A convolutional spiking neural network with adaptive coding for motor imagery classification

Electroencephalography (EEG) signals have been using for brain-computer interface applications for the last two decades. Motor imagery (MI) signals are one of the EEG signal types formed by imagining a limb's movement. Recently with the help of deep neural networks (DNN) for classifying MI signals using time-frequency (TF) features, considerable performance improvement has been reported. This paper proposes using a well-known TF representation technique called Constant-Q Transform (CQT) for the MI signal classification. Experiments conducted on BCI IV 2b dataset with DNN classifier using CQT spectrogram show that CQT outperforms traditional short-time Fourier transform (STFT) representation.

Brain-Computer Interfaces (BCI) based on Electroencephalography (EEG) signals, in particular motor imagery (MI) data have received a lot of attention and show the potential towards the design of key technologies both in healthcare and other industries. MI data is generated when a subject imagines movement of limbs and can be used to aid rehabilitation as well as in autonomous driving scenarios. Thus, classification of MI signals is vital for EEG-based BCI systems. Recently, MI EEG classification techniques using deep learning have shown improved performance over conventional techniques. However, due to inter-subject variability, the scarcity of unseen subject data, and low signal-to-noise ratio, extracting robust features and improving accuracy is still challenging. In this context, we propose a novel two-way few shot network that is able to efficiently learn how to learn representative features of unseen subject categories and how to classify them with limited MI EEG data. The pipeline includes an embedding module that learns feature representations from a set of samples, an attention mechanism for key signal feature discovery, and a relation module for final classification based on relation scores between a support set and a query signal. In addition to the unified learning of feature similarity and a few shot classifier, our method leads to emphasize informative features in support data relevant to the query data, which generalizes better on unseen subjects. For evaluation, we used the BCI competition IV 2b dataset and achieved an 9.3% accuracy improvement in the 20-shot classification task with state-of-the-art performance. Experimental results demonstrate the effectiveness of employing attention and the overall generality of our method.

Multi-source transfer learning via optimal transport feature ranking for EEG classification

Brain computer interface (BCI) aims at providing a brand new communication approach without brain's traditional output through nerve and muscle. "Electroencephalography" has been widely used for BCI system as it is a non-invasive approach. Recently, various classifiers have been used for the analysis of EEG signals measured under the planning and relaxed state. The major work addressed in the paper is the classification of EEG signals (motor imagery) measured under planning and relaxed state using advanced learning classifiers. The dataset of planning and relaxed state is a benchmark data and it is taken from UCI (University of California, Irvine) repository. Semi supervised ELM (SS-ELM) and unsupervised ELM (US-ELM) are recently developed networks and used for the EEG signal classification task. Both of these algorithms can be fit in to a unified framework and handle multi-class classification or multi-cluster clustering. SS-ELM algorithm performs better than US-ELM and other real valued algorithms in classifying planning and relaxed states. The improvement is due to the use of spectral techniques in embedding and clustering.

In recent years, the utilization of motor imagery (MI) signals derived from electroencephalography (EEG) has shown promising applications in controlling various devices such as wheelchairs, assistive technologies, and driverless vehicles. However, decoding EEG signals poses significant challenges due to their complexity, dynamic nature, and low signal-to-noise ratio (SNR). Traditional EEG pattern recognition algorithms typically involve two key steps: feature extraction and feature classification, both crucial for accurate operation. In this work, we propose a novel method that addresses these challenges by employing empirical mode decomposition (EMD) for feature extraction and a parallel convolutional neural network (PCNN) for feature classification. This approach aims to mitigate non-stationary issues, improve performance speed, and enhance classification accuracy. We validate the effectiveness of our proposed method using datasets from the BCI competition IV, specifically datasets 2a and 2b, which contain motor imagery EEG signals. Our method focuses on identifying two- and four-class motor imagery EEG signal classifications. Additionally, we introduce a transfer learning technique to fine-tune the model for individual subjects, leveraging important features extracted from a group dataset. Our results demonstrate that the proposed EMD-PCNN method outperforms existing approaches in terms of classification accuracy. We conduct both qualitative and quantitative analyses to evaluate our method. Qualitatively, we employ confusion matrices and various performance metrics such as specificity, sensitivity, precision, accuracy, recall, and f1-score. Quantitatively, we compare the classification accuracies of our method with those of existing approaches. Our findings highlight the superiority of the proposed EMD-PCNN method in accurately classifying motor imagery EEG signals. The enhanced performance and robustness of our method underscore its potential for broader applicability in real-world scenarios.

