Information

Can you extract specific data from EEG

Can you extract specific data from EEG



We are searching data for your request:

Forums and discussions:
Manuals and reference books:
Data from registers:
Wait the end of the search in all databases.
Upon completion, a link will appear to access the found materials.

First of all, sorry if this is the wrong place to ask this question, please redirect me if it is so.

I have a project in mind involving and EEG, which is the following :

Using a "consumer-grade" EEG (see this one, for example) I would like to be able to control a binary system with my mind (for example, turning a led on and off). From what I've seen until now, this seems to be possible since the headset is able to detect eye blinks, for example. It also gives access to two variables "focus" and "relaxation", which you can learn to control somewhat accurately (accurately enough for a binary system, at least).

Now here's my problem. While the methods that I described above do work, they would also continuously activate even when I don't want them to. Everytime I blink, my led would turn on, even though my intention wasn't to turn the led on. Everytime the "focus" level goes over 50/100, the led would turn on, even though I'm just focusing on my physics problem.

Having said that, I was wondering if it is possible to pick up more subtle and "controlled" information on the EEG. One thing I was thinking about is, if I think and visualise the color red, maybe that could cause a signal that can be picked up ?(Of course the led would activate when I look at something red, but that's still an improvement) Or even looking at the led I want to turn on, would that have any discernable effect on the EEG ? My guess is that those "thoughts" are way to subtle to be picked up by an EEG, which is just an average of the brain activity, but I'm not an expert on the subject !

So I guess my question is : what are the "kind" of thoughts that I can somewhat reliably see on the EEG data ? For example, I know I can reliably pick up a eye-blink. Are there any thoughts that are not related to muscle movement that can also be reliably read on a EEG ?


Short answer
The key word in EEG-driven mind control is brain-computer interface (BCI). In contrast, eye blinks can simply be detected with an eye tracker.

Background
As far as I know, EEG-driven computer control (The force is strong in you) is based on recording the EEG while thinking of certain actions, or simply doing them. As you likely understand by now, thinking of moving your arm activates much of the same brain circuitry as actually making the move, up until the pre-motor cortex. The motor cortex itself stays silent (otherwise you would actually make the move (Griggs, 2013).

So EEG correlates of motor activity can be translated into digitized electrical brain activity. In turn, these brain waves can be put to use from playing pong by mind force, to state-of-the-art applications like driving artificial (bionic) limbs for the lame. By using artificial neural networks / deep learning techniques / and multiple EEG electrodes, the combined activity can be registered of many brain regions and certain signatures may pop out and be trained for a computer to learn them. In tun, that can be used to, say, play a computer game.

For a commercial alternative, delivered with an SDK, check out (Pogue, 2012):

References
- Griggs, New Scientist, January 2013
- Pogue, Sci Am, December 2012)


Can you extract specific data from EEG - Biology

Sari Saba-Sadiya 1,2 , Eric Chantland 1 , Taosheng Liu 1 , Tuka Alhanai 3 , Mohammad Ghassemi 1
1 Human Augmentation and Artificial Intelligence lab, Michigan State University, Department of Computer Science
2 Neuroimaging of Perception and Attention Lab, Michigan State University, Department of Psychology
3 Computer Human Intelligence Lab, New York University Abu Dhabi, Department of Electrical and Computer Engineering

A pyhton package for extracting EEG features. First developed for the paper "Unsupervised EEG Artifact Detection and Correction", published in Frontiers in Digital Health, Special issue on Machine Learning in Clinical Decision-Making. Press here for a BibTex citation (or scroll to the bottom of this page).

To the best of our knowledge EEGExtract is the most comprehensive library for EEG feature extraction currently available. This library is actively maintained, please open an issue if you believe adding a specific feature will be of benefit for the community!

  1. Make sure that you have the required packages listed in requirements.txt . Use pip install -r requirements.txt if unsure.
  2. Simply download and place the EEGExtract.py file in the same folder as your repo. You can then use import EEGExtract as eeg .

Free to use and modify, but must cite the original publication below.

