scholarly journals A novel multi-class imbalanced EEG signals classification based on the adaptive synthetic sampling (ADASYN) approach

2021 ◽  
Vol 7 ◽  
pp. e523
Author(s):  
Adi Alhudhaif
Keyword(s):  
Random Forests ◽  
Time Domain ◽  
Imbalanced Data ◽  
Majority Voting ◽  
Eeg Signal ◽  
Eeg Signals ◽  
The Third ◽  
Eyes Closed ◽  
Voting Scheme ◽  
Sampling Approach

Background Brain signals (EEG—Electroencephalography) are a gold standard frequently used in epilepsy prediction. It is crucial to predict epilepsy, which is common in the community. Early diagnosis is essential to reduce the treatment process of the disease and to keep the process healthier. Methods In this study, a five-classes dataset was used: EEG signals from different individuals, healthy EEG signals from tumor document, EEG signal with epilepsy, EEG signal with eyes closed, and EEG signal with eyes open. Four different methods have been proposed to classify five classes of EEG signals. In the first approach, the EEG signal was first divided into four different bands (beta, alpha, theta, and delta), and then 25 time-domain features were extracted from each band, and the main EEG signal and these extracted features were combined to obtain 125-time domain features (feature extraction). Using the Random Forests classifier, EEG activities were classified into five classes. In the second approach, each One-Against-One (OVO) approach with 125 attributes was split into ten parts, pairwise, and then each piece was classified with the Random Forests classifier. The majority voting scheme was used to combine decisions from the ten classifiers. In the third proposed method, each One-Against-All (OVA) approach with 125 attributes was divided into five parts, and then each piece was classified with the Random Forests classifier. The majority voting scheme was used to combine decisions from the five classifiers. In the fourth proposed approach, each One-Against-All (OVA) approach with 125 attributes was divided into five parts. Since each piece obtained had an imbalanced data distribution, an adaptive synthetic (ADASYN) sampling approach was used to stabilize each piece. Then, each balanced piece was classified with the Random Forests classifier. To combine the decisions obtanied from each classifier, the majority voting scheme has been used. Results The first approach achieved 71.90% classification success in classifying five-class EEG signals. The second approach achieved a classification success of 91.08% in classifying five-class EEG signals. The third method achieved 89% success, while the fourth proposed approach achieved 91.72% success. The results obtained show that the proposed fourth approach (the combination of the ADASYN sampling approach and Random Forest Classifier) achieved the best success in classifying five class EEG signals. This proposed method could be used in the detection of epilepsy events in the EEG signals.

scholarly journals Development of an EEG signal analysis application through a convolution of a complex Morlet wavelet: preliminary results

2019 ◽  
Vol 8 (2) ◽  
pp. B1-1-B1-19
Author(s):  
José Humberto Trueba Perdomo ◽  
◽  
Ignacio Herrera Aguilar ◽  
Francesca Gasparini ◽  
◽  
...  
Keyword(s):  
Morlet Wavelet ◽  
Eeg Signal ◽  
Eeg Signals ◽  
Eyes Closed ◽  
Eyes Open ◽  
Analysis Application ◽  
The Subject ◽  
Complex Morlet Wavelet ◽  
Electroencephalogram Eeg ◽  
Eeg Signal Analysis

This paper presents a new application for analyzing electroencephalogram (EEG) signals. The signals are pre-filtered through MATLAB's EEGLAB tool. The created application performs a convolution between the original EEG signal and a complex Morlet wavelet. As a final result, the application shows the signal power value and a spectrogram of the convoluted signal. Moreover, the created application compares different EEG channels at the same time, in a fast and straightforward way, through a time and frequency analysis. Finally, the effectiveness of the created application was demonstrated by performing an analysis of the alpha signals of healthy subjects, one signal created by the subject with eyes closed and the other, with which it was compared, was created by the same subject with eyes open. This also served to demonstrate that the power of the alpha band of the closed-eyed signal is higher than the power of the open-eyed signal.

