Emotion Detection Using EEG Signals

Comparative exploration on EEG signal filtering using window control methods

In this study cyclic changes of human sleep structure were examined. For whole-night polysomnograms of 35 healthy volunteers of both sexes, manual hypnograms were created and divided into NREM-REM cycles. EEG signals from C3-A2 derivation were analysed by computer using a Fast Fourier Transform (FFT). For consecutive NREM-REM cycles of individual sleep stages, EEG power density contents for delta, theta, alpha, sigma and beta waves were analysed. For consecutive sleep cycles, a clear decrease in NREM sleep duration, especially slow wave sleep duration, was obtained. In addition, a decrease in power density of delta waves was observed. For consecutive sleep cycles, increases in REM sleep duration and in power density of theta and alpha waves were obtained. In consecutive sleep cycles, high amplitude delta slow waves are replaced by higher frequency and lower amplitude waves. Thus stages of NREM sleep are replaced by stages of REM.

This study aims to analyze the relationship between brainwave activity and the learning readiness of students with disabilities by utilizing EEG (Electroencephalography) signals. EEG signals are used to detect the brain's electrical activity that reflects mental states, including focus, concentration, and readiness to receive learning. This study was conducted at SLB 'Aisyiyah Krian with a quantitative approach through EEG signal measurement before and during the learning process. The results showed a significant correlation between the dominance of alpha and beta waves with learning readiness, while the dominance of theta and delta waves indicated unpreparedness. These findings provide a foundation for the development of a more inclusive, objective, and adaptive neurotechnology-based learning approach for students with disabilities.

This paper studied the epilepsy signal in different frequency bands based on the average phase-synchronization time matrix (APSTM). APSTM algorithm can probe the change in the synchrony of the underlying system with high sensitivity, and be applied to multichannel, nonlinear time series in noisy. This paper uses the EEG filter provided by the EEGLAB to extract the four common waves : theta, alpha, beta and gamma, which are from the normal and epilepsy EEG signals. The four frequency bands of EEG signals are analysed based on the APSTM algorithm, and the results show that the APSTM determinant can distinguish the epilepsy from the normal EEG signals clearly. And when APSTM determinant detects epileptic discharge ,the theta wave is the most significant, and the beta wave can only generally detect epileptic discharge, while alpha and gamma waves are ineffective.

BackgroundHighly structured electroencephalography (EEG) oscillations can occur in adults during etomidate-induced general anesthesia, but the link between these two phenomena is poorly understood. Therefore, in the present study, we investigated the electroencephalogram dynamics of etomidate-induced loss of consciousness (LOC) in order to understand the neurological mechanism of etomidate-induced LOC.MethodsThis study is a prospective observational study. Etomidate-induced anesthesia was performed on eligible patients undergoing elective surgery. We analyzed EEG data from 20 patients who received etomidate for the induction of general anesthesia. We used power spectra and coherence methods to process and analyze the EEG data. Our study was based on 4-channel EEG recordings.ResultsCompared with the baseline (awake period), etomidate induced an increase in power in delta, theta, alpha and beta waves during LOC. Compared with the awake period, the delta-wave (1–4 Hz), alpha-wave(8–13 Hz), and theta-wave(4–8 Hz) coherence increased significantly during LOC, while the slow-wave (< 1 Hz) coherence decreased. However, the delta wave (1.0–4.0 Hz) during etomidate-induced LOC was more coherent than during the awake period (1.86–3.17 Hz, two-group test for coherence, p < 0.001).ConclusionsThe neural circuit mechanism of etomidate-induced LOC is closely related to the induction of oscillation in delta, theta, alpha and beta waves and the enhancement of delta-wave coherence.Trial registrationChiCTR1800017110

Background. The method of anterior decompression (discectomy) for monosegmental stenosis of the cervical spinal canal is subjectively assessed as highly effective by both neurosurgeons and the vast majority of patients. However, the objective criteria for the early effectiveness of this intervention have not been sufficiently studied to date. Aim of the study to evaluate the dynamics of electroencephalography parameters in the preoperative and early postoperative period in patients with monosegmental stenosis of the cervical spine. Materials and methods. Electroencephalography studies were conducted on 22 patients of the neurosurgery department, before and after surgical treatment under code A16.23.085.001. The spectral composition of the bioelectrical activity of the brain (alpha, beta, delta and theta rhythms), as well as the coherence of oscillations in selected leads, were studied. Results. In the preoperative period, a disorganized type of electroencephalogramm was recorded in the examined group according to the classification of E.A. Zhirmunskaya; there was a decrease in the index and amplitude of the alpha rhythm in the parietal-occipital leads; predominance of high-amplitude beta activity in the frontal-central leads; presence of diffuse delta activity of the average index and theta activity of the average index, localized in leads P3, P4, C3, C4. On the 5th day after the operation, an organized type of electroencephalography was recorded on the encephalogram; a well-modulated alpha rhythm was observed, with a frequency in the range from 9 to 10 Hz, and an amplitude of 70 to 80 microvolts. Low-amplitude beta rhythm activity was recorded in the frontocentral leads. Low-amplitude delta and theta rhythms were recorded in the parieto-occipital leads and had a low index. Overall, the obtained data indicated positive dynamics in the restoration of cortical rhythms. Conclusion. The positive dynamics of cerebral cortex biorhythms in the early postoperative period allows the use of the electroencephalography method to objectify the results of surgical treatment, and in the future for the purposes of neurorehabilitation.