Signal Descriptor Brief Description Function
Complexity Features degree of randomness or irregularity
Shannon Entropy additive measure of signal stochasticity shannonEntropy
Tsalis Entropy (n=10) non-additive measure of signal stochasticity tsalisEntropy
Information Quantity (δ,α,θ,β,γ) entropy of a wavelet decomposed signal filt_data + shannonEntropy
Cepstrum Coefficients (n=2) rate of change in signal spectral band power mfcc
Lyapunov Exponent separation between signals with similar trajectories lyapunov
Fractal Embedding Dimension how signal properties change with scale hFD
Hjorth Mobility mean signal frequency hjorthParameters
Hjorth Complexity rate of change in mean signal frequency hjorthParameters
False Nearest Neighbor signal continuity and smoothness falseNearestNeighbor
ARMA Coefficients (n=2) autoregressive coefficient of signal at (t-1) and (t-2) arma
Continuity Features clinically grounded signal characteristics
Median Frequency the median spectral power medianFreq
δ band Power spectral power in the 0-3Hz range bandPower
α band Power spectral power in the 4-7Hz range bandPower
θ band Power spectral power in the 8-15Hz range bandPower
β band Power spectral power in the 16-31Hz range bandPower
γ band Power spectral power above 32Hz bandPower
Median Frequency median spectral power medianFreq
Standard Deviation average difference between signal value and it's mean eegStd
α/δ Ratio ratio of the power spectral density in α and δ bands eegRatio
Regularity (burst-suppression) measure of signal stationarity / spectral consistency eegRegularity
Voltage < (5μ, 10μ, 20μ) low signal amplitude eegVoltage
Normal EEG Peak spectral power textgreater= 8Hz
Diffuse Slowing indicator of peak power spectral density less than 8Hz diffuseSlowing
Spikes signal amplitude exceeds μ by 3σ for 70 ms or less spikeNum
Delta Burst after spike Increased δ after spike, relative to δ before spike burstAfterSpike
Sharp spike spikes lasting less than 70 ms shortSpikeNum
Number of Bursts number of amplitude bursts numBursts
Burst length μ and σ statistical properties of bursts burstLengthStats
Burst band powers (δ,α,θ,β,γ) spectral power of bursts burstBandPowers
Number of Suppressions segments with contiguous amplitude suppression numSuppressions
Suppression length μ and σ statistical properties of suppressions suppressionLengthStats
Connectivity Features interactions between EEG electrode pairs
Coherence - δ correlation in in 0-4 Hz power between signals filt_data + coherence
Coherence - All correlation in overall power between signals coherence
Mutual Information measure of dependence calculate2Chan_MI
Granger causality - All measure of causality calcGrangerCausality
Phase Lag Index association between the instantaneous phase of signals phaseLagIndex
Cross-correlation Magnitude maximum correlation between two signals crossCorrMag
Crosscorrelation - Lag time-delay that maximizes correlation between signals corrCorrLagAux

Additionally, EEGExtract also contains implementations for a number of auxiliary functions

Function params Brief Description
filt_data eegData, lowcut, highcut, fs, order=7 midpass filter between lowcut and highcut
fcnRemoveShortEvents z,n z=[chan x samples ], n is threshold
get_intervals A,B,endIdx Find interval of consistent values in binary 1D numpy array

The feature extractor is an independent section that can be used with any artifact correction method (recently there have been quite a few including some notable example [1,2]). If you are interested in the specific setup that was used in the paper, as well as a link to the data, please visit the following repository.

[1] S. Phadikar, N. Sinha, and R. Ghosh, “Automatic eeg eyeblink artifact identification and removal technique using independent component analysis in combination with support vector machines and denoising autoencoder”

[2] B. Somers, T. Francart, and A. Bertrand, “A generic eeg artifact removal algorithm based on the multi-channel wiener filter.”


Electroencephalogram (EEG) signal analysis, which is widely used for human-computer interaction and neurological disease diagnosis, requires a large amount of labeled data for training. However, the collection of substantial EEG data could be difficult owing to its randomness and non-stationary. Moreover, there is notable individual difference in EEG data, which affects the reusability and generalization of models. For mitigating the adverse effects from the above factors, transfer learning is applied in this field to transfer the knowledge learnt in one domain into a different but related domain. Transfer learning adjusts models with small-scale data of the task, and also maintains the learning ability with individual difference. This paper describes four main methods of transfer learning and explores their practical applications in EEG signal analysis in recent years. Finally, we discuss challenges and opportunities of transfer learning and suggest areas for further study.

Zitong Wan received the M.S. degree in Applied Informatics from University of Liverpool, Liverpool, United Kingdom, in 2019. She is currently working towards the Ph.D. degree in University of Liverpool, Liverpool, United Kingdom. Her research interests include transfer learning and biomedical signal analysis.

