Decoding Individual Finger Movements from One Hand Using Human EEG Signals

Abstract

Brain computer interface (BCI) is an assistive technology, which decodes neurophysiological signals generated by the human brain and translates them into control signals to control external devices, e.g., wheelchairs. One problem challenging noninvasive BCI technologies is the limited control dimensions from decoding movements of, mainly, large body parts, e.g., upper and lower limbs. It has been reported that complicated dexterous functions, i.e., finger movements, can be decoded in electrocorticography (ECoG) signals, while it remains unclear whether noninvasive electroencephalography (EEG) signals also have sufficient information to decode the same type of movements. Phenomena of broadband power increase and low-frequency-band power decrease were observed in EEG in the present study, when EEG power spectra were decomposed by a principal component analysis (PCA). These movement-related spectral structures and their changes caused by finger movements in EEG are consistent with observations in previous ECoG study, as well as the results from ECoG data in the present study. The average decoding accuracy of 77.11% over all subjects was obtained in classifying each pair of fingers from one hand using movement-related spectral changes as features to be decoded using a support vector machine (SVM) classifier. The average decoding accuracy in three epilepsy patients using ECoG data was 91.28% with the similarly obtained features and same classifier. Both decoding accuracies of EEG and ECoG are significantly higher than the empirical guessing level (51.26%) in all subjects (p<0.05). The present study suggests the similar movement-related spectral changes in EEG as in ECoG, and demonstrates the feasibility of discriminating finger movements from one hand using EEG. These findings are promising to facilitate the development of BCIs with rich control signals using noninvasive technologies.

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

“…Recently, it was demonstrated that MRCPs associated with movements performed with different levels of force and speed of the same body part (wrist and foot movements) could be decoded from the EEG using only information prior to the onset of the movement [13,14,21]. Also, different movement types have been classified such as hand grasping, opening and reaching [1,2,4], movement direction and kinematics (see [19] for a recent review), wrist movements [12,[40][41][42], shoulder and elbow movements [8,[47][48][49] and finger movements [26,27,44].…”

Classification of different reaching movements from the same limb using EEG

“…We applied FBCSP as feature extraction method because it uses frequency filtering into multiple frequency bands, which could benefit the decoding of different motor tasks as demonstrated previously [33]. Furthermore, CSP algorithm has been proven its efficacy calculating optimal spatial filters for motor related BCIs [25,33,35]. Spatial filters were created for three frequency windows: 7-15 Hz, 15-25 Hz, and 25-30 Hz.…”

“…Liao et al investigated the binary classification of ten different pairs of executed finger movements using 128-channel EEG signals achieving a promising average decoding performance of 77.1% [35]. In another study, six different wrist movement pairs (e.g.…”

PCA Based EEG Event Features Extraction for Robotics Dexterous Grasping

“…They tried to implement similar techniques but using EEG. Since earlier studies found that low-pass filtered ECoG (local motor potential LMP) shows precise features, Liao et al [4] tried to decode individual finger movement, hence they used findings from previous ECoG and implemented them using EEG, hence compared the results with ECoG findings. More complex techniques try to estimate the movement and approach of the hands.…”