Embedded Brain Machine Interface based on motor imagery paradigm to control prosthetic hand

Condori, Kevin Acuna; Urquizo, Erick Carranza; Achanccaray, David

doi:10.1109/andescon.2016.7836266

Cited by 16 publications

(14 citation statements)

References 12 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…One promising approach is based on motor-imagery (MI), which is the cognitive process of thinking about the motion of a body part, e.g., the left hand, without actually performing it. MI-BMIs assist people with impairments to regain independence, e.g., by steering a wheelchair [2], controlling a prosthesis [3], [4], or by enabling motor rehabilitation [5].…”

Section: Introductionmentioning

confidence: 99%

EEG-TCNet: An Accurate Temporal Convolutional Network for Embedded Motor-Imagery Brain-Machine Interfaces

Ingolfsson¹,

Hersche²,

Wang³

et al. 2020

Preprint

View full text Add to dashboard Cite

In recent years, deep learning (DL) has contributed significantly to the improvement of motor-imagery brainmachine interfaces (MI-BMIs) based on electroencephalography (EEG). While achieving high classification accuracy, DL models have also grown in size, requiring a vast amount of memory and computational resources. This poses a major challenge to an embedded BMI solution that guarantees user privacy, reduced latency, and low power consumption by processing the data locally. In this paper, we propose EEG-TCNET, a novel temporal convolutional network (TCN) that achieves outstanding accuracy while requiring few trainable parameters. Its low memory footprint and low computational complexity for inference make it suitable for embedded classification on resource-limited devices at the edge. Experimental results on the BCI Competition IV-2a dataset show that EEG-TCNET achieves 77.35% classification accuracy in 4-class MI. By finding the optimal network hyperparameters per subject, we further improve the accuracy to 83.84%. Finally, we demonstrate the versatility of EEG-TCNET on the Mother of All BCI Benchmarks (MOABB), a large scale test benchmark containing 12 different EEG datasets with MI experiments. The results indicate that EEG-TCNET successfully generalizes beyond one single dataset, outperforming the current state-of-the-art (SoA) on MOABB by a meta-effect of 0.25.

show abstract

Section: Introductionmentioning

confidence: 99%

EEG-TCNet: An Accurate Temporal Convolutional Network for Embedded Motor-Imagery Brain-Machine Interfaces

Ingolfsson¹,

Hersche²,

Wang³

et al. 2020

Preprint

View full text Add to dashboard Cite

show abstract

“…Most of these models are evaluated remotely offline, without considering the possibility to bring the computation closer to the sensors, where the data is acquired. Few studies have shown embedded implementations using traditional MI-BCIs with separate feature extractors [22], [23], [24], but, to the best of our knowledge, no previous work has demonstrated accurate embedded MI-BCI on low-power MCUs using CNNs, which offers better accuracy at lower latency. In this paper, we propose a CNN novel model based on EEGNet to perform MI classification on Physionet dataset [18].…”

Section: Related Workmentioning

confidence: 97%

An Accurate EEGNet-based Motor-Imagery Brain–Computer Interface for Low-Power Edge Computing

Wang

Hersche

Tömekce

et al. 2020

2020 IEEE International Symposium on Medical Measurements and Applications (MeMeA)

View full text Add to dashboard Cite

This paper presents an accurate and robust embedded motor-imagery brain-computer interface (MI-BCI). The proposed novel model, based on EEGNet [1], matches the requirements of memory footprint and computational resources of low-power microcontroller units (MCUs), such as the ARM Cortex-M family. Furthermore, the paper presents a set of methods, including temporal downsampling, channel selection, and narrowing of the classification window, to further scale down the model to relax memory requirements with negligible accuracy degradation. Experimental results on the Physionet EEG Motor Movement/Imagery Dataset show that standard EEGNet achieves 82.43%, 75.07%, and 65.07% classification accuracy on 2-, 3-, and 4-class MI tasks in global validation, outperforming the stateof-the-art (SoA) convolutional neural network (CNN) by 2.05%, 5.25%, and 6.49%. Our novel method further scales down the standard EEGNet at a negligible accuracy loss of 0.31% with 7.6× memory footprint reduction and a small accuracy loss of 2.51% with 15× reduction. The scaled models are deployed on a commercial Cortex-M4F MCU taking 101 ms and consuming 4.28 mJ per inference for operating the smallest model, and on a Cortex-M7 with 44 ms and 18.1 mJ per inference for the mediumsized model, enabling a fully autonomous, wearable, and accurate low-power BCI.

show abstract

“…EEG has been widely used in neural engineering, neuroscience, and brain-computer interface (BCI) systems [1][2][3]. The Motor Imagery (MI) paradigm is commonly used in the electroencephalogram brain-computer interface (EEG-BCI) system [4][5][6], which requires subjects to imagine the movement of different parts of the body, rather than the actual movement. Therefore, the accurate classification of EEG signals from different MI tasks is important for the BCI system [5].…”

Section: Introductionmentioning

confidence: 99%

A Transformer-Based Approach Combining Deep Learning Network and Spatial-Temporal Information for Raw EEG Classification

Xie

Zhang

Sun

et al. 2022

IEEE Trans. Neural Syst. Rehabil. Eng.

125

View full text Add to dashboard Cite

The attention mechanism of the Transformer has the advantage of extracting feature correlation in the long-sequence data and visualizing the model. As time-series data, the spatial and temporal dependencies of the EEG signals between the time points and the different channels contain important information for accurate classification. So far, Transformer-based approaches have not been widely explored in motor-imagery EEG classification and visualization, especially lacking general models based on cross-individual validation. Taking advantage of the Transformer model and the spatial-temporal characteristics of the EEG signals, we designed Transformer-based models for classifications of motor imagery EEG based on the PhysioNet dataset. With 3s EEG data, our models obtained the best classification accuracy of 83.31%, 74.44%, and 64.22% on two-, three-, and four-class motor-imagery tasks in cross-individual validation, which outperformed other state-of-the-art models by 0.88%, 2.11%, and 1.06%. The inclusion of the positional embedding modules in the Transformer could improve the EEG classification performance. Furthermore, the visualization results of attention weights provided insights into the working mechanism of the Transformer-based networks during motor imagery tasks. The topography of the attention weights revealed a pattern of event-related desynchronization (ERD) which was consistent with the results from the spectral analysis of Mu and beta rhythm over the sensorimotor areas. Together, our deep learning methods not only provide novel and powerful tools for classifying and understanding EEG data but also have broad applications for brain-computer interface (BCI) systems.

show abstract

Embedded Brain Machine Interface based on motor imagery paradigm to control prosthetic hand

Cited by 16 publications

References 12 publications

EEG-TCNet: An Accurate Temporal Convolutional Network for Embedded Motor-Imagery Brain-Machine Interfaces

EEG-TCNet: An Accurate Temporal Convolutional Network for Embedded Motor-Imagery Brain-Machine Interfaces

An Accurate EEGNet-based Motor-Imagery Brain–Computer Interface for Low-Power Edge Computing

A Transformer-Based Approach Combining Deep Learning Network and Spatial-Temporal Information for Raw EEG Classification

Contact Info

Product

Resources

About