Performance enhancement of mental task classification using EEG signal: a study of multivariate feature selection methods

Gupta, Akanksha; Agrawal, R. K.; Kaur, Baljeet

doi:10.1007/s00500-014-1443-1

Cited by 53 publications

(28 citation statements)

References 46 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…To represent each of these IMFs per segment per channel compactly, eight statistical or uncertainty parameters ( Root Mean Square (RMS), Variance, Skewness, Kurtosis, Hurst Exponent (Hurst, 1951), Shannon Entropy, Central Frequency, Maximum Frequency ) are calculated for a given subject. Some of these parameters represent linear characteristics of the EEG signal and other represent non-linear properties of EEG Gupta and Agrawal, 2012;Gupta et al, 2015). In this work, the parameters are selected empirically as every signal or data has the distinguishable property in terms of a certain set of statistical parameters associated with the signal or data as shown in Figure 2.…”

Section: Dataset and Constructing Feature Vectormentioning

confidence: 99%

Performance Evaluation of Empirical Mode Decomposition Algorithms for Mental Task Classification

Gupta¹,

Kumar²,

Chakraborti³

et al. 2016

Preprint

Self Cite

View full text Add to dashboard Cite

Brain Computer Interface (BCI), a direct pathway between the human brain and computer, is one of the most pragmatic applications of EEG signal. The electroencephalograph (EEG) signal is one of the monitoring techniques to observe brain functionality. Mental Task Classification (MTC) based on EEG signals is a demanding BCI. Success of BCI system depends on the efficient analysis of these signals. Empirical Mode Decomposition (EMD) is a filter based heuristic technique which is utilized to analyze EEG signal in recent past. There are several variants of EMD algorithms which have their own merits and demerits. In this paper, we have explored three variants of EMD algorithms named Empirical Mode Decomposition (EMD), Ensemble Empirical Mode Decomposition (EEMD) and Complete Ensemble Empirical Mode Decomposition with Adaptive Noise (CEEMDAN) on EEG data for MTC-based BCI. Features are extracted from EEG signal in two phases; in the first phase, the signal is decomposed into different oscillatory functions with the help of different EMD algorithms and eight different parameters (features) are calculated for each function for compact representation in the second phase. These features are fed into Support Vector Machine (SVM) classifier to classify the different mental tasks. We have formulated two different types of MTC, the first one is binary and second one is multi-MTC. The proposed work outperforms the existing work for both binary and multi mental tasks classification.

show abstract

Section: Dataset and Constructing Feature Vectormentioning

confidence: 99%

Performance Evaluation of Empirical Mode Decomposition Algorithms for Mental Task Classification

Gupta¹,

Kumar²,

Chakraborti³

et al. 2016

Preprint

Self Cite

View full text Add to dashboard Cite

show abstract

“…With DWT, a higher number of useful information can be extracted from a non-stationary signal if compared to STFT [9] with better time resolution. It has been applied to studies ranging from neurophysiological disorders to brain computer interfaces [12][13][14].…”

Section: Introductionmentioning

confidence: 99%

Selection of Symlets wavelet function order for EEG signal feature extraction in children with dyslexia

Mahmoodin

Jalalludin

Mansor

et al. 2015

2015 IEEE Student Symposium in Biomedical Engineering &Amp; Sciences (ISSBES)

View full text Add to dashboard Cite

Electroencephalograph (EEG) signal provides information on brain functionalities where electrodes are placed on the surface of the scalp and is suitable in analyzing neurological based disorder such as dyslexia. Known to cause learning disorder, dyslexic tends to utilize different areas of the brain in processing information compared to that of a normal learner. Being non-stationary, the wavelet theory has been extensively used in extracting relevant features from the noisy EEG signal with a wide option of wavelet families. The aim of this paper is to identify a suitable function order within the Symlets family to extract power feature in the EEG signal of dyslexic children during writing. Recorded EEG signals from 8 electrode locations of C3, C4, P3, P4, FC5, FC6, T7 and T8 were analyzed using Symlets function of order 5, 7, 8 and 9. The final selection are based on the order ability to provide the most distinctive variance and consistency in term of its beta band power feature. Results indicated that Symlets of order 5 and 7 (Sym-5, Sym-7) are suitable for extracting power band feature for EEG signal of poor dyslexic children during writing. However, results with capable dyslexic children were inconsistent.

show abstract

“…The extracted features should be extremely discriminative to recognize different mental states in online applications. 12 Various efficient pre-processing and feature extraction techniques are suggested in the literature to prepare a discriminative feature set. [12][13][14][15][16] Siuly et al developed crosscorrelation based feature extraction methodology and used Least Square Support Vector Machine (LS-SVM) for motor imagery signals classification.…”

Section: Introductionmentioning

confidence: 99%

“…12 Various efficient pre-processing and feature extraction techniques are suggested in the literature to prepare a discriminative feature set. [12][13][14][15][16] Siuly et al developed crosscorrelation based feature extraction methodology and used Least Square Support Vector Machine (LS-SVM) for motor imagery signals classification. 16 Kaya et al proposed a one-dimensional binary pattern based feature extraction technique for epileptic EEG signals classification.…”

Section: Introductionmentioning

confidence: 99%

“…[18][19][20][21] EEG signals show low voltage (10-30 µV) and fast EEG activity (16)(17)(18)(19)(20)(21)(22)(23)(24)(25) for awake humans, whereas high voltage (20-40 µV) and slow EEG activity (8)(9)(10)(11)(12) Hz, alpha rhythm) for relaxed humans. 22 Due to the change in mental state or alertness level (i.e., drowsy and alert), brain electrical activities change severely, which in turn alter EEG patterns to a large extent and cause false classification of EEG signals.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Application of S-Transform for Automated Detection of Vigilance Level Using Eeg Signals

2016

View full text Add to dashboard Cite

This paper presents an S-transform-based Electroencephalogram channel optimization and feature extraction methodology for monitoring mental vigilance level of humans. Vigilance level detection methodology consists of four steps. In the first stage, two types of Electroencephalogram signals (alert and drowsy) are acquired from 30 healthy subjects and decomposed into sub-bands using the S-transform. In the second stage, permutation entropy of the S-transform coefficients is calculated and Electroencephalogram channel optimization is performed. S-transform-based statistical features are computed from the optimized Electroencephalogram channels, in the third stage. In the fourth stage, artificial intelligence techniques such as Least Square-Support Vector Machine, Artificial Neural Network and Naive Bayes Classifier are used for the classification of Electroencephalogram signals using extracted features. The performance of the feature extraction methodology is tested on the Electroencephalogram data of 30 healthy subjects. Experimental results ensured the effectiveness of proposed methodology for the estimation of mental vigilance level by using Electroencephalogram signals. It is observed that the Artificial Neural Network classifier is a good candidate for pre-emptive automatic vigilance level detection system for Brain-Computer Interface applications.

show abstract

Performance enhancement of mental task classification using EEG signal: a study of multivariate feature selection methods

Cited by 53 publications

References 46 publications

Performance Evaluation of Empirical Mode Decomposition Algorithms for Mental Task Classification

Performance Evaluation of Empirical Mode Decomposition Algorithms for Mental Task Classification

Selection of Symlets wavelet function order for EEG signal feature extraction in children with dyslexia

Application of S-Transform for Automated Detection of Vigilance Level Using Eeg Signals

Contact Info

Product

Resources

About