EEG Signals Feature Extraction Based on DWT and EMD Combined with Approximate Entropy

A brain functional network feature extraction method based on directed transfer function and graph theory for MI-BCI decoding tasks

Background

The development of Brain-Computer Interface (BCI) technology has brought tremendous potential to various fields. In recent years, prominent research has focused on enhancing the accuracy of BCI decoding algorithms by effectively utilizing meaningful features extracted from electroencephalographic (EEG) signals.

Objective

This paper proposes a method for extracting brain functional network features based on directed transfer function (DTF) and graph theory. The method incorporates the extracted brain network features with common spatial pattern (CSP) to enhance the performance of motor imagery (MI) classification task.

Methods

The signals from each electrode of the EEG, utilizing a total of 32 channels, are used as input signals for the network nodes. In this study, 26 healthy participants were recruited to provide EEG data. The brain functional network is constructed in Alpha and Beta bands using the DTF method. The node degree (ND), clustering coefficient (CC), and global efficiency (GE) of the brain functional network are obtained using graph theory. The DTF network features and graph theory are combined with the traditional signal processing method, the CSP algorithm. The redundant network features are filtered out using the Lasso method, and finally, the fused features are classified using a support vector machine (SVM), culminating in a novel approach we have termed CDGL.

Results

For Beta frequency band, with 8 electrodes, the proposed CDGL method achieved an accuracy of 89.13%, a sensitivity of 90.15%, and a specificity of 88.10%, which are 14.10, 16.69, and 11.50% percentage higher than the traditional CSP method (75.03, 73.46, and 76.60%), respectively. Furthermore, the results obtained with 8 channels were superior to those with 4 channels (82.31, 83.35, and 81.74%), and the result for the Beta frequency band were better than those for the Alpha frequency band (87.42, 87.48, and 87.36%). Similar results were also obtained on two public datasets, where the CDGL algorithm's performance was found to be optimal.

Conclusion

The feature fusion of DTF network and graph theory features enhanced CSP algorithm's performance in MI task classification. Increasing the number of channels allows for more EEG signal feature information, enhancing the model's sensitivity and discriminative ability toward specific activities in brain regions. It should be noted that the functional brain network features in the Beta band exhibit superior performance improvement for the algorithm compared to those in the Alpha band.

An emotion recognition method based on EWT-3D-CNN-BiLSTM-GRU-AT model

This has become a significant study area in recent years because of its use in brain-machine interaction (BMI). The robustness problem of emotion classification is one of the most basic approaches for improving the quality of emotion recognition systems. One of the two main branches of these approaches deals with the problem by extracting the features using manual engineering and the other is the famous artificial intelligence approach, which infers features of EEG data. This study proposes a novel method that considers the characteristic behavior of EEG recordings and based on the artificial intelligence method. The EEG signal is a noisy signal with a non-stationary and non-linear form. Using the Empirical Wavelet Transform (EWT) signal decomposition method, the signal's frequency components are obtained. Then, frequency-based features, linear and non-linear features are extracted. The resulting frequency-based, linear, and nonlinear features are mapped to the 2-D axis according to the positions of the EEG electrodes. By merging this 2-D images, 3-D images are constructed. In this way, the multichannel brain frequency of EEG recordings, spatial and temporal relationship are combined. Lastly, 3-D deep learning framework was constructed, which was combined with convolutional neural network (CNN), bidirectional long-short term memory (BiLSTM) and gated recurrent unit (GRU) with self-attention (AT). This model is named EWT-3D-CNN-BiLSTM-GRU-AT. As a result, we have created framework comprising handcrafted features generated and cascaded from state-of-the-art deep learning models. The framework is evaluated on the DEAP recordings based on the person-independent approach. The experimental findings demonstrate that the developed model can achieve classification accuracies of 90.57 % and 90.59 % for valence and arousal axes, respectively, for the DEAP database. Compared with existing cutting-edge emotion classification models, the proposed framework exhibits superior results for classifying human emotions.

The applied principles of EEG analysis methods in neuroscience and clinical neurology

Electroencephalography (EEG) is a non-invasive measurement method for brain activity. Due to its safety, high resolution, and hypersensitivity to dynamic changes in brain neural signals, EEG has aroused much interest in scientific research and medical fields. This article reviews the types of EEG signals, multiple EEG signal analysis methods, and the application of relevant methods in the neuroscience field and for diagnosing neurological diseases. First, three types of EEG signals, including time-invariant EEG, accurate event-related EEG, and random event-related EEG, are introduced. Second, five main directions for the methods of EEG analysis, including power spectrum analysis, time-frequency analysis, connectivity analysis, source localization methods, and machine learning methods, are described in the main section, along with different sub-methods and effect evaluations for solving the same problem. Finally, the application scenarios of different EEG analysis methods are emphasized, and the advantages and disadvantages of similar methods are distinguished. This article is expected to assist researchers in selecting suitable EEG analysis methods based on their research objectives, provide references for subsequent research, and summarize current issues and prospects for the future.