Breastfeeding is a process of nursing a baby with milk straight from the women’s breast. It is suggested that a baby should be breastfed within one hour of birth, exclusively breastfed for the first six months, and then breastfed until age two with age-appropriate, nutritionally sufficient and harmless complementary diets. This paper focuses on the examination of breastfeeding women on their stress level and the brainwave characteristics. The brainwave signals were documented using wireless Electroencephalogram (EEG) equipment via Bluetooth while. The stress level was performed using a questionnaire. The EEG signals were derived using an existing system with the electrodes attached to human scalp. These electrodes measure the electrical signals which are produced by the activities of the neurons in the human brain, such as Delta, Theta, Alpha and Beta waves in the brain to determine the Brainwave Balancing Index (BBI) and also the brain hemispheric dominance which is right or left dominance. The outcome presented balanced BBI of the breastfeeding women after the breastfeeding session, although most of them were high in stress. Right brain dominance was also recorded for the majority of them for both sessions, before and after breastfeeding. Statistical investigation leads to no significant correlations between stress and BBI of breastfeeding women after breastfeeding session, in terms of breastfeeding method and in terms of breastfeeding women’ categories.

Drowsiness presents major safety concerns for tasks that require long periods of focus and alertness. While there is a body of work on drowsiness detection using EEG signals in neuroscience and engineering, there exist unanswered questions pertaining to the best mechanisms to use for detecting drowsiness. Targeting a range of practical safety-awareness applications, this study adopts a machine learning based approach to build support vector machine (SVM) classifiers to distinguish between awake and drowsy states. While broadband alpha, beta, delta, and theta waves are often used as features in the existing work, lack of widely agreed precise definitions of such broadband signals and difficulty in accounting for interpersonal variability has led to poor classification performance as demonstrated in this study. Furthermore, the transition from wakefulness to drowsiness and deeper sleep stages is a complex multifaceted process. The richness of this process calls for inclusion of sub-band features for more accurate drowsiness detection. To shed light on the effectiveness of sub-banding, we quantitatively compare the performances of a large set of SVM classifiers trained upon a varying number of 1Hz sub band features. More importantly, we identify a compact set of neuroscientifcally motivated EEG features and demonstrate that the resulting classifier not only outperforms traditional broadband based classifiers but also is on a par with or superior than the best sub-band classifiers found by thorough search in a large space of 1Hz sub band features.

Aiming to develop an noninvasive BMI control system with EEG (electroencephalogram) signals to control external devices such as prostheses and robots for rehabilitation and/or power support, four different tasks corresponding to different brain excitation degrees are designed. Their EEG spectra are analyzed with short-time fast Fourier transform (STFFT), and their features of mu and beta rhythms corresponding to the different tasks are extracted. The extracted features are used to control a one-joint robot arm and their corresponding results are compared. The results show that the EEG signal when a subject is holding a weight is comparatively more stable than the EEG signals in other tasks such as motor imagery. This implies an effective way for power assist by EEG signals.

In order to verify whether there is a correlation between human behavior and EEG signal, proposes a method based on exploratory analysis to study the relationship between human behavior and EEG. Through the acquisition of mice EEG and respiratory signal under sleep state, using exploratory analysis modeling to construct a transmission system of the linear time invariant multi-resolution model, then aggregate and disaggregate the respiratory signal. Through the analysis of EEG signals in time domain and frequency domain, experiments show that the EEG signal can control respiration and respiratory signal can also affect EEG rhythms, EEG rhythm and respiratory signals is relevant.

