Classification of epileptic seizures in EEG signals based on phase space representation of intrinsic mode functions

Sharma, Rajeev; Pachori, Ram Bilas

doi:10.1016/j.eswa.2014.08.030

Cited by 369 publications

(156 citation statements)

References 62 publications

Supporting

Mentioning

149

Contrasting

Unclassified

Order By: Relevance

“…Repeat from 2 till 'i' becomes equal to 4. Note that the procedure described in (21) to (23) can be related to the Empirical Mode Decomposition (EMD)-based procedure of signal component extraction [3]. However, the aforementioned procedure based on quadratic TFDs offers a higher resolution as compared with the EMD, as has been shown in previous studies [17].…”

mentioning

confidence: 84%

“…Most of the existing abnormality detection methodologies require visual analysis by a neurophysiologist. Detection of abnormality in EEG signal is a non-stationary signal classification problem that involves extraction of features from time-domain, frequency domain or joint t-f domain representations of signal [1][2][3][4][5][6]. Recent studies have indicated that EEG signals have non-stationary characteristics, so time-frequency methods are preferred tools for their analysis [2].…”

Section: Introductionmentioning

confidence: 99%

“…Typical t-f signal classification approaches can be classified into two categories: 1) template matching approaches, where a t-f representation of a given signal is correlated with stored templates to detect the presence of abnormality [7]; 2) machine learning approaches that involve such steps as feature extraction and classifier training [2]. The timefrequency features can be extracted by dimensionality reduction approaches such as singular value decomposition [2], interpreting TFDs as images and using texture information as features [8,9], separating signal components using empirical mode decomposition and extracting features from the separated components [3,5,6].…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Classification of EEG Signals Using Adaptive Time-Frequency Distributions

Khan¹,

Ali²

2016

Metrology and Measurement Systems

View full text Add to dashboard Cite

Time-Frequency (t-f) distributions are frequently employed for analysis of new-born EEG signals because of their non-stationary characteristics. Most of the existing time-frequency distributions fail to concentrate energy for a multicomponent signal having multiple directions of energy distribution in the t-f domain. In order to analyse such signals, we propose an Adaptive Directional Time-Frequency Distribution (ADTFD). The ADTFD outperforms other adaptive kernel and fixed kernel TFDs in terms of its ability to achieve high resolution for EEG seizure signals. It is also shown that the ADTFD can be used to define new time-frequency features that can lead to better classification of EEG signals, e.g. the use of the ADTFD leads to 97.5% total accuracy, which is by 2% more than the results achieved by the other methods.

show abstract

mentioning

confidence: 84%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Classification of EEG Signals Using Adaptive Time-Frequency Distributions

Khan¹,

Ali²

2016

Metrology and Measurement Systems

View full text Add to dashboard Cite

show abstract

“…The common methods of dealing message are independent vector based method, Fourier transforms method, and wavelet transforms method and so on [6][7][8][9][10][11][12][13][14][15]. Given the instantaneity of developed system, we use FFT to transform the EEG signal from time domain to frequency domain, and extract the corresponding features in frequency domain.…”

Section: Extraction Of Brainwave Controlmentioning

confidence: 99%

Remote controller using steady state visual evoked potential

Song¹,

Wang²,

Wang³

et al. 2017

2nd Annual International Conference on Energy, Environmental &Amp; Sustainable Ecosystem Development (EESED 2016)

View full text Add to dashboard Cite

This paper develops a new air-conditioning remote ccontrol system which based on brain waves and the Android system. First of all, the desired brain waves in EEG signals in the form of steady-state visual evoked is collected. By extracting and analysis the feature hidden in EEG signal, the system can identify the operation intention of volunteer to control air-conditioning machine, such as open or close and addition or subtraction about temperature. In addition, the control coding and wireless connections are implemented based on Bluetooth technology. Finally, we realize the Android mobile phones as the core of whole remote control. The eexperimental results show that brain wave control system of air conditioner remote is capable of stable and rapid detection of brain signals to control commands. Compared to commonly used buttons remote control, our designed system can realize the goal of non-contact control for air-conditioning.

show abstract

“…There is also inter-reader differences during the visual analysis and it suggest that the visual analysis could be insufficient. With that reason, new computer evaluation techniques are developed and performed in healthy and diseased individuals (5)(6)(7)(8)(9)(10)(11)(12)(13). Most of these studies consist of two steps: Feature extraction from the EEG signals and then classification of these features.…”

Section: Introductionmentioning

confidence: 99%

The Comparison of Different Dimension Reduction and Classification Methods in Electroencephalogram Signals

Öztürk¹,

Türe²,

Kıylıoğlu³

et al. 2018

meandros

View full text Add to dashboard Cite

Objective: Electroencephalogram (EEG) signals have been broadly utilized for the diagnosis of epilepsy. Expert physicians must monitor long-term EEG signals that is sometimes difficult and time consuming process for epilepsy diagnosis. In this study, classification performances of Support Vector Machine (SVM) and Linear Discriminant Analysis (LDA), which are widely used in computer supported epilepsy diagnosis, were compared by using wavelet-based features of extracted from EEG signals which were derived in either normal or inter-ictal periods. In addition, Principal Component Analysis (PCA) and Independent Component Analysis (ICA) were used to determine the effects of dimension reduction on classification success. Materials and Methods:The EEG data were sampled from the EEG laboratory of the Department of Neurology and Clinical Neurophysiology in Adnan Menderes University. Study was approved by local ethics committee with protocol number 2016/873. Ten patients with epilepsy (male -female, age range) and 10 normal (male -female, age range) were the study group. EEG signals of patients with epilepsy were contains only seizure free-epochs. EEG signals were first decomposed into frequency sub-bands by using Discrete Wavelet Transform (DWT) and then some statistical features were calculated from those to classify it's as normal or epileptic. Results: In classification of the EEG signals, it's as normal or epileptic, we achieved %88.9 accuracy rate using SVM with Radial Basis Function (RBF) kernel without dimension reduction. Conclusion: Results showed that, SVM was a powerful tool in classifying EEG signals if it's normal or epileptic.Amaç: Bu çalışmada, epileptik ve epileptik olmayan EEG (Elektroensefelografi) sinyallerinden elde edilen özniteliklerin boyutlarının Temel Bileşenler Analizi (TBA) ve Bağımsız Bileşenler Analizi (BBA) yöntemleri ile indirgenmesinin sınıflandırma başarısı üzerine etkilerinin belirlenmesi ve Doğrusal Ayırma Analizi (DAA) ile Destek Vektör Makinesi (DVM) yöntemlerinin sınıflandırma performanslarının karşılaştırılması amaçlandı. Gereç ve Yöntem: Çalışmaya 10 kontrol ve uzman hekim tarafından epilepsi tanısı konmuş 10 hasta olmak üzere toplam 20 kişi dahil edildi. Epilepsi tanısı konmuş hastalardan alınan EEG kayıtları nöbet geçirmedikleri sırada alınan kayıtlardı. Epileptik

show abstract

Classification of epileptic seizures in EEG signals based on phase space representation of intrinsic mode functions

Cited by 369 publications

References 62 publications

Classification of EEG Signals Using Adaptive Time-Frequency Distributions

Classification of EEG Signals Using Adaptive Time-Frequency Distributions

Remote controller using steady state visual evoked potential

The Comparison of Different Dimension Reduction and Classification Methods in Electroencephalogram Signals

Contact Info

Product

Resources

About