Comparative analysis of ANN performance of four feature extraction methods used in the detection of epileptic seizures

Epilepsy, a prevalent neurological disorder characterized by disrupted brain activity, affects over 70 million individuals worldwide, as reported by the World Health Organization (WHO). The development of computer-aided diagnosis systems has become vital in assessing epilepsy severity promptly and initiating timely treatment. These systems enable the detection of epileptic seizures by analyzing the electrical activity in the EEG recordings of the patients. In addition, it helps doctors to choose suitable treatment by quickly determining the type, duration, and characteristics of seizures and increases the patient's quality of life. The proposed computer-aided diagnosis system in this study comprises three modules: preprocessing, feature extraction, and classification. The initial module employs a low-pass Chebyshev II filter to eliminate noise artifacts from signal recordings. The second module involves deriving feature vectors using Bispectrum Analysis, Empirical Mode Decomposition, Discrete Wavelet Transform, and Wavelet Packet Analysis. The third module employs the Artificial Neural Networks method for epileptic seizure detection. This study not only enables the comparison of feature extraction efficacy among Bispectrum Analysis, Empirical Mode Decomposition, Discrete Wavelet Transform, and Wavelet Packet Analysis techniques, but it also reveals that Bispectrum Analysis and Empirical Mode Decomposition yield the highest accuracy rate. The method achieves 100% accuracy in detecting epileptic seizures. Additionally, sensitivity analysis has been conducted to enhance the success of Discrete Wavelet Transform and Wavelet Packet Analysis methods and to identify significant features.

Deep temporal networks for EEG-based motor imagery recognition

The electroencephalogram (EEG) based motor imagery (MI) signal classification, also known as motion recognition, is a highly popular area of research due to its applications in robotics, gaming, and medical fields. However, the problem is ill-posed as these signals are non-stationary and noisy. Recently, a lot of efforts have been made to improve MI signal classification using a combination of signal decomposition and machine learning techniques but they fail to perform adequately on large multi-class datasets. Previously, researchers have implemented long short-term memory (LSTM), which is capable of learning the time-series information, on the MI-EEG dataset for motion recognition. However, it can not model very long-term dependencies present in the motion recognition data. With the advent of transformer networks in natural language processing (NLP), the long-term dependency issue has been widely addressed. Motivated by the success of transformer algorithms, in this article, we propose a transformer-based deep learning neural network architecture that performs motion recognition on the raw BCI competition III IVa and IV 2a datasets. The validation results show that the proposed method achieves superior performance than the existing state-of-the-art methods. The proposed method produces classification accuracy of 99.7% and 84% on the binary class and the multi-class datasets, respectively. Further, the performance of the proposed transformer-based model is also compared with LSTM.

OculusGraphy: Signal Analysis of the Electroretinogram in a Rabbit Model of Endophthalmitis Using Discrete and Continuous Wavelet Transforms

BACKGROUND

The electroretinogram is a clinical test used to assess the function of the photoreceptors and retinal circuits of various cells in the eye, with the recorded waveform being the result of the summated response of neural generators across the retina.

METHODS

The present investigation involved an analysis of the electroretinogram waveform in both the time and time-frequency domains through the utilization of the discrete wavelet transform and continuous wavelet transform techniques. The primary aim of this study was to monitor and evaluate the effects of treatment in a New Zealand rabbit model of endophthalmitis via electroretinogram waveform analysis and to compare these with normal human electroretinograms.

RESULTS

The wavelet scalograms were analyzed using various mother wavelets, including the Daubechies, Ricker, Wavelet Biorthogonal 3.1 (bior3.1), Morlet, Haar, and Gaussian wavelets. Distinctive variances were identified in the wavelet scalograms between rabbit and human electroretinograms. The wavelet scalograms in the rabbit model of endophthalmitis showed recovery with treatment in parallel with the time-domain features.

CONCLUSIONS

The study compared adult, child, and rabbit electroretinogram responses using DWT and CWT, finding that adult signals had higher power than child signals, and that rabbit signals showed differences in the a-wave and b-wave depending on the type of response tested, while the Haar wavelet was found to be superior in visualizing frequency components in electrophysiological signals for following the treatment of endophthalmitis and may give additional outcome measures for the management of retinal disease.