One of the essential challenges in brain–computer interface is to classify motor imagery (MI) signals. In this paper, an ensemble SVM-based voting system is proposed. In each line of this system, the EEG signal is transformed into different representations based on discrete cosine transform, Fourier transform, common spatial pattern, and empirical mode decomposition, and then these representations are combined in a triple-frame matrix. These frames are fed into a pre-trained deep convolutional neural network as a feature extractor. For each line, an SVM is employed to classify the extracted feature vectors. Finally, a decision is made based on voting between these SVMs. Performance of the proposed method is examined on the BCI Competition III dataset Iva to separate right hand and foot movement imagery. The simple proposed method achieves the average accuracy of 96.34% for all of the subjects, and 99.70% for the best situation that is an improvement in MI classification. In addition, it can be seen that right side of the brain is more effective than the other side in EEG-based MI classification.

Motor imagery brain-computer interfaces (MI-BCIs) have gained a lot of attention in recent years thanks to their potential to enhance rehabilitation and control of prosthetic devices for individuals with motor disabilities. However, accurate classification of motor imagery signals remains a challenging task due to the high inter-subject variability and non-stationarity in the electroencephalogram (EEG) data. In the context of MI-BCIs, with limited data availability, the acquisition of EEG data can be difficult. In this study, several data augmentation techniques have been compared with the proposed data augmentation technique adaptive cross-subject segment replacement (ACSSR). This technique, in conjunction with the proposed deep learning framework, allows for a combination of similar subject pairs to take advantage of one another and boost the classification performance of MI-BCIs. The proposed framework features a multi-domain feature extractor based on common spatial patterns with a sliding window and a parallel two-branch convolutional neural network. The performance of the proposed methodology has been evaluated on the multi-class BCI Competition IV Dataset 2a through repeated 10-fold cross-validation. Experimental results indicated that the implementation of the ACSSR method (80.47%) in the proposed framework has led to a considerable improvement in the classification performance compared to the classification without data augmentation (77.63%), and other fundamental data augmentation techniques used in the literature. The study contributes to the advancements for the development of effective MI-BCIs by showcasing the ability of the ACSSR method to address the challenges in motor imagery signal classification tasks.

Motor imagery EEG (MI-EEG) signal classification is one of the key challenges in Brain-computer interface (BCI) technology. Currently, MI-EEG signal analysis methods based on Riemannian geometry are usually based on a single symmetric positive definite (SPD) manifold. This approach offers a relatively simple geometric structure. However, it struggles to fully capture the complex geometric characteristics of MI-EEG signals. To address this, this paper introduces the Gaussian SPD manifold in addition to the classical SPD manifold. The method extracts more discriminative kernel features from both manifolds. These features are then fused for improved classification performance. The Gaussian SPD manifold models the traditional SPD manifold with a Gaussian distribution. By doing so, it can more accurately describe the statistical characteristics and variations of MI-EEG signals, compensating for the limitations of the single SPD manifold. The method was validated on the OpenBMI binary classification dataset, achieving an average classification accuracy of $80.8 \%$ with a standard deviation of $10.8 \%$. The approach presented in this paper provides a new perspective for the geometric analysis of MI-EEG signals, allowing for a deeper understanding and analysis of their complex geometric structure.

Brain-computer interface (BCI) systems create a novel communication method between humans and machines by translating human thoughts into actionable commands to control external devices. Motor imagery (MI) electroencephalogram (EEG) signals have significant applicability in various medical and non-medical industries, including stroke rehabilitation, wheelchair control, and drone operation. However, the practical application of EEG remains limited by the decoding performance and generalization ability of MI signalsThis study introduces a multi-branch self-attention network for motor imagery (MI) signal classification. Each branch independently processes EEG signals decomposed into distinct frequency bands through convolutional neural networks (CNNs) and multi-head self-attention (MHA) mechanisms, enabling the extraction of both fundamental and discriminative spatial-temporal features. To further capture dynamic temporal dependencies, long short-term memory (LSTM) networks are integrated. We systematically evaluate three signal decomposition ensemble empirical mode decomposition (EEMD), wavelet packet decomposition (WPD), and brain rhythm-based decomposition-to optimize feature representation. Extensive experiments on the BCI Competition IV 2a dataset demonstrate state-of-the-art performance, with subject-dependent and subject-independent accuracies of 84.04% and 71.67%, respectively. Comparative analyses against benchmark models (EEGNet, EEGTCNet, ShallowConvNet, etc.) validate the superiority of our approach in classification accuracy and generalization capabilityClinical relevance- This study investigates the methods for decoding motor imagery EEG signals and establishes the positive role of each module in classification. The improvement in accuracy can lead to better outcomes in medical applications such as controlling prosthetics, wheelchairs, and stroke rehabilitation.

