fNIRS-EEG BCIs for Motor Rehabilitation: A Review

Bioengineering, Год журнала: 2023, Номер 10(12), С. 1393 - 1393

Опубликована: Дек. 6, 2023

Motor impairment has a profound impact on significant number of individuals, leading to substantial demand for rehabilitation services. Through brain–computer interfaces (BCIs), people with severe motor disabilities could have improved communication others and control appropriately designed robotic prosthetics, so as (at least partially) restore their abilities. BCI plays pivotal role in promoting smoother interactions between individuals impairments others. Moreover, they enable the direct assistive devices through brain signals. In particular, most potential lies realm rehabilitation, where BCIs can offer real-time feedback assist users training continuously monitor brain’s state throughout entire process. Hybridization different brain-sensing modalities, especially functional near-infrared spectroscopy (fNIRS) electroencephalography (EEG), shown great creation rehabilitating motor-impaired populations. EEG, well-established methodology, be combined fNIRS compensate inherent disadvantages achieve higher temporal spatial resolution. This paper reviews recent works hybrid fNIRS-EEG emphasizing methodologies that utilized imagery. An overview system its key components was introduced, followed by an introduction various devices, strengths weaknesses signal processing techniques, applications neuroscience clinical contexts. The review concludes discussing possible challenges opportunities future development.

Язык: Английский

---

Machine learning in biosignals processing for mental health: A narrative review

Frontiers in Psychology, Год журнала: 2023, Номер 13

Опубликована: Янв. 13, 2023

Machine Learning (ML) offers unique and powerful tools for mental health practitioners to improve evidence-based psychological interventions diagnoses. Indeed, by detecting analyzing different biosignals, it is possible differentiate between typical atypical functioning achieve a high level of personalization across all phases care. This narrative review aimed at presenting comprehensive overview how ML algorithms can be used infer the states from biosignals. After that, key examples they in clinical activity research are illustrated. A description biosignals typically cognitive emotional correlates (e.g., EEG ECG), will provided, alongside their application Diagnostic Precision Medicine, Affective Computing, brain–computer Interfaces. The contents then focus on challenges questions related applied analysis, pointing out advantages drawbacks connected widespread AI medical/mental fields. integration data science facilitate transition personalized effective medicine, and, do so, important that researchers psychological/ medical disciplines/health care professionals scientists share common background vision current research.

Язык: Английский

---

EEG-fNIRS-based hybrid image construction and classification using CNN-LSTM

Frontiers in Neurorobotics, Год журнала: 2022, Номер 16

Опубликована: Авг. 31, 2022

The constantly evolving human-machine interaction and advancement in sociotechnical systems have made it essential to analyze vital human factors such as mental workload, vigilance, fatigue, stress by monitoring brain states for optimum performance safety. Similarly, signals become paramount rehabilitation assistive purposes fields brain-computer interface (BCI) closed-loop neuromodulation neurological disorders motor disabilities. complexity, non-stationary nature, low signal-to-noise ratio of pose significant challenges researchers design robust reliable BCI accurately detect meaningful changes outside the laboratory environment. Different neuroimaging modalities are used hybrid settings enhance accuracy, increase control commands, decrease time required activity detection. Functional near-infrared spectroscopy (fNIRS) electroencephalography (EEG) measure hemodynamic electrical with a good spatial temporal resolution, respectively. However, settings, where both output BCI, their data compatibility due huge discrepancy between sampling rate number channels remains challenge real-time applications. Traditional methods, downsampling channel selection, result important information loss while making compatible. In this study, we present novel recurrence plot (RP)-based time-distributed convolutional neural network long short-term memory (CNN-LSTM) algorithm integrated classification fNIRS EEG acquired first projected into non-linear dimension RPs fed CNN extract features without performing any downsampling. Then, LSTM is learn chronological time-dependence relation activity. average accuracies achieved proposed model were 78.44% fNIRS, 86.24% EEG, 88.41% EEG-fNIRS BCI. Moreover, maximum 85.9, 88.1, 92.4%, results confirm viability RP-based deep-learning successful systems.

Язык: Английский

---

Parallel genetic algorithm based common spatial patterns selection on time–frequency decomposed EEG signals for motor imagery brain-computer interface

Biomedical Signal Processing and Control, Год журнала: 2022, Номер 80, С. 104397 - 104397

Опубликована: Ноя. 7, 2022

Язык: Английский

---

A Hybrid GCN and Filter-Based Framework for Channel and Feature Selection: An fNIRS-BCI Study

International Journal of Intelligent Systems, Год журнала: 2023, Номер 2023, С. 1 - 14

Опубликована: Март 27, 2023

In this study, a channel and feature selection methodology is devised for brain-computer interface (BCI) applications using functional near-infrared spectroscopy (fNIRS). A graph convolutional network (GCN) employed to select the appropriate correlated fNIRS channels. Furthermore, in extraction phase, performance of two filter-based algorithms, (i) minimum redundancy maximum relevance (mRMR) (ii) ReliefF, investigated. The five most commonly used temporal statistical features (i.e., mean, slope, maximum, skewness, kurtosis) are used, whereas conventional support vector machine (SVM) utilized as classifier training testing. proposed validated an available online dataset motor imagery (left- right-hand), mental arithmetic, baseline tasks. First, efficacy shown two-class BCI left- vs. right-hand arithmetic baseline). Second, framework applied four-class results show that number channels was significantly reduced, resulting significant increase classification accuracy both applications, respectively. mRMR 87.8% imagery, 87.1% 78.7% four-class) ReliefF 90.7% 93.7% 81.6% yielded high average $\left(p<0.05\right)$ . However, algorithm more stable significant.