scholarly journals Research on EEG Features in Different Emotional States

2021 ◽  
Author(s):  
Xiaotian Wang ◽  
Zuo Wang ◽  
Jiawei Guo ◽  
Chunying Pang ◽  
Jikui Liu
Keyword(s):  
Frequency Domain ◽  
Time Domain ◽  
Reference Group ◽  
Neurological Diseases ◽  
Eysenck Personality Questionnaire ◽  
Emotional States ◽  
Eeg Signals ◽  
Time Frequency ◽  
Eyes Closed ◽  
Eeg Features

Abstract In order to improve the detection and treatment of neurological diseases effectively, it is a significant means to analysis EEG features. In this study, extrovert and stable persons were selected as the subjects according to the Eysenck Personality Questionnaire. Then set the subjects’ EEG signals in a quiet state with eyes closed as a reference group. Four types of pure music were selected as stimulus materials to induce four different kinds of emotions: pleasure, sadness, irritability, and fear. During the period, evoked EEG signals was acquired. Then, some signal processing methods were used to de-noise for EEG and separate EOG artifacts from EEG signals. Finally, EEG signals’ features in time domain, frequency domain and time-frequency domain were extracted, especially the method which combined Hilbert transform based on EMD with information entropy to calculate EEG signals’ Hilbert spectrum entropy for four emotional states. The results showed that EEG signals’ features in different emotional states changed with gender, brain and mood objectively, all differences mainly reflected in time domain features, frequency domain features and time-frequency domain features. All the results reveal that EEG signals’ variation characteristics in the process of auditory stimulation, and can be an adjustment basis for detection and treatment of neurological diseases.

Complexity Measures of Brain Electrophysiological Activity

2010 ◽  
Vol 24 (2) ◽  
pp. 131-135 ◽  
Author(s):  
Włodzimierz Klonowski ◽  
Pawel Stepien ◽  
Robert Stepien
Keyword(s):  
Brain Activity ◽  
Deterministic Chaos ◽  
Epileptic Seizures ◽  
Eeg Signal ◽  
Eeg Signals ◽  
Complexity Measures ◽  
Electrophysiological Activity ◽  
Signal Complexity ◽  
Physiological Sleep ◽  
The Brain

Over 20 years ago, Watt and Hameroff (1987 ) suggested that consciousness may be described as a manifestation of deterministic chaos in the brain/mind. To analyze EEG-signal complexity, we used Higuchi’s fractal dimension in time domain and symbolic analysis methods. Our results of analysis of EEG-signals under anesthesia, during physiological sleep, and during epileptic seizures lead to a conclusion similar to that of Watt and Hameroff: Brain activity, measured by complexity of the EEG-signal, diminishes (becomes less chaotic) when consciousness is being “switched off”. So, consciousness may be described as a manifestation of deterministic chaos in the brain/mind.

scholarly journals Eye-blink artifact removal from single channel EEG with k-means and SSA

2021 ◽  
Vol 11 (1) ◽  
Author(s):  
Ajay Kumar Maddirala ◽  
Kalyana C Veluvolu
Keyword(s):  
Machine Learning ◽  
Single Channel ◽  
Learning Algorithm ◽  
Singular Spectrum Analysis ◽  
Machine Learning Algorithm ◽  
Eeg Signal ◽  
Eeg Signals ◽  
Unsupervised Machine Learning ◽  
Eye Blink ◽  
Blink Artifact

