scholarly journals Sleep State Classification Using Power Spectral Density and Residual Neural Network with Multichannel EEG Signals

2020 ◽  
Vol 10 (21) ◽  
pp. 7639
Author(s):  
Md Junayed Hasan ◽  
Dongkoo Shon ◽  
Kichang Im ◽  
Hyun-Kyun Choi ◽  
Dae-Seung Yoo ◽  
...  
Keyword(s):  
Neural Network ◽  
Spectral Density ◽  
Power Spectral Density ◽  
Sleep Stage ◽  
Human Subjects ◽  
Sleep Stages ◽  
Eeg Signals ◽  
Healthy Human ◽  
Power Spectral ◽  
Eeg Data

This paper proposes a classification framework for automatic sleep stage detection in both male and female human subjects by analyzing the electroencephalogram (EEG) data of polysomnography (PSG) recorded for three regions of the human brain, i.e., the pre-frontal, central, and occipital lobes. Without considering any artifact removal approach, the residual neural network (ResNet) architecture is used to automatically learn the distinctive features of different sleep stages from the power spectral density (PSD) of the raw EEG data. The residual block of the ResNet learns the intrinsic features of different sleep stages from the EEG data while avoiding the vanishing gradient problem. The proposed approach is validated using the sleep dataset of the Dreams database, which comprises of EEG signals for 20 healthy human subjects, 16 female and 4 male. Our experimental results demonstrate the effectiveness of the ResNet based approach in identifying different sleep stages in both female and male subjects compared to state-of-the-art methods with classification accuracies of 87.8% and 83.7%, respectively.

scholarly journals Fractal Methods and Power Spectral Density as Means to Explore EEG Patterns in Patients Undertaking Mental Tasks

2021 ◽  
Vol 5 (4) ◽  
pp. 225
Author(s):  
Carlos Alberto Valentim ◽  
Claudio Marcio Cassela Inacio ◽  
Sergio Adriani David
Keyword(s):  
Spectral Density ◽  
Power Spectral Density ◽  
Brain Activity ◽  
Time Domain Analysis ◽  
Relevant Information ◽  
Fluctuation Analysis ◽  
Power Spectral ◽  
Eeg Data ◽  
Electroencephalogram Eeg ◽  
Mental Tasks

Brain electrical activity recorded as electroencephalogram data provides relevant information that can contribute to a better understanding of pathologies and human behaviour. This study explores extant electroencephalogram (EEG) signals in search of patterns that could differentiate subjects undertaking mental tasks and reveals insights on said data. We estimated the power spectral density of the signals and found that the subjects showed stronger gamma brain waves during activity while presenting alpha waves at rest. We also found that subjects who performed better in those tasks seemed to present less power density in high-frequency ranges, which could imply decreased brain activity during tasks. In a time-domain analysis, we used Hall–Wood and Robust–Genton estimators along with the Hurst exponent by means of a detrented fluctuation analysis and found that the first two fractal measures are capable of better differentiating signals between the rest and activity datasets. The statistical results indicated that the brain region corresponding to Fp channels might be more suitable for analysing EEG data from patients conducting arithmetic tasks. In summary, both frequency- and time-based methods employed in the study provided useful insights and should be preferably used together in EEG analysis.

Flank Wear Estimation in Turning Through Wavelet Representation of Acoustic Emission Signals

1997 ◽  
Vol 122 (1) ◽  
pp. 12-19 ◽  
Author(s):  
S. V. Kamarthi ◽  
S. R. T. Kumara ◽  
P. H. Cohen
Keyword(s):  
Neural Network ◽  
Acoustic Emission ◽  
Fourier Transform ◽  
Spectral Density ◽  
Power Spectral Density ◽  
Flank Wear ◽  
Wavelet Representation ◽  
Power Spectral ◽  
Frequency Components ◽  
Ae Signals

This paper investigates a flank wear estimation technique in turning through wavelet representation of acoustic emission (AE) signals. It is known that the power spectral density of AE signals in turning is sensitive to gradually increasing flank wear. In previous methods, the power spectral density of AE signals is computed from Fourier transform based techniques. To overcome some of the limitations associated with the Fourier representation of AE signals for flank wear estimation, wavelet representation of AE signals is investigated. This investigation is motivated by the superiority of the wavelet transform over the Fourier transform in analyzing rapidly changing signals such as AE, in which high frequency components are to be studied with sharper time resolution than low frequency components. The effectiveness of the wavelet representation of AE signals for flank wear estimation is investigated by conducting a set of turning experiments on AISI 6150 steel workpiece and K68 (C2) grade uncoated carbide inserts. In these experiments, flank wear is monitored through AE signals. A recurrent neural network of simple architecture is used to relate AE features to flank wear. Using this technique, accurate flank wear estimation results are obtained for the operating conditions that are within in the range of those used during neural network training. These results compared to those of Fourier transform representation are much superior. These findings indicate that the wavelet representation of AE signals is more effective in extracting the AE features sensitive to gradually increasing flank wear than the Fourier representation. [S1087-1357(00)71401-8]

