Figure - available from: Frontiers in Neuroscience
This content is subject to copyright.
Source publication
In recent years, brain–computer interface (BCI) is expected to solve the physiological and psychological needs of patients with motor dysfunction with great individual differences. However, the classification method based on feature extraction requires a lot of prior knowledge when extracting data features and lacks a good measurement standard, whi...
Similar publications
A brain-computer interface (BCI) user awareness of an error is associated with a cortical signature named error-related potential (ErrP). The incorporation of ErrPs' detection in BCIs can improve BCIs' performance.
Objective:
This work is three-folded. First, we investigate if an ErrP classifier is transferable from able-bodied participants to pa...
Attention Deficit Hyperactivity Disorder (ADHD) isa neurodevelopmental disorder affecting a certain amount ofchildren and their way of living. A novel method to treat thisdisorder is to use Brain-Computer Interfaces (BCI) throughoutthe patient learns to self-regulate his symptoms by herself. Inthis context, researches have led to tools aiming to es...
Citations
... The superiority of DL in signal processing has prompted researchers to adopt end-to-end algorithms based on the backpropagation mechanism for classification (Wang et al., 2020;Tang et al., 2023b;Zhang H. et al., 2023;. A multitude of models have been devised which transfigure unprocessed EEG signals into spatial-spectral-temporal forms for categorization, including CNN (Hossain et al., 2023), ANN (Subasi, 2005), and EEGNET (Lawhern et al., 2018). ...
Introduction
Within the development of brain-computer interface (BCI) systems, it is crucial to consider the impact of brain network dynamics and neural signal transmission mechanisms on electroencephalogram-based motor imagery (MI-EEG) tasks. However, conventional deep learning (DL) methods cannot reflect the topological relationship among electrodes, thereby hindering the effective decoding of brain activity.
Methods
Inspired by the concept of brain neuronal forward-forward (F-F) mechanism, a novel DL framework based on Graph Neural Network combined forward-forward mechanism (F-FGCN) is presented. F-FGCN framework aims to enhance EEG signal decoding performance by applying functional topological relationships and signal propagation mechanism. The fusion process involves converting the multi-channel EEG into a sequence of signals and constructing a network grounded on the Pearson correlation coeffcient, effectively representing the associations between channels. Our model initially pre-trains the Graph Convolutional Network (GCN), and fine-tunes the output layer to obtain the feature vector. Moreover, the F-F model is used for advanced feature extraction and classification.
Results and discussion
Achievement of F-FGCN is assessed on the PhysioNet dataset for a four-class categorization, compared with various classical and state-of-the-art models. The learned features of the F-FGCN substantially amplify the performance of downstream classifiers, achieving the highest accuracy of 96.11% and 82.37% at the subject and group levels, respectively. Experimental results affirm the potency of FFGCN in enhancing EEG decoding performance, thus paving the way for BCI applications.
... Deep learning algorithms have powerful end-to-end self-learning capabilities and can automatically extract effective features from complex data. Using deep learning methods to process MI-EEG signals can effectively improve the decoding performance [14,15]. ...
EEG decoding based on motor imagery is an important part of brain–computer interface technology and is an important indicator that determines the overall performance of the brain–computer interface. Due to the complexity of motor imagery EEG feature analysis, traditional classification models rely heavily on the signal preprocessing and feature design stages. End-to-end neural networks in deep learning have been applied to the classification task processing of motor imagery EEG and have shown good results. This study uses a combination of a convolutional neural network (CNN) and a long short-term memory (LSTM) network to obtain spatial information and temporal correlation from EEG signals. The use of cross-layer connectivity reduces the network gradient dispersion problem and enhances the overall network model stability. The effectiveness of this network model is demonstrated on the BCI Competition IV dataset 2a by integrating CNN, BiLSTM and ResNet (called CLRNet in this study) to decode motor imagery EEG. The network model combining CNN and BiLSTM achieved 87.0% accuracy in classifying motor imagery patterns in four classes. The network stability is enhanced by adding ResNet for cross-layer connectivity, which further improved the accuracy by 2.0% to achieve 89.0% classification accuracy. The experimental results show that CLRNet has good performance in decoding the motor imagery EEG dataset. This study provides a better solution for motor imagery EEG decoding in brain–computer interface technology research.
... Wang et al. [25] aimed to design a BCI system to extract features and classify the EEG signals accurately by employing Deep Learning Methods. The work is demonstrated on Convolutional Neural networks and Long-term Short-term memory networks. ...
