Comparison of algorithms for detecting hand movement from EEG signals

BackgroundFor severely paralyzed people, a brain-computer interface (BCI) provides a way of re-establishing communication. Although subjects with muscular dystrophy (MD) appear to be potential BCI users, the actual long-term effects of BCI use on brain activities in MD subjects have yet to be clarified. To investigate these effects, we followed BCI use by a chronic tetraplegic subject with MD over 5 months. The topographic changes in an electroencephalogram (EEG) after long-term use of the virtual reality (VR)-based BCI were also assessed. Our originally developed BCI system was used to classify an EEG recorded over the sensorimotor cortex in real time and estimate the user's motor intention (MI) in 3 different limb movements: feet, left hand, and right hand. An avatar in the internet-based VR was controlled in accordance with the results of the EEG classification by the BCI. The subject was trained to control his avatar via the BCI by strolling in the VR for 1 hour a day and then continued the same training twice a month at his home.ResultsAfter the training, the error rate of the EEG classification decreased from 40% to 28%. The subject successfully walked around in the VR using only his MI and chatted with other users through a voice-chat function embedded in the internet-based VR. With this improvement in BCI control, event-related desynchronization (ERD) following MI was significantly enhanced (p < 0.01) for feet MI (from -29% to -55%), left-hand MI (from -23% to -42%), and right-hand MI (from -22% to -51%).ConclusionsThese results show that our subject with severe MD was able to learn to control his EEG signal and communicate with other users through use of VR navigation and suggest that an internet-based VR has the potential to provide paralyzed people with the opportunity for easy communication.

Brain Computer Interfaces (BCIs) have several applications. One of the most crucial domains that BCIs cater to is prosthetics, orthotics and rehabilitation devices. Such devices aim to better the lives of specially-abled people. Motor Imagery or Movement Intention (MI) neural signals are collected to obtain a better insight of the underlying neural activities. EEG is the most popular modality for obtaining neural signals due to its advantages like non-invasiveness, portability, and the ease of use. The utilization of MI EEG signals to design BCIs has been heavily exploited. Spectral estimation methods have been exploited to delineate different MI tasks. This article focusses on exploring channel-wise temporal and spectral features of MI EEG signals. A rich MI EEG dataset involving five different motor imageries has been utilized in this study. The analysis based upon channel-wise temporal and spectral decomposition involves two major biomarkers, Event Related Spectral Perturbation (ERSP) and Inter Trial Coherence (ITC). ERSP can be considered as a generalization of power increase and decrease within a frequency range of interest. ITC reflects consistency of rhythms across the trials. This article aims to exploit ERSP and ITC methods to explore relevant time segment, frequency range and informative channels associated to MI signatures.

Motor imagery EEG recognition based on conditional optimization empirical mode decomposition and multi-scale convolutional neural network

The design and analysis of software which implements digital signal processing (DSP) algorithms on multiprocessor systems is examined. The DSP algorithms that are considered exhibit certain characteristics which are common of DSP algorithms used in communication and control systems. The analysis methods developed use linear complexity algorithms to analyze the software that implements the DSP algorithms. The first step involves finding the repeat factors associated with a basic cycle of the algorithm. Using these repeat factors it is straightforward to (1) find the precedence relationships between tasks and finally a feasible schedule for the multiprocessor, and (2) coordinate and organize the efforts to optimize the software. >

EEG signal is one of the biological signals that can be useful to control wearable robotic devices, according to the human motion intention. However, the real-time estimation of the user's motion intention from EEG signals is cumbersome. The user's motion intention might not be estimated when the user does not concentrate on the control of the robot, distracted by other things or disturbed by the outside interferences. In this paper, a neural network based real-time estimation method is proposed to detect human motion intention in terms of intended task, using EEG signals. The inputs of bandpower time series signals let the neural network identify the dynamic nature of the tasks performed. Experimental details, methodology and the prediction results are presented.

