Classification Of Brain Signals Research Articles

Fuzzy deep learning for modeling uncertainty in character recognition using EEG signals

Classification of brain signals for character recognition is a challenging task associated with uncertainties. This study aims to present an Improved Type-2 Fuzzy Deep Learning (IT2FDL) framework for uncertainty management in character recognition using EEG signals by learning rules from each other in the learning layer. The Evolutionary Algorithm (EA) was employed for this study's optimum design of the proposed IT2FDL model. This algorithm was used to determine the T2F set parameters. The model parameters were tuned by Parallel Swarm Optimization (PSO) Algorithm. The present framework optimized the fusion layer of the model. This layer is a multi-layered Recurrent Type2 Fuzzy Neural Network (RT2FNN) with a learning layer composed of RNN cells. For performance evaluation, the models were examined using three public databases: BCI Competition III-Dataset II, BCI Competition II-Dataset IIb, and EEG Dataset. The optimized IT2FDL model outperformed the counterpart models with a significant improvement of test score of 2.5% for Competition III-Dataset II at epoch 15, 2.5% for Competition II-Dataset IIb at epoch 3, and 1% for EEG Dataset at epoch 15. The proposed IT2FDL-PSO (GRU) model showed a mean test score of 96.2% at epoch 15 for all 58 subjects, which outperformed other models with many subjects for character recognition.

Supervised machine learning algorithms for brain signal classification

Supervised machine learning algorithms for brain signal classification

E‐CNNet: Time‐reassigned Multisynchrosqueezing transform‐based deep learning framework for MI‐BCI task classification

AbstractThe classification of electroencephalograms‐based motor imagery signals poses a significant issue in the design and development of brain‐computer interfaces. Neural Networks are observed to be successful in classification of motor imagery brain signals. However, the existing motor imagery data sets are of limited size and suffer from low signal to noise ratio. Hence, to achieve high performance with small datasets, this paper proposes a novel combination of time frequency analysis along with deep learning network to perform the brain signal classification task. The proposed framework consists of two parts: (1) Time‐reassigned Multisynchrosqueezing Transform to efficiently capture the dynamic properties of non‐stationary EEG; and (2) A new hybrid model E‐CNNet is proposed for feature extraction and classification of brain signals. A robust classification pipeline is constructed to classify the extracted features into respective motor imagery tasks. Ensemble of boosting classifiers is used to generate the final predictions, thus, reducing the variance and bias of individual classifiers. The performance of the proposed methodology is evaluated using two publicly available datasets: BCI competition III, dataset IIIa and BCI competition IV, dataset IIa. We have obtained the average classification accuracy of 94.44% on BCI competition III, dataset IIIa and 89.25% on BCI competition IV, dataset IIa.

A DM-ELM based classifier for EEG brain signal classification for epileptic seizure detection

ABSTRACT Epilepsy is one of the dreaded conditions that had taken billions of people under its cloud worldwide. Detecting the seizure at the correct time in an individual is something that medical practitioners focus in order to help people save their lives. Analysis of the Electroencephalogram (EEG) signal from the scalp area of the human brain can help in detecting the seizure beforehand. This paper presents a novel classification technique to classify EEG brain signals for epilepsy identification based on Discrete Wavelet Transform and Moth Flame Optimization-based Extreme Learning Machine (DM-ELM). ELM is a very popular machine learning method based on Neural Networks (NN) where the model is trained rigorously to get the minimized error rate and maximized accuracy. Here we have used several experimental evaluations to compare the performance of basic ELM and DM-ELM and it has been experimentally proved that DM-ELM outperforms basic ELM but with few time constraints.