The Brain is the main controller of the human body consisting of neurons which generate electrical signals to control the body. Different neurological diseases can cause brain abnormalities such as ALS that affect the electrical activity of the brain which can be seen in the EEG signal. Therefore, these abnormalities can be detected by analyzing the EEG signal. As the Alpha and Beta waves are recorded during the active state of the brain, the effect of abnormalities can be seen in the waves. This study proposes a technique to detect the brain abnormalities and detect ALS syndromes based on Alpha and Beta waves. In this study, the Alpha and Beta waves are extracted from the raw EEG signal by discrete wavelet transformation. Here, the raw EEG signal is divided into several orthogonal wavelets using Doubechis 4 wavelet transform; Alpha and Beta wave frequency components are selected and reconstructed. Then these waves can be compared between different types of ALS patients and normal people based on amplitude and event related potential. The result showed great variation in amplitude as well as event related potential for different ALS patients and normal people. The proposed technique could be used in detecting abnormalities and their severity. It could also help in detecting ALS at a primary stage.

Automated accurate emotion recognition system using rhythm-specific deep convolutional neural network technique with multi-channel EEG signals

Electroencephalographic (EEG) abnormalities are seen in patients with Alzheimer's disease (AD) and mild cognitive impairment (MCI) with characteristic features of cognitive impairment. The most common findings of EEG features in AD and MCI patients are increased relative power of slow oscillations (delta and theta rhythms) and decreased relative power of fast oscillations (alpha, beta and gamma rhythms). However, impairments in cognitive processes in AD and MCI are not sufficiently reflected by brain oscillatory activity in a particular frequency band. MCI patients are at high risk of progressing to AD. Cross-frequency coupling (CFC), which refers to coupling between different frequency bands, is a crucial tool for comprehending changes in brain oscillations and cognitive performance. CFC features exhibit some specificity in patients with AD and MCI, but a comparison between CFC features in individuals with these disorders is still lacking. The aim of this study was to explore changes in CFC properties in MCI and AD and to explore the relationship between CFC properties and multiple types of cognitive functional performance. We recorded resting-state EEG (rsEEG) signals in 46 MCI patients, 43 AD patients, and 43 cognitively healthy controls (HCs) and analyzed the changes in CFC as well as the relationship between CFC and scores on clinical tests of cognitive function. Multiple couplings between low-frequency oscillations and high-frequency oscillations were found to be significantly enhanced in AD patients compared to those of HCs and MCI, while delta-gamma as well as theta-gamma couplings in the right temporal and parietal lobes were significantly enhanced in MCI patients compared to HCs. Moreover, theta-gamma coupling in the right temporal lobe tended to be stronger in MCI patients than in HCs, and it was stronger in AD than in MCI. Multiple CFC properties were found to correlate significantly with various cognitive domains, especially the memory function domain. Overall, these findings suggest that AD and MCI patients must use more neural resources to maintain a resting brain state and that alterations in theta-gamma coupling in the temporal lobe become progressively obvious during disease progression and are likely to be a valuable indicator of MCI and AD pathology.

The simultaneous acquisition of electroencephalogram (EEG) and functional MRI (fMRI) signals is potentially advantageous because of the superior resolution that is achieved in both the temporal and spatial domains, respectively. However, ballistocardiographic artifacts along with ocular artifacts are a major obstacle for the detection of the EEG signatures of interest. Since the sources corresponding to these artifacts are independent from those producing the EEG signatures, we applied the Infomax-based independent component analysis (ICA) technique to separate the EEG signatures from the artifacts. The isolated EEG signatures were further utilized to model the canonical hemodynamic response functions (HRFs). Subsequently, the brain areas from which these EEG signatures originated were identified as locales of activation patterns from the analysis of fMRI data. Upon the identification and subsequent evaluation of brain areas generating interictal epileptic discharge (IED) spikes from an epileptic subject, the presented method was successfully applied to detect the theta and alpha rhythms that are sleep onset-related EEG signatures along with the subsequent neural circuitries from a sleep-deprived volunteer. These results suggest that the ICA technique may be useful for the preprocessing of simultaneous EEG–fMRI acquisitions, especially when a reference paradigm is unavailable.

Epilepsy is the most common neurological disorder characterized by recurrent seizures due to the abnormality of brain neuronal discharge. One of the tools to help neurologists diagnose epilepsy relies on EEG signals extensively because it can represent the brain's neuron activity. Due to the EEG signal being considered a complex biological signal, the signal complexity-based feature extraction method is suitable for characterizing epileptic EEG signals. One method for extracting EEG signals is entropy which is able to quantify signal complexity. Several previously proposed methods were wavelet entropy and IMF entropy. This study proposed multi-distance signal level difference (MSLD) entropy as a feature extraction method to extract the EEG signal complexity. The decomposed signal from MSLD was then extracted using entropy measurement. In the classification process, a Support Vector Machine (SVM) was applied to classify the normal, pre-ictal, and ictal signals of EEG signals. The highest accuracy of 96% was obtained using cubic SVM as the classifier. The proposed method provides an alternative method for analyzing EEG or other biomedical signals based on signal complexity.