Hybrid Deep Learning Approach for Stress Detection Using Decomposed EEG Signals

Stress has an impact, not only on a person's physical health, but also on the ability to perform at the workplace in daily life. The well-established relation between psychological stress and its pathogeneses highlights the need for detecting psychological stress early, in order to prevent disease advancement and to save human lives. Electroencephalography (EEG) signal recording tools are widely used to collect these psychological signals/brain rhythms in the form of electric waves. The aim of the current research was to apply automatic feature extraction to decomposed multichannel EEG recordings, in order to efficiently detect psychological stress. The traditional deep learning techniques, namely the convolution neural network (CNN), long short-term memory (LSTM), bidirectional long short-term memory (BiLSTM), gated recurrent unit (GRU) and recurrent neural network (RNN) models, have been frequently used for stress detection. A hybrid combination of these techniques may provide improved performance, and can handle long-term dependencies in non-linear brain signals. Therefore, this study proposed an integration of deep learning models, called DWT-based CNN, BiLSTM, and two layers of a GRU network, to extract features and classify stress levels. Discrete wavelet transform (DWT) analysis was used to remove the non-linearity and non-stationarity from multi-channel (14 channel) EEG recordings, and to decompose them into different frequency bands. The decomposed signals were utilized for automatic feature extraction using the CNN, and the stress levels were classified using BiLSTM and two layers of GRU. This study compared five combinations of the CNN, LSTM, BiLSTM, GRU and RNN models with the proposed model. The proposed hybrid model performed better in classification accuracy compared to the other models. Therefore, hybrid combinations are appropriate for the clinical intervention and prevention of mental and physical problems.

Nonlinear dynamics of EEG responses to unmanned vehicle visual detection with different levels of task difficulty

The main objective of this study was to examine the presence of chaos in the EEG recordings of brain activity under simulated unmanned ground vehicle visual detection scenarios with different levels of task difficulty. One hundred and fifty people participated in the experiment and completed four visual detection task scenarios: (1) change detection, (2) a threat detection task, (3) a dual-task with different change detection task rates, and (4) a dual-task with different threat detection task rates. We used the largest Lyapunov exponent and correlation dimension of the EEG data and performed 0-1 tests on the EEG data. The results revealed a change in the level of nonlinearity in the EEG data corresponding to different levels of cognitive task difficulty. The differences in EEG nonlinearity measures among the studied levels of task difficulty, as well as between a single task scenario and a dual-task scenario, have also been assessed. The results increase our understanding of the nature of unmanned systems' operational requirements.

Detection of motor imagery based on short-term entropy of time-frequency representations

BACKGROUND

Motor imagery is a cognitive process of imagining a performance of a motor task without employing the actual movement of muscles. It is often used in rehabilitation and utilized in assistive technologies to control a brain-computer interface (BCI). This paper provides a comparison of different time-frequency representations (TFR) and their Rényi and Shannon entropies for sensorimotor rhythm (SMR) based motor imagery control signals in electroencephalographic (EEG) data. The motor imagery task was guided by visual guidance, visual and vibrotactile (somatosensory) guidance or visual cue only.

RESULTS

When using TFR-based entropy features as an input for classification of different interaction intentions, higher accuracies were achieved (up to 99.87%) in comparison to regular time-series amplitude features (for which accuracy was up to 85.91%), which is an increase when compared to existing methods. In particular, the highest accuracy was achieved for the classification of the motor imagery versus the baseline (rest state) when using Shannon entropy with Reassigned Pseudo Wigner-Ville time-frequency representation.

CONCLUSIONS

Our findings suggest that the quantity of useful classifiable motor imagery information (entropy output) changes during the period of motor imagery in comparison to baseline period; as a result, there is an increase in the accuracy and F1 score of classification when using entropy features in comparison to the accuracy and the F1 of classification when using amplitude features, hence, it is manifested as an improvement of the ability to detect motor imagery.

Motor imagery EEG signal classification with a multivariate time series approach

BACKGROUND

Electroencephalogram (EEG) signals record electrical activity on the scalp. Measured signals, especially EEG motor imagery signals, are often inconsistent or distorted, which compromises their classification accuracy. Achieving a reliable classification of motor imagery EEG signals opens the door to possibilities such as the assessment of consciousness, brain computer interfaces or diagnostic tools. We seek a method that works with a reduced number of variables, in order to avoid overfitting and to improve interpretability. This work aims to enhance EEG signal classification accuracy by using methods based on time series analysis. Previous work on this line, usually took a univariate approach, thus losing the possibility to take advantage of the correlation information existing within the time series provided by the different electrodes. To overcome this problem, we propose a multivariate approach that can fully capture the relationships among the different time series included in the EEG data. To perform the multivariate time series analysis, we use a multi-resolution analysis approach based on the discrete wavelet transform, together with a stepwise discriminant that selects the most discriminant variables provided by the discrete wavelet transform analysis RESULTS: Applying this methodology to EEG data to differentiate between the motor imagery tasks of moving either hands or feet has yielded very good classification results, achieving in some cases up to 100% of accuracy for this 2-class pre-processed dataset. Besides, the fact that these results were achieved using a reduced number of variables (55 out of 22,176) can shed light on the relevance and impact of those variables.