Classification of Epileptic Brain Signals of College Students Based on Deep Learning

Epilepsy, as a common nervous system disease in the world, urgently needs effective methods for diagnosis and treatment. Scalp electroencephalogram (EEG) contains a lot of physiological and pathological information, which plays a very important role in the diagnosis of brain diseases such as epilepsy. At present, the clinical analysis of EEG signal is mainly based on the clinician’s visual analysis, which makes the clinician’s task heavy, and there is no quantitative standard for the analysis results. Therefore, the automatic classification of epileptic EEG signals has great potential in current clinical application. Based on the deep learning VGG16 convolutional neural network model, a method for automatic detection of seizure signals is proposed in this paper. Firstly, the samples are preprocessed, then enter the VGG16 convolutional neural network model for training, and finally input the validation set for validation. The experimental results indicate that this model can distinguish the pre-ictal EEG, interictal EEG and ictal EEG.

An automated deep learning enabled brain signal classification for epileptic seizure detection on complex measurement systems

Recent advancements in machine learning and deep learning models find them helpful in designing effective complex measurement systems. At the same time, examining the brain’s activities using Electroencephalography (EEG) is essential to determine the mental state or thought of a person. It is essential in several application areas, such as Brain-Computer Interface (BCI), emotion recognition, and mental disease diagnosis. The proper brain signal classification using EEG finds helpful diagnose epileptic seizures. Since the traditional seizure detection process is a lengthy and challenging task, the automated identification of epilepsy is a significant problem. In order to resolve the issues that exist in the traditional brain signal classification models, this study designs Automated Deep Learning-Enabled Brain Signal Classification for Epileptic Seizure Detection (ADLBSC-ESD). The proposed ADLBSC-ESD technique aims to classify the brain signals to determine the existence of seizures or not. In addition, the presented model involves the design of the Improved Teaching and Learning-Enabled Optimization (ITLBO) technique for selecting features from EEG signals. Moreover, the Deep Belief Network (DBN) model is used for an effectual classification of EEG signals, and the hyperparameters of the DBN model are optimally tuned using the Swallow Swarm Optimization Algorithm (SSA). In order to ensure the improved brain signal classification performance of the ADLBSC-ESD technique, a series of simulations take place, and the outcomes are investigated concerning different measures. The experimental values highlighted the better performance of the ADLBSC-ESD technique over the current state of art techniques with maximum accuracy of 0.8316 and 0.8609 under binary and multiple classes, respectively.

Multi-class classification of action intention understanding brain signals based on thresholding graph metric

BACKGROUND: Classification of action intention understanding is extremely important for human computer interaction. Many studies on the action intention understanding classification mainly focus on binary classification, while the classification accuracy is often unsatisfactory, not to mention multi-class classification. METHOD: To complete the multi-class classification task of action intention understanding brain signals effectively, we propose a novel feature extraction procedure based on thresholding graph metric. RESULTS: Both the alpha frequency band and full-band obtained considerable classification accuracies. Compared with other methods, the novel method has better classification accuracy. CONCLUSIONS: Brain activity of action intention understanding is closely related to the alpha band. The new feature extraction procedure is an effective method for the multi-class classification of action intention understanding brain signals.

Analyzing Classification Performance of fNIRS-BCI for Gait Rehabilitation Using Deep Neural Networks.

This research presents a brain-computer interface (BCI) framework for brain signal classification using deep learning (DL) and machine learning (ML) approaches on functional near-infrared spectroscopy (fNIRS) signals. fNIRS signals of motor execution for walking and rest tasks are acquired from the primary motor cortex in the brain’s left hemisphere for nine subjects. DL algorithms, including convolutional neural networks (CNNs), long short-term memory (LSTM), and bidirectional LSTM (Bi-LSTM) are used to achieve average classification accuracies of 88.50%, 84.24%, and 85.13%, respectively. For comparison purposes, three conventional ML algorithms, support vector machine (SVM), k-nearest neighbor (k-NN), and linear discriminant analysis (LDA) are also used for classification, resulting in average classification accuracies of 73.91%, 74.24%, and 65.85%, respectively. This study successfully demonstrates that the enhanced performance of fNIRS-BCI can be achieved in terms of classification accuracy using DL approaches compared to conventional ML approaches. Furthermore, the control commands generated by these classifiers can be used to initiate and stop the gait cycle of the lower limb exoskeleton for gait rehabilitation.