AbstractIn recent years, the usage of portable electroencephalogram (EEG) devices are becoming popular for both clinical and non-clinical applications. In order to provide more comfort to the subject and measure the EEG signals for several hours, these devices usually consists of fewer EEG channels or even with a single EEG channel. However, electrooculogram (EOG) signal, also known as eye-blink artifact, produced by involuntary movement of eyelids, always contaminate the EEG signals. Very few techniques are available to remove these artifacts from single channel EEG and most of these techniques modify the uncontaminated regions of the EEG signal. In this paper, we developed a new framework that combines unsupervised machine learning algorithm (k-means) and singular spectrum analysis (SSA) technique to remove eye blink artifact without modifying actual EEG signal. The novelty of the work lies in the extraction of the eye-blink artifact based on the time-domain features of the EEG signal and the unsupervised machine learning algorithm. The extracted eye-blink artifact is further processed by the SSA method and finally subtracted from the contaminated single channel EEG signal to obtain the corrected EEG signal. Results with synthetic and real EEG signals demonstrate the superiority of the proposed method over the existing methods. Moreover, the frequency based measures [the power spectrum ratio ($$\Gamma $$ Γ ) and the mean absolute error (MAE)] also show that the proposed method does not modify the uncontaminated regions of the EEG signal while removing the eye-blink artifact.

AGE-BASED VARIATIONS OF FRACTAL STRUCTURE OF EEG SIGNAL IN PATIENTS WITH EPILEPSY

Fractals ◽  
2018 ◽  
Vol 26 (04) ◽  
pp. 1850051 ◽  
Author(s):  
HAMIDREZA NAMAZI ◽  
SAJAD JAFARI
Keyword(s):  
Fractal Dimension ◽  
Brain Research ◽  
Age Groups ◽  
Eeg Signal ◽  
Brain Disorders ◽  
Eeg Signals ◽  
Important Challenge ◽  
Patients With Epilepsy ◽  
Process Complexity ◽  
Electroencephalogram Eeg

It is known that aging affects neuroplasticity. On the other hand, neuroplasticity can be studied by analyzing the electroencephalogram (EEG) signal. An important challenge in brain research is to study the variations of neuroplasticity during aging for patients suffering from epilepsy. This study investigates the variations of the complexity of EEG signal during aging for patients with epilepsy. For this purpose, we employed fractal dimension as an indicator of process complexity. We classified the subjects in different age groups and computed the fractal dimension of their EEG signals. Our investigations showed that as patients get older, their EEG signal will be more complex. The method of investigation that has been used in this study can be further employed to study the variations of EEG signal in case of other brain disorders during aging.

DESIGN AND IMPLEMENTATION OF WIRELESS MULTI-CHANNEL EEG RECORDING SYSTEM AND STUDY OF EEG CLUSTERING METHOD

2006 ◽  
Vol 18 (06) ◽  
pp. 276-283 ◽  
Author(s):  
ROBERT LIN ◽  
REN-GUEY LEE ◽  
CHWAN-LU TSENG ◽  
YAN-FA WU ◽  
JOE-AIR JIANG
Keyword(s):  
Energy Operator ◽  
Digital Processing ◽  
Recording System ◽  
Ar Model ◽  
Characteristic Matrix ◽  
Eeg Signal ◽  
Eeg Signals ◽  
Long Distance ◽  
Communication Module ◽  
Processing Circuit

A multi-channel wireless EEG (electroencephalogram) acquisition and recording system is developed in this work. The system includes an EEG sensing and transmission unit and a digital processing circuit. The former is composed of pre-amplifiers, filters, and gain amplifiers. The kernel of the later digital processing circuit is a micro-controller unit (MCU, TI-MSP430), which is utilized to convert the EEG signals into digital signals and fulfill the digital filtering. By means of Bluetooth communication module, the digitized signals are sent to the back-end such as PC or PDA. Thus, the patient's EEG signal can be observed and stored without any long cables such that the analogue distortion caused by long distance transmission can be reduced significantly. Furthermore, an integrated classification method, consisting of non-linear energy operator (NLEO), autoregressive (AR) model, and bisecting k-means algorithm, is also proposed to perform EEG off-line clustering at the back-end. First, the NLEO algorithm is utilized to divide the EEG signals into many small signal segments according to the features of the amplitude and frequency of EEG signals. The AR model is then applied to extract two characteristic values, i.e., frequency and amplitude (peak to peak value), of each segment and to form characteristic matrix for each segment of EEG signal. Finally, the improved modified k-means algorithm is utilized to assort similar EEG segments into better data classification, which allows accessing the long-term EEG signals more quickly.