CONCLUSIONS

This work has a potentially large impact, as it enables classification of EEG data based on multivariate time series analysis in an interpretable way with high accuracy. The method allows a model with a reduced number of features, facilitating its interpretability and improving overfitting. Future work will extend the application of this classification method to help in diagnosis procedures for detecting brain pathologies and for its use in brain computer interfaces. In addition, the results presented here suggest that this method could be applied to other fields for the successful analysis of multivariate temporal data.

Approximate entropy analysis across electroencephalographic rhythmic frequency bands during physiological aging of human brain

Aging is the inevitable biological process that results in a progressive structural and functional decline associated with alterations in the resting/task-related brain activity, morphology, plasticity, and functionality. In the present study, we analyzed the effects of physiological aging on the human brain through entropy measures of electroencephalographic (EEG) signals. One hundred sixty-one participants were recruited and divided according to their age into young (n = 72) and elderly (n = 89) groups. Approximate entropy (ApEn) values were calculated in each participant for each EEG recording channel and both for the total EEG spectrum and for each of the main EEG frequency rhythms: delta (2-4 Hz), theta (4-8 Hz), alpha 1 (8-11 Hz), alpha 2 (11-13 Hz), beta 1 (13-20 Hz), beta 2 (20-30 Hz), and gamma (30-45 Hz), to identify eventual statistical differences between young and elderly. To demonstrate that the ApEn represents the age-related brain changes, the computed ApEn values were used as features in an age-related classification of subjects (young vs elderly), through linear, quadratic, and cubic support vector machine (SVM). Topographic maps of the statistical results showed statistically significant difference between the ApEn values of the two groups found in the total spectrum and in delta, theta, beta 2, and gamma. The classifiers (linear, quadratic, and cubic SVMs) revealed high levels of accuracy (respectively 93.20 ± 0.37, 93.16 ± 0.30, 90.62 ± 0.62) and area under the curve (respectively 0.95, 0.94, 0.93). ApEn seems to be a powerful, very sensitive-specific measure for the study of cognitive decline and global cortical alteration/degeneration in the elderly EEG activity.

A Literature Review Research on Monitoring Conditions of Mechanical Equipment Based on Edge Computing

The motivation of this research is to review all methods used in data compression of collected data in monitoring the condition of equipment based on the framework of edge computing. Since a large amount of signal data is collected when monitoring conditions of mechanical equipment, namely, signals of running machines are continuously transmitted to be crunched, compressed data should be handled effectively. However, this process occupies resources since data transmission requires the allocation of a large capacity. To resolve this problem, this article examines the monitoring conditions of equipment based on edge computing. First, the signal is pre-processed by edge computing, so that the fault characteristics can be identified quickly. Second, signals with difficult-to-identify fault characteristics need to be compressed to save transmission resources. Then, different types of signal data collected in mechanical equipment conditions are compressed by various compression methods and uploaded to the cloud. Finally, the cloud platform, which has powerful processing capability, is processed to improve the volume of the data transmission. By examining and analyzing the monitoring conditions and signal compression methods of mechanical equipment, the future development trend is elaborated to provide references and ideas for the contemporary research of data monitoring and data compression algorithms. Consequently, the manuscript presents different compression methods in detail and clarifies the data compression methods used for the signal compression of equipment based on edge computing.

Travieso-González C. Analysis of Brain Computer Interface Using Deep and Machine Learning

Pattern recognition is becoming increasingly important topic in all sectors of society. From the optimization of processes in the industry to the detection and diagnosis of diseases in medicine. Brain-computer interfaces are introduced in this chapter. Systems capable of analyzing brain signal patterns, processing and interpreting them through machine and deep learning algorithms. In this chapter, a hybrid deep/machine learning ensemble system for brain pattern recognition is proposed. It is capable to recognize patterns and translate the decisions to BCI systems. For this, a public database (Physionet) with data of motor tasks and mental tasks is used. The development of this chapter consists of a brief summary of the state of the art, the presentation of the model together with some results and some promising conclusions.

Heartfulness Meditation Alters Electroencephalogram Oscillations: An Electroencephalogram Study

Background

Heartfulness meditation (HM) has been shown to have positive impacts on cognition and well-being, which makes it important to look into the neurophysiological mechanisms underlying the phenomenon.

Aim

A cross-sectional study was conducted on HM meditators and nonmeditators to assess frontal electrical activities of the brain and self-reported anxiety and mindfulness.

Settings and Design

The present study employed a cross-sectional design.

Methods

Sixty-one participants were recruited, 28 heartfulness meditators (average age male: 31.54 ± 4.2 years and female: 30.04 ± 7.1 years) and 33 nonmeditators (average age male: 25 ± 8.5 years and female: 23.45 ± 6.5 years). An electroencephalogram (EEG) was employed to assess brain activity during baseline (5 min), meditation (10 min), transmission (10 min) and post (5 min). Self-reported mindfulness and anxiety were also collected in the present study. The EEG power spectral density (PSD) and coherence were processed using MATLAB. The statistical analysis was performed using an independent sample t-test for trait mindfulness and anxiety, repeated measures analysis of variance (ANOVA) for state mindfulness and anxiety, and Two-way multivariate ANOVA for EEG spectral frequency and coherence.