Rui Yang received the B.Eng. degree in Computer Engineering and the Ph.D. degree in Electrical and Computer Engineering from National University of Singapore in 2008 and 2013 respectively. He is currently an Assistant Professor in the School of Advanced Technology, Xi’an Jiaotong-Liverpool University, Suzhou, China, and an Honorary Lecturer in the Department of Computer Science, University of Liverpool, Liverpool, United Kingdom. His research interests include machine learning based data analysis and applications.

Mengjie Huang received the Ph.D. degree from National University of Singapore in 2014, and the B.Eng degree from Sichuan University in 2009. She is now an Assistant Professor in the Design School, Xi’an Jiaotong-Liverpool University, Suzhou, China. Dr. Huang’s current research interests include human–computer interaction and applications.

Nianyin Zeng was born in Fujian Province, China, in 1986. He received the B.Eng. degree in Electrical Engineering and Automation in 2008 and the Ph. D. degree in Electrical Engineering in 2013, both from Fuzhou University. From October 2012 to March 2013, he was a RA in the Department of Electrical and Electronic Engineering, the University of Hong Kong. From September 2017 to August 2018, he as an ISEF Fellow founded by the Korea Foundation for Advance Studies and also a Visiting Professor at the Korea Advanced Institute of Science and Technology. Currently, he is an Associate Professor with the Department of Instrumental & Electrical Engineering of Xiamen University. His current research interests include intelligent data analysis, computational intelligent, time-series modeling and applications. He is the author or co-author of several technical papers and also a very active reviewer for many international journals and conferences. Dr. Zeng is currently serving as an Associate Editor for Neurocomputing, and also Editorial Board members for Computers in Biology and Medicine and Biomedical Engineering Online. He also serves as a technical program committee member for ICBEB 2014, an Invited Session Chair of ICCSE 2017.

Xiaohui Liu received the B.Eng. degree in Computing from Hohai University, Nanjing, China, in 1982 and the Ph.D. degree in Computer Science from Heriot-Watt University, Edinburg, U.K., in 1988. He is a Professor of Computing with Brunel University London, Uxbridge, U.K., where he directs the Centre for Intelligent Data Analysis. He has over 100 journal publications in computational intelligence and data science. Prof. Liu was a recipient of the Highly Cited Researchers Award by Thomson Reuters.

This document is partially supported by National Natural Science Foundation of China (61603223), Key Program Special Fund in XJTLU (KSF-E-34) and Research Development Fund of XJTLU (RDF-18-02-30).


EEG-based emotion recognition using 4D convolutional recurrent neural network

In this paper, we present a novel method, called four-dimensional convolutional recurrent neural network, which integrating frequency, spatial and temporal information of multichannel EEG signals explicitly to improve EEG-based emotion recognition accuracy. First, to maintain these three kinds of information of EEG, we transform the differential entropy features from different channels into 4D structures to train the deep model. Then, we introduce CRNN model, which is combined by convolutional neural network (CNN) and recurrent neural network with long short term memory (LSTM) cell. CNN is used to learn frequency and spatial information from each temporal slice of 4D inputs, and LSTM is used to extract temporal dependence from CNN outputs. The output of the last node of LSTM performs classification. Our model achieves state-of-the-art performance both on SEED and DEAP datasets under intra-subject splitting. The experimental results demonstrate the effectiveness of integrating frequency, spatial and temporal information of EEG for emotion recognition.

This is a preview of subscription content, access via your institution.


A Pervasive Approach to EEG-Based Depression Detection

Nowadays, depression is the world’s major health concern and economic burden worldwide. However, due to the limitations of current methods for depression diagnosis, a pervasive and objective approach is essential. In the present study, a psychophysiological database, containing 213 (92 depressed patients and 121 normal controls) subjects, was constructed. The electroencephalogram (EEG) signals of all participants under resting state and sound stimulation were collected using a pervasive prefrontal-lobe three-electrode EEG system at Fp1, Fp2, and Fpz electrode sites. After denoising using the Finite Impulse Response filter combining the Kalman derivation formula, Discrete Wavelet Transformation, and an Adaptive Predictor Filter, a total of 270 linear and nonlinear features were extracted. Then, the minimal-redundancy-maximal-relevance feature selection technique reduced the dimensionality of the feature space. Four classification methods (Support Vector Machine, K-Nearest Neighbor, Classification Trees, and Artificial Neural Network) distinguished the depressed participants from normal controls. The classifiers’ performances were evaluated using 10-fold cross-validation. The results showed that K-Nearest Neighbor (KNN) had the highest accuracy of 79.27%. The result also suggested that the absolute power of the theta wave might be a valid characteristic for discriminating depression. This study proves the feasibility of a pervasive three-electrode EEG acquisition system for depression diagnosis.