CLASSIFICATION OF ICTAL EEG USING MODELING BASED SPECTRAL AND TEMPORAL FEATURES ON INSTANTANEOUS AMPLITUDE-FREQUENCY COMPONENTS OF IMFs

2018 ◽  
Vol 30 (06) ◽  
pp. 1850042 ◽  
Author(s):  
K. S. Biju ◽  
M. G. Jibukumar
Keyword(s):  
Spectral Density ◽  
Power Spectral Density ◽  
Classification Accuracy ◽  
Spectral Features ◽  
Eeg Signal ◽  
Instantaneous Amplitude ◽  
Eeg Signals ◽  
Hilbert Huang Transform ◽  
Temporal Features ◽  
Power Spectral

In the present study, a method for classifying the different ictal stages in electroencephalogram (EEG) signals is proposed. The main symptoms of epilepsy are indicated by ictal activities, which trigger widespread neurological disorders other than stroke and thus affect the world population. In this work, a novel ictal classification method that combines the spectral and temporal features of twin components in Hilbert–Huang transform is proposed. Spectral features of instantaneous amplitude (IA) function are obtained based on the power spectral density of autoregressive (AR) modeling. Here four different cases of ictal activities of EEG signal are classified. In each case first and second intrinsic mode function of Hilbert–Huang transform are tabulated. The power spectral density of AR(6) and AR(10) model are done for IA1 and IA2 components of each case. Temporal features of either instantaneous frequency (IF) function or IA are computed. The feature vectors are tested in a well-known database of different classes in interictal, ictal, and normal activities of EEG signals. The discriminating power of each vector is evaluated through one-way analysis of variance, and the classification results are verified using an artificial neural network (ANN) classifier. The performance of the classifier was assessed in term of sensitivity, specificity, and total classification accuracy. The spectral features of the AR(10) of IA and the temporal features of IA yielded 100% accuracy, 100% sensitivity, and 100% specificity in the ictal classification. By contrast, these features obtained only 83.33% of the total classification accuracy in ictal and interictal EEG signal.

scholarly journals Sleep as a random walk - A superstatistical analysis of EEG data across sleep stages

2021 ◽  
Author(s):  
Claus Metzner ◽  
Achim Schilling ◽  
Maximilian Traxdorf ◽  
Holger Schulze ◽  
Patrick Krauss
Keyword(s):  
Sleep Stage ◽  
Muscular Activity ◽  
Temporal Correlation ◽  
Time Dependent ◽  
Sleep Stages ◽  
Eeg Signals ◽  
Human Sleep ◽  
Eeg Data ◽  
Different Levels ◽  
Temporal Correlation Function

In clinical practice, human sleep is classified into stages, each associated with different levels of muscular activity and marked by characteristic patterns in the EEG signals. It is however unclear whether this subdivision into discrete stages with sharply defined boundaries is truly reflecting the dynamics of human sleep. To address this question, we consider one-channel EEG signals as heterogeneous random walks: stochastic processes controlled by hyper-parameters that are themselves time-dependent. We first demonstrate the heterogeneity of the random process by showing that each sleep stage has a characteristic distribution and temporal correlation function of the raw EEG signals. Next, we perform a superstatistical analysis by computing 'hyper-parameters', such as the standard deviation, kurtosis and skewness of the raw signal distributions, within subsequent 30-second epochs. It turns out that also the hyper-parameters have characteristic, sleep-stage-dependent distributions, which can be exploited for a simple Bayesian sleep stage detection. Moreover, we find that the hyper-parameters are not piece-wise constant, as the traditional hypnograms would suggest, but show rising or falling trends within and across sleep stages, pointing to an underlying continuous rather than subdivided process that controls human sleep.

scholarly journals Denoising of EEG Signal using Matlab and SIMULINK Techniques and Estimation of Power Spectral Density of EEG Signal using SIMULINK AR Models