Results

The results showed higher state and trait mindfulness, P < 0.05 and P < 0.01, respectively, and lower state and trait anxiety, P < 0.05 and P < 0.05, respectively. The PSD outcomes showed higher theta (P < 0.001) and alpha (P < 0.01); lower beta (P < 0.001) and delta (P < 0.05) power in HM meditators compared to nonmeditators. Similarly, higher coherence was found in the theta (P < 0.01), alpha (P < 0.05), and beta (P < 0.01) bands in HM meditators.

Conclusions

These findings suggest that HM practice may result in wakeful relaxation and internalized attention that can influence cognition and behavior.

Sleep staging classification based on a new parallel fusion method of multiple sources signals

APPROACH

First, the heart rate variability (HRV) is extracted from EOG with the Weight Calculation Algorithm (WCA) and an "HYF" RR interval detection algorithm. Second, three feature sets were extracted from HRV segments and EOG segments: time-domain features, frequency domain features and nonlinear-domain features. The frequency domain features and nonlinear-domain features were extracted by using Discrete Wavelet Transform (DWT), Autoregressive (AR), and Power Spectral entropy (PSE), and Refined Composite Multiscale Dispersion Entropy (RCMDE). Third, a new "Parallel Fusion Method" (PFM) for sleep stage classification is proposed. Three kinds of feature sets from EOG and HRV segments are fused by using PFM. Fourth, Extreme Gradient Boosting (XGBoost) and Support Vector Machine (SVM) classification models is employed for sleep staging.

MAIN RESULTS

Our experimental results show significant performance improvement on automatic sleep staging on the target domains achieved with the new sleep staging approach. The performance of the proposed method is testedby evaluating the average accuracy, Kappa coefficient. The average accuracy of sleep classification results by using XGBoost classification model with PFM is 82.7% and the kappa coefficient is 0.711, also by using SVM classification model with the PFM is 83.7%, and the kappa coefficient is 0.724. Experimental results show that the performance of the proposed method is competitive with the most current methods and results, and the recognition rate of S1 stage is significantly improved. Significance： As a consequence, it would enable one to improve the quality of automatic sleep staging models when the EOG and HRV signals are fused, which can be beneficial for monitor sleep quality and keep abreast of health conditions. Besides, our study provides good research ideas and methods for scholars, doctors and individuals.

Automated emotion recognition: Current trends and future perspectives

BACKGROUND

Human emotions greatly affect the actions of a person. The automated emotion recognition has applications in multiple domains such as health care, e-learning, surveillance, etc. The development of computer-aided diagnosis (CAD) tools has led to the automated recognition of human emotions.

OBJECTIVE

This review paper provides an insight into various methods employed using electroencephalogram (EEG), facial, and speech signals coupled with multi-modal emotion recognition techniques. In this work, we have reviewed most of the state-of-the-art papers published on this topic.

METHOD

This study was carried out by considering the various emotion recognition (ER) models proposed between 2016 and 2021. The papers were analysed based on methods employed, classifier used and performance obtained.

RESULTS

There is a significant rise in the application of deep learning techniques for ER. They have been widely applied for EEG, speech, facial expression, and multimodal features to develop an accurate ER model.

CONCLUSION

Our study reveals that most of the proposed machine and deep learning-based systems have yielded good performances for automated ER in a controlled environment. However, there is a need to obtain high performance for ER even in an uncontrolled environment.

Deep Feature Mining via the Attention-Based Bidirectional Long Short Term Memory Graph Convolutional Neural Network for Human Motor Imagery Recognition

Recognition accuracy and response time are both critically essential ahead of building the practical electroencephalography (EEG)-based brain–computer interface (BCI). However, recent approaches have compromised either the classification accuracy or the responding time. This paper presents a novel deep learning approach designed toward both remarkably accurate and responsive motor imagery (MI) recognition based on scalp EEG. Bidirectional long short-term memory (BiLSTM) with the attention mechanism is employed, and the graph convolutional neural network (GCN) promotes the decoding performance by cooperating with the topological structure of features, which are estimated from the overall data. Particularly, this method is trained and tested on the short EEG recording with only 0.4 s in length, and the result has shown effective and efficient prediction based on individual and groupwise training, with 98.81% and 94.64% accuracy, respectively, which outperformed all the state-of-the-art studies. The introduced deep feature mining approach can precisely recognize human motion intents from raw and almost-instant EEG signals, which paves the road to translate the EEG-based MI recognition to practical BCI systems.