1. Introduction

Depression is a common mood disorder, which might cause persistent feeling of sadness, loss of interest, and impairment of memory and concentration. Depressed patients normally experience cognitive impairment and suffer long and severe emotional depression. In severe cases, some patients will experience paranoia and illusion [1]. According to the World Health Organization statistics, >300 million individuals suffer from depression worldwide approximately 800,000 people die due to it every year [2]. Thus, depression is predicted to become the second most common disease after heart disease by the year 2020 [3]. Hence, the diagnosis of depression in the early curable stages is critical and might save the life of a patient [4].

Presently, the study on the human cerebral is currently under intensive focus in order to understand the mechanism underlying persistent negative emotion and depression. Therefore, the most commonly used diagnosis of depression is a scale-based interview conducted by a psychologist or psychiatrist. The current international standard mostly used is “In Diagnostic and Statistical Manual of Mental Disorders (Fourth Edition)” (DSM-IV) [5], and the clinical test, Mini-Mental State Examination (MMSE), is commonly applied [6]. Other conventional psychometric questionnaires, such as Beck depression inventory (BDI) [7] and Hamilton Depression Rating Scale (HDRS) [8], are also used as screening tools rather than as the instrument for the diagnosis of depression.

The current methods of depression detection are human-intensive, and the results are dependent on the doctor’s experience. Furthermore, depressed individuals are less likely to seek help due to fear of stigma and the nature of the disorder. As a result, a large number of depressed patients, not diagnosed accurately, do not receive optimal treatment and adequate recovery period. Therefore, finding convenient and effective methods for the detection of depression is an emerging topic for research. With the latest advances in the sensor and mobile technology, the exploration using physiological data for the diagnosis of mental disorder opens a new avenue for an objective and accurate tool for depression detection. Among all kinds of physiological data, electroencephalogram (EEG) reflects emotional human brain activity in real time [9].

The EEG signal is a recording of the spontaneous, rhythmic, electrical activity of brain neurons from the scalp surface. Since the earliest discovery from the rabbit and monkey brain and the first recording of the human EEG signal by German psychiatrist Hans Berger in 1926, studies on the analytical method of EEG and the interpretation of the association between the brain function and mental disorders have been continued for over a century [10]. Neuroscience, psychology, and cognitive science research showed that a majority of the psychological activities and cognitive behavior could be indicated by EEG [11–13]. The EEG signal is closely related to the brain activities and emotional states, and it could reflect the emotional transformation in real time. Cole and Ray [14] found that the EEG signal collected from the parietal lobe of brain is associated with the cognitive tasks and emotional states. Klimesch et al. found that the alpha waves with low frequency could reflect some of the features of attention, such as vigilance and expectations [15]. Srinivasan et al. demonstrated that the frequency domain features of EEG could be used to predict the level of attention [16]. Therefore, the EEG signal is critical for understanding the processing of human brain information and emotional state transformation.

The studies on EEG could be used to understand the mechanism underlying brain activity, human cognitive process, and diagnosis of brain disease, as well as the field of the Brain Computer Interface (BCI), which has attracted much attention in recent years [17]. Compared to Computed Tomography (CT) and functional Magnetic Resonance Imaging (fMRI), EEG has a higher time resolution, a lower maintenance cost, and a simpler operation method. Thus, as an objective physiological method to obtain data, EEG was proposed as a nonintrusive approach to study cognitive behavior [18–20] and other illness symptoms, such as insomnia [21–23], epilepsy [24–26], and sleep disorder [27]. EEG has also been used in the diagnosis of mental disorders, such as anxiety [28–30], psychosis [31–34], and depression [35–38]. In addition, depression as a mental disorder with clinical manifestations such as significant depression and slow thinking is always accompanied by abnormal brain activity and obvious emotional alternation. Therefore, as a method tracking the brain functions, EEG can detect these abnormal activities.

The frequency of the EEG signal can be divided into 5 wave-bands: delta wave (<4 Hz), which normally appears in an adult’s slow-wave sleep theta wave (4–8 Hz), which is usually found when someone is sleepy alpha wave (8–14 Hz), which is normally detected when someone is relaxed beta wave (14–30 Hz), which commonly appears when someone is actively thinking and gamma wave (30–50 Hz), which could appear during meditation. The EEG signals undergo changes in the amplitude as well as frequency, while different mental tasks are performed [39–42].