A new dynamically convergent differential neural network for brain signal recognition

In this paper, a dynamically convergent differential neural network (DCDNN) is proposed for P300 brain signal classification, which can be applied to brain-computer interface (BCI) systems. Being different from most of state-of-the-art neural networks with thousands of parameters to adjust, the proposed neural network possesses fast training rate since it is a lightweight neural network. In the framework, data preprocessing includes time window interception, bandpass filtering, moving average filtering and training set balance. After that, feature extraction based on PCA is used, and an ensemble DCDNN (E-DCDNN) is proposed for classification. The proposed framework can effectively increase signal-to-noise ratio (SNR), reduce classification dimension without distortion, and eliminate classifier variability. In this work, the proposed framework achieves 100% and 98% accuracy on Data Set IIb of BCI Competition II and Data Set II of BCI Competition III, which mean the state-of-the-art character recognition performance in existing methods.

An empirical comparison of machine learning algorithms for the classification of brain signals to assess the impact of combined yoga and Sudarshan Kriya

Today’s fast paced life reports so much stress among people that it may lead to various psychological and physical illnesses. Yoga and meditation are the best strategies to reduce the effect of stress on physical and mental level without any side-effects. In this study, combined yoga and Sudarshan Kriya (SK) has been used as an alternative and complementary therapy for the management of stress. The aim of the study is to find a method to classify the meditator and non-meditator states with the best accuracy. The 50 subjects have been participating in this study and divided into two groups, i.e. study and control group. The subjects with regular practice of Yoga and SK are known as meditators and the ones without any practice of yoga and meditation were known as non-meditators. Electroencephalogram (EEG) signals were acquired from these both groups before and after 3 months. The statistical parameters were computed from these acquired EEG signals using Discrete Wavelet Transform (DWT). These extracted statistical parameters were given as input to the classifiers. The decision tree, discriminant analysis, logistic regression, Support Vector Machine (SVM), Weighted K- Nearest Neighbour (KNN) and ensemble classifiers were used for classification of meditator and non- meditator states from the acquired EEG signals. The results have demonstrated that the SVM method gives the highest classification accuracy as compared to other classifiers. The proposed method can be used as a diagnosis system in clinical practices.

Wireless Soft Scalp Electronics and Virtual Reality System for Motor Imagery-Based Brain-Machine Interfaces.

Motor imagery offers an excellent opportunity as a stimulus‐free paradigm for brain–machine interfaces. Conventional electroencephalography (EEG) for motor imagery requires a hair cap with multiple wired electrodes and messy gels, causing motion artifacts. Here, a wireless scalp electronic system with virtual reality for real‐time, continuous classification of motor imagery brain signals is introduced. This low‐profile, portable system integrates imperceptible microneedle electrodes and soft wireless circuits. Virtual reality addresses subject variance in detectable EEG response to motor imagery by providing clear, consistent visuals and instant biofeedback. The wearable soft system offers advantageous contact surface area and reduced electrode impedance density, resulting in significantly enhanced EEG signals and classification accuracy. The combination with convolutional neural network‐machine learning provides a real‐time, continuous motor imagery‐based brain–machine interface. With four human subjects, the scalp electronic system offers a high classification accuracy (93.22 ± 1.33% for four classes), allowing wireless, real‐time control of a virtual reality game.

Epileptic Seizure Detection on an Ultra-Low-Power Embedded RISC-V Processor Using a Convolutional Neural Network.