Язык: Английский

---

Rethinking Delayed Hemodynamic Responses for fNIRS Classification

IEEE Transactions on Neural Systems and Rehabilitation Engineering, Год журнала: 2023, Номер 31, С. 4528 - 4538

Опубликована: Янв. 1, 2023

Functional near-infrared spectroscopy (fNIRS) is a non-invasive neuroimaging technology for monitoring cerebral hemodynamic responses. Enhancing fNIRS classification can improve the performance of brain-computer interfaces (BCIs). Currently, deep neural networks (DNNs) do not consider inherent delayed responses signals, which causes many optimization and application problems. Considering kernel size receptive field convolutions, as domain knowledge are introduced into classification, concise efficient model named fNIRSNet proposed. We empirically summarize three design guidelines fNIRSNet. In subject-specific subject-independent experiments, outperforms other DNNs on open-access datasets. Specifically, with only 498 parameters 6.58% higher than convolutional network (CNN) millions mental arithmetic tasks floating-point operations (FLOPs) much lower CNN. Therefore, friendly to practical applications reduces hardware cost BCI systems. It may inspire more research knowledge-driven models BCIs. Code available at https://github.com/wzhlearning/fNIRSNet.

Язык: Английский

---

From lab to life: challenges and perspectives of fNIRS for haemodynamic-based neurofeedback in real-world environments

Philosophical Transactions of the Royal Society B Biological Sciences, Год журнала: 2024, Номер 379(1915)

Опубликована: Окт. 21, 2024

Neurofeedback allows individuals to monitor and self-regulate their brain activity, potentially improving human function. Beyond the traditional electrophysiological approach using primarily electroencephalography, haemodynamics measured with functional magnetic resonance imaging (fMRI) more recently, near-infrared spectroscopy (fNIRS) have been used (haemodynamic-based neurofeedback), particularly improve spatial specificity of neurofeedback. Over recent years, especially fNIRS has attracted great attention because it offers several advantages over fMRI such as increased user accessibility, cost-effectiveness mobility—the latter being most distinct feature fNIRS. The next logical step would be transfer haemodynamic-based neurofeedback protocols that already proven validated by mobile However, this undertaking is not always easy, since novices may miss important fNIRS-specific methodological challenges. This review aimed at researchers from different fields who seek exploit unique capabilities for It carefully addresses challenges suggestions possible solutions. If raised are addressed further developed, could emerge a useful technique its own application potential—the targeted training activity in real-world environments, thereby significantly expanding scope scalability applications. article part theme issue ‘Neurofeedback: new territories neurocognitive mechanisms endogenous neuromodulation’.

Язык: Английский

---

Viewing neurovascular coupling through the lens of combined EEG–fNIRS: A systematic review of current methods

Psychophysiology, Год журнала: 2022, Номер 59(6)

Опубликована: Март 31, 2022

Abstract Neurovascular coupling is a key physiological mechanism that occurs in the healthy human brain, and understanding this process has implications for aging neuropsychiatric populations. Combined electroencephalography (EEG) functional near‐infrared spectroscopy (fNIRS) emerged as promising, noninvasive tool probing neurovascular interactions humans. However, utility of approach critically depends on methodological quality used multimodal integration. Despite growing number combined EEG–fNIRS applications reported recent years, rigor past studies remains unclear, limiting accurate interpretation findings hindering translational application approach. To fill knowledge gap, we evaluated various aspects previous performed individuals. A literature search was conducted using PubMed PsycINFO June 28, 2021. Studies involving concurrent EEG fNIRS measurements awake individuals were selected. After screening eligibility assessment, 96 included evaluation. Specifically, reviewed participant sampling, experimental design, signal acquisition, data preprocessing, outcome selection, analysis, results presentation these studies. Altogether, identified several notable strengths limitations existing literature. In light features EEG–fNIRS, recommendations are made to improve standardize research practices facilitate use when studying processes alterations among

Язык: Английский

---

Metaheuristic Optimization-Based Feature Selection for Imagery and Arithmetic Tasks: An fNIRS Study

Sensors, Год журнала: 2023, Номер 23(7), С. 3714 - 3714

Опубликована: Апрель 3, 2023

In recent decades, the brain-computer interface (BCI) has emerged as a leading area of research. The feature selection is vital to reduce dataset's dimensionality, increase computing effectiveness, and enhance BCI's performance. Using activity-related features leads high classification rate among desired tasks. This study presents wrapper-based metaheuristic framework for BCI applications using functional near-infrared spectroscopy (fNIRS). Here, temporal statistical (i.e., mean, slope, maximum, skewness, kurtosis) were computed from all available channels form training vector. Seven optimization algorithms tested their performance k-nearest neighbor-based cost function: particle swarm optimization, cuckoo search firefly algorithm, bat flower pollination whale grey wolf (GWO). presented approach was validated based on an online dataset motor imagery (MI) mental arithmetic (MA) tasks 29 healthy subjects. results showed that accuracy significantly improved by utilizing selected relative those obtained full set features. All abovementioned reduced vector size. GWO yielded highest average rates (p < 0.01) 94.83 ± 5.5%, 92.57 6.9%, 85.66 7.3% MA, MI, four-class (left- right-hand baseline) tasks, respectively. may be helpful in phase selecting appropriate robust fNIRS-based applications.

Язык: Английский

---

An EEG-fNIRS neurovascular coupling analysis method to investigate cognitive-motor interference

Computers in Biology and Medicine, Год журнала: 2023, Номер 160, С. 106968 - 106968

Опубликована: Май 6, 2023

Язык: Английский

---