Classification of lower limb motor imagery based on iterative EEG source localization and feature fusion

Motor imagery (MI) brain–computer interface (BCI) systems have broad application prospects in rehabilitation and other fields. However, to achieve accurate and practical MI-BCI applications, there are still several critical issues, such as channel selection, electroencephalogram (EEG) feature extraction and EEG classification, needed to be better resolved. In this paper, these issues are studied for lower limb MI which is more difficult and less studied than upper limb MI. First, a novel iterative EEG source localization method is proposed for channel selection. Channels FC1, FC2, C1, C2 and Cz, instead of the commonly used traditional channel set (TCS) C3, C4 and Cz, are selected as the optimal channel set (OCS). Then, a multi-domain feature (MDF) extraction algorithm is presented to fuse single-domain features into multi-domain features. Finally, a particle swarm optimization based support vector machine (SVM) method is utilized to classify the EEG data collected by the lower limb MI experiment designed by us. The results show that the classification accuracy is 88.43%, 3.35–5.41% higher than those of using traditional SVM to classify single-domain features on the TCS, which proves that the combination of OCS and MDF can not only reduce the amount of data processing, but also retain more feature information to improve the accuracy of EEG classification.

Application of multi-layer denoising based on ensemble empirical mode decomposition in extraction of fault feature of rotating machinery

Aiming at the problem that the weak features of non-stationary vibration signals are difficult to extract under strong background noise, a multi-layer noise reduction method based on ensemble empirical mode decomposition (EEMD) is proposed. First, the original vibration signal is decomposed by EEMD, and the main intrinsic modal components (IMF) are selected using comprehensive evaluation indicators; the second layer of filtering uses wavelet threshold denoising (WTD) to process the main IMF components. Finally, the virtual noise channel is introduced, and FastICA is used to de-noise and unmix the IMF components processed by the WTD. Next, perform spectral analysis on the separated useful signals to highlight the fault frequency. The feasibility of the proposed method is verified by simulation, and it is applied to the extraction of weak signals of faulty bearings and worn polycrystalline diamond compact bits. The analysis of vibration signals shows that this method can efficiently extract weak fault characteristic information of rotating machinery.

Accurate assessment of low-function autistic children based on EEG feature fusion

Autism spectrum disorder (ASD) is a very serious neurodevelopmental disorder and diagnosis mainly depends on the clinical scale, which has a certain degree of subjectivity. It is necessary to make accurate evaluation by objective indicators. In this study, we enrolled 96 children aged from 3 to 6 years: 48 low-function autistic children (38 males and 10 females; mean±SD age: 4.9±1.1 years) and 48 typically developing (TD) children (38 males and 10 females; mean±SD age: 4.9 ± 1.2 years) to participate in our experiment. We investigated to fuse multi-features (entropy, relative power, coherence and bicoherence) to distinguish low-function autistic children and TD children accurately. Minimum redundancy maximum correlation algorithm was used to choose the features and support vector machine was used for classification. Ten-fold cross validation was used to test the accuracy of the model. Better classification result was obtained. We tried to provide a reliable basis for clinical evaluation and diagnosis for ASD.

Depth of anesthesia prediction via EEG signals using convolutional neural network and ensemble empirical mode decomposition

According to a recently conducted survey on surgical complication mortality rate, 47% of such cases are due to anesthetics overdose. This indicates that there is an urgent need to moderate the level of anesthesia. Recently deep learning (DL) methods have played a major role in estimating the depth of Anesthesia (DOA) of patients and has played an essential role in control anesthesia overdose. In this paper, Electroencephalography (EEG) signals have been used for the prediction of DOA. EEG signals are very complex signals which may require months of training and advanced signal processing techniques. It is a point of debate whether DL methods are an improvement over the already existing traditional EEG signal processing approaches. One of the DL algorithms is Convolutional neural network (CNN) which is very popular algorithm for object recognition and is widely growing its applications in processing hierarchy in the human visual system. In this paper, various decomposition methods have been used for extracting the features EEG signal. After acquiring the necessary signals values in image format, several CNN models have been deployed for classification of DOA depending upon their Bispectral Index (BIS) and the signal quality index (SQI). The EEG signals were converted into the frequency domain using and Empirical Mode Decomposition (EMD), and Ensemble Empirical Mode Decomposition (EEMD). However, because of the inter mode mixing observed in EMD method; EEMD have been utilized for this study. The developed CNN models were used to predict the DOA based on the EEG spectrum images without the use of handcrafted features which provides intuitive mapping with high efficiency and reliability. The best trained model gives an accuracy of 83.2%. Hence, this provides further scope and research which can be carried out in the domain of visual mapping of DOA using EEG signals and DL methods.

