Figure 3.

Scheme of the proposed probabilistic prediction model. (A) Given a query subject Xq ∈ TE, a set of EMG signals <a onClick="popup('http://www.biomedcentral.com/1471-2202/14/110/mathml/M16','MathML',630,470);return false;" target="_blank" href="http://www.biomedcentral.com/1471-2202/14/110/mathml/M16">View MathML</a> are obtained as a response to repeated electrical stimulation of ten sites on the sole of the foot. (B) A probability distribution histogram Pqj is constructed from each signal Fqj (or combination of signals from multiple sites) to be used as classification feature. (C) The signal Fqj is labelled p (for patient) or h (for healthy), depending on the distances dqj to the closest neighbouring histograms Pi, derived from the set of training subjects {Xi ∈ TR}. (D) The final prediction for the subject Xq is carried out based on the labels lqj derived from the individual assessment of all four signals. Query subjects Xq ∈ V were used instead for all validation procedures (site combination and training set selection).

Biurrun Manresa et al. BMC Neuroscience 2013 14:110   doi:10.1186/1471-2202-14-110
Download authors' original image