The treatment of refractory epilepsy via closed-loop implantable devices that act on seizures either by drug release or electrostimulation is a highly attractive option. For such implantable medical devices, efficient and low energy consumption, small size, and efficient processing architectures are essential. To meet these requirements, epileptic seizure detection by analysis and classification of brain signals with a convolutional neural network (CNN) is an attractive approach. This work presents a CNN for epileptic seizure detection capable of running on an ultra-low-power microprocessor. The CNN is implemented and optimized in MATLAB. In addition, the CNN is also implemented on a GAP8 microprocessor with RISC-V architecture. The training, optimization, and evaluation of the proposed CNN are based on the CHB-MIT dataset. The CNN reaches a median sensitivity of 90% and a very high specificity over 99% corresponding to a median false positive rate of 6.8 s per hour. After implementation of the CNN on the microcontroller, a sensitivity of 85% is reached. The classification of 1 s of EEG data takes and consumes an average power of . The proposed detector outperforms related approaches in terms of power consumption by a factor of 6. The universal applicability of the proposed CNN based detector is verified with recording of epileptic rats. This results enable the design of future medical devices for epilepsy treatment.

SeizSClas: An Efficient and Secure Internet-of-Things-Based EEG Classifier

The Internet of Things (IoT) is one of the fastest growing areas of research. Considering the IoT and healthcare simultaneously, classifying brain signals using smart IoT sensors is one of the standing nontrivial problems of literature. The issue is further exacerbated by noise in brain signals, and there is no efficient solution for classifying brain signals as seizorous or nonseizorous, yet. Moreover, research has mostly ignored the security and privacy aspect of this problem. Therefore, in this article, we try to bridge this gap and present a secure privacy-preserving technique for brain signal classification. We first transform a brain signal into an image. Subsequently, we apply transfer learning to solve the classification problem. To do that, we use the pretrained VGG-19 as a base model. In addition, we discuss a scheme to store images in a blockchain so as to make the overall architecture privacy aware. By conducting comprehensive numerical simulations on a supercomputer and using the famous TUH Abnormal EEG data set, we show the efficacy of the proposed work. The work presented here not only makes the storage of patient data secure and private but also outperforms all existing techniques in terms of classification accuracy.

Exploiting sparse representation in the P300 speller paradigm

A Brain-Computer Interface (BCI) aims to produce a new way for people to communicate with computers. Brain signal classification is a challenging issue owing to the high-dimensional data and low Signal-to-Noise Ratio (SNR). In this paper, a novel method is proposed to cope with this problem through sparse representation for the P300 speller paradigm. This work is distinguished using two key contributions. First, we investigate sparse coding and its feasibility for brain signal classification. Training signals are used to learn the dictionaries and test signals are classified according to their sparse representation and reconstruction errors. Second, sample selection and a channel-aware dictionary are proposed to reduce the effect of noise, which can improve performance and enhance the computing efficiency simultaneously. A novel classification method from the sample set perspective is proposed to exploit channel correlations. Specifically, the brain signal of each channel is classified jointly using its spatially neighboring channels and a novel weighted regulation strategy is proposed to overcome outliers in the group. Experimental results have demonstrated that our methods are highly effective. We achieve a state-of-the-art recognition rate of 72.5%, 88.5%, and 98.5% at 5, 10, and 15 epochs, respectively, on BCI Competition III Dataset II.

Dual stream neural networks for brain signal classification

Objective. The primary objective of this work is to develop a neural nework classifier for arbitrary collections of functional neuroimaging signals to be used in brain–computer interfaces (BCIs). Approach. We propose a dual stream neural network (DSNN) for the classification problem. The first stream is an end-to-end classifier taking raw time-dependent signals as input and generating feature identification signatures from them. The second stream enhances the identified features from the first stream by adjoining a dynamic functional connectivity matrix aimed at incorporating nuanced multi-channel information during specified BCI tasks. Main results. The proposed DSNN classifier is benchmarked against three publicly available datasets, where the classifier demonstrates performance comparable to, or better than the state-of-art in each instance. An information theoretic examination of the trained network is also performed, utilizing various tools, to demonstrate how to glean interpretive insight into how the hidden layers of the network parse the underlying biological signals. Significance . The resulting DSNN is a subject-independent classifier that works for any collection of 1D functional neuroimaging signals, with the option of integrating domain specific information in the design.