In brain–computer interfaces (BCIs), it is crucial to process brain signals to improve the accuracy of the classification of motor movements. Machine learning (ML) algorithms such as artificial neural networks (ANNs), linear discriminant analysis (LDA), decision tree (D.T.), K-nearest neighbor (KNN), naive Bayes (N.B.), and support vector machine (SVM) have made significant progress in classification issues. This paper aims to present a signal processing analysis of electroencephalographic (EEG) signals among different feature extraction techniques to train selected classification algorithms to classify signals related to motor movements. The motor movements considered are related to the left hand, right hand, both fists, feet, and relaxation, making this a multiclass problem. In this study, nine ML algorithms were trained with a dataset created by the feature extraction of EEG signals.The EEG signals of 30 Physionet subjects were used to create a dataset related to movement. We used electrodes C3, C1, CZ, C2, and C4 according to the standard 10-10 placement. Then, we extracted the epochs of the EEG signals and applied tone, amplitude levels, and statistical techniques to obtain the set of features. LabVIEW™2015 version custom applications were used for reading the EEG signals; for channel selection, noise filtering, band selection, and feature extraction operations; and for creating the dataset. MATLAB 2021a was used for training, testing, and evaluating the performance metrics of the ML algorithms. In this study, the model of Medium-ANN achieved the best performance, with an AUC average of 0.9998, Cohen’s Kappa coefficient of 0.9552, a Matthews correlation coefficient of 0.9819, and a loss of 0.0147. These findings suggest the applicability of our approach to different scenarios, such as implementing robotic prostheses, where the use of superficial features is an acceptable option when resources are limited, as in embedded systems or edge computing devices.

Existing research methods for recognizing EEG (Electroencephalogram) signals in motor imagery (MI) often overlook the dynamic changes of brain networks over time, resulting in insufficient classification accuracy for MI tasks. This article addresses the recognition problem of dynamic changes in brain networks during MI tasks and applies an EEG signal classification method based on multi-layer time-varying functional brain networks. This article uses the BCI (Brain-Computer Interface) Competition IV 2a dataset to preprocess the raw EEG signals through bandpass filtering and CSP (Common Spatial Pattern) algorithm. The EEG signals of the MI task are divided into 7 1-second time windows with a step size of 0.5 seconds. Within each time window, Pearson correlation coefficients between EEG channels can be calculated to generate corresponding brain networks, and multiple time-varying functional brain networks can be constructed by stacking the brain networks from multiple time windows. The network topology features, node degree, clustering coefficient, network efficiency, and multi-layer network features of each window can be extracted, including Multiplex Clustering Coefficient (MCC), Multiplex Participation Coefficient (MPC), and inter layer correlation coefficient. By dividing the dataset through 10 fold cross validation, the random forest algorithm can be used to classify and recognize four types of motion imagination tasks. The experimental results show that the average recognition rate of the article’s method in four types of MI tasks reached 89.19%. This method can improve the classification accuracy of MI tasks and enhance a comprehensive understanding of the dynamic changes in brain networks during the process of MI.

The electroencephalogram (EEG) signal is a medium to realize a brain-computer interface (BCI) system due to its zero clinical risk and portable acquisition devices. Current EEG-based BCI research usually requires a subject-specific adaptation step before a BCI can be employed by a new user. In contrast, the subject-independent scenario, where a well trained model can be directly applied to new users without precalibration, is particularly desired. Considering this critical gap, the focus in this letter is developing an effective EEG signal analysis adaptively applied to subject-independent settings. We present a convolutional recurrent attention model (CRAM) that utilizes a convolutional neural network to encode the high-level representation of EEG signals and a recurrent attention mechanism to explore the temporal dynamics of the EEG signals as well as to focus on the most discriminative temporal periods. Extensive experiments on a benchmark multiclass EEG dataset containing four movement intentions indicate that the proposed model is capable of exploiting the underlying invariant EEG patterns across different subjects and generalizing the patterns to new subjects with better performance than a series of state-of-the-art and baseline approaches by at least eight percentage points. The implementation code is made publicly available. <sup xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">11</sup> https://github.com/dalinzhang/CRAM.

