From Spinach Documentation Wiki
Jump to: navigation, search

Uses pre-trained neural networks to extract background functions from DEER data. See our paper ( for further details.




   deer_trace - experimental DEER trace, a column vector

   time_axis  - experimental time axis, a column vector in 
                microseconds, must start at zero and have
                a uniform time step

   net_dir    - directory containing the network ensemble
                as *.m files generated by train_one_net.m
                and the corresponding netset_params.m and 
                good_nets.mat files.


   time_axis  - a column vector (microseconds)

   bcgs       - background signals, a horizontal array
                of column vectors. The number of column
                vectors is equal to the number of networks
                in the ensemble.

If no output parameters are specified, the function produces a plot.


The output of one of the example calculations supplied with Spinach (examples/deernet) is shown below.

Deer bckg.png


The input DEER trace must be cropped on the left to make the first point of the trace correspond to the maximum.

Deernet preprocess.png

This is done automatically in elexsys2deernet.m, and this is the only preprocessing required by DEERNet.

See also

Neural network module

DEER/PELDOR experiments

Version 2.5, authors: Ilya Kuprov, Steve Worswick