Improved SFFS method for channel selection in motor imagery based BCI

Qiu, Zhaoyang; Jin, Jing; Lam, Hak‐Keung; Yu, Zhang; Wang, Xingyu; Cichocki, Andrzej

doi:10.1016/j.neucom.2016.05.035

Cited by 138 publications

(106 citation statements)

References 47 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…5, respectively. We can find that the most effective components of the decomposed EEG are mainly concentrated in the two components 2 f and 3 f by calculating the correlation coefficient threshold. , 2 imf , 3 imf , 4 imf , 5 imf , 6 imf , 7 imf , 8 imf , 9 imf , respectively).…”

Section: Methodsmentioning

confidence: 99%

See 1 more Smart Citation

EEG Recognition of Motor Imagery Based on EWT in Driving Assistance

Shan¹,

Wang²,

He³

et al. 2017

Advances in Computer Science Research

View full text Add to dashboard Cite

Abstract. Electroencephalogram (EEG) feature extraction is one of the key techniques for BrainComputer Interface (BCI) in driving assistance. In this paper, empirical wavelet transform (EWT) is introduced for EEG feature extraction, and then a new EEG recognition method based on EWT is proposed. In the proposed method, the EEG features of the left arm flexion and extension motor imagery mode were first extracted via EWT and compared with those extracted by the empirical mode decomposition (EMD), and then the extracted features were classified by support vector machine (SVM). The results show that the EWT method significantly outperforms the EMD method, which can effectively decompose the intrinsic modes of EEG, and it presents several merits of fewer modes, no false mode and low computation cost. Therefore, the EWT method can effectively extract the local transient features of EEG and realize the effective classification through SVM, thus providing the chance of driving assistance through the arm flexion and extension imagination.

show abstract

Section: Methodsmentioning

confidence: 99%

“…There are two types of BCI: spontaneous EEG, and evoked EEG based on BCI systems [2]. Today, BCI technology not only can be used as an important means of rehabilitation, but also can be used in the driving assistance area of the car, 1) the driver's fatigue state monitoring [3]; 2)an assistant control [4].…”

Section: Introductionmentioning

confidence: 99%

EEG Recognition of Motor Imagery Based on EWT in Driving Assistance

Shan¹,

Wang²,

He³

et al. 2017

Advances in Computer Science Research

View full text Add to dashboard Cite

show abstract

“…Many search strategies have been designed to avoid the exhaustive search even though the feature set obtained may be suboptimal. The sequential forward floating selection (SFFS) algorithm is a relatively new strategy, and has been widely applied in practice [20][21][22].…”

Section: Sequential Forward Floating Selectionmentioning

confidence: 99%

Real-time Monitoring for Disk Laser Welding Based on Feature Selection and SVM

et al. 2017

View full text Add to dashboard Cite

Abstract:In order to automatically evaluate the welding quality during high-power disk laser welding, a real-time monitoring system was developed. The images of laser-induced metal vapor during welding were captured and fifteen features were extracted. A feature selection method based on a sequential forward floating selection algorithm was employed to identify the optimal feature subset, and a support vector machine (SVM) classifier was built to recognize the welding quality. The experiment results demonstrated that this method had satisfactory performance, and could be applied in laser welding monitoring applications.

show abstract

“…These patterns are known as ERD/ERS. As these event-related potentials occur in the motor cortex region, so using electrodes only from this area can help to avoid redundant information and noise for data processing [39]. Thus to improve the classification accuracy channel selection is very important.…”

Section: Channel Selectionmentioning

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

Improved SFFS method for channel selection in motor imagery based BCI

Cited by 138 publications

References 47 publications

EEG Recognition of Motor Imagery Based on EWT in Driving Assistance

EEG Recognition of Motor Imagery Based on EWT in Driving Assistance

Real-time Monitoring for Disk Laser Welding Based on Feature Selection and SVM

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

Contact Info

Product

Resources

About