This paper presents a wireless universal brain-machine interface (BMI) system. The proposed system integrates three main modules, including an electroencephalogram (EEG) signal analyzer, a neural stimulator, and a PC user interface. Its functionalities include EEG signal acquisition, digital signal processing, electrical stimulation and so on. It can continuously monitor EEG signal status in real time, quickly diagnose brain abnormal activities and correctly generate a proper stimulation if needed. In the EEG signal analyzer, the EEG signal acquisition pathway consists of a four-channel analog front-end featuring high gain and high CMRR. Under the control of an MCU, EEG data are transmitted to the PC in real time through a Bluetooth connection. Then the PC analyzes the EEG signals through the algorithm based on the new Teager energy operator and multiscale entropy. The neural stimulator can provide both positive and negative current stimulations which have programmable pulse width and frequency. Experiment results show that the neural stimulator can generate ±1 mA stimulation current output at ±5 V supply voltage.

BackgroundA novel artefact removal algorithm is proposed for a self-paced hybrid brain-computer interface (BCI) system. This hybrid system combines a self-paced BCI with an eye-tracker to operate a virtual keyboard. To select a letter, the user must gaze at the target for at least a specific period of time (dwell time) and then activate the BCI by performing a mental task. Unfortunately, electroencephalogram (EEG) signals are often contaminated with artefacts. Artefacts change the quality of EEG signals and subsequently degrade the BCI’s performance.MethodsTo remove artefacts in EEG signals, the proposed algorithm uses the stationary wavelet transform combined with a new adaptive thresholding mechanism. To evaluate the performance of the proposed algorithm and other artefact handling/removal methods, semi-simulated EEG signals (i.e., real EEG signals mixed with simulated artefacts) and real EEG signals obtained from seven participants are used. For real EEG signals, the hybrid BCI system’s performance is evaluated in an online-like manner, i.e., using the continuous data from the last session as in a real-time environment.ResultsWith semi-simulated EEG signals, we show that the proposed algorithm achieves lower signal distortion in both time and frequency domains. With real EEG signals, we demonstrate that for dwell time of 0.0s, the number of false-positives/minute is 2 and the true positive rate (TPR) achieved by the proposed algorithm is 44.7%, which is more than 15.0% higher compared to other state-of-the-art artefact handling methods. As dwell time increases to 1.0s, the TPR increases to 73.1%.ConclusionsThe proposed artefact removal algorithm greatly improves the BCI’s performance. It also has the following advantages: a) it does not require additional electrooculogram/electromyogram channels, long data segments or a large number of EEG channels, b) it allows real-time processing, and c) it reduces signal distortion.

Non-invasive brain-computer interfaces (BCIs) have been widely used for neural decoding, linking neural signals to control devices. Hybrid BCI systems using electroencephalography (EEG) and functional near-infrared spectroscopy (fNIRS) have received significant attention for overcoming the limitations of EEG- and fNIRS-standalone BCI systems. However, most hybrid EEG-fNIRS BCI studies have focused on late fusion because of discrepancies in their temporal resolutions and recording locations. Despite the enhanced performance of hybrid BCIs, late fusion methods have difficulty in extracting correlated features in both EEG and fNIRS signals. Therefore, in this study, we proposed a deep learning-based early fusion structure, which combines two signals before the fully-connected layer, called the fNIRS-guided attention network (FGANet). First, 1D EEG and fNIRS signals were converted into 3D EEG and fNIRS tensors to spatially align EEG and fNIRS signals at the same time point. The proposed fNIRS-guided attention layer extracted a joint representation of EEG and fNIRS tensors based on neurovascular coupling, in which the spatially important regions were identified from fNIRS signals, and detailed neural patterns were extracted from EEG signals. Finally, the final prediction was obtained by weighting the sum of the prediction scores of the EEG and fNIRS-guided attention features to alleviate performance degradation owing to delayed fNIRS response. In the experimental results, the FGANet significantly outperformed the EEG-standalone network. Furthermore, the FGANet has 4.0% and 2.7% higher accuracy than the state-of-the-art algorithms in mental arithmetic and motor imagery tasks, respectively.

