Feature Extraction by Mutual Information Based on Minimal-Redundancy-Maximal-Relevance Criterion and Its Application to Classifying EEG Signal for Brain-Computer Interfaces

Erfanian, Abbas; Oveisi, Farid; Shadvar, Ali

doi:10.5772/13935

Cited by 3 publications

(7 citation statements)

References 28 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Assume a random variable X representing continuous-valued random feature vector, and a discrete-valued random variable C representing the class labels. In accordance with Shannon's information theory, the uncertainty of the class label C can be measured by entropy H(C) as (Erfanian et al, 2011).…”

Section: Mutual Information Theory (Mi)mentioning

confidence: 99%

Untitled

Ghassemzadeh

Haghipour

2016

Int. J. Adv. Biol. Biomed. Res.

View full text Add to dashboard Cite

Word or Tex form) to their personal website or institutional repository. Authors requiring further information regarding CASRP΄s archiving and manuscript policies encouraged to visit: http://www.casrp.co.uk/journals Abstract The brain -computer interface (BCI) provides a communicational channel between human and machine. Most of these systems are based on brain activities. Brain Computer-Interfacing is a methodology that provides a way for communication with the outside environment using the brain thoughts. The success of this methodology depends on the selection of methods to process the brain signals in each phase Feature extraction is one of the most important stages in distinguishing of brain activities from EEG. New features are produced by primary features. Today, in the field of EEG signal processing methods for the best feature extraction are so important. In this article we mentioned EEG based brain computer interface ( BCI) systems feature extraction such as Principle Component Analysis (PCA), Linear Discriminant Analysis(LDA), Independent Component Analysis (ICA), Mutual information theory (MI), Empirical Mode Decomposition(EMD), High-order frequency component, Wavelet Transform, Common Spatial Pattern ( CSP), Complex Band Power (CBP).

show abstract

Section: Mutual Information Theory (Mi)mentioning

confidence: 99%

Untitled

Ghassemzadeh

Haghipour

2016

Int. J. Adv. Biol. Biomed. Res.

View full text Add to dashboard Cite

show abstract

“…The waves are sometimes classified on both frequency and on their shape. There are six types of important signals [4], [8][9][10][11][12]. 1) Beta waves: Frequency of these waves is between 13 and 30 Hz and the voltage or amplitude is very low about 5 to 30 µV.…”

Section: Signal Classificationmentioning

confidence: 99%

An Exploration on Brain Computer Interface and Its Recent Trends

Rao¹,

Rajyalakshmi²,

Prasad³

2012

IJARAI

View full text Add to dashboard Cite

Abstract-Detailed exploration on Brain Computer Interface (BCI) and its recent trends has been done in this paper. Work is being done to identify objects, images, videos and their color compositions. Efforts are on the way in understanding speech, words, emotions, feelings and moods. When humans watch the surrounding environment, visual data is processed by the brain, and it is possible to reconstruct the same on the screen with some appreciable accuracy by analyzing the physiological data. This data is acquired by using one of the non-invasive techniques like electroencephalography (EEG) in BCI. The acquired signal is to be translated to produce the image on to the screen. This paper also lays suitable directions for future work.

show abstract

“…Indeed, MI is zero if and only if the two random variables are strictly independent (Erfanian et al, 2011).…”

Section: Mutual Information Theory (Mi)mentioning

confidence: 99%

“…It is equal if and only if one has independence between two variables C and X. The amount by which the class uncertainty is decreased is, by definition, the mutual information, I(X;C) = H(C) − H , and after applying the identities p(c,x) = p p(x) and can be expressed as: ( Erfanian et al, 2011).…”

Section: Mutual Information Theory (Mi)mentioning

confidence: 99%

See 1 more Smart Citation

A review on EEG based brain computer interface systems feature extraction methods

2016

Int. J. Adv. Biol. Biom. Res.

View full text Add to dashboard Cite

Feature Extraction by Mutual Information Based on Minimal-Redundancy-Maximal-Relevance Criterion and Its Application to Classifying EEG Signal for Brain-Computer Interfaces

Cited by 3 publications

References 28 publications

Untitled

Untitled

An Exploration on Brain Computer Interface and Its Recent Trends

A review on EEG based brain computer interface systems feature extraction methods

Contact Info

Product

Resources

About