A Novel Flexible Model for the Extraction of Features from Brain Signals in the Time-Frequency Domain

Figure 12

Mean snaGe models per simulated SNR. Models were averaged across the ten noise realizations by direct parameter vector averaging. The curve of peaks (white line) is shown as well as the models’ predicted data 𝑦^{(𝑠𝑛𝑎𝐺𝑒)}(𝑡,𝑓). Compare with Figure 9.

(a)

(b)

(c)

(d)

(e)

(f)

(g)

(h)

(i)

(j)