Electroencephalography (EEG)-based control has emerged as a promising solution for intuitive and non-invasive control of assistive robotic devices, particularly for individuals with severe limb loss or neuromuscular impairments where muscle signals are unavailable. This paper presents the design and development of a low-cost, lightweight 3D-printed prosthetic arm controlled exclusively by EEG signals. The proposed system decodes user movement intention directly from brain activity using signal processing, sensor fusion, and adaptive machine learning techniques. EEG signals are acquired through a non—invasive multi-channel headset, conditioned to suppress artifacts, and transformed into meaningful features representing motor imagery and movement intention. To improve reliability and reduce noise sensitivity inherent in EEG signals, multiple signal fusion and filtering techniques—including averaging, weighted averaging, Principal Component Analysis (PCA), and Kalman filtering—are investigated. Experimental results demonstrate that Kalman filter-based fusion significantly enhances signal stability and control accuracy in real-time prosthetic operation. The prosthetic arm employs a modular 3D-printed mechanical structure with servo-driven actuation, ensuring affordability and customization. Additionally, a future bidirectional feedback framework based on deep learning is proposed to enhance user adaptation and sensory perception. This work contributes toward accessible, intelligent, and fully brain-controlled prosthetic systems for medical rehabilitation and assistive healthcare.

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.

Multi-channel Electroencephalograph (EEG) signal is an important source of neural information for motor imagery (MI) limb movement intent decoding. The decoded MI movement intent often serve as potential control input for brain-computer interface (BCI) based rehabilitation robots. However, the presence of multiple dynamic artifacts in EEG signal leads to serious processing challenge that affects the BCI system in practical settings. Hence, this study propose a hybrid approach based on Low-rank spatiotemporal filtering technique for concurrent elimination of multiple EEG artifacts. Afterwards, a convolutional neural network based deep learning model (ConvNet-DL) that extracts neural information from the cleaned EEG signal for MI tasks decoding was built. The proposed method was studied in comparison with existing artifact removal methods using EEG signals of transhumeral amputees who performed five different MI tasks. Remarkably, the proposed method led to significant improvements in MI task decoding accuracy for the ConvNet-DL model in the range of 8.00~13.98%, while up to 14.38% increment was recorded in terms of the MCC: Mathew correlation coefficients at p<0.05. Also, a signal to error ratio of more than 11 dB was recorded by the proposed method.Clinical Relevance- This study showed that a combination of the proposed hybrid EEG artifact removal method and ConvNet-DL can significantly improve the decoding accuracy of MI upper limb movement tasks. Our findings may provide potential control input for BCI rehabilitation robotic systems.

Recent advances in deep learning have had a methodological and practical impact on brain-computer interface (BCI) research. Among the various deep network architectures, convolutional neural networks (CNNs) have been well suited for spatio-spectral-temporal electroencephalogram (EEG) signal representation learning. Most of the existing CNN-based methods described in the literature extract features at a sequential level of abstraction with repetitive nonlinear operations and involve densely connected layers for classification. However, studies in neurophysiology have revealed that EEG signals carry information in different ranges of frequency components. To better reflect these multi-frequency properties in EEGs, we propose a novel deep multi-scale neural network that discovers feature representations in multiple frequency/time ranges and extracts relationships among electrodes, i.e., spatial representations, for subject intention/condition identification. Furthermore, by completely representing EEG signals with spatio-spectral-temporal information, the proposed method can be utilized for diverse paradigms in both active and passive BCIs, contrary to existing methods that are primarily focused on single-paradigm BCIs. To demonstrate the validity of our proposed method, we conducted experiments on various paradigms of active/passive BCI datasets. Our experimental results demonstrated that the proposed method achieved performance improvements when judged against comparable state-of-the-art methods. Additionally, we analyzed the proposed method using different techniques, such as PSD curves and relevance score inspection to validate the multi-scale EEG signal information capturing ability, activation pattern maps for investigating the learned spatial filters, and t-SNE plotting for visualizing represented features. Finally, we also demonstrated our method's application to real-world problems. Based on our experimental results and analyses, we believe that the proposed multi-scale neural network can be useful for various BCI paradigms, as a starting model or as a backbone network in any new BCI experiments.