scholarly journals Single channel approach for filtering EEG signals strongly contaminated with facial EMG

2020 ◽  
Author(s):  
Gustavo Moreira da Silva ◽  
Carlos Magno Medeiros Queiroz ◽  
Steffen Walter ◽  
Luciano Brink Peres ◽  
Luiza Maire David Luiz ◽  
...  
Keyword(s):  
Power Spectrum ◽  
Single Channel ◽  
Least Square ◽  
Recursive Least Square ◽  
Eeg Signals ◽  
Denoising Method ◽  
Brain Rhythms ◽  
Facial Emg ◽  
Emg Signal ◽  
Mode Decomposition

Abstract Background Eliminating facial electromyography (EMG) from the electroencephalogram (EEG) is essential for the accuracy of applications such as brain computer interfaces (BCIs) and quantification of brain functionality. Although it is possible to find several studies that address EEG filtering, there is lack of researches that improve the filtering of EEG strongly corrupted by EMG signals with single-channel approaches, which are necessary in situations in which the number of available channels is reduced for the application of filtering methods based on multichannel techniques. In this context, this research proposes an EEG denoising method for filtering EMG from the masseter and frontal. This method, so-called EMDRLS, combines the use of Empirical Mode Decomposition (EMD) and a Recursive Least Square (RLS) filter to attenuate facial EMG noise from EEG. The results were compared with those obtained from Wavelet, EMD, Wiener and Wavelet-RLS (WRLS) filters. Besides the visual inspection of the resultant waveform of filtered signals, the following objective metrics were employed to contrast the performance of the filtering methods: (i) the signal-noise ratio (SNR) of the contaminated signal, (ii) the root mean square error (RMSE) between the power spectrum of artifact free and filtered EEG epochs, (iii) the spectral preservation of brain rhythms (i.e., delta, theta, alpha, beta, and gamma rhythms) of filtered signals.Results The EMDRLS method yielded filtered EEG signals with SNR varying from 0 to 10 dB for EEG signals with SNR below -10dB. The Spearman’s correlation coefficient estimated between the SNR of filtered and corrupted signals was below 0.04, suggesting, in the evaluated conditions, the independence of the EMDRLS filtering performance to the SNR of noisy signals. The technique also improved the RMSE between the power spectrum of artifact free and filtered EEG epochs by a factor of 27 (from 5.429 to 0.197) in the most corrupted EEG channels with the masseter muscle contraction. The Kruskal-Wallis test and the Tukey-Kramer post-hoc test (p < 0.05) confirmed the preservation of all brain rhythms given by EEG signals filtered with the EMDRLS method.Conclusions The results showed that the single-channel EMDRLS method can be applied to highly contaminated EEG signals by facial EMG signal with performance superior to that of the compared methods. The method can be applied for the offline filtering of EEG signals contaminated by facial EMG.

scholarly journals Preterm-Term Birth Classification Using EMD-Based Time-Domain Features of Single-Channel Electrohysterogram Data

2021 ◽  
Author(s):  
Suparerk Janjarasjitt
Keyword(s):  
Preterm Birth ◽  
Time Domain ◽  
Single Channel ◽  
Support Vector ◽  
Computational Results ◽  
Intrinsic Mode Functions ◽  
Term Birth ◽  
Emg Signal ◽  
Mode Decomposition ◽  
The Time Domain

Abstract The preterm birth anticipation is a crucial task that can reduce the rate of preterm birth and also the complications of preterm birth. Electrohysterogram (EHG) or uterine electromyogram (EMG) data have been evidenced that they can provide an information useful for preterm birth anticipation. Four distinct time-domain features, i.e., mean absolute value, average amplitude change, difference absolute standard deviation value, and log detector, commonly applied to EMG signal processing are applied and investigated in this study. A single-channel of EHG data is decomposed into its constituent components, i.e., intrinsic mode functions, using empirical mode decomposition (EMD) before their time-domain features are extracted. The time-domain features of intrinsic mode functions of EHG data associated with preterm and term births are applied for preterm-term birth classification using support vector machine (SVM) with a radial basis function. The preterm-term classifications are validated using 10-fold cross validation. From the computational results, it is shown that the excellent preterm-term birth classification can be achieved using a single-channel of EHG data. The computational results further suggest that the best overall performance on preterm-term birth classification is obtained when thirteen (out of sixteen) EMD-based time-domain features are applied. The best accuracy, sensitivity, specificity, and F1-score achieved are, respectively, 0.9382, 0.9130, 0.9634, and 0.9366.

Noise Removal from EMG Signal Using Adaptive Enhanced Squirrel Search Algorithm

2020 ◽  
Vol 19 (04) ◽  
pp. 2050039
Author(s):  
B. Nagasirisha ◽  
V. V. K. D. V. Prasad
Keyword(s):  
Adaptive Filters ◽  
Search Algorithm ◽  
Cuckoo Search ◽  
Maximum Error ◽  
Noise Removal ◽  
Least Square ◽  
Mean Square ◽  
Least Mean Square ◽  
Recursive Least Square ◽  
Emg Signal

Electromyogram (EMG) signals are mostly affected by a large number of artifacts. Most commonly affecting artifacts are power line interference (PLW), baseline noise and ECG noise. This work focuses on a novel attenuation noise removal strategy which is concentrated on adaptive filtering concepts. In this paper, an enhanced squirrel search (ESS) algorithm is applied to remove noise using adaptive filters. The noise eliminating filters namely adaptive least mean square (LMS) filter and adaptive recursive least square (RLS) filters are designed, which is correlated with an ESS. This novel algorithm yields better performance than other existing algorithms. Here the performances are measured in terms of signal-to-noise ratio (SNR) in decibel, maximum error (ME), mean square error (MSE), standard deviation, simulation time and mean value difference. The proposed work has been implemented at the MATLAB simulation platform. Testing of their noise attenuation capability is also validated with different evolutionary algorithms namely squirrel search, particle swarm optimization (PSO), artificial bee colony (ABC), firefly, ant colony optimization (ACO) and cuckoo search (CS). The proposed work eliminates the noises and provides noise-free EMG signal at the output which is highly efficient when compared with existing methodologies. Our proposed work achieves 4%, 40%, 4%, 7%, 9% and 70% better performance than the literature mentioned in the results.

