Energy extraction method for EEG channel selection

Fauzi, Hilman; Azzam, Mohamed; Shapiai, Mohd Ibrahim; Kyoso, Masaki; Khairuddin, Uswah; Komura, Tadayasu

doi:10.12928/telkomnika.v17i5.12805

Cited by 9 publications

(6 citation statements)

References 37 publications

(56 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The method outperformed previous version of PSO by reducing the error rate by 10.4%. Fauzi et al [6] used L2-norm to calculate the energy of each channel and selected the channels with high energies as the active channels for EEG classification. For the hand MI EEG dataset, C3-Cp3-C4-Cp4-Cz, C3-Cp3-C4-Cz-Cpz and Cp3-Cp4-Cpz were selected.…”

Section: Introductionmentioning

confidence: 99%

Classification of lower limb motor imagery based on iterative EEG source localization and feature fusion

Peng

Liu

Huang

et al. 2022

Neural Comput & Applic

View full text Add to dashboard Cite

Motor imagery (MI) brain–computer interface (BCI) systems have broad application prospects in rehabilitation and other fields. However, to achieve accurate and practical MI-BCI applications, there are still several critical issues, such as channel selection, electroencephalogram (EEG) feature extraction and EEG classification, needed to be better resolved. In this paper, these issues are studied for lower limb MI which is more difficult and less studied than upper limb MI. First, a novel iterative EEG source localization method is proposed for channel selection. Channels FC1, FC2, C1, C2 and Cz, instead of the commonly used traditional channel set (TCS) C3, C4 and Cz, are selected as the optimal channel set (OCS). Then, a multi-domain feature (MDF) extraction algorithm is presented to fuse single-domain features into multi-domain features. Finally, a particle swarm optimization based support vector machine (SVM) method is utilized to classify the EEG data collected by the lower limb MI experiment designed by us. The results show that the classification accuracy is 88.43%, 3.35–5.41% higher than those of using traditional SVM to classify single-domain features on the TCS, which proves that the combination of OCS and MDF can not only reduce the amount of data processing, but also retain more feature information to improve the accuracy of EEG classification.

show abstract

Section: Introductionmentioning

confidence: 99%

Classification of lower limb motor imagery based on iterative EEG source localization and feature fusion

Peng

Liu

Huang

et al. 2022

Neural Comput & Applic

View full text Add to dashboard Cite

show abstract

“…The wrapper method involves a feature extraction process for performing channel selection. Some wrapper methods are presented and proposed in [19], [20]. The hybrid method is a method of channel selection by combining filtering and wrapper methods.…”

Section: B Investigation Of Channel Selection For Bcimentioning

confidence: 99%

Defining Common Inter-Session and Inter-Subject EEG Channels Using Spatial Selection Method

Fauzi

Komura

Kyoso

et al. 2022

Int. J. Artif. Intell. Res

Self Cite

View full text Add to dashboard Cite

Redundancy of information on brain signals can lead to reduce brain-computer interface (BCI) performance in applications. To overcome this, EEG channel selection is performed to reduce and/or eliminate a number of channels with irrelevant information. In the previous studies, there is energy calculation methods that have been proposed to perform EEG channel selection to improve BCI performance in classifying the brain command of motor imagery stimulation. In this study, channel selection scheme on motor movement signal will be experimented by using spatial selection method. This study performs the common active channel mechanism that divided into two parts: 1) common active channels between sessions, which known as common Inter-session channels and common active channels. These two techniques can be used by all subjects to interpret motor movement type known as common Inter-subject channels. In order to validate the performance of the proposed framework, CSP (common spatial pattern) is used as a feature extraction method and k-NN with k = 3 as the classification method. The obtained results shows that the proposed channel selection technique is able to choose common active channels in five combination numbers on Inter-sessions and Inter-subjects of the acquired EEG signals. Both types of common active channels are proven to improve BCI performance with an accuracy increase of up to 66%.

show abstract

“…The rhythmic activity is divided into wave bands by frequency while the transient is referring to spontaneous spikes and wave formations that are sharp [23]. There are five types at the most critical frequency ranges: delta (2-4Hz), theta (4-8Hz), alpha (8-12Hz), beta (15-30Hz), and gamma (30-80Hz) [6,24].…”

Section: Features Of Eeg Signalsmentioning

confidence: 99%

Brain computer interface based smart keyboard using neurosky mindwave headset

Salih

Abdal

2020

TELKOMNIKA

View full text Add to dashboard Cite

In the last decade, numerous researches in the field of electro-encephalography (EEG) and brain-computer-interface (BCI) have been accomplished. BCI has been developed to aid disabled/partially disabled people to efficiently communicate with the community. This paper presents a control tool using the Neurosky Mindwave headset, which detects brainwaves (voluntary blinks and attention) to form a braincomputer interface (BCI) by receiving the system signals from the frontal lobe. This paper proposed an alternative computer input device for those disabled people (who are physically challenged) rather than the conventional one. The work suggested to use two virtual keyboard designs. The conducted experiment revealed a significant result in developing user printing skills on PCs. Encouraging results (1.55-1.8 word per minute (WPM)) were obtained in this research in comparison to other studies.

show abstract

Energy extraction method for EEG channel selection

Cited by 9 publications

References 37 publications

Classification of lower limb motor imagery based on iterative EEG source localization and feature fusion

Classification of lower limb motor imagery based on iterative EEG source localization and feature fusion

Defining Common Inter-Session and Inter-Subject EEG Channels Using Spatial Selection Method

Brain computer interface based smart keyboard using neurosky mindwave headset

Contact Info

Product

Resources

About