this is for holding javascript data
Ardo Illaste edited results_sensitivity.md
almost 10 years ago
Commit id: ebddf4248dfdc1cb4a43fb49e8f57d97229fd3b6
deletions | additions
diff --git a/results_sensitivity.md b/results_sensitivity.md
index 89a703a..ba16f3d 100644
--- a/results_sensitivity.md
+++ b/results_sensitivity.md
...
## Sensitivity analysis
### Pixel trace
The sensitivity of the method was explored by estimating the probabilty of detecting an event and the accuracy of the fit. The original signal to be fitted was generated from the fitting function for various amplitudes. To this signal different levels of normally distributed noise was added.
Figure x shows the probability of detecting the event in the signal. As the amplitude of the event increases so does the noise level at which the the probability of detecting the event goes below a given treshold (0.95 on the figure). It is more informative to look at the relationship between detection probability and the signal to noise ratio of the event. This is calculated as:
\[
SNR = \frac{\frac{1}{b-a}}{\int_a^b f(t)^2\,dt}{\sigma_n^2}
\]
The accuracy of the fit is calculated as the average square difference between the fit and the original clean signal. It is presented as a percentage of the maximal error which is obtained when no event regions are detected and the entire signal is fitted with just the baseline function.
The sensitivity of the denoising method was explored by creating a synthetic signal with 3 pixel events (one wave and two sparks), similar to the signal shown in Figure \ref{fig:fit}, and adding to it normally distributed noise with increasing values of standard deviation. The accuracy of the fit is calculated as the average square difference between the fit and the original clean signal. It is presented as a percentage of the maximal error which is obtained when no ###Release event
regions are detected and the entire signal is fitted with just the baseline function. detection