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

Abstract

Brain-computer interfaces can be used for motor substitution and recovery; therefore, detection and classification of movement intention is crucial for optimal control. In this study, palmar, lateral and pinch grasps were differentiated from the idle state and classified from single-trial EEG using only information prior the movement onset. Fourteen healthy subjects performed the three grasps 100 times while EEG was recorded from 25 electrodes. Temporal and spectral features were extracted from each electrode, and feature reduction was performed using sequential forward selection (SFS) and principal component analysis (PCA).The detection problem was investigated as the ability to discriminate between movement preparation and the idle state. Furthermore, all task pairs and the three movements together were classified. The best detection performance across movements (79±8%) was obtained by combining temporal and spectral features. The best movement-movement discrimination was obtained using spectral features; 76±9% (2-class) and 63±10% (3-class). For movement detection and discrimination, the performance was similar across grasp types and task pairs; SFS outperformed PCA. The results show it is feasible to detect different grasps and classify the distinct movements using only information prior to the movement onset; which may enable brain-computer interface-based neurorehabilitation of upper limb function through Hebbian learning mechanisms.

A Ternary Brain-Computer Interface Based on Single-Trial Readiness Potentials of Self-initiated Fine Movements: A Diversified Classification Scheme

“…Herein, the achieved results (average k score of 0.769% and associated average classification accuracy of 82.13%) are comparable to published results on RP-based binary BCIs: 76% average sensitivity in predicting gross movement from idle state (Lew et al, 2012); 82.21% average classification accuracy in predicting fine movements from idle state (Abou Zeid and Chau, 2015); 76.27% (Lu et al, 2014) and 74.99% (Abou Zeid et al, 2016) average classification accuracies in predicting the laterality of fine movements. Furthermore, the results in this paper are superior to reported performance on multiclass classification of movement related potentials: 59.25% average classification accuracy amongst four different levels and speeds of intended right ankle movements (Jochumsen et al, 2013); 63% average classification accuracy amongst three different grasp tasks (Jochumsen et al, 2015); 73% average classification accuracy amongst two different right angle movements, following detection of movement from rest (Hassan et al, 2015). …”

“…In Jochumsen et al (2013), authors achieved average classification accuracy of 59.25% between four different levels and speeds of intended right ankle movements. Another study (Jochumsen et al, 2015) showed the possibility of classifying between three different grasp tasks with an accuracy of 63%. A most recent study (Hassan et al, 2015) showed that, following detection of movement from rest, an average classification accuracy of 73% can be achieved between two different right ankle movements.…”

Prediction of Hand Movement Speed and Force from Single-trial EEG with Convolutional Neural Networks

“…However, classification rates for multi-class classification problems are still relatively low in healthy volunteers. As an example, recent studies directed towards the extraction of additional information from movement intention beyond simple detection, such as the prediction of the body part that is about to perform the movement [18], or the classification between different types of movement used in daily life, such as palmar, lateral and pinch grasps [10], resulted in classification accuracies not better than chance levels for the 4-class classification attempts.…”

“…The movement decoding process is generally focused on detecting a predetermined final state and lacks attention regarding the quality of the action, resulting in simple, rough commands [8]. Research on fine movements of body structures such as fingers [9], or complex movement control [10] is comparatively scarce. It is straightforward to hypothesise that better commands can be achieved if movement kinematics and kinetics are taken into account in the decoding process [11].…”

“…It is straightforward to hypothesise that better commands can be achieved if movement kinematics and kinetics are taken into account in the decoding process [11]. Indeed, the decoding of hand movement velocities [12,13] and 3D trajectories [14] as well as the prediction of force and speed from a specific movement [15,10] showed promising results. However, recent attempts to predict speed and force from a hand grasping tasks resulted in a classification accuracy not better than chance level [16,17,18], stressing the need for more accurate prediction schemes.…”