HIGHER ORDER COMPLEXITY OF TIME SERIES

2004 ◽  
Vol 14 (08) ◽  
pp. 2979-2990 ◽  
Author(s):  
FANJI GU ◽  
ENHUA SHEN ◽  
XIN MENG ◽  
YANG CAO ◽  
ZHIJIE CAI
Keyword(s):  
Time Series ◽  
Mental Arithmetic ◽  
Higher Order ◽  
Second Order ◽  
Stationary Time Series ◽  
Eeg Signals ◽  
Eyes Closed ◽  
Logistic Mapping ◽  
Original Time ◽  
Different Order

A concept of higher order complexity is proposed in this letter. If a randomness-finding complexity [Rapp & Schmah, 2000] is taken as the complexity measure, the first-order complexity is suggested to be a measure of randomness of the original time series, while the second-order complexity is a measure of its degree of nonstationarity. A different order is associated with each different aspect of complexity. Using logistic mapping repeatedly, some quasi-stationary time series were constructed, the nonstationarity degree of which could be expected theoretically. The estimation of the second-order complexity of these time series shows that the second-order complexities do reflect the degree of nonstationarity and thus can be considered as its indicator. It is also shown that the second-order complexities of the EEG signals from subjects doing mental arithmetic are significantly higher than those from subjects in deep sleep or resting with eyes closed.

SIMULATION AND MODELING OF EVOKED RESPONSE ELECTROENCEPHALOGRAPH SIGNAL

1999 ◽  
Vol 10 (04) ◽  
pp. 759-776
Author(s):  
D. R. KULKARNI ◽  
J. C. PARIKH ◽  
R. PRATAP
Keyword(s):  
Small Range ◽  
Eeg Signal ◽  
Simulation And Modeling ◽  
State Space Reconstruction ◽  
Eyes Closed ◽  
Normal Individuals ◽  
Eeg Data ◽  
Closed Data ◽  
Simulation Results ◽  
Low Dimensional

Electroencephalograph (EEG) data for normal individuals with eyes-closed and under stimuli is analyzed. The stimuli consisted of photo, audio, motor and mental activity. We use several measures from nonlinear dynamics to analyze and characterize the data. We find that the dynamics of the EEG signal is deterministic and chaotic but it is not a low dimensional chaotic system. The evoked responses lead to a redistribution of strengths relative to eyes-closed data. Basically, strength in α waves decreases whereas that in β wave increases. We also carried out simulations separately and in combination for δ, θ, α and β waves to understand the data. From the simulation results, it appears that the characteristics of EEG data are consequences of filtering the data with a relatively small range of frequency (0.5–32 Hz). In view of this, we believe that calculation of known nonlinear measures is not likely to be very useful for studying the dynamics of EEG data. We have also successfully modeled the EEG time series using the concept of state space reconstruction in the framework of artificial neural network. It gives us confidence that one would be able to understand, in a more basic way, how collectivity in EEG signal arises.

Trends in Heart Rate and Heart Rate Variability during Pregnancy and Three Months Postpartum: Continuous Monitoring in a Free-Living Context (Preprint)

2021 ◽  
Author(s):  
Fatemeh Sarhaddi ◽  
Iman Azimi ◽  
Anna Axelin ◽  
Hannakaisa Niela-Vilen ◽  
Pasi Liljeberg ◽  
...  
Keyword(s):  
Heart Rate ◽  
Heart Rate Variability ◽  
Pregnant Women ◽  
Time Domain ◽  
Second Trimester ◽  
Third Trimester ◽  
Non Invasive ◽  
The Third ◽  
Invasive Method ◽  
Frequency Power

BACKGROUND Heart rate variability (HRV) is a non-invasive method reflecting autonomic nervous system (ANS) regulations. Altered HRV is associated with adverse mental or physical health complications. ANS also has a central role in physiological adaption during pregnancy causing normal changes in HRV. OBJECTIVE Assessing trends in heart rate (HR) and HRV parameters as a non-invasive method for remote maternal health monitoring during pregnancy and three months postpartum. METHODS Fifty-eight pregnant women were monitored using an Internet-of-Things (IoT)-based remote monitoring system during pregnancy and 3-months postpartum. Pregnant women were asked to continuously wear Gear sport smartwatch to monitor their HR and HRV. In addition, a cross-platform mobile application was utilized for collecting pregnancy-related information. The trends of HR and HRV parameters were extracted using reliable data. We also analyzed the trends of normalized HRV parameters based on HR to remove the effect of HR changes on HRV trends. Finally, we exploited hierarchical linear mixed models to analyze the trends of HR, HRV, and normalized HRV parameters. RESULTS HR increased significantly during the second trimester (P<.001) and decreased significantly during the third trimester (P<.01). Time-domain HRV parameters, average normal interbeat intervals (AVNN), standard deviation of normal interbeat intervals (SDNN), root mean square of the successive difference of normal interbeat intervals (RMSSD), normalized SDNN (nSDNN), and normalized RMSSD (nRMSSD) decreased significantly during the second trimester (P<.001) then increased significantly during the third trimester (P<.01). Some of the frequency domain parameters, low-frequency power (LF), high-frequency power (HF), and normalized HF (nHF) decreased significantly during the second trimester (P<.01), and HF increased significantly during the third trimester (P<.01). In the postpartum period, nRMSSD decreased (P<.05), and the LF to HF ratio (LF/HF) increased significantly (P<.01). CONCLUSIONS Our study showed that HR increased and HRV parameters decreased as the pregnancy proceeded, and the values returned to normal after the delivery. Moreover, our results show that HR started to decrease while time-domain HRV parameters and HF started to increase during the third trimester. Our results also demonstrate the possibility of continuous HRV monitoring in everyday life settings.

scholarly journals An Automated Approach for Epilepsy Detection Based on Tunable Q-Wavelet and Firefly Feature Selection Algorithm

2018 ◽  
Vol 2018 ◽  
pp. 1-12 ◽  
Author(s):  
Ahmed I. Sharaf ◽  
Mohamed Abu El-Soud ◽  
Ibrahim M. El-Henawy
Keyword(s):  
Feature Selection ◽  
Correlation Energy ◽  
Epileptic Seizures ◽  
Compact Set ◽  
Eeg Signal ◽  
Selection Algorithm ◽  
Feature Selection Algorithm ◽  
Eeg Signals ◽  
Computer Aided ◽  
Firefly Optimization

Detection of epileptic seizures using an electroencephalogram (EEG) signals is a challenging task that requires a high level of skilled neurophysiologists. Therefore, computer-aided detection provides an asset to the neurophysiologist in interpreting the EEG. This paper introduces a novel approach to recognize and classify the epileptic seizure and seizure-free EEG signals automatically by an intelligent computer-aided method. Moreover, the prediction of the preictal phase of the epilepsy is proposed to assist the neurophysiologist in the clinic. The proposed method presents two perspectives for the EEG signal processing to detect and classify the seizures and seizure-free signals. The first perspectives consider the EEG signal as a nonlinear time series. A tunable Q-wavelet is applied to decompose the signal into smaller segments called subbands. Then a chaotic, statistical, and power spectrum features sets are extracted from each subband. The second perspectives process the EEG signal as an image; hence the gray-level co-occurrence matrix is determined from the image to obtain the textures of contrast, correlation, energy, and homogeneity. Due to a large number of features obtained, a feature selection algorithm based on firefly optimization was applied. The firefly optimization reduces the original set of features and generates a reduced compact set. A random forest classifier is trained for the classification and prediction of the seizures and seizure-free signals. Afterward, a dataset from the University of Bonn, Germany, is used for benchmarking and evaluation. The proposed approach provided a significant result compared with other recent work regarding accuracy, recall, specificity, F-measure, and Matthew’s correlation coefficient.

Sign in / Sign up

Export Citation Format

Share Document