Predictive classification of self-paced upper-limb analytical movements with EEG

Abstract

The extent to which the electroencephalographic activity allows the characterization of movements with the upper limb is an open question. This paper describes the design and validation of a classifier of upper-limb analytical movements based on electroencephalographic activity extracted from intervals preceding self-initiated movement tasks. Features selected for the classification are subject specific and associated with the movement tasks. Further tests are performed to reject the hypothesis that other information different from the task-related cortical activity is being used by the classifiers. Six healthy subjects were measured performing self-initiated upper-limb analytical movements. A Bayesian classifier was used to classify among seven different kinds of movements. Features considered covered the alpha and beta bands. A genetic algorithm was used to optimally select a subset of features for the classification. An average accuracy of 62.9 ± 7.5% was reached, which was above the baseline level observed with the proposed methodology (30.2 ± 4.3%). The study shows how the electroencephalography carries information about the type of analytical movement performed with the upper limb and how it can be decoded before the movement begins. In neurorehabilitation environments, this information could be used for monitoring and assisting purposes.

Detecting and classifying three different hand movement types through electroencephalography recordings for neurorehabilitation

“…individual finger movements [4], types of wrist movement [14,41,42], analytical upper limb movements [16], and variation in speed and force of foot movements [13,21]. However, the performance was better compared to the findings in a recent study where force and speed were decoded from the MRCP associated with palmar grasps using a single electrode and a single Laplacian-filtered channel [20] suggesting that several electrodes are needed to obtain high classification accuracy.…”

Classification of different reaching movements from the same limb using EEG

“…In the here presented work we report the performance of a BCI using 1 s time windows and 19 EEG electrodes and it has been already shown that the accuracy of classifier increases using longer time window after onset [38] and denser EEG electrodes around the motor cortex [33]. Adding more features such as movement related cortical potential (MRCP) to the proposed system may further improve the performance [30,32].…”

“…flexion versus extension or pronation versus supination) were decoded with average accuracy ranging from 60 to 80% [36]. A few other groups have reported some preliminary work on multi-class decoding using motor imagery and execution of movements from the same upper limb [33,37,38]. Yong et al have shown a 3-class BCI system that discriminates EEG signals corresponding to rest, imaginary grasp, and elbow movement [33].…”

Estado del Arte en Neurotecnologías para la Asistencia y la Rehabilitación en España: Tecnologías Fundamentales

“…(4) El uso del robot de rehabilitación y el sistema sensorial adjunto para la valoración del progreso en el proceso de rehabilitación y asistencia, mediante variables biomecánicas (de los , mediante variables bioeléctricas periféricas tales como EMG de las que extraer fenómenos tales como la fatiga muscular asociada al uso de la tecnología o aspectos relacionados con la coordinación muscular Barroso et al, 2016), y mediante variables bioeléctricas centrales, tales como EEG, (Ibáñez et al, 2015).…”