Classification of Motor Imagery (MI) signals is the heart of Brain-Computer Interface (BCI) based applications. Spatial filtering is an important step in this process that produce new set of signals for better discrimination of two classes of EEG signals. In this work, a new approach of spatial filtering called Space-Frequency Localized Spatial Filtering (SFLSF) is proposed to enhance the performances of MI classification. The SFLSF method initially divides the scalp-EEG channels into local overlapping spatial windows. Then a filter bank is used to divide the signals into local frequency bands. The group of channels, localized in space and frequency, are then processed with spatial filter, and features are subsequently extracted for classification task. Experimental results corroborate that the proposed space localization helps to increase the classification accuracy when compared to the existing methods using spatial filters. The classification performance is further improved when frequency localization is incorporated. Thus, the proposed space-frequency localized approach of spatial filtering helps to deliver better classification result which is consistently 3-5% higher than traditional methods.

Chapter 8 - Ensemble Learning Approach to Motor Imagery EEG Signal Classification

Segment alignment based cross-subject motor imagery classification under fading data

By 2021, WHO projects over a billion incapacitated people, with 20% facing daily functional impairments.Brain-Computer Interface (BCI) offers effortless machine control via direct brain-computer interaction, with Motor Imagery (MI) Electroencephalogram (EEG) as the key BCI foundation.The MI EEG signals were collected from the BNCI horizon2020 database for nine participants.The MI EEG data includes four tasks: imaginative movement of the left hand, right hand, feet, and tongue.There are 22 EEG channels with a sampling rate of 250Hz in the data.The MI EEG signals were band-pass filtered with a lower cut-off frequency of 0.5 Hz and an upper cut-off frequency of 100 Hz.Based on the energy count threshold approach (ECTA) nine channels were identified as dominating channels from the filtered MI EEG signals.Energy values for each channel were extracted in the ECTA method for the 3-sec window.And if the energy value of a channel for a particular window is greater than 60% of the maximum channel's energy, then the energy count value will be incremented by one.Finally whichever channels had larger energy counts were identified as a dominant channel.On these nine dominant MI EEG signals discrete wavelet transform using Daubechies 4 mother wavelet a four-level decomposition is applied, and Mu and beta rhythms were extracted.For a 3-sec window from the nine dominant channels, the energy and entropy feature values from the Mu and Beta rhythms were extracted.From the extracted features, 80% of the data is used for training Linear Discriminant Analysis (LDA) and Support Vector Machine (SVM) and 20% for testing classifier models.Both the models performed well on the test data and the results obtained had a highest accuracy 91.72.7 for subject-9 and these results were compared with the existing methods.The obtained results of MI EEG signals classification using BCI holds potential for revolutionizing assistive technology, stroke rehabilitation, virtual reality gaming,

Motor imagery signals are one of the electroencephalography signals that occurs by subjects imagining the movement of a body limb and they used in brain computer interface applications. With the use of deep neural networks in motor imagery signal classification, classification performance has increased. Deep belief networks are one of the networks that increase performance. In this study, using a stacked autoencoders and BCI IV 2b dataset, a deep belief network and education method with more robust and higher performance is proposed. Average classification performance is obtained as 80.44%.

Advances in the field of Brain-Computer Interfaces (BCIs) aim, among other applications, to improve the movement capacities of people suffering from the loss of motor skills. The main challenge in this area is to achieve real-time and accurate bio-signal processing for pattern recognition, especially in Motor Imagery (MI). The significant interaction between brain signals and controllable machines requires instantaneous brain data decoding. In this study, an embedded BCI system based on fist MI signals is developed. It uses an Emotiv EPOC+ Brainwear®, an Altera SoCKit® development board, and a hexapod robot for testing locomotion imagery commands. The system is tested to detect the imagined movements of closing and opening the left and right hand to control the robot locomotion. Electroencephalogram (EEG) signals associated with the motion tasks are sensed on the human sensorimotor cortex. Next, the SoCKit processes the data to identify the commands allowing the controlled robot locomotion. The classification of MI-EEG signals from the F3, F4, FC5, and FC6 sensors is performed using a hybrid architecture of Convolutional Neural Networks (CNNs) and Long Short-Term Memory (LSTM) networks. This method takes advantage of the deep learning recognition model to develop a real-time embedded BCI system, where signal processing must be seamless and precise. The proposed method is evaluated using k-fold cross-validation on both created and public Scientific-Data datasets. Our dataset is comprised of 2400 trials obtained from four test subjects, lasting three seconds of closing and opening fist movement imagination. The recognition tasks reach 84.69% and 79.2% accuracy using our data and a state-of-the-art dataset, respectively. Numerical results support that the motor imagery EEG signals can be successfully applied in BCI systems to control mobile robots and related applications such as intelligent vehicles.