Skip to main content

Table 2 Comparison of common Level 1 BCI-based AAC performance metrics

From: Performance assessment in brain-computer interface-based augmentative and alternative communication

Metric

Description/Equation

Evaluation criteria

  

Throughput

Categorical outputs

Unbiased

Practicality

Accuracy/Error Rate

Acc = P; Err = (1 - P)

 

✓

 

✓

Cohen’s Kappa

κ = P − 1 / N 1 − 1 / N

 

✓

 

✓

Confusion Matrix

A matrix with intended (true) outputs as rows, actual outputs as columns, and the number of occurrences in the intersections.

 

✓

✓

 

IMutual Information or the formulation in[97]

I X ; Y = ∑ Y ∑ X p x , y × log p x , y p x * p y

(Note this can be used to measure throughput rate by simply dividing by the time per trial)

✓

✓

✓

 

Information Transfer Rate (ITR)

ITR = 1 c log 2 N + P log 2 P + 1 − P log 2 1 − P N − 1

✓

✓

 

✓

  1. P: probability of correct selection; N: number of choices; p(x): marginal distribution of X; p(x,y): joint distribution of X and Y; c: time per selection.
  2. Check marks indicate that the metric fulfills the evaluation criterion.