scholarly journals Nonlinear analysis of EEG signals at different mental states

2004 ◽  
Vol 3 (1) ◽  
Author(s):  
Kannathal Natarajan ◽  
Rajendra Acharya U ◽  
Fadhilah Alias ◽  
Thelma Tiboleng ◽  
Sadasivan K Puthusserypady
Keyword(s):  
Nonlinear Analysis ◽  
Mental States ◽  
Eeg Signals

Improving Emotion Analysis for Speech-Induced EEGs Through EEMD-HHT-Based Feature Extraction and Electrode Selection

2021 ◽  
Vol 12 (2) ◽  
pp. 1-18
Author(s):  
Jing Chen ◽  
Haifeng Li ◽  
Lin Ma ◽  
Hongjian Bo
Keyword(s):  
Feature Extraction ◽  
Statistical Analysis ◽  
Orbitofrontal Cortex ◽  
Mental States ◽  
Emotion Detection ◽  
Emotional Speech ◽  
Eeg Signals ◽  
Cognitive Response ◽  
Extensive Analysis ◽  
Electrode Selection

Emotion detection using EEG signals has advantages in eliminating social masking to obtain a better understanding of underlying emotions. This paper presents the cognitive response to emotional speech and emotion recognition from EEG signals. A framework is proposed to recognize mental states from EEG signals induced by emotional speech: First, speech-evoked emotion cognitive experiment is designed, and EEG dataset is collected. Second, power-related features are extracted using EEMD-HHT, which is more accurate to reflect the instantaneous frequency of the signal than STFT and WT. An extensive analysis of relationships between frequency bands and emotional annotation of stimulus are presented using MIC and statistical analysis. The strongest correlations with EEG signals are found in lateral and medial orbitofrontal cortex (OFC). Finally, the performance of different feature set and classifier combinations are evaluated, and the experiments show that the framework proposed in this paper can effectively recognize emotion from EEG signals with accuracy of 75.7% for valence and 71.4% for arousal.

scholarly journals Classification of Drowsiness Levels Based on a Deep Spatio-Temporal Convolutional Bidirectional LSTM Network Using Electroencephalography Signals

2019 ◽  
Vol 9 (12) ◽  
pp. 348 ◽  
Author(s):  
Ji-Hoon Jeong ◽  
Baek-Woon Yu ◽  
Dae-Hyeok Lee ◽  
Seong-Whan Lee
Keyword(s):  
Short Term Memory ◽  
Mental States ◽  
Critical Issue ◽  
High Accuracy ◽  
Classification Performance ◽  
Eeg Signals ◽  
Aviation Accidents ◽  
Spatio Temporal ◽  
Lstm Network

Non-invasive brain-computer interfaces (BCI) have been developed for recognizing human mental states with high accuracy and for decoding various types of mental conditions. In particular, accurately decoding a pilot’s mental state is a critical issue as more than 70% of aviation accidents are caused by human factors, such as fatigue or drowsiness. In this study, we report the classification of not only two mental states (i.e., alert and drowsy states) but also five drowsiness levels from electroencephalogram (EEG) signals. To the best of our knowledge, this approach is the first to classify drowsiness levels in detail using only EEG signals. We acquired EEG data from ten pilots in a simulated night flight environment. For accurate detection, we proposed a deep spatio-temporal convolutional bidirectional long short-term memory network (DSTCLN) model. We evaluated the classification performance using Karolinska sleepiness scale (KSS) values for two mental states and five drowsiness levels. The grand-averaged classification accuracies were 0.87 (±0.01) and 0.69 (±0.02), respectively. Hence, we demonstrated the feasibility of classifying five drowsiness levels with high accuracy using deep learning.

scholarly journals Fronto-Temporal Analysis of EEG Signals of Patients with Depression: Characterisation, Nonlinear Dynamics and Surrogate Analysis

2020 ◽  
Author(s):  
Subha D. Puthankattil
Keyword(s):  
Time Series ◽  
Unipolar Depression ◽  
Temporal Analysis ◽  
Mental States ◽  
Eeg Signals ◽  
Biosignal Analysis ◽  
Eyes Closed ◽  
Eyes Open ◽  
Eeg Recordings ◽  
The Brain

The recent advances in signal processing techniques have enabled the analysis of biosignals from brain so as to enhance the predictive capability of mental states. Biosignal analysis has been successfully used to characterise EEG signals of unipolar depression patients. Methods of characterisation of EEG signals and the use of nonlinear parameters are the major highlights of this chapter. Bipolar frontopolar-temporal EEG recordings obtained under eyes open and eyes closed conditions are used for the analysis. A discussion on the reliability of the use of energy distribution and Relative Wavelet Energy calculations for distinguishing unipolar depression patients from healthy controls is presented. The potential of the application of Wavelet Entropy to differentiate states of the brain under normal and pathologic condition is introduced. Details are given on the suitability of ascertaining certain nonlinear indices on the feature extraction, assuming the time series to be highly nonlinear. The assumption of nonlinearity of the measured EEG time series is further verified using surrogate analysis. The studies discussed in this chapter indicate lower values of nonlinear measures for patients. The higher values of signal energy associated with the delta bands of depression patients in the lower frequency range are regarded as a major characteristic indicative of a state of depression. The chapter concludes by presenting the important results in this direction that may lead to better insight on the brain activity and cognitive processes. These measures are hence posited to be potential biomarkers for the detection of depression.

scholarly journals COMBINING METHODS OF FREQUENCY FILTERING AND NONLINEAR ANALYSIS FOR SOMNOLOGICAL STUDY OF EEG SIGNALS

2016 ◽  
Vol 1 (3) ◽  
pp. 45-50
Author(s):  
O I Antipov ◽  
A V Zakharov
Keyword(s):  
Nonlinear Analysis ◽  
Classical Method ◽  
Deterministic Chaos ◽  
Entropy Method ◽  
Preliminary Treatment ◽  
Frequency Filtering ◽  
Eeg Signals ◽  
Recovery Method ◽  
Correlation Integral ◽  
Non Linear

Aim - combined use of frequency and nonlinear analysis methods for obtaining hypnograms by analyzing electroencephalographic (EEG) signals during somnological studies. Methods. Frequency filtering methods were used for preliminary treatment of EEG signals before the following nonlinear analysis. As non-linear methods of analysis we used fractal methods of deterministic chaos, such as Hurst’s method of the normalized amplitude, approximate entropy method, calculation of the correlation integral by Grassberger and Procaccia’s method. For the possibility of applying the last two methods we used quasi phase space recovery method according to the Taken’s theorem. As a result of non-linear analysis we obtained hypnograms reflecting the transition between the stages of sleep in patients undergoing somnological examination. To assess the reliability of the results, they were compared to the hypnograms obtained by the classical method based on the rules of Rehchaffen and Keyls. Also the problems associated with the occurrence of various types of interference were considered and methods for reducing their influence on the final results were suggested. Results. We can conclude that using these methods with appropriate selection of the parameters, employing the necessary normalization of raw data, and averaging the results allow us to obtain hypnogram having a full match of defined phases of sleep for about half of the periods recorded by EEG. To obtain these results it is sufficient to use only one channel of EEG recording.

scholarly journals Determining Mental State from EEG Signals Using Parallel Implementations of Neural Networks

1995 ◽  
Vol 4 (3) ◽  
pp. 171-183 ◽  
Author(s):  
Charles W. Anderson ◽  
Saikumar V. Devulapalli ◽  
Erik A. Stolz
Keyword(s):  
Mental States ◽  
Difficult Problem ◽  
Eeg Analysis ◽  
Dimensional Representation ◽  
Eeg Signals ◽  
Cortical Dynamics ◽  
Speed Up ◽  
Karhunen Loeve Transform ◽  
Eeg Pattern ◽  
Eeg Pattern Recognition

EEG analysis has played a key role in the modeling of the brain's cortical dynamics, but relatively little effort has been devoted to developing EEG as a limited means of communication. If several mental states can be reliably distinguished by recognizing patterns in EEG, then a paralyzed person could communicate to a device such as a wheelchair by composing sequences of these mental states. EEG pattern recognition is a difficult problem and hinges on the success of finding representations of the EEG signals in which the patterns can be distinguished. In this article, we report on a study comparing three EEG representations, the unprocessed signals, a reduced-dimensional representation using the Karhunen – Loève transform, and a frequency-based representation. Classification is performed with a two-layer neural network implemented on a CNAPS server (128 processor, SIMD architecture) by Adaptive Solutions, Inc. Execution time comparisons show over a hundred-fold speed up over a Sun Sparc 10. The best classification accuracy on untrained samples is 73% using the frequency-based representation.

Nonlinear analysis of EEG signals: Surrogate data analysis

IRBM ◽  
2008 ◽  
Vol 29 (4) ◽  
pp. 239-244 ◽  
Author(s):  
R. Kunhimangalam ◽  
P.K. Joseph ◽  
O.K. Sujith
Keyword(s):  
Data Analysis ◽  
Nonlinear Analysis ◽  
Surrogate Data ◽  
Eeg Signals

scholarly journals K-th Nearest Neighbor (KNN) Entropy Estimates of Complexity and Integration from Ongoing and Stimulus-Evoked Electroencephalographic (EEG) Recordings of the Human Brain

Entropy ◽  
2019 ◽  
Vol 21 (1) ◽  
pp. 61
Author(s):  
Logan Trujillo
Keyword(s):  
Human Brain ◽  
Nearest Neighbor ◽  
Phase Synchronization ◽  
Mental States ◽  
Statistical Dependence ◽  
Eeg Signals ◽  
Multivariate Statistical ◽  
Dynamical Interaction ◽  
Information Theoretic ◽  
Brain States

Information-theoretic measures for quantifying multivariate statistical dependence have proven useful for the study of the unity and diversity of the human brain. Two such measures–integration, I(X), and interaction complexity, CI(X)–have been previously applied to electroencephalographic (EEG) signals recorded during ongoing wakeful brain states. Here, I(X) and CI(X) were computed for empirical and simulated visually-elicited alpha-range (8–13 Hz) EEG signals. Integration and complexity of evoked (stimulus-locked) and induced (non-stimulus-locked) EEG responses were assessed using nonparametric k-th nearest neighbor (KNN) entropy estimation, which is robust to the nonstationarity of stimulus-elicited EEG signals. KNN-based I(X) and CI(X) were also computed for the alpha-range EEG of ongoing wakeful brain states. I(X) and CI(X) patterns differentiated between induced and evoked EEG signals and replicated previous wakeful EEG findings obtained using Gaussian-based entropy estimators. Absolute levels of I(X) and CI(X) were related to absolute levels of alpha-range EEG power and phase synchronization, but stimulus-related changes in the information-theoretic and other EEG properties were independent. These findings support the hypothesis that visual perception and ongoing wakeful mental states emerge from complex, dynamical interaction among segregated and integrated brain networks operating near an optimal balance between order and disorder.

Sign in / Sign up

Export Citation Format

Share Document