Presently, for research purposes, the most commonly used are 128-electrode and 256-electrode EEG systems [43, 44], which are specifically designed for research purposes. The operation of the instruments was not only difficult to initiate but also it required technicians to apply conductive gel to each electrode on the participant’s head before each use. The preparation process alone takes 30 minutes on average. In addition, these EEG systems are expensive. Overall, these systems are not practical for pervasive depression detection.

In the present study, the pervasive three-electrode EEG acquisition system, developed independently by the Ubiquitous Awareness and Intelligent Solutions Lab (UAIS) of Lanzhou University [45], was employed to construct a database containing both depressed patients and normal controls. Thus, the use of the latest data processing technique and machine learning to explore a pervasive EEG-based depression detection system has been the focus of investigation. In order to support this research: (1) A pervasive three-electrode EEG acquisition system has been introduced (Section 2.1). (2) A psychophysiological experiment has been conducted, in which EEG of 213 participants has been recorded. These physiological data provided a comprehensive database for further analysis, construction, and evaluation of a pervasive EEG-based depression detection system (Sections 2.2 and 2.3). (3) Several EEG preprocessing steps and methods were applied on the raw EEG data (Section 3.1). (4) 270 features were identified and extracted from the recoded database. By employing a feature selection technique, an optimum feature matrix was constructed for the depression classification process (Section 3.2). (5) Four classification algorithms, including K-Nearest Neighbor (KNN), Support Vector Machine (SVM), Classification Tree (CT), and Artificial Neural Network (ANN), have been evaluated and compared, using a 10-fold cross-validation (Section 4).

2. Pervasive Three-Electrode EEG Database Construction

2.1. Pervasive Three-Electrode EEG Acquisition System

The 10-20 system, proposed by Jasper in 1958, defined the name of the electrode and later became the international standard EEG placement system [46]. With the development of sensor technology, the electrode became smaller than that in previous systems and the electrodes recorded a detailed EEG. In 1985, Chatrian et al. added extra electrodes in intermediate sites halfway between those of the existing 10-20 system, thereby expanding it to a 64-electrode system [47]. Due to the complexity of the full-brain 128-electrode and 256-electrode systems, the investigators restricted themselves from mobile and pervasive application. Thus, with the development of universal and pervasive electronic technology, the 8-electrode and 16-electrode systems with small volume were also developed gradually.

As shown in Figure 1, F represents the frontal lobe, T represents the temporal lobe, C represents the center, P represents the parietal lobe, and O represents the occipital lobe. EEG reacts to the biological activity of the brain tissue, thereby indicating the functional status of the brain [48]. The EEG signal collected from the different locations of the scalp reflects a variety of information. For example, EEG from the frontal lobe reflects human memory, computational power, attention, and responsiveness EEG from the parietal lobe is associated with somatic responses EEG from the occipital lobe can be used as a reference for visual reactions EEG from temporal lobe is related to auditory reactions. Therefore, for different research direction and purpose, the appropriate EEG collection location is essential.

Prefrontal cortex is the center of consciousness thus, the better the control of the forehead cortex, the better the emotional control. Jasper studied the resting-state EEG of severe depression patients showing that when the body suffered from severe depression, the activity of the cerebral cortex was altered [49]. Nauta emphasized that the prefrontal cortex played a major role in different aspects of emotional processes [50]. Rolls put forward the importance of prefrontal cortex for emotional and motivational processes [51]. Harmon-Jones suggested that the specific forms of anger, or anger elicited in particular contexts, are associated with left-sided prefrontal activation [52]. In conclusion, the above studies have shown that the electrode sites located in the prefrontal cortex are associated with emotional process and psychiatric disorders. Therefore, Fp1, Fp2, and Fpz are the ideal choices of scalp position in the current experiment. The hair in the frontal lobe is absent and contact dry electrode should be sufficient without the need for applying conductive gel. The pervasive three-electrode EEG acquisition system (Figure 2), developed by UAIS from Lanzhou University [53], runs on rechargeable battery and transmits all the EEG data through Bluetooth 2.0 wirelessly. The system is extremely small in size and can be easily placed on the location. The sampling frequency is 250 Hz and according to the EGI engineers, all electrodes have an impedance of <50 kΩ. Since the frequency of EEG is 0.5–50 Hz, the passband of the EEG acquisition is 0.5–50 Hz.

2.2. Experiment Method

Compared to the normal controls, depressed patients responded differently to outside stimulus [54, 55]. The feedback of the depressed patients to the positive and negative stimuli weakened. As the positive stimulus feedback weakened further, the overall performance was negative emotions and reflected as such in the emotional response of the different subsystems. In summary, no significant difference was observed in the positive stimulus between normal controls and depressed patients, and depressed patients would produce more negative emotions under negative stimulus as compared to normal controls. Beck’s cognitive behavioral model of depression postulated that the depressed patients are likely to support a negative view of themselves, the world, and even the future. In order to maintain this negative self-view, they even resist the environmental feedback that is inconsistent with the view [56]. Epstein et al. suggested that, in comparison to normal controls, depressed patients responded with less bilateral ventral striatal activation to positive stimuli, which leads to the decreased interest in performance of activities [57]. Bylsma et al. proved that depressed patients exhibit less reactivity to all stimuli and events, irrespective of positive or negative nature [58].

Therefore, recording and analysis of the EEG signal in different stimuli may help in the identification of patients with depression. This study was designed to record the participants’ EEG in four different cases: in resting state, under negative stimulus, under neutral stimulus, and under positive stimulus. The source of stimulus is soundtracks from the International Affective Digitized Sounds (IADS-2) [59], which is a standardized database of 167 naturally occurring sounds, widely used in the study of emotions.

The experiment was performed in a quiet room. Firstly, the experiment objective and procedures were described to the participants. Then, the pervasive three-electrode EEG acquisition system was placed on the participants’ foreheads and checked for reception. After one minute of relaxation, the experiment begins again. At first stage, 90 s of resting-state EEG was recorded. Then, the participants were asked to remain seated with eyes closed with as little body movements as possible, followed by another minute of rest. In the second stage, stimulation soundtracks will be played to participants. Each soundtrack was 6 s long with a 6 s break between each soundtrack. The process would continue until the experiment is completed. The process of EEG acquisition is shown in Figure 3.

A total of 6 stimulation soundtracks (according to IADS-2) existed, including 2 neutral stimulation soundtracks, 2 negative stimulation soundtracks, and 2 positive stimulation soundtracks. Table 1 describes each audio stimulation.

2.3. Psychophysiological Database

Of the total 250 participants, 213 (92 depressed patients and 121 normal controls) completed the experiment, successfully. The raw EEG data from all the electrodes were recorded. Depressed participants were selected by professional psychiatrists using MMSE [6], which is a 30-point questionnaire used by the psychiatrist during a face-to-face interview to assess the degree of cognitive dysfunction in patients with diffuse brain disorders. In addition, all participants are asked to fill the following scales for cross-referencing: (A) The Patient Health Questionnaire (PHQ-9) [60] is a 9-question-based multipurpose instrument for screening, diagnosing, monitoring, and measuring the severity of depression. We chose this questionnaire in order to find the relevance between the EEG characteristic and the severity of depression. (B) Life Event Scale (LES) [61] contains 48 questions including events of family, work, and social support. The influence of each event is evaluated for severity, duration, and frequency. We chose this questionnaire for cross-referencing purposes. (C) Pittsburgh Sleep Quality Index (PSQI) [62] contains 19 self-reported items, creating 7 components to diagnose sleep disorders. We chose this index to explore the direct link between sleep qualities with depression in EEG. (D) Generalized Anxiety Disorder Scale-7 (GAD-7) [63] contains only 7 self-report questions for screening and measuring the severity of generalized anxiety disorder. We chose this questionnaire for cross-referencing between depression and anxiety.

3. Data Processing

In this study, all preprocessing, and data analyses have been implemented using MATLAB software (version R2014a).

3.1. Preprocessing

EEG is a noninvasive method of capturing the physiological signal of brainwave activity. However, EEG data recorded are normally mixed with interferences from surrounding environment, such as close-by power line. Furthermore, other physiological signals, including electrocardiogram (ECG), electrooculogram (EOG), and electromyograph (EMG), could also be detected and recorded by EEG sensors [55]. To ensure an accurate result in the feature selection and classification, all the raw data should be denoised first.

ECG is a smooth signal among the physiological electrical signals, with a large amplitude. As the heart is located distally from the head, the ECG signal will be greatly attenuated when spread to the scalp. EMG is produced by muscle contraction, with an amplitude of 10 μV to 15 mV. The frequency of EMG is concentrated primarily in the high band > 100 Hz. Power-line interference focuses on fixed operation frequency. In order to remove these interference signals, we followed the results of several investigators. Yang proposed a cascade of three adaptive filters based on the least mean squares (LMS) algorithm and verified that the proposed filter reduced the interference in EEG signals [64]. Tong et al. validated the use of independent component analysis (ICA) for an efficient suppression of the interference of ECG from EEG [65]. The National Institute of Mental Health announced that using an adaptive filter to estimate the contaminants can subtract them from the EEG data [66].

