Electrode Fusion for the Prediction of Self-Initiated Fine Movements from Single-Trial Readiness Potentials

Abstract

Current human-machine interfaces (HMIs) for users with severe disabilities often have difficulty distinguishing between intentional and inadvertent activations. Pre-movement neuro-cortical activity may aid in this elusive discrimination task but has not been exploited in HMIs. This work investigates the utility of the readiness potential (RP), a slow negative cortical potential preceding voluntary movement, for detecting the intention of self-initiated fine movements prior to their motoric realization. We recorded electroencephalography from the frontal, central, parietal and occipital lobes of 10 participants using a self-initiated switch activation protocol. Eye movement artifacts were removed by regression and the RP was detected on a single-trial basis, in a narrow frequency range (0.1-1 Hz). Common average reference was applied prior to windowed-averaging for feature extraction. Electrodes were selected according to a separability measure based on Fisher projection. Our findings demonstrate that feature fusion from an optimal number of electrodes achieves a statistically significant lower classification error than the best single classifier. Finally, voluntary fine movement intention was detected on a single-trial basis at above-chance levels approximately 396 ms before physical switch activation. These findings encourage the development of rapid-response, intention-aware HMIs for individuals with severe disabilities who struggle with executing voluntary fine motor movements.

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

“…Nikjoo et al (2011) suggested a reputation-based classification in which the decision of each classifier was weighed on the basis of its past performance. In this work, we use the reliability weighted average (RWA) technique (Abou Zeid and Chau, 2015). It weights the classification algorithms by their validation accuracies.…”

“…Following the estimation of the class-conditional Gaussian distributions from training data, Bayes' theorem is used to infer the posterior probability of a test case belonging to a certain class. We presented a complete mathematical formulation of LPGM in Abou Zeid and Chau (2015). …”

“…However, being a slow non-oscillatory cortical potential and occurring concurrently with task-unrelated brain activity, the RP is typically not visible in single trials and is, therefore challenging to detect. Nonetheless, two recent studies of single-trial RP signals demonstrated the detection of self-paced fine movement (Abou Zeid and Chau, 2015) and arm reaching movement (Lew et al, 2012) intention from rest state. The lateralized RP has also been exploited in combination with imagined movement rhythms to improve the speed and accuracy of BCIs (Blankertz et al, 2003, 2006).…”

“…The majority of RP-based BCI studies have investigated a binary classification problem such as detecting movement intention from a rest state (Lew et al, 2012; Abou Zeid and Chau, 2015) or laterality prediction of movement (Blankertz et al, 2001, 2011; Wang et al, 2004; Liao et al, 2007; Tomioka and Müller, 2010; Lu et al, 2014; Abou Zeid et al, 2016). Limited work has considered the differentiation of more than two states.…”

MUSIC-Expected maximization gaussian mixture methodology for clustering and detection of task-related neuronal firing rates

“…However, a neuron’s firing rate, or the rate at which action potentials are generated, is known to be information-rich. This firing rate is used to decode or interpret complex behaviors of a subject such as movement (Carmena et al, 2003; Lebedev et al, 2005; Abou Zeid and Chau, 2015; Suberbiola et al, 2015; Villar et al, 2016), slow eye movements (Takemura et al, 2001; Ghahari and Enderle, 2014), attention (Ecker et al, 2016), or memory recall (Janetsian et al, 2015) among others. The relationship between firing rate and behavior can be made directly via correlation (Takemura et al, 2001), or indirectly using triggered averaging schemes to observe the contribution of a neuron to the recruitment of a particular muscle (Davidson et al, 2007).…”