2019 ◽  
Vol 9 (2) ◽  
pp. 418-422
Keyword(s):  
Spectral Density ◽  
Power Spectral Density ◽  
Signal To Noise Ratio ◽  
Standard Technique ◽  
Research Paper ◽  
Eeg Signal ◽  
Eeg Signals ◽  
Power Spectral ◽  
Electroencephalogram Eeg ◽  
Ocular Artifacts

The Electroencephalogram (EEG) is the standard technique for investigating the brain’s electrical activity in different psychological and pathological states. Analysis of Electroencephalogram (EEG) signal is a challenging task by reason of the presence of different artifacts such as Ocular Artifacts (OA) and Electromyogram. Normally EEG signals falls in the frequency range of DC to 60 Hz and amplitude of 1-5 µv. Ocular artifacts do have the similar statistical properties of EEG signals, often interfere with EEG signal, thereby making the analysis of EEG signals more complex. In this research paper, removal of artifacts was done using wavelets (matlab coding) as well as using SIMULINK DWT and IDWT blocks and estimated the SNR. In the next stage the output of IDWT block was taken as input to Burg model and Yule walker model to estimate the power spectral density of EEG signal by setting the various parameters of the blocks. The implementation of denoising of EEG signal using SIMULINK DWT and IDWT blocks and estimation of power spectral density of denoised EEG signal using Burg model and Yule walker model was explained in detail in the paper under the methodology heading. In this research paper, the collected EEG signal is normalized and later linearly mixed with the normalized EOG signal resulting in a noisy EEG signal. This noisy EEG signal is decomposed to 4 levels by using different wavelets. This decomposition of EEG signals yields approximate and detail coefficients. Later different thresholding techniques were applied to detail coefficients and estimated the Signal to Noise Ratio of it and estimated the power spectral density of denoised EEG signal obtained from dB4 wavelet as it is providing better SNR than other wavelets mentioned in the results.

scholarly journals A comparison between power spectral density and network metrics: an EEG study

2019 ◽  
Author(s):  
Matteo Demuru ◽  
Simone Maurizio La Cava ◽  
Sara Maria Pani ◽  
Matteo Fraschini
Keyword(s):  
Spectral Density ◽  
Power Spectral Density ◽  
Good Practice ◽  
Clustering Coefficient ◽  
Volume Conduction ◽  
Functional Correlation ◽  
Power Spectral ◽  
Eeg Data ◽  
Similar Information ◽  
Network Metrics

AbstractPower spectral density (PSD) and network analysis performed on functional correlation (FC) patterns represent two common approaches used to characterize Electroencephalographic (EEG) data. Despite the two approaches are widely used, their possible association may need more attention. To investigate this question, we performed a comparison between PSD and some widely used nodal network metrics (namely strength, clustering coefficient and betweenness centrality), using two different publicly available resting-state EEG datasets, both at scalp and source levels, employing four different FC methods (PLV, PLI, AEC and AECC). Here we show that the two approaches may provide similar information and that their correlation depends on the method used to estimate FC. In particular, our results show a strong correlation between PSD and nodal network metrics derived from FC methods (PLV and AEC) that do not limit the effects of volume conduction/signal leakage. The correlations are less relevant for more conservative FC methods (AECC). These findings suggest that the results derived from the two different approaches may be not independent and should not be treated as distinct analyses. We conclude that it may represent good practice to report the findings from the two approaches in conjunction to have a more comprehensive view of the results.

scholarly journals Identification of Anesthesia Stages from EEG Signals using Wavelet Entropy and Backpropagation Neural Network

2019 ◽  
pp. 17-20
Author(s):  
Ahmed Abdal Shafi Rasel
Keyword(s):  
Neural Network ◽  
Back Propagation ◽  
Back Propagation Neural Network ◽  
Training Data ◽  
Eeg Signals ◽  
The Neural Network ◽  
Power Spectral ◽  
Eeg Data ◽  
Density Analysis ◽  
Key Features

This study focuses on entropy based analysis of EEG signals for extracting features for a neural network based solution for identifying anesthetic levels. The process involves an optimized back propagation neural network with a supervised learning method. We provided the extracted features from EEG signals as training data for the neural network. The target outputs provided are levels of anesthesia stages. Wavelet analysis provides more effective extraction of key features from EEG data than power spectral density analysis using Fourier transform. The key features are used to train the Back Propagation Neural Network (BPNN) for pattern classification network. The final result shows that entropy-based feature extraction is an effective procedure for classifying EEG data.

Sign in / Sign up

Export Citation Format

Share Document