No overlap occurred between the frequency of EEG signal and power-line interferences, EMG and ECG thus, Finite Impulse Response (FIR) filter based on the Blackman time window was used to remove these interference signals. The adequate linearity of the FIR filter is widely used in modern electronic communication. It can guarantee any amplitude frequency characteristics simultaneously, with strict linear phase-frequency characteristics. In addition, the unit sampling response is finite, which stabilized the filter. In order to reduce the energy leakage of the spectrum, the signal can be truncated by different interception functions. This truncation function is known as the window function. The time domain representation of the Blackman time window is


Conclusions

This study has shown that nonlinear networks that were set to operate in a weakly coupled regime called CAS can be used to feed data to a machine-learning-like model that can be trained by an unsupervised approach. Importantly, the output from the CAS model can reproduce EEG signals of both healthy and epileptic conditions in the predicting regime and reproduce the characteristics of the EEG signals in terms of the Hurst exponent and the power spectrum.

We have tested the performance of the CAS model based on various neuron and network types using the modeled data from healthy and epileptic subjects. Interestingly, the prediction errors between the EEG dataset and the CAS produced signals indicate that critical to better predicting the EEG signals is that artificial neurons should weakly interact with each other to ensure that the CAS can be generated. Thus, this suggests the generality of the CAS model, a weakly coupled chaotic system, in representing brain dynamics independent of the neuronal dynamics and types of the networks.

However, some limitations need to be addressed to improve this model in the future. Our model is based on a linear regression that provides a good approximation of the experimental EEG signal, but with a unique set of constant weight coefficients, a network with invariant topology, and constant coupling strength connecting the nodes. However, EEG signals are nonstationary in nature. Therefore, for long-term predictions, our model should incorporate some time-varying configurations tuned to adapt to the varying nature of the experimental signal being modeled.

Standard approaches to model EEG rely on auto-regression 11,12 or artificial neural networks 28 . These methods, although successful in reproducing the characteristics of EEG signals, can only successfully predict the EEG signals for time intervals shorter than 1 s. The difficulty in predicting EEG signals is due to the nonstationary nature of the EEG signals. The proposed method, fundamentally based on a nonlinear network that has nodes set to operate in a CAS regime (that effectively makes their trajectories wander along a large set of periodic orbits), can lead to a successful prediction of time intervals of the order of 5.76 s.


Download EEG Guide

Fortunately, the complexity of running and analyzing EEG experiments can be significantly simplified by piloting, collecting clean data, and making informed decisions along the way of pre-processing and statistically analyzing the data.

Do not hesitate to talk to us here at iMotions if you would like to enrich your research endeavor with EEG and other physiological sensors. We will be happy to provide you with the necessary tools and information to get you started with the collection of high-quality data in no time! Contact us here

Continue to read here for information about academic research or commercial research!


Background

Dementia is a broad group of brain disorders leading to a cognitive impairment because of a gradual dysfunction and death of brain cells. The World Alzheimer Report 2015 has been estimated that 36 million people were living with dementia in 2010, nearly doubling every 20 years to 66 million by 2030 and to 115 million by 2050 [1]. Given the continuous growth of incidence of this illness, dementia represents one of the major plague for the modern society. The most widespread cause of dementia is the Alzheimer’s disease (AD), which involves serious memory loss, cognitive impairment, and behavioural changes. Thus, AD interferes with daily, social and professional functioning of patients, also affecting the daily life of their families [2]. The intermediate stage between the normal cognitive deficit due to aging and dementia is defined as Mild Cognitive Impairment (MCI). Several symptoms distinguish MCI, but the loss of memory is a risk factor to develop AD [3]. In Europe, only 50% of the patients with dementia receive a diagnosis by a specialist centre, and tests for dementia are carried out after the patient has already started showing symptoms and the disease has progressed [4]. Usually, the process for obtaining a clinical diagnosis for dementia of a patient is mainly based on the delivery of a questionnaire in order to assess its cognitive abilities. However, a timely diagnosis would facilitate care, reduce the progression of the disease, and improve the patient’s management to alleviate the burden. This might be achieved through a combination of diagnosis criteria and reliable biomarkers.