Time-resolved classification of dog brain signals reveals early processing of faces, species and emotion

Dogs process faces and emotional expressions much like humans, but the time windows important for face processing in dogs are largely unknown. By combining our non-invasive electroencephalography (EEG) protocol on dogs with machine-learning algorithms, we show category-specific dog brain responses to pictures of human and dog facial expressions, objects, and phase-scrambled faces. We trained a support vector machine classifier with spatiotemporal EEG data to discriminate between responses to pairs of images. The classification accuracy was highest for humans or dogs vs. scrambled images, with most informative time intervals of 100–140 ms and 240–280 ms. We also detected a response sensitive to threatening dog faces at 30–40 ms; generally, responses differentiating emotional expressions were found at 130–170 ms, and differentiation of faces from objects occurred at 120–130 ms. The cortical sources underlying the highest-amplitude EEG signals were localized to the dog visual cortex.

BCI 제어를 위한 뇌신호 분류에서의 딥러닝 모델 개발

BCI 제어를 위한 뇌신호 분류에서의 딥러닝 모델 개발

Brain signal classification for creative tasks

We tried to determine if emotive self-feedback from conscious assessment of artists’ own works generates sufficient impetus for accomplishment of goals. Self-reports from participants of an ‘experimental’ group working independently and without external feedback on their work are examined. The performance of this group is compared to ‘control’ performers in tutored sessions (with external feedback). On the whole a two-fold analysis was carried out. First, verbal reports of the participants’ feelings about their work in both experimental and control settings were analyzed. Second, a brainwave analysis of each participant was conducted while they were engaged in the same tasks so as to examine effects of concentration and energy output. The Hilbert-Huang transform was used to filter data frequency for brainwaves emitted at channels AF4, AF3, F6 and F7, all positioned along the pre-frontal cortex. Results of participants’ brainwave behavior within frequency ranges of 14–16 Hz, as well as for higher ranges (above 60 Hz), do not show significant difference in the two groups. This indicates that brainwave activity is sustained in individuals who depend on self-feedback appraisals, at least within the domain of creativity investigated in this paper.

On the use of pairwise distance learning for brain signal classification with limited observations.

The increasing access to brain signal data using electroencephalography creates new opportunities to study electrophysiological brain activity and perform ambulatory diagnoses of neurological disorders. This work proposes a pairwise distance learning approach for schizophrenia classification relying on the spectral properties of the signal. To be able to handle clinical trials with a limited number of observations (i.e. case and/or control individuals), we propose a Siamese neural network architecture to learn a discriminative feature space from pairwise combinations of observations per channel. In this way, the multivariate order of the signal is used as a form of data augmentation, further supporting the network generalization ability. Convolutional layers with parameters learned under a cosine contrastive loss are proposed to adequately explore spectral images derived from the brain signal. The proposed approach for schizophrenia diagnostic was tested on reference clinical trial data under resting-state protocol, achieving 0.95 ± 0.05 accuracy, 0.98 ± 0.02 sensitivity and 0.92 ± 0.07 specificity. Results show that the features extracted using the proposed neural network are remarkably superior than baselines to diagnose schizophrenia (+20pp in accuracy and sensitivity), suggesting the existence of non-trivial electrophysiological brain patterns able to capture discriminative neuroplasticity profiles among individuals. The code is available on Github: https://github.com/DCalhas/siamese_schizophrenia_eeg.

Brain Signal Classification Based on Deep CNN

It is essential to increase the accuracy and robustness of classification of brain data, including EEG, in order to facilitate a direct communication between the human brain and computerized devices. Different machine learning approaches, such as support vector machine (SVM), neural network, and linear discrimination analysis (LDA), have been applied to set up automatic subjective-classifier, and the findings for their capacities in this regard have been inconclusive. The present study developed an effective classifier for human mental status using deep learning in a convolutional neural network. In contrast to most previous studies commonly using EEG waveform or numeric value of brain signals for classification, the authors utilised imaging features generated from EEG data at alpha frequency band. A new model proposed in this study provides a simple and computationally efficient approach to distinguish mental status during resting. With training, this model could predict new 2D EEG images with above 90% accuracy, while traditional machine learning techniques failed to achieve this accuracy.