Asynchronous decoding of finger movements from ECoG signals using long-range dependencies conditional random fields

Saa, Jaime Fernando Delgado; Pesters, Adriana de; Çetin, Müjdat

doi:10.1088/1741-2560/13/3/036017

Cited by 14 publications

(20 citation statements)

References 23 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Pistohl et al, Chestek et al, and Wang et al also showed that high classification of gesture types could be obtained from the channels on the postcentral gyrus [ 12 , 15 , 23 ]. It is worth noting that Wang et al managed to decode 3D arm movement with the ECoG signals obtained from the postcentral gyrus of a paralyzed participant, who cannot move his limbs at all [ 24 ]. Therefore, it suggested that the activation of the postcentral gyrus played an influential role in hand movement.…”

Section: Discussionmentioning

confidence: 99%

Gesture Decoding Using ECoG Signals from Human Sensorimotor Cortex: A Pilot Study

Zhang

Jin

et al. 2017

Behavioural Neurology

View full text Add to dashboard Cite

Electrocorticography (ECoG) has been demonstrated as a promising neural signal source for developing brain-machine interfaces (BMIs). However, many concerns about the disadvantages brought by large craniotomy for implanting the ECoG grid limit the clinical translation of ECoG-based BMIs. In this study, we collected clinical ECoG signals from the sensorimotor cortex of three epileptic participants when they performed hand gestures. The ECoG power spectrum in hybrid frequency bands was extracted to build a synchronous real-time BMI system. High decoding accuracy of the three gestures was achieved in both offline analysis (85.7%, 84.5%, and 69.7%) and online tests (80% and 82%, tested on two participants only). We found that the decoding performance was maintained even with a subset of channels selected by a greedy algorithm. More importantly, these selected channels were mostly distributed along the central sulcus and clustered in the area of 3 interelectrode squares. Our findings of the reduced and clustered distribution of ECoG channels further supported the feasibility of clinically implementing the ECoG-based BMI system for the control of hand gestures.

show abstract

Section: Discussionmentioning

confidence: 99%

Gesture Decoding Using ECoG Signals from Human Sensorimotor Cortex: A Pilot Study

Zhang

Jin

et al. 2017

Behavioural Neurology

View full text Add to dashboard Cite

show abstract

“…These different frequency bands have been extensively used as features to model brain phenomena [1,2,3,4,5,6,7,8,9,10,11,12]. For instance, LFC usually measured as the raw brain signal low-pass filtered (below 40 Hz) [13,14,15], have been used in many applications, including decoding of position, velocity and acceleration of executed motor tasks [16,17,18,19,20,21,13,14,15] leading to improvements compared to models restricted to amplitude modulations in only the alpha and beta bands [22,19,20]. Given the enhanced signal to noise ratio compared with both EEG and MEG, ECoG can also exploit high-frequency components above 100 Hz.…”

Section: Introductionmentioning

confidence: 99%

“…Given the enhanced signal to noise ratio compared with both EEG and MEG, ECoG can also exploit high-frequency components above 100 Hz. High frequency band activity (HFB), usually measured as the averaged power changes in the band from 70 to 200 Hz, has been used for decoding in multiple tasks, including motor, auditory, and visual [16,17,18,19,20]. The extracted features are used to model brain responses for basic brain research, medical diagnostic, and rehabilitation areas.…”

Section: Introductionmentioning

confidence: 99%

“…These features involve spatial patterns discovery [25,26], temporal modeling through probabilistic approaches such as hidden Markov models [27,28], conditional random fields [16,6,7,8,9] and recurrent neural networks [29]. In addition, features based on frequency decomposition of brain signals performed through either Fourier or wavelet transform are well described in the literature.…”

Section: Introductionmentioning

confidence: 99%

“…Without appropriate regularization this can introduce model over-fitting. In probabilistic graphical models and deep neural networks architectures, temporal relationships can be incorporated through modeling of long-range dependencies [16,29]. However, these approaches require the use of a considerable amount of data that is usually not available in experiments with humans, limiting the performance of these methods [32].…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Coherence-based spectro-spatial fillters for stimulus features prediction from electrocorticographic recordings

Delgado

Christen

Martin

et al. 2018

Preprint

View full text Add to dashboard Cite

The traditional approach in neuroscience relies on encoding models where brain responses to different stimuli are related to the latter to establish reproducible dependencies. To reduce neuronal and experimental noise, brain signals are usually averaged across trials to detect reliable and coherent brain activity.However, neural representations of stimulus features can be spread over time, frequency, and space, motivating the use of alternative methods that relate stimulus features to brain responses. We propose a Coherence-based spectro-spatial filter method that reconstructs stimulus features from intracortical brain signals. The proposed method models trials of an experiment as realizations of a random process and extracts patterns that are common across brain signals and the presented stimuli. These patterns, originating from different recording sites, are then combined (spatial filtering) to form a final prediction. Our results from three different cognitive tasks (motor movements, speech perception and speech production), concur to show that the proposed method significantly improves the ability to predict stimulus features over traditional methods such as multilinear regression with distributed lags and artificial neural networks. Furthermore, analyses of the model parameters show anatomical discriminability for execution of different motor movements. This anatomical discriminability is also observed in the perception and production of different words. These features could be exploited in the design of neuroprosthesis, as well as for exploring

show abstract

ConvNets for Electroencephalographic Decoding of Attempted Arm and Hand Movements of People with Spinal Cord Injury

Cancino,

López,

Delgado Saa

et al. 2023

Advanced Intelligent Systems

View full text Add to dashboard Cite

Brain–computer interfaces (BCIs) facilitate communication between the brain and external devices, providing an alternative solution for individuals with upper limb disabilities. The decoding of brain movement commands in BCIs relies on signal feature extraction and classification. Herein, the BNCI Horizon 2020 dataset is employed, which consists of electroencephalographic signals from ten participants with subacute and chronic cervical spinal cord injuries. These participants perform or attempt five distinct types of arm and hand movements. To extract signal features, a novel technique is introduced that estimates movement‐related cortical potentials and incorporates them into the processing pipeline. Moreover, a time‐frequency domain representation of the dataset is used as input for the classifier. Given the promising outcomes demonstrated by deep learning models in BCI classification, a pretrained ConvNet AlexNet is adopted to decode the motor tasks. The proposed method exhibits a remarkable average accuracy of 76.0% across all five categories, representing a significant advancement over existing state‐of‐the‐art techniques. Additionally, an in‐depth analysis of the convolutional layers in the model is conducted to gain comprehensive insights into the classification process. By examining the ConvNet filters and activations, the method contributes to a deeper understanding of the electrophysiology that underlies attempted movement.

show abstract

Asynchronous decoding of finger movements from ECoG signals using long-range dependencies conditional random fields

Cited by 14 publications

References 23 publications

Gesture Decoding Using ECoG Signals from Human Sensorimotor Cortex: A Pilot Study

Gesture Decoding Using ECoG Signals from Human Sensorimotor Cortex: A Pilot Study

Coherence-based spectro-spatial fillters for stimulus features prediction from electrocorticographic recordings

ConvNets for Electroencephalographic Decoding of Attempted Arm and Hand Movements of People with Spinal Cord Injury

Contact Info

Product

Resources

About