Abdul Majeed A. The classification of motor imagery response: an accuracy enhancement through the ensemble of random subspace k-NN

Brain-computer interface (BCI) is a viable alternative communication strategy for patients of neurological disorders as it facilitates the translation of human intent into device commands. The performance of BCIs primarily depends on the efficacy of the feature extraction and feature selection techniques, as well as the classification algorithms employed. More often than not, high dimensional feature set contains redundant features that may degrade a given classifier's performance. In the present investigation, an ensemble learning-based classification algorithm, namely random subspace k-nearest neighbour (k-NN) has been proposed to classify the motor imagery (MI) data. The common spatial pattern (CSP) has been applied to extract the features from the MI response, and the effectiveness of random forest (RF)-based feature selection algorithm has also been investigated. In order to evaluate the efficacy of the proposed method, an experimental study has been implemented using four publicly available MI dataset (BCI Competition III dataset 1 (data-1), dataset IIIA (data-2), dataset IVA (data-3) and BCI Competition IV dataset II (data-4)). It was shown that the ensemble-based random subspace k-NN approach achieved the superior classification accuracy (CA) of 99.21%, 93.19%, 93.57% and 90.32% for data-1, data-2, data-3 and data-4, respectively against other models evaluated, namely linear discriminant analysis, support vector machine, random forest, Naïve Bayes and the conventional k-NN. In comparison with other classification approaches reported in the recent studies, the proposed method enhanced the accuracy by 2.09% for data-1, 1.29% for data-2, 4.95% for data-3 and 5.71% for data-4, respectively. Moreover, it is worth highlighting that the RF feature selection technique employed in the present study was able to significantly reduce the feature dimension without compromising the overall CA. The outcome from the present study implies that the proposed method may significantly enhance the accuracy of MI data classification.

Gastric slow wave rhythm identification using new approach based on noise-assisted multivariate empirical mode decomposition and Hilbert-Huang transform

BACKGROUND

Electrogastrography (EGG) is the method of cutaneous recording of the myoelectrical activity of the stomach. A multi-channel signal is recorded non-invasively by means of electrodes placed outside the epigastric area. The normal electrical rhythm of the stomach (slow wave) may become significantly disturbed due to disorders of gastrointestinal tract. Abnormally fast electrical rhythms are termed tachygastria, while abnormally slow rhythms are known as bradygastria. Because some features of biological signals may go undetected using the classical methods of signal spectral analysis, we propose a new method for EGG rhythm identification.

METHODS

In this study, the calculation of the basic rhythms of multi-channel EGG signals is performed by means of the noise-assisted multivariate empirical mode decomposition (NA-MEMD) and Hilbert-Huang transform (HHT), using EGG data from eight healthy subjects. The results were compared with those obtained using classical spectral analysis.

KEY RESULTS

The mean values of the normogastric index for preprandial and two postprandial stages were found to be 64.78 ± 11.37%, 61.29 ± 15.86%, and 63.80 ± 13.24%, respectively. The obtained values of normogastric index are consistent with the normal human physiological value, which is approximately 70% for healthy subjects.

CONCLUSIONS

This method is able to capture features of the signal which are mostly undetectable by standard EGG processing methods. The EGG dominant rhythm identification using the instantaneous normogastric, bradygastric, and tachygastric indices provides new insights into biological EGG patterns.

Using an Optimization Algorithm to Detect Hidden Waveforms of Signals

Source signals often contain various hidden waveforms, which further provide precious information. Therefore, detecting and capturing these waveforms is very important. For signal decomposition (SD), discrete Fourier transform (DFT) and empirical mode decomposition (EMD) are two main tools. They both can easily decompose any source signal into different components. DFT is based on Cosine functions; EMD is based on a collection of intrinsic mode functions (IMFs). With the help of Cosine functions and IMFs respectively, DFT and EMD can extract additional information from sensed signals. However, due to a considerably finite frequency resolution, EMD easily causes frequency mixing. Although DFT has a larger frequency resolution than EMD, its resolution is also finite. To effectively detect and capture hidden waveforms, we use an optimization algorithm, differential evolution (DE), to decompose. The technique is called SD by DE (SDDE). In contrast, SDDE has an infinite frequency resolution, and hence it has the opportunity to exactly decompose. Our proposed SDDE approach is the first tool of directly applying an optimization algorithm to signal decomposition in which the main components of source signals can be determined. For source signals from four combinations of three periodic waves, our experimental results in the absence of noise show that the proposed SDDE approach can exactly or almost exactly determine their corresponding separate components. Even in the presence of white noise, our proposed SDDE approach is still able to determine the main components. However, DFT usually generates spurious main components; EMD cannot decompose well and is easily affected by white noise. According to the superior experimental performance, our proposed SDDE approach can be widely used in the future to explore various signals for more valuable information.

Using Nonlinear Dynamics and Multivariate Statistics to Analyze EEG Signals of Insomniacs with the Intervention of Superficial Acupuncture

Objective

As a noninvasive and nonpharmacological therapeutic approach, superficial acupuncture (SA) is a special method of acupuncture. In this study, using nonlinear dynamics and multivariate statistics, we studied the electroencephalography (EEG) of primary insomnia under SA intervention to investigate how brain regions change.

Method

This study included 30 adults with primary insomnia. They underwent superficial acupuncture at the Shangen acupoint. The EEG signals were collected for 10 minutes at each state, including the resting state, the intervention state, and the postintervention state. The data were conducted using nonlinear dynamics (including approximate entropy (ApEn) and correlation dimension (CD)) and multivariate statistics.

Result

The repeated-measures ANOVA results showed that both ApEn and CD values were not significantly different at the three states (p > 0.05). The paired t-test results showed that the ApEn values of electrodes O2 (the right occipital lobe) at the postintervention state have decreased, compared with the resting state (p < 0.05), and no difference was detected in CD (p > 0.05). The cluster analysis results of ApEn showed that patients' EEG has changed from the right prefrontal lobe (electrode Fp2) to the right posterior temporal lobe (electrode T6) and finally to the right occipital lobe (electrode O2), before, during, and after the SA intervention. In addition, the factor analysis results of CD revealed that patients' EEG of all brain regions except for the occipital lobes has changed to the frontal lobes and anterior temporal and frontal lobes from pre- to postintervention.

Conclusion

SA activated the corresponding brain regions and reduced the complexity of the brain involved. It is feasible to use nonlinear dynamics analysis and multivariate statistics to examine the effects of SA on the human brain.

Affective State Assistant for Helping Users with Cognition Disabilities Using Neural Networks

Non-verbal communication is essential in the communication process. This means that its lack can cause misinterpretations of the message that the sender tries to transmit to the receiver. With the rise of video calls, it seems that this problem has been partially solved. However, people with cognitive disorders such as those with some kind of Autism Spectrum Disorder (ASD) are unable to interpret non-verbal communication neither live nor by video call. This work analyzes the relationship between some physiological measures (EEG, ECG, and GSR) and the affective state of the user. To do that, some public datasets are evaluated and used for a multiple Deep Learning (DL) system. Each physiological signal is pre-processed using a feature extraction process after a frequency study with the Discrete Wavelet Transform (DWT), and those coefficients are used as inputs for a single DL classifier focused on that signal. These multiple classifiers (one for each signal) are evaluated independently and their outputs are combined in order to optimize the results and obtain additional information about the most reliable signals for classifying the affective states into three levels: low, middle, and high. The full system is carefully detailed and tested, obtaining promising results (more than 95% accuracy) that demonstrate its viability.

Current Status, Challenges, and Possible Solutions of EEG-Based Brain-Computer Interface: A Comprehensive Review

Brain-Computer Interface (BCI), in essence, aims at controlling different assistive devices through the utilization of brain waves. It is worth noting that the application of BCI is not limited to medical applications, and hence, the research in this field has gained due attention. Moreover, the significant number of related publications over the past two decades further indicates the consistent improvements and breakthroughs that have been made in this particular field. Nonetheless, it is also worth mentioning that with these improvements, new challenges are constantly discovered. This article provides a comprehensive review of the state-of-the-art of a complete BCI system. First, a brief overview of electroencephalogram (EEG)-based BCI systems is given. Secondly, a considerable number of popular BCI applications are reviewed in terms of electrophysiological control signals, feature extraction, classification algorithms, and performance evaluation metrics. Finally, the challenges to the recent BCI systems are discussed, and possible solutions to mitigate the issues are recommended.

Research on State Recognition and Failure Prediction of Axial Piston Pump Based on Performance Degradation Data

Degradation state recognition and failure prediction are the key steps of prognostic and health management (PHM), which directly affect the reliability of the equipment and the selection of preventive maintenance strategy. Given the problem that the distinction between feature vectors is not obvious and the accuracy of fault prediction is low, a method based on multi-class Gaussian process classification and Gaussian process regression (GPR) is studied by the vibration signal and flow signal in six degraded states of the axial piston pump. For degradation state recognition, the variational mode decomposition (VMD) was used to decompose the vibration signal, and obtaining intrinsic mode function (IMF) components with rich information. Subsequently, multi-scale permutation entropy (MPE) was employed to select feature vectors of IMF components in different states. In order to reduce feature dimensions and improve recognition performance, ReliefF was used to select feature vectors with high weight, then a method based on multi-class Gaussian process classification was established by using these feature vectors to realize the research on the degradation state recognition. The test results demonstrate that the method can effectively identify the degradation state. Its recognition rate reaches 98.9%. Besides, for failure prediction, through the analysis of the wear process and wear mechanism of the valve plate, the curve fitting between the flow and the wear amount was performed by GPR to realize the failure prediction of the axial piston pump. Depending on the evaluation index, the GPR obtained a better failure prediction effect. The results will assist in the realization of predictive maintenance, and which also has significant practical value in project items.