In the past years, significant progresses have been made to detect the early stages of dementia through biochemical, genetic, neuroimaging, and neurophysiological biomarkers such as Electroencephalography (EEG) [5–9]. EEG provides the electrical activity of the brain by tracking the connectivity of neurons in the recording sites of the scalp [10], processing it with milliseconds precision. The condition of the brain physiology can be inferred from the EEG signals recorded, and thus abnormalities can be identified through the detection of unusual frequency patterns [11]. Indeed, different rhythms with diverse frequency bands describe the activity of the brain and can be recorded by EEG. Among them, the main ones are alpha (8-13 Hz, 30-50 μV amplitude), beta (13-30 Hz, 5-30 μV amplitude), gamma (≥ 30 Hz), delta (0.5-4 Hz), and theta (4-7 Hz, ≥ 20μV amplitude).

Although it is characterized by a lower spatial resolution than other neuroimaging techniques, EEG provides high temporal resolution [12]. Moreover, EEG is non-invasive, ease and faster to use and able to differentiate severity of dementia at a lower cost than other imaging devices [13, 14]. Thanks to its reduced costs EEG can be easily implemented for population screening to detect pre-clinical biomarkers.

EEG signal analysis may provide useful indications of the patterns of brain activity and predict the stages of dementia [15, 16] because of its significant capacity to detect brain rhythm abnormalities, generally correlated with the severity of cognitive impairment [17]. In particular, different clinical studies confirm EEG as suitable technique to early detect AD [18–20], due to the following effects on EEG signals: reduction of the complexity, perturbation of the synchrony, and slowingdown of the rhythms [19, 21, 22]. The slowing of the rhythms in the EEG signals of subjects affected by AD can be explained by a gain of the activity in the theta and delta frequency ranges, and a reduction of the activity in the alpha and beta frequency ranges [23–26]. The reduction of complexity in the EEG temporal patterns can be explained by a modification of the neural network architecture observed in subjects affected by AD [27, 28] due to loss of neurons and functional interaction alteration which make the activity of the brain more predictable, more regular, and simpler than in healthy control samples (HC) [29]. Therefore, we can state that EEG signals related to healthy controls subjects can be distinguished from those ones of subjects affected by neurodegenerative diseases (e.g., AD) or other pathologies (e.g., epilepsy).

Nevertheless, AD and MCI subjects are characterized by a huge variability and thus discriminating artifacts and patterns similarities to physiological brain activity still remain a crucial issue. In this regard, EEG signal processing integrated with computational algorithms based on machine learning methods may contribute to a deeper comprehension of the disease and simplify the work of neurologists providing an additional tool to diagnose the stage of dementia [20, 30–33].

In this paper, we propose a procedure based on EEG-signal preprocessing and automatic classification with supervised learning methods, and its application to discriminate subjects belonging to AD, or MCI, or HC classes. This is an extension of a preliminary work [34] in which we processed an EEG data set composed of 49 AD, 37 MCI and 14 healthy controls subjects (HC) by means of a spectrum analysis based on the Fourier Transformation, and we automatically classified them with supervised machine learning methods. Here, we have increased the number of HC subjects of the data set to 23 in order to balance the number of samples for each category. We have also improved the EEG-signal preprocessing and spectrum analysis techniques through the application of the Wavelet Transform as an efficient method for noise reduction and feature extraction, obtaining a more reliable method to distinguish healthy from diseased subjects.


EEG-based deep learning model for the automatic detection of clinical depression

Clinical depression is a neurological disorder that can be identified by analyzing the Electroencephalography (EEG) signals. However, the major drawback in using EEG to accurately identify depression is the complexity and variation that exist in the EEG of a depressed individual. There are several strategies for automated depression diagnosis, but they all have flaws, which make the diagnostic task inaccurate. In this paper, a deep model is designed in which an integration of Convolution Neural Network (CNN) and Long Short Term Memory (LSTM) is implemented for the detection of depression. CNN and LSTM are used to learn the local characteristics and the EEG signal sequence, respectively. In the deep learning model, filters in the convolution layer are convolved with the input signal to generate feature maps. All the extracted features are given to the LSTM for it to learn the different patterns in the signal, after which the classification is performed using fully connected layers. LSTM has memory cells to remember the essential features for a long time. It also has different functions to update the weights during training. Testing of the model was done by random splitting technique and obtained 99.07% and 98.84% accuracies for the right and left hemispheres EEG signals, respectively.

This is a preview of subscription content, access via your institution.