Dataset Information

Brain-inspired spiking neural networks for decoding and understanding muscle activity and kinematics from electroencephalography signals during hand movements.

ABSTRACT: Compared to the abilities of the animal brain, many Artificial Intelligence systems have limitations which emphasise the need for a Brain-Inspired Artificial Intelligence paradigm. This paper proposes a novel Brain-Inspired Spiking Neural Network (BI-SNN) model for incremental learning of spike sequences. BI-SNN maps spiking activity from input channels into a high dimensional source-space which enhances the evolution of polychronising spiking neural populations. We applied the BI-SNN to predict muscle activity and kinematics from electroencephalography signals during upper limb functional movements. The BI-SNN extends our previously proposed eSPANNet computational model by integrating it with the 'NeuCube' brain-inspired SNN architecture. We show that BI-SNN can successfully predict continuous muscle activity and kinematics of upper-limb. The experimental results confirmed that the BI-SNN resulted in strongly correlated population activity and demonstrated the feasibility for real-time prediction. In contrast to the majority of Brain-Computer Interfaces (BCIs) that constitute a 'black box', BI-SNN provide quantitative and visual feedback about the related brain activity. This study is one of the first attempts to examine the feasibility of finding neural correlates of muscle activity and kinematics from electroencephalography using a brain-inspired computational paradigm. The findings suggest that BI-SNN is a better neural decoder for non-invasive BCI.

SUBMITTER: Kumarasinghe K

PROVIDER: S-EPMC7844055 | biostudies-literature | 2021 Jan

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

Brain-inspired spiking neural networks for decoding and understanding muscle activity and kinematics from electroencephalography signals during hand movements.

Kumarasinghe Kaushalya K Kasabov Nikola N Taylor Denise D

Scientific reports 20210128 1

Compared to the abilities of the animal brain, many Artificial Intelligence systems have limitations which emphasise the need for a Brain-Inspired Artificial Intelligence paradigm. This paper proposes a novel Brain-Inspired Spiking Neural Network (BI-SNN) model for incremental learning of spike sequences. BI-SNN maps spiking activity from input channels into a high dimensional source-space which enhances the evolution of polychronising spiking neural populations. We applied the BI-SNN to predict ...[more]

PMID: 33510245

Similar Datasets

Project description:Objective: Brain-machine interfaces (BMIs) are useful for inducing plastic changes in cortical representation. A BMI first decodes hand movements using cortical signals and then converts the decoded information into movements of a robotic hand. By using the BMI robotic hand, the cortical representation decoded by the BMI is modulated to improve decoding accuracy. We developed a BMI based on real-time magnetoencephalography (MEG) signals to control a robotic hand using decoded hand movements. Subjects were trained to use the BMI robotic hand freely for 10 min to evaluate plastic changes in the cortical representation due to the training. Method: We trained nine young healthy subjects with normal motor function. In open-loop conditions, they were instructed to grasp or open their right hands during MEG recording. Time-averaged MEG signals were then used to train a real decoder to control the robotic arm in real time. Then, subjects were instructed to control the BMI-controlled robotic hand by moving their right hands for 10 min while watching the robot's movement. During this closed-loop session, subjects tried to improve their ability to control the robot. Finally, subjects performed the same offline task to compare cortical activities related to the hand movements. As a control, we used a random decoder trained by the MEG signals with shuffled movement labels. We performed the same experiments with the random decoder as a crossover trial. To evaluate the cortical representation, cortical currents were estimated using a source localization technique. Hand movements were also decoded by a support vector machine using the MEG signals during the offline task. The classification accuracy of the movements was compared among offline tasks. Results: During the BMI training with the real decoder, the subjects succeeded in improving their accuracy in controlling the BMI robotic hand with correct rates of 0.28 ± 0.13 to 0.50 ± 0.11 (p = 0.017, n = 8, paired Student's t-test). Moreover, the classification accuracy of hand movements during the offline task was significantly increased after BMI training with the real decoder from 62.7 ± 6.5 to 70.0 ± 11.1% (p = 0.022, n = 8, t(7) = 2.93, paired Student's t-test), whereas accuracy did not significantly change after BMI training with the random decoder from 63.0 ± 8.8 to 66.4 ± 9.0% (p = 0.225, n = 8, t(7) = 1.33). Conclusion: BMI training is a useful tool to train the cortical activity necessary for BMI control and to induce some plastic changes in the activity.