This book presents use-cases of IoT, AI and Machine Learning (ML) for healthcare delivery and medical devices. It compiles 15 topics that discuss the applications, opportunities, and future trends of machine intelligence in the medical domain. The objective of the book is to demonstrate how these technologies can be used to keep patients safe and healthy and, at the same time, to empower physicians to deliver superior care. Readers will be familiarized with core principles, algorithms, protocols, emerging trends, security problems, and the latest concepts in e-healthcare services. It also includes a quick overview of deep feed forward networks, regularization, optimization algorithms, convolutional networks, sequence modeling, practical methodology, and how they can be used to provide better solutions to healthcare related issues. The book is a timely update for basic and advanced readers in medicine, biomedical engineering, and computer science. Key topics covered in the book: o An introduction to the concept of the Internet of Medical Things (IoMT). o Cloud-edge based IoMT architecture and performance optimization in the context of Medical Big Data. o A comprehensive survey on different IoMT interference mitigation techniques for Wireless Body Area Networks (WBANs). o Artificial Intelligence and the Internet of Medical Things. o A review of new machine learning and AI solutions in different medical areas. o A Deep Learning based solution to optimize obstacle recognition for visually impaired patients. o A survey of the latest breakthroughs in Brain-Computer Interfaces and their applications. o Deep Learning for brain tumor detection. o Blockchain and patient data management.
... The aim of the researchers in [25] is to design a BCI system to extract features and classify the EEG signals accurately by employing Deep Learning Methods. The work is demonstrated on Convolutional Neural networks and Long-term Short-term memory networks. ...
BCI systems are able to communicate directly between the brain and computer using neural activity measurements without the involvement of muscle movements. For BCI systems to be widely used by people with severe disabilities, long-term studies of their real-world use are needed, along with effective and feasible dissemination models. In addition, the robustness of the BCI systems' performance should be improved so they reach the same level of robustness as natural muscle-based health monitoring. In this chapter, we review the recent BCI related studies, followed by the most relevant applications of BCI systems. We also present the key issues and challenges which exist in regard to the BCI systems and also provide future directions.
... Clear examples are subjects affected by neuromuscular disorders, such as MD, ALS, MS, SCI, and CP, or even poststroke patients and amputees [5,[18][19][20]. In this scenario, two main targets can be identified: robotic control [14,15,34,49,50,[64][65][66][67][68][69] and prosthetic control [46][47][48][69][70][71][72][73][74][75][76][77][78]. ...
... Clear examples are subjects affected by neuromuscular disorders, such as MD, ALS, MS, SCI, and CP, or even poststroke patients and amputees [5,[18][19][20]. In this scenario, two main targets can be identified: robotic control [14,15,34,49,50,[64][65][66][67][68][69] and prosthetic control [46][47][48][69][70][71][72][73][74][75][76][77][78]. ...
As a definition, Human–Machine Interface (HMI) enables a person to interact with a de‐ vice. Starting from elementary equipment, the recent development of novel techniques and unob‐ trusive devices for biosignals monitoring paved the way for a new class of HMIs, which take such biosignals as inputs to control various applications. The current survey aims to review the large literature of the last two decades regarding biosignal‐based HMIs for assistance and rehabilitation to outline state‐of‐the‐art and identify emerging technologies and potential future research trends. PubMed and other databases were surveyed by using specific keywords. The found studies were further screened in three levels (title, abstract, full‐text), and eventually, 144 journal papers and 37 conference papers were included. Four macrocategories were considered to classify the different biosignals used for HMI control: biopotential, muscle mechanical motion, body motion, and their combinations (hybrid systems). The HMIs were also classified according to their target application by considering six categories: prosthetic control, robotic control, virtual reality control, gesture recognition, communication, and smart environment control. An ever‐growing number of publica‐ tions has been observed over the last years. Most of the studies (about 67%) pertain to the assistive field, while 20% relate to rehabilitation and 13% to assistance and rehabilitation. A moderate in‐ crease can be observed in studies focusing on robotic control, prosthetic control, and gesture recog‐ nition in the last decade. In contrast, studies on the other targets experienced only a small increase. Biopotentials are no longer the leading control signals, and the use of muscle mechanical motion signals has experienced a considerable rise, especially in prosthetic control. Hybrid technologies are promising, as they could lead to higher performances. However, they also increase HMIs’ complex‐ ity, so their usefulness should be carefully evaluated for the specific application.
... As shown in Figure 1, the neural activities are captured by the neural recorder chips through electrodes, and the outside machines can be controlled through a signal processor and a computer. Meanwhile, the signals captured by the machines can be also sensed back to the neural stimulator chips through pressure or image sensors for closed-loop neural modulation (Bauer and Gharabaghi, 2015;Li et al., 2017;Silva, 2018;Wang et al., 2020;Seok et al., 2021). It can be found that the neural stimulator chip plays an important role in the feedback system for human-machine interface. ...
This paper proposes a neural stimulator silicon chip design with an improved charge balancing technology. The proposed neural stimulation integrated circuit (IC) uses two charge balancing modules including synchronous charge detection module and short-time pulse insertion module. The synchronous charge detection module is designed based on a current splitter with ultra-small output current and an integrator circuit for neural stimulation pulse width control, which greatly reduces the residual charge remained on the electrode-tissue interface. The short-time pulse insertion module is designed based on the electrode voltage detection and compensation current control, which further reduces the accumulated residual charge and keeps the electrode voltage within a safety range of ±25 mV during multiple stimulation cycles. Finally, this neural stimulator is implemented in TSMC 0.18-μm CMOS process technology, and the chip function is tested and verified in both experiments with the electrode-tissue RC model and the PBS saline solution environment. The measurement result shows the neural stimulator chip achieves improved charge balancing with the residual charge smaller than 0.95 nC, which is the lowest compared to the traditional neural stimulator chips.
... Data from 10 volunteers showed a success rate of 70% from the raw EEG and a success rate of 96% from the spectrum. DL methods are better than machine learning algorithms when the data is complex, unstructured, abundant, and feature rich [89,90]. Also, DL can easily describe complex relationships and preserve the information extracted from brain networks [91] or even as [92] expressed, DL techniques are useful to infer information about the correctness of action in BCI applications. ...
In recent years, various studies have demonstrated the potential of electroencephalographic (EEG) signals for the development of brain-computer interfaces (BCIs) in the rehabilitation of human limbs. This article is a systematic review of the state of the art and opportunities in the development of BCIs for the rehabilitation of upper and lower limbs of the human body. The systematic review was conducted in databases considering using EEG signals, interface proposals to rehabilitate upper/lower limbs using motor intention or movement assistance and utilizing virtual environments in feedback. Studies that did not specify which processing system was used were excluded. Analyses of the design processing or reviews were excluded as well. It was identified that 11 corresponded to applications to rehabilitate upper limbs, six to lower limbs, and one to both. Likewise, six combined visual/auditory feedback, two haptic/visual, and two visual/auditory/haptic. In addition, four had fully immersive virtual reality (VR), three semi-immersive VR, and 11 non-immersive VR. In summary, the studies have demonstrated that using EEG signals, and user feedback offer benefits including cost, effectiveness, better training, user motivation and there is a need to continue developing interfaces that are accessible to users, and that integrate feedback techniques.
Deep-learning (DL) is a new paradigm in the artificial intelligence field associated with learning structures able to connect directly numeric data with high-level patterns or categories. DL seems to be a suitable technique to deal with computationally challenging Brain Computer Interface (BCI) problems. Following DL strategy, a new modular and self-organized architecture to solve BCI problems is proposed. A pattern recognition system to translate the measured signals in order to establish categories representing thoughts, without previous pre-processing, is developed. To achieve an easy interpretability of the system internal functioning, a neuro-fuzzy module and a learning methodology are carried out. The whole learning process is based on machine learning. The architecture and the learning method are tested on a representative BCI application to detect and classify motor imagery thoughts. Data is gathered with a low-cost device. Results prove the efficiency and adaptability of the proposed DL architecture where the used classification module (S-dFasArt) exhibits a better behaviour compared with the usual classifiers. Additionally, it employs neuro-fuzzy modules which allow to offer results in a rules format. This improves the interpretability with respect to the black-box description. A DL architecture, going from the raw data to the labels, is proposed. The proposed architecture, based on Adaptive Resonance Theory (ART) and Fuzzy ART modules, performs data processing in a self-organized way. It follows the DL paradigm, but at the same time, it allows an interpretation of the operation stages. Therefore this approach could be called Transparent Deep Learning.
This book presents use-cases of IoT, AI and Machine Learning (ML) for healthcare delivery and medical devices. It compiles 15 topics that discuss the applications, opportunities, and future trends of machine intelligence in the medical domain. The objective of the book is to demonstrate how these technologies can be used to keep patients safe and healthy and, at the same time, to empower physicians to deliver superior care. Readers will be familiarized with core principles, algorithms, protocols, emerging trends, security problems, and the latest concepts in e-healthcare services. It also includes a quick overview of deep feed forward networks, regularization, optimization algorithms, convolutional networks, sequence modeling, practical methodology, and how they can be used to provide better solutions to healthcare related issues. The book is a timely update for basic and advanced readers in medicine, biomedical engineering, and computer science. Key topics covered in the book: o An introduction to the concept of the Internet of Medical Things (IoMT). o Cloud-edge based IoMT architecture and performance optimization in the context of Medical Big Data. o A comprehensive survey on different IoMT interference mitigation techniques for Wireless Body Area Networks (WBANs). o Artificial Intelligence and the Internet of Medical Things. o A review of new machine learning and AI solutions in different medical areas. o A Deep Learning based solution to optimize obstacle recognition for visually impaired patients. o A survey of the latest breakthroughs in Brain-Computer Interfaces and their applications. o Deep Learning for brain tumor detection. o Blockchain and patient data management.