A Methodical Healthcare Model to Eliminate Motion Artifacts from Big EEG Data

2017 ◽  
Vol 29 (4) ◽  
pp. 84-102 ◽  
Author(s):  
Vandana Roy ◽  
Shailja Shukla
Keyword(s):  
Single Channel ◽  
Diagnostic Procedures ◽  
Ensemble Empirical Mode Decomposition ◽  
Motion Artifacts ◽  
Eeg Signals ◽  
Combination Technique ◽  
Mode Decomposition ◽  
Eeg Data ◽  
Healthcare Model

The Big data as Electroencephalography (EEG) can induce by artifacts during acquisition process which will obstruct the features and quality of interest in the signal. The healthcare diagnostic procedures need strong and viable biomedical signals and elimination of artifacts from EEG is important. In this research paper, an improved ensemble approach is proposed for single channel EEG signal motion artifacts removal. Ensemble Empirical Mode Decomposition and Canonical Correlation Analysis (EEMD-CCA) filter combination are applied to remove artifact effectively and further Stationary Wavelet Transform (SWT) is applied to remove the randomness and unpredictability due to motion artifacts from EEG signals. This new filter combination technique was tested against currently available artifact removal techniques and results indicate that the proposed algorithm is suitable for use as a supplement to algorithms currently in use.

NOVEL APPROACHES OF EEG SIGNAL CLASSIFICATION USING IMF BANDWIDTH AND DCT FREQUENCY

2015 ◽  
Vol 27 (03) ◽  
pp. 1550027 ◽  
Author(s):  
Mohammad Zavid Parvez ◽  
Manoranjan Paul
Keyword(s):  
Feature Extraction ◽  
Brain Activity ◽  
Electrical Signal ◽  
Least Square ◽  
Brain Diseases ◽  
Support Vector ◽  
Eeg Signals ◽  
Discrete Cosine Transformation ◽  
Mode Decomposition ◽  
Interictal Eeg

Electroencephalogram (EEG) is a record of ongoing electrical signal to represent the human brain activity. It has great potential for the diagnosis to treatment of mental disorder and brain diseases such as epileptic seizure. Features extraction and classification is a crucial task to detect the stage of ictal (i.e. seizure period) and interictal (i.e. period between seizures) EEG signals for the treatment and precaution of the patient. However, existing seizure and non-seizure feature extraction techniques are not good enough for the classification of ictal and interictal EEG signals considering their non-abrupt phenomena and inconsistency in different brain locations. In this paper, we present new approaches for feature extraction using high-frequency components from discrete cosine transformation (DCT) and intrinsic mode function (IMF) extracted from empirical mode decomposition (EMD). These features are then used as an input to least square-support vector machine (LV-SVM) to classify ictal and interictal EEG signals. Experimental results show that the proposed methods outperform the existing state-of-the-art method for better classification in terms of sensitivity, specificity, and accuracy with greater consistence of ictal and interictal period of epilepsy for benchmark dataset from different brain locations.

scholarly journals An EEG-Based Attentiveness Recognition System Using Hilbert–Huang Transform and Support Vector Machine

2019 ◽  
Vol 40 (2) ◽  
pp. 230-238
Author(s):  
Chia-Ju Peng ◽  
Yi-Chun Chen ◽  
Chun-Chuan Chen ◽  
Shih-Jui Chen ◽  
Barthélemy Cagneau ◽  
...  
Keyword(s):  
Support Vector Machine ◽  
Single Channel ◽  
Approximate Entropy ◽  
Recognition System ◽  
Support Vector ◽  
Intrinsic Mode Functions ◽  
Eeg Signals ◽  
Hilbert Huang Transform ◽  
Mode Decomposition

Abstract Purpose Attentiveness recognition benefits the detection of the mental state and concentration when humans perform specific tasks. Hilbert–Huang transform (HHT) is useful for the analysis of nonlinear or nonstationary bio-signals including brainwaves. In this work, a method is proposed for the characterization of attentiveness levels by using electroencephalogram (EEG) signals and HHT analysis. Methods Single-channel EEG signals from the frontal area were acquired from participants at different levels of attentiveness and were decomposed into a set of intrinsic mode functions (IMF) by empirical mode decomposition (EMD). Hilbert transform analysis was applied to each IMF to obtain the marginal frequency spectrum. Then the band powers and spectral entropies (SEs) were selected as the attributes of a support vector machine (SVM) for a two-class classification task. Results Compared with the predictive models of approximate entropy (ApEn) and fast Fourier transform (FFT), the results show that the band powers extracted from IMF2 to IMF5 of $$\alpha$$α and $$\beta$$β waves and their SE can best discriminate between attentive and relaxed states with the average classification accuracy of 84.80%. Conclusion In conclusion, this integrated signal processing method is capable of attentiveness recognition that can offer efficient differentiation and may be used in a clinical setting for the detection of attention deficit.

Sign in / Sign up

Export Citation Format

Share Document