Project description:The oscillatory patterns of electroencephalography (EEG), during resting states, are informative and helpful in understanding the functional states of brain network and their contribution to behavioral performances. The aim of this study is to characterize the functional brain network alterations in patients with amnestic mild cognitive impairment (aMCI). To this end, rsEEG signals were recorded before and after a cognitive task. Functional connectivity metrics were calculated using debiased weighted phase lag index (DWPLI). Topological features of the functional connectivity network were analyzed using both the classical graph approach and minimum spanning tree (MST) algorithm. Subsequently, the network and connectivity values together with Mini-Mental State Examination cognitive test were used as features to classify the participants. Results showed that: (1) across the pre-task condition, in the theta band, the aMCI group had a significantly lower global mean DWPLI than the control group; the functional connectivity patterns were different in the left hemisphere between two groups; the aMCI group showed significantly higher average clustering coefficient and the remarkably lower global efficiency than the control. (2) Analysis of graph measures under post-task resting state, unveiled that for the percentage change of post-task vs. pre-task in beta EEG, a significant increase in tree hierarchy was observed in aMCI group (2.41%) than in normal control (-3.89%); (3) Furthermore, the classification analysis of combined measures of functional connectivity, brain topology, and MMSE test showed improved accuracy compared to the single method, for which the connectivity patterns and graph metrics were used as separate inputs. The classification accuracy obtained for the case of post-task resting state was 87.2%, while the one achieved under pre-task resting state was found to be 77.7%. Therefore, the functional network alterations in aMCI patients were more prominent during the post-task resting state. This study suggests that the disintegration observed in MCI functional network during the resting states, preceding and following a task, might be possible biomarkers of cognitive dysfunction in aMCI patients.

Project description:UnlabelledObjectiveMany daily activities involve intrinsic or extrinsic goal-directed eye and hand movements. An extensive visuomotor coordination network including nigro-striatal pathways is required for efficient timing and positioning of eyes and hands. The aim of this study was to investigate how Parkinson's disease (PD) affects eye-hand coordination in tasks with different cognitive complexity.MethodsWe used a touch screen, an eye-tracking device and a motion capturing system to quantify changes in eye-hand coordination in early-stage PD patients (H&Y < 2.5) and age-matched controls. Timing and kinematics of eye and hand were quantified in four eye-hand coordination tasks (pro-tapping, dual planning, anti-tapping and spatial memory task).ResultsIn the pro-tapping task, saccade initiation towards extrinsic goals was not impaired. However, in the dual planning and anti-tapping task initiation of saccades towards intrinsic goals was faster in PD patients. Hand movements were differently affected: initiation of the hand movement was only delayed in the pro-tapping and dual planning task. Overall, hand movements in PD patients were slower executed compared to controls.InterpretationWhereas initiation of saccades in an extrinsic goal-directed task (pro-tapping task) is not affected, early stage PD patients have difficulty in suppressing reflexive saccades towards extrinsic goals in tasks where the endpoint is an intrinsic goal (e.g. dual planning and anti-tapping task). This is specific for eye movements, as hand movements have delayed responses in the pro-tapping and dual planning task. This suggests that reported impairment of the dorsolateral prefrontal cortex in early-stage PD patients affects only inhibition of eye movements. We conclude that timing and kinematics of eye and hand movements in visuomotor tasks are affected in PD patients. This result may have clinical significance by providing a behavioral marker for the early diagnosis of PD.

Dataset Information

Brain-inspired spiking neural networks for decoding and understanding muscle activity and kinematics from electroencephalography signals during hand movements.

Publications

Brain-inspired spiking neural networks for decoding and understanding muscle activity and kinematics from electroencephalography signals during hand movements.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets