features. This suggests that FCBF is a powerful method for BCI systems based on MI. Knowledge gained here about procedural combinations has the potential to produce useful BCI tool, that can provide effective motor control for the users.

show abstract

“…Reference [48] uses Common Average Reference(CAR) to filter the offline data, and eliminate the instability of EEG signal to a certain extent. Many feature extraction algorithms based on CSP are used to eliminate the instability.…”

Section: B Feature Extractionmentioning

confidence: 99%

Review of Brain Computer Interface Components and Corresponding Research Topics

Wang¹,

Wang²,

Liang³

et al. 2016

Advances in Computer Science Research

View full text Add to dashboard Cite

Abstract-This paper conducts a research on the literature of Brain Computer Interface(BCI) in recent years, inducing the four components of BCI and the research topics respectively, and providing a guide to newcomers for exploring BCI. BCI is divided into four parts including signal collection, feature extraction, feature classification and practical application. Papers of above four parts are retrieved respectively from the SCI database. Topics of all papers are concluded, based on which the research topics of BCI are assigned to the four parts of BCI. In topics of each part of BCI, similar topics are summarized to the unique topic. Finally some research topics may cover dozens of papers while some topics may cover only several papers. In each of the four BCI components, there are several topics attracting most of the attention. BCI still has a great research value and good prospects for study.

show abstract

Analysis the effect of PCA for feature reduction in non-stationary EEG based motor imagery of BCI system

Cited by 106 publications

References 6 publications

A Review on the Components of EEG-based Motor Imagery Classification with Quantitative Comparison

A Review on the Components of EEG-based Motor Imagery Classification with Quantitative Comparison

Assessment of feature selection and classification methods for recognizing motor imagery tasks from electroencephalographic signals

Review of Brain Computer Interface Components and Corresponding Research Topics

